Image sensors deployed in the Internet of Things (IoT) generate vast volumes of digital images. These images may be subject to deliberate alteration, compromising their trustworthiness. Estimating the trustworthiness of this image data is crucial for many applications; however, this aspect has not been adequately explored in the existing literature. In this article, we propose a robust and real-time trust estimation framework for IoT image data, leveraging numeric data generated from other types of sensors deployed in the same Area of Interest (AoI). The theoretical model was developed using statistical approaches, and Shannon’s entropy was employed to measure the uncertainty associated with sensor readings during a specific event. Later, we applied Dempster-Shafer theory (DST) of combination to fuse information collected from image as well as numeric data-generating sensors where both types of sensors were observing the same event in the same AoI concomitantly. To evaluate the proposed framework, we implemented an IoT testbed using LoRa sensor nodes, edge devices, an LoRaWAN gateway, the things network (TTN), and a data analytics server. The testbed was used to collect observation data of a fire event using image and temperature sensors in an indoor residential setup in different conditions. Consequently, eight data sets (four authentic and four hacked) were built, each containing both image and temperature data readings under various scenarios. The proposed trust framework accurately estimated the trust score of images (91% overall accuracy) across all the data sets and outperformed existing trust models.

Existing deep learning-based point cloud denoising methods are generally trained in a supervised manner that requires clean data as ground-truth labels. However, in practice, it is not always feasible to obtain clean point clouds. In this paper, we introduce a novel unsupervised point cloud denoising method that eliminates the need to use clean point clouds as groundtruth labels during training. We demonstrate that it is feasible for neural networks to only take noisy point clouds as input, and learn to approximate and restore their clean versions. In particular, we generate two noise levels for the original point clouds, requiring the second noise level to be twice the amount of the first noise level. With this, we can deduce the relationship between the displacement information that recovers the clean surfaces across the two levels of noise, and thus learn the displacement of each noisy point in order to recover the corresponding clean point. Comprehensive experiments demonstrate that our method achieves outstanding denoising results across various datasets with synthetic and real-world noise, obtaining better performance than previous unsupervised methods and competitive performance to current supervised methods.

Research in texture feature approximation is still in the embryonic stage because of difficulties in developing a sound theoretical model to express the unique pattern in the intensity-variation of pixels in the neighbourhood of the pixel-of-interest so that it can sufficiently discriminate different textures. Local texture descriptors are widely used in image segmentation as they comprise pixel-wise features. The Weber local descriptor (WLD) with differential excitation and gradient orientation components, inspired by Weber's Law, has been leveraged in the state-of-the-art iterative contraction and merging (ICM) image segmentation technique. However, WLD has inherent drawbacks in the formulation of the components that limit its discriminatory capability. This paper introduces a novel texture descriptor by directly modelling the distribution of intensity-variation in the parametric space of the Weibull distribution using its shape and scale parameters. A unified ‘joint scale’ texture property is introduced, which can discriminate textures better than the individual parameters while keeping the length of the descriptor shorter. Additionally, the accuracy of WLD's gradient orientation component is improved by using an extended Sobel operator and expressing gradients in$[-\pi /2,\pi /2)$range. When incorporated in ICM, the proposed texture descriptor has consistently outperformed WLD and a recent enhancement with radial mean WLD (RM-WLD) on three benchmark datasets. It has also outperformed two other texture segmentation techniques and their deep learning based improvements.

Video coding techniques minimize spatial and temporal redundancies inherent in video sequences based on non-overlapping block-based image partitioning. Due to depending on the information from already encoded neighboring blocks, these algorithms lack efficient techniques to exploit the overall global redundancies. Compared to the traditional block-based coding, the cuboid coding (2D) framework has been proven to be a more effective method of image compression that exploits global redundancy by considering homogeneous pixel correlation within a frame. In this paper, we improved the idea of 2D cuboid coding to exploit both local and global redundancy from a video sequence by adopting a three-dimensional (3D) cuboid partitioning scheme for SHVC compression improvement of 360-degree videos. The proposed method considers a group of successive frames as a 3D cuboid and recursively partitions it into sub-3D cuboids where static information over a selected GOP share the same cuboid and moving regions share new cuboids with better-defined objects. All the 3D cuboids are then encoded to create a coarse representation of the video stream. Experiments indicate that the proposed framework significantly outperforms its relevant benchmarks, notably by 17.18% (average) in BD-Rate reduction and 0.82 dB in BD-PSNR gain with respect to the standard SHVC codec.

The relentless expansion of video based applications is underpinned by video coding technologies. The latest video coding standard i.e. versatile video coding (VVC) can provide superior compression performance than its predecessors. In this regard, motion modeling plays a central role. Experimental results showed that the discrete cosine basis oriented motion model can describe complex motion better than an affine motion model, adopted in the VVC. Hence, in this paper we propose to augment the VVC motion modeling technique with a set of discrete cosine basis oriented motion models and the applicability region of each such motion model is determined by non-overlapping rectangular regions, known as cuboids. Experimental results show a bit rate savings of up to 2.37% is achievable with respect to a VVC reference.

For 3D object representation, volumetric contents like meshes and point clouds provide suitable formats. However, a dynamic mesh sequence may require significantly large amount of data because it consists of information that varies with time. Hence, for the facilitation of storage and transmission of such content, efficient compression technologies are required. MPEG has started standardization activities aiming to develop a mesh compression standard that would be able to handle dynamic meshes with time varying connectivity information and time varying attribute maps. The attribute maps are features associated with the mesh surface and stored as 2D images/videos. In this paper, we propose to capture the commonality information in the dynamic mesh attribute maps using the cuboidal partitioning algorithm. This algorithm is capable of modeling both the global and local commonality within an image in a compact and computationally efficient way. Experimental results show that the proposed approach can outperform the anchor HEVC codec, suggested by MPEG to encode such sequences, with a bit rate savings of up to 3.66%.

To exploit high temporal correlations in video frames of the same scene, the current frame is predicted from the already-encoded reference frames using block-based motion estimation and compensation techniques. While this approach can efficiently exploit the translation motion of the moving objects, it is susceptible to other types of affine motion and object occlusion/deocclusion. Recently, deep learning has been used to model the high-level structure of human pose in specific actions from short videos and then generate virtual frames in future time by predicting the pose using a generative adversarial network (GAN). Therefore, modelling the high-level structure of human pose is able to exploit semantic correlation by predicting human actions and determining its trajectory. Video surveillance applications will benefit as stored “big” surveillance data can be compressed by estimating human pose trajectories and generating future frames through semantic correlation. This paper explores a new way of video coding by modelling human pose from the already-encoded frames and using the generated frame at the current time as an additional forward-referencing frame. It is expected that the proposed approach can overcome the limitations of the traditional backward-referencing frames by predicting the blocks containing the moving objects with lower residuals. Our experimental results show that the proposed approach can achieve on average up to 2.83 dB PSNR gain and 25.93% bitrate savings for high motion video sequences compared to standard video coding.

The scalable extension of High Efficiency Video Coding, SHVC can code Ultra High-Definition (UHD) video, including 360-degree video for various devices to serve a single bitstream with different display resolutions and qualities. To improve the SHVC compression efficiency, this paper proposes a novel intra and inter-frame coding scheme by first separating the common/visually important information and then applying cuboid-based variable size block partitioning and coding process for the common/visually important information in the base layer. In cuboid-based partitioning a video frame is partitioned into arbitrary shaped rectangular regions, known as cuboids, based on the distribution of relatively homogeneous pixel values. As the cuboid adopts a variable block partitioning based on the homogeneity of the data value, the partitioned blocks have better alignment with the object boundary. Moreover, in the cuboid coding process, only the partitioning tree information and a single value for each block need to be coded which takes lower number of bits and computational time compared to the traditional SHVC base layer. To verify the performance of the proposed method we embedded the proposed scheme as a base layer into the standard SHVC reference software and used several popular UHD/360-degree videos. The experimental results indicate that the proposed scalable coding strategy achieves an average of 14.04% BD-Rate reduction and 0.61 dB BD-PSNR gain for UHD/360-video compared to the operation points provided by an SHVC conforming encoder.

Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint distribution of seen-unseen classes and preserving the distinction between seen-unseen classes is crucial for GZSL methods. However, existing methods only learn the underlying distribution of seen data, although unseen class semantics are available in the GZSL problem setting. Most methods neglect retaining seen-unseen classes distinction and use the learned distribution to recognize seen and unseen data. Consequently, they do not perform well. In this work, we utilize the available unseen class semantics alongside seen class semantics and learn joint distribution through a strong visual-semantic coupling. We propose a bidirectional mapping coupled generative adversarial network (BMCoGAN) by extending the concept of the coupled generative adversarial network into a bidirectional mapping model. We further integrate a Wasserstein generative adversarial optimization to supervise the joint distribution learning. We design a loss optimization for retaining distinctive information of seen-unseen classes in the synthesized features and reducing bias towards seen classes, which pushes synthesized seen features towards real seen features and pulls synthesized unseen features away from real seen features. We evaluate BMCoGAN on benchmark datasets and demonstrate its superior performance against contemporary methods.

Video coding algorithms attempt to minimize the significant commonality that exists within a video sequence. Each new video coding standard contains tools that can perform this task more efficiently compared to its predecessors. Modern video coding systems are block-based wherein commonality modeling is carried out only from the perspective of the block that need be coded next. In this work, we argue for a commonality modeling approach that can provide a seamless blending between global and local homogeneity information. For this purpose, at first the frame that need be coded, is recursively partitioned into rectangular regions based on the homogeneity information of the entire frame. After that each obtained rectangular region’s feature descriptor is taken to be the average value of all the pixels’ intensities encompassing the region. In this way, the proposed approach generates a coarse representation of the current frame by minimizing both global and local commonality. This coarse frame is computationally simple and has a compact representation. It attempts to preserve important structural properties of the current frame which can be viewed subjectively as well as from improved rate-distortion performance of a reference scalable HEVC coder that employs the coarse frame as a reference frame for encoding the current frame.

Immersive media representation format based on point clouds has underpinned significant opportunities for extended reality applications. Point cloud in its uncompressed format require very high data rate for storage and transmission. The video based point cloud compression technique projects a dynamic point cloud into geometry and texture video sequences. The projected texture video is then coded using modern video coding standard like HEVC. Since the properties of projected texture video frames are different from traditional video frames, HEVC-based commonality modeling can be inefficient. An improved commonality modeling technique is proposed that employs discrete cosine basis oriented motion models and the domains of such models are approximated by homogeneous regions called cuboids. Experimental results show that the proposed commonality modeling technique can yield savings in bit rate of up to 4.17%.

Video coding algorithms encode and decode an entire video frame while feature coding techniques only preserve and communicate the most critical information needed for a given application. This is because video coding targets human perception, while feature coding aims for machine vision tasks. Recently, attempts are being made to bridge the gap between these two domains. In this work, we propose a video coding framework by leveraging on to the commonality that exists between human vision and machine vision applications using cuboids. This is because cuboids, estimated rectangular regions over a video frame, are computationally efficient, has a compact representation and object centric. Such properties are already shown to add value to traditional video coding systems. Herein cuboidal feature descriptors are extracted from the current frame and then employed for accomplishing a machine vision task in the form of object detection. Experimental results show that a trained classifier yields superior average precision when equipped with cuboidal features oriented representation of the current test frame. Additionally, this representation costs 7% less in bit rate if the captured frames are need be communicated to a receiver.

Point cloud in its uncompressed format require very high data rate for storage and transmission. The video based point cloud compression (V-PCC) technique projects a dynamic point cloud into geometry and texture video sequences. The projected geometry and texture video frames are then encoded using modern video coding standard like HEVC. However, HEVC encoder is unable to exploit the global commonality that exists within a geometry frame and between successive geometry frames to a greater extent. This is because in HEVC, the current frame partitioning starts from a rigid $64 \times 64$ pixels level without considering the structure of the scene need be coded. In this paper, an improved commonality modeling framework is proposed, by leveraging on cuboid-based frame partitioning, to encode point cloud geometry frames. The associated frame-partitioning scheme is based on statistical properties of the current geometry frame and therefore yields a flexible block partitioning structure composed of cuboids. Additionally, the proposed commonality modeling approach is computationally efficient and has a compact representation. Experimental results show that if the V-PCC reference encoder is augmented by the proposed commonality modeling technique, a bit rate savings of 2.71% and 4.25% are achieved for full body and upper body of human point clouds’ geometry sequences respectively.

Domain adaptation aims to transfer knowledge from a domain with adequate labeled samples to a domain with scarce labeled samples. Prior research has introduced various open set domain adaptation settings in the literature to extend the applications of domain adaptation methods in real-world scenarios. This paper focuses on the type of open set domain adaptation setting where the target domain has both private (‘unknown classes’) label space and the shared (‘known classes’) label space. However, the source domain only has the ‘known classes’ label space. Prevalent distribution-matching domain adaptation methods are inadequate in such a setting that demands adaptation from a smaller source domain to a larger and diverse target domain with more classes. For addressing this specific open set domain adaptation setting, prior research introduces a domain adversarial model that uses a fixed threshold for distinguishing known from unknown target samples and lacks at handling negative transfers. We extend their adversarial model and propose a novel adversarial domain adaptation model with multiple auxiliary classifiers. The proposed multi-classifier structure introduces a weighting module that evaluates distinctive domain characteristics for assigning the target samples with weights which are more representative to whether they are likely to belong to the known and unknown classes to encourage positive transfers during adversarial training and simultaneously reduces the domain gap between the shared classes of the source and target domains. A thorough experimental investigation shows that our proposed method outperforms existing domain adaptation methods on a number of domain adaptation datasets.

In conventional video compression systems, motion model is used to approximate the geometry of moving object boundaries. It is possible to relieve motion model from describing discontinuities in the underlying motion field, by incorporating motion hint that can predict the spatial structure of future frames using the structure of reference frames. However, formation of highly accurate motion hint is computationally demanding, in particular for high resolution video sequences. Cuboids, rectangular regions derived using statistical features, attempt to separate out different objects present in the scene; they are computationally efficient and have sparse representation. Leveraging on the advantages of cuboids, in this paper, we propose to discover homogeneous motion regions and their associated motion based on cuboids. Afterwards, the estimated motion models and their domains are applied to form a prediction of the current frame. Experimental results show that a savings in bit rate of 3.96% is achievable over standalone HEVC reference, if this predicted frame is used as an additional reference frame for the current frame.

Texture is an indispensable property to develop many vision based autonomous applications. Compared to colour, feature dimension in a local texture descriptor is quite large as dense texture features need to represent the distribution of pixel intensities in the neighbourhood of each pixel. Large dimensional features require additional time for further processing that often restrict real-time applications. In this paper, a robust local texture descriptor is enhanced by reducing feature dimension by three folds without compromising the accuracy in region-based image segmentation applications. Reduction in feature dimension is achieved by exploiting the mean of neighbourhood pixel intensities radially along lines across a certain radius, which eliminates the need for sampling intensity distribution at three scales. Both the results of benchmark metrics and computational time are promising when the enhanced texture feature is used in a region-based hierarchical segmentation algorithm, a recent state-of-the-art technique.

With the growth of video technologies, super-resolution videos, including 360-degree immersive video has become a reality due to exciting applications such as augmented/virtual/mixed reality for better interaction and a wide-angle user-view experience of a scene compared to traditional video with narrow-focused viewing angle. The new generation video contents are bandwidth-intensive in nature due to high resolution and demand high bit rate as well as low latency delivery requirements that pose challenges in solving the bottleneck of transmission and storage burdens. There is limited optimisation space in traditional video coding schemes for improving video coding efficiency in intra-frame due to the fixed size of processing block. This paper presents a new approach for improving intra-frame coding especially at low bit rate video transmission for 360-degree video for lossy mode of HEVC. Prior to using traditional HEVC intra-prediction, this approach exploits the global redundancy of entire frame by extracting common important information using multi-level discrete wavelet transformation. This paper demonstrates that the proposed method considering only low frequency information of a frame and encoding this can outperform the HEVC standard at low bit rates. The experimental results indicate that the proposed intra-frame coding strategy achieves an average of 54.07% BD-rate reduction and 2.84 dB BD-PSNR gain for low bit rate scenario compared to the HEVC. It also achieves a significant improvement in encoding time reduction of about 66.84% on an average. Moreover, this finding also demonstrates that the existing HEVC block partitioning can be applied in the transform domain for better exploitation of information concentration as we applied HEVC on wavelet frequency domain.

Video coding algorithms attempt to minimize the significant commonality that exists within a video sequence. Each new video coding standard contains tools that can perform this task more efficiently compared to its predecessors. In this work, we form a coarse representation of the current frame by minimizing commonality within that frame while preserving important structural properties of the frame. The building blocks of this coarse representation are rectangular regions called cuboids, which are computationally simple and has a compact description. Then we propose to employ the coarse frame as an additional source for predictive coding of the current frame. Experimental results show an improvement in bit rate savings over a reference codec for HEVC, with minor increase in the codec computational complexity.

Depth coding in 3D-HEVC deforms object shapes due to block-level edge-approximation and lacks efficient techniques to exploit the statistical redundancy, due to the frame-level clustering tendency in depth data, for higher coding gain at near-lossless quality. This paper presents a standalone mono-view depth sequence coder, which preserves edges implicitly by limiting quantization to the spatial-domain and exploits the frame-level clustering tendency efficiently with a novel binary tree-based decomposition (BTBD) technique. The BTBD can exploit the statistical redundancy in frame-level syntax, motion components, and residuals efficiently with fewer block-level prediction/coding modes and simpler context modeling for context-adaptive arithmetic coding. Compared with the depth coder in 3D-HEVC, the proposed one has achieved significantly lower bitrate at lossless to near-lossless quality range for mono-view coding and rendered superior quality synthetic views from the depth maps, compressed at the same bitrate, and the corresponding texture frames.

Hand vein biometric is an important modality for human authentication and liveness detection in many applications. Reliable feature extraction is vital to any biometric system. Over the past years, two major categories of vein features, namely vein structures and vein image textures, were proposed for hand dorsal vein based biometric identification. Of them, texture features seem important as it can combine skin micro-textures along with vein properties. In this study, we have performed a comparative study to identify potential texture features and feature-classifier combination that produce efficient vein biometric systems. Seven texture features (HOG, GABOR, GLCM, SSF, DWT, WPT, and LBP) and three multiclass classifiers (LDA, ESVM, and KNN) were explored towards the supervised identification of human from vein images. An experiment with 400 infrared (IR) hand images from 40 adults indicates the superior performance of the histogram of oriented gradients (HOG) and simple local statistical feature (SSF) with LDA and ESVM classifiers in terms of average accuracy (> 90%), average Fscore (> 58%) and average specificity (>93%). The decision-level fusion of the LDA and ESVM classifier with single texture features showed improved performances (by 2.2 to 13.2% of average Fscore) over individual classifier for human identification with IR hand vein images.

Depth maps are becoming increasingly important in the context of emerging video coding and processing applications. Depth images represent the scene surface and are characterized by areas of smoothly varying grey levels separated by sharp edges at the position of object boundaries. To enable high quality view rendering at the receiver side, preservation of these characteristics is important. Lossless coding enables avoiding rendering artifacts in synthesized views due to depth compression artifacts. In this paper, we propose a binary tree based lossless depth coding scheme that arranges the residual frame into integer or binary residual bitmap. High spatial correlation in depth residual frame is exploited by creating large homogeneous blocks of adaptive size, which are then coded as a unit using context based arithmetic coding. On the standard 3D video sequences, the proposed lossless depth coding has achieved compression ratio in the range of 20 to 80.

Participatory sensing is a revolutionary new paradigm where citizens voluntarily sense their surroundings using readily available sensing devices such as mobile phones and share this information for mutual benefit of community members. To encourage ample participation of users, ensuring their privacy is inevitable. Existing techniques that attempt to protect location privacy with spatial cloaking suffer from irrecoverable data quality degradation. To the best of our knowledge, very few works provided a solution preserving high data quality/utility at the destination server, however, suffered from unacceptable computational overhead. This paper presents an improved deterministic alternative and also a faster variant by exploiting several optimization issues. Theoretical formulations and extensive simulation results are presented to establish the applicability of our proposed techniques.

Motion vectors of depth-maps in multiview and free-viewpoint videos exhibit strong spatial as well as inter-component clustering tendency. This paper presents a novel motion vector coding technique that first compresses the multidimensional bitmaps of macro block mode information and then encodes only the non-zero components of motion vectors. The bitmaps are partitioned into disjoint cuboids using binary tree based decomposition so that the 0's and 1's are either highly polarized or further sub-partitioning is unlikely to achieve any compression. Each cuboid is entropy-coded as a unit using binary arithmetic coding. This technique is capable of exploiting the spatial and inter-component correlations efficiently without the restriction of scanning the bitmap in any specific linear order as needed by run-length coding. As encoding of non-zero component values no longer requires denoting the zero value, further compression efficiency is achieved. Experimental results on standard multiview test video sequences have comprehensively demonstrated the superiority of the proposed technique, achieving overall coding gain against the state-of-the-art in the range [17%,51%] and on average 31%.

The striking feature of High Efficiency Video Coding (HEVC) Standard is emphasized by 50% bit-rate reduction compared to its predecessor H.264/AVC while keeping the same perceptual image quality. The time complexity - a congenital issue of HEVC has also increased to intensify the compression ratio. However, it is really a demanding task for the researchers to reduce the encoding time while preserving expected quality of the video sequences. Our contribution is to trim down the computational time by efficient selection of appropriate block-partitioning modes in HEVC using motion features based on phase-correlation. In this paper, we use phase-correlation between current and reference blocks to extract three motion features and combine them to determine binary motion pattern of the current block. The motion pattern is then matched against a codebook of predefined pattern templates to determine a subset of the inter-modes. Only the selected modes are exhaustively motion estimated and compensated for a coding unit. The experimental outcomes demonstrate that the average computational time can be down scaled by 30% of the HEVC while providing improved rate-distortion performance.

We present a computationally efficient RGB-D based pose estimation solution for less computationally resourced MAVs, which are ideally suited as members in a swarm. Our approach applies the sufficient statistics derived for a least-squares problem to our problem context. RANSAC-based outlier detection in aligning corresponding feature points is a time consuming operation in visual pose estimation. The additive nature of the used sufficient statistics significantly reduces the computation time of the RANSAC procedure since the pose estimation in each test loop can be computed by reusing previously computed sufficient statistics. This eliminates the need for recomputing estimates from scratch each time. A simpler hypotheses testing method gave similar performance in terms of speed but less accurate than our proposed method. We further increase the efficiency by reducing the problem size to four dimensions using attitude data from an Attitude and Heading Reference System (AHRS). Using a real-world dataset, we show that our algorithm saves up to 94% of computation time for the RANSAC-based procedure in pose estimation while improving the accuracy.

A key goal in transportation system is to attain efficient road traffic through minimization of trip time, fuel consumption and pollutant-emission without compromising safety. In dense traffic lane-changes and merging are often key ingredients to cause safety hazards, traffic breakdowns and travel delays. In this paper, we propose an efficient cooperative lane-changing algorithm CLA for sensor- and communication-enabled automated vehicles to reduce the lane-changing bottlenecks. For discretionary lane-changing, we consider the advantages of the subject vehicle, the follower in the current lane and k (an integer) lag vehicles in the target lane to maximize speed gains. Our algorithm simultaneously minimizes the impact of lane-change on traffic flow and the overall trip time, fuel-consumption and pollutant-emission. For mandatory lane-changing CLA dissociates the decision-making point from the actual mandatory lane-changing point and computes a suitable lane-changing slot in order to minimize lane-changing (merging) time. Our algorithm outperforms the potential cooperative lane-changing algorithm MOBIL proposed by Kesting et al. [1] in terms of merging time and rate, waiting time, fuel consumption, average velocity and flow (especially at the point in front of the merging point) at the cost of slightly increased average trip time for the mainroad vehicles compared to MOBIL. We also highlight important directions for further research.

State-of-the-art lossless image compression schemes, such as, JPEG-LS and CALIC, have been proposed in the context adaptive predictive coding framework. These schemes involve a prediction step followed by context adaptive entropy coding of the residuals. It can be observed that there exist significant spatial correlation among the residuals after prediction. The efficient schemes proposed in the literature rely on context adaptive entropy coding to exploit this spatial correlation. In this paper, we propose an alternative approach to exploit this spatial correlation. The proposed scheme also involves a prediction stage. However, we resort to a binary tree based hierarchical decomposition technique to efficiently exploit the spatial correlation. On a set of standard test images, the proposed scheme, using the same predictor as JPEG-LS, achieved an overall compression gain of 2.1% against JPEG-LS.

Motion vectors of depth-maps in multiview and free-viewpoint videos exhibit strong spatial as well as inter-component clustering tendency. This paper presents a novel coding technique that first compresses the multidimensional bitmaps of macroblock mode and then encodes only the non-zero components of motion vectors. The bitmaps are partitioned into disjoint cuboids using binary tree based decomposition so that the 0's and 1's are either highly polarized or further sub-partitioning is unlikely to achieve any compression. Each cuboid is entropy-coded as a unit using binary arithmetic coding. This technique is capable of exploiting the spatial and inter-component correlations efficiently without the restriction of scanning the bitmap in any specific linear order as needed by run-length coding. As encoding of non-zero component values no longer requires denoting the zero value, further compression efficiency is achieved. Experimental results on standard multiview test video sequences have comprehensively demonstrated the superiority of the proposed technique, achieving overall coding gain against the state-of-the-art in the range [22%, 54%] and on average 38%.

Video coding techniques utilising background frames, provide better rate distortion performance by exploiting coding efficiency in uncovered background areas compared to the latest video coding standard. Parametric approaches such as the mixture of Gaussian (MoG) based background modeling has been widely used however they require prior knowledge about the test videos for parameter estimation. Recently introduced non-parametric (NP) based background modeling techniques successfully improved video coding performance through a HEVC integrated coding scheme. The inherent nature of the NP technique naturally exhibits superior performance in dynamic background scenarios compared to the MoG based technique without a priori knowledge of video data distribution. Although NP based coding schemes showed promising coding performances, they suffer from a number of key challenges - (a) determination of the optimal subset of training frames for generating a suitable background that can be used as a reference frame during coding, (b) incorporating dynamic changes in the background effectively after the initial background frame is generated, (c) managing frequent scene change leading to performance degradation, and (d) optimizing coding quality ratio between an I-frame and other frames under bit rate constraints. In this study we develop a new scene adaptive coding scheme using the NP based technique, capable of solving the current challenges by incorporating a new continuously updating background generation process. Extensive experimental results are also provided to validate the effectiveness of the new scheme.

In this paper, we have extended the Rice-Golomb code so that it can operate at fractional precision to efficiently exploit the real-valued predictions. Coding at infinitesimal precision allows the residuals to be modeled with the Lap lace distribution. Unlike the Rice-Golomb code, which maps equally probable opposite-signed residuals to different integers, the proposed coding scheme is symmetric in the sense that, at infinitesimal precision, it assigns code words of equal length to equally probable residual intervals. The symmetry of both the Lap lace distribution and the coding scheme facilitates the analysis of the proposed coding scheme to determine the average code-length and the optimal value of the associated coding parameter.

In a transform domain distributed video coding scheme, the correlation between the current encoding unit, e.g. block and slice, and the corresponding side-information is modeled using a virtual channel. This correlation model is then used for rate allocation, quantization, and Wyner-Ziv coding. Since the encoder can only have an estimate of the correlation instead of the exact knowledge of the side-information, the decoder will fail to recover the quantized transformed coefficients with a nonzero probability. In this paper, we propose to integrate a scheme at the decoder to recover the undecoded coefficients using the spatial smoothness property of individual video frames. Simulation results demonstrated that, at different decoding failure probabilities, a transformed coefficient recovery scheme can significantly improve the quality of videos in terms of both PSNR and SSIM.

Capturing a scene using multiple cameras from different angles is expected to provide the necessary interactivity in the 3D space to satisfy end-users' demands for observing objects and actions from different angles and depths. Existing multiview video coding (MVC) technologies are not sufficiently agile to exploit the interactivity and inefficient in terms of image quality and computational time. In this paper a novel technique is proposed using disparity-adjusted 3D MVC (DA-3D-MVC) with 3D motion estimation (ME) and 3D coding to overcome the problems. In the proposed scheme, a 3D frame is formed using the same temporal frames of all disparity-adjusted views and ME is carried out for the current 3D macroblock using the immediate previous 3D frame as a reference frame. Then, 3D coding technique is used for better compression. As all the same temporal position frames of all views are encoded at the same time, the proposed scheme provides better interactivity and reduced computational time compared to the H.264/MVC. To improve the rate-distortion (RD) performance of the proposed technique, an additional reference frame comprising dynamic background is also used. Experimental results reveal that the proposed scheme outperforms the H.264/MVC in terms of RD performance, computational time, and interactivity.

View-invariant action recognition is one of the most challenging problems in computer vision. Various representations are being devised for matching actions across different viewpoints to achieve view invariance. In this paper, we explore the invariance property of temporal order of action instances during action execution and utilize it for devising a new view-invariant action recognition approach. To ensure temporal order during matching, we utilize spatiotemporal features, feature fusion and temporal order consistency constraint. We start by extracting spatiotemporal cuboid features from video sequences and applying feature fusion to encapsulate within-class similarity for the same viewpoints. For each action class, we construct a feature fusion table to facilitate feature matching across different views. An action matching score is then calculated based on global temporal order constraint and number of matching features. Finally, the action label of the class with the maximum value of the matching score is assigned to the query action. Experimentation is performed on multiple view Inria Xmas motion acquisition sequences and West Virginia University action datasets, with encouraging results, that are comparable to the existing view-invariant action recognition techniques.

Developing universal and context-invariant methods is one of the hardest challenges in computer vision. Background subtraction (BS), an essential precursor in most machine vision applications used for foreground detection, is no exception. Due to overreliance on statistical observations, most BS techniques show unpredictable behavior in dynamic unconstrained scenarios in which the characteristics of the operating environment are either unknown or change drastically. To achieve superior foreground detection quality across unconstrained scenarios, we propose a new technique, called perception-inspired background subtraction (PBS), which avoids overreliance on statistical observations by making key modeling decisions based on the characteristics of human visual perception. PBS exploits the human perception-inspired confidence interval to associate an observed intensity value with another intensity value during both model learning and background-foreground classification. The concept of perception-inspired confidence interval is also used for identifying redundant samples, thus ensuring the optimal number of samples in the background model. Furthermore, PBS dynamically varies the model adaptation speed (learning rate) at pixel level based on observed scene dynamics to ensure faster adaptation of changed background regions, as well as longer retention of stationary foregrounds. Extensive experimental evaluations on a wide range of benchmark datasets validate the efficacy of PBS compared to the state of the art for unconstraint video analytics.

Robust background subtraction (BS) is essential for high quality foreground detection in most video analytics systems. Recent BS techniques achieve superior detection quality mostly by exploiting the complementary strengths of multiple background models or processing stages. Consequently, these techniques fail to meet the operational requirements of real-time video analytics due to high computational overhead where BS is just the primary processing task. In this paper, we propose a new BS technique, named multi-hypothesis mixture-of-Gaussians (MH-MOG), suitable for real-time video analytics. The essential idea is to maintain a single background model based on perception-aware mixture-of-Gaussians and then, generating multiple detection hypotheses with different processing bases. Finally, only during the detection stage, the complementary strengths of the hypotheses are exploited to achieve superior detection quality without significant computational overhead. Comprehensive experimental evaluation validates the efficacy of MH-MOG.

Traditionally, event centric Wireless Sensor Network (WSN) applications treat all events with equal importance, implicitly assuming that all events have same priority. However, in real world applications events may have different level of severity and sensitivity based on their cost of potential damage, occurrence location and frequency. Such applications demand that a detection scheme adopt differentiated treatment of events considering above criteria. Recent works proposed multi-modal sensor nodes for detection of different types of event in a single sensor network and mobile nodes for on-demand attendance of events. When a multi- modal WSN is deployed to monitor events of varied priority, major challenges lies to allocate resources and mobilize mobile nodes in an optimized way to maximize detection performance. We introduce the concept of varied priority and cost of mis-detection of events, and propose a detection scheme for multiple simultaneous events in a hybrid sensor network. Mobile nodes are mobilized through formulation of an optimization problem that maximizes the prioritized accuracy while minimizing detection delay. Theoretical and simulation results demonstrate that our scheme significantly outperforms other scheme that treats all events equally.

Opportunistic access of licensed spectrum using a cognitive radio network (CRN) is getting research attraction due to its ability to improve utilisation of this scarce resource without affecting the primary users (PUs). To improve wide acceptability of CRN, it must be equipped with efficient protocols to deal with multiple primary networks to provision QoS guarantee for demand-driven applications by the secondary users (SUs). In this paper, an accurate unsaturated throughput analysis is presented for our novel CSMA/CA-based multi-channel cognitive radio medium access control (MCR-MAC) protocol. Developed by modifying the 4-way handshaking-based IEEE 802.11 DCF, MCR-MAC dynamically assigns contending SUs to free channels using an innovative random arbitration scheme while keeping cognitive interference to the PUs in check by attenuating the packet size. Not only has the analytical model covered the full spectrum, from very light load to saturation, extensive simulation results have validated the accuracy of the analysis.

Vertical handoff plays an important role to provide seamless connectivity for a mobile user in an overlapped multinetwork environment. On the other hand in order to maintain network stability, efficient management of available radio resource becomes crucial as network operators want high network utilization and maximum profit generation. For vertical handoff management, existing research works considered these user centric vertical handoff decision algorithm and network centric call admission control as two isolated decision mechanisms in heterogeneous wireless environment. In this paper, however, we propose a correlation between vertical handoff decisions and call admission control policies. We have developed a novel vertical handoff decision model using the Markov decision process based vertical handoff decision algorithm by refining the optimality criterion to factor in the probabilistic consequence of the call dropping rates so that mobile-centric vertical handoff decision algorithm and network-centric call admission control can work through a feedback mechanism to maximize respective objectives in synergy.

In passive localization, sensors try to locate an event without any knowledge of event's emitted power. So, this is a more challenging problem compared to active localization. Existing passive localization schemes use expensive and noise-vulnerable range-based techniques. In this paper, we propose, to the best of our knowledge for the first time, a cost-effective range-free passive localization scheme exploiting hybrid sensor network model where mobile sensors are deployed on demand once an event is sensed by a static sensor. Efficient use of mobile sensors leads to two concomitant optimization problems: (1) positioning the mobile sensors so that the expected possible event location area is minimized; and (2) minimizing their overall traversed distance. To solve the first problem, we have developed a novel arc-coding based range-free localization technique that can accurately define the area of possible event location from the feedback of arbitrarily placed sensors without relying on expensive hardware to estimate range of signals. We have achieved significantly high localization accuracy with a low number of mobile sensors even after considering significant environmental noise. To solve the second problem, three alternative deployment strategies for the mobile sensors were simulated to recommend the best.

Multiuser dynamic OFDMA based IEEE 802.11 distributed coordination function (DCF) has received significant interest from the researchers in recent time. Though several proposals have been made, to the best of our knowledge, none of these have presented an analytical model for this kind of medium access control protocols for IEEE 802.11. This paper provides a simple, nevertheless, very accurate analytical model to estimate the performance characteristics of IEEE 802.11 DCF with OFDMA under the assumptions of ideal channel conditions and saturation load. Our model accounts for important system parameters like throughput, collision rate, transmission delay, average contention window size, average retry count and average time wasted in backoff. Analytical results are verified through extensive simulations.

Evolutionary algorithms (EAs) often fail to find the global optimum due to genetic drift. As the protein structure prediction problem is multimodal having several global optima, EAs empowered with combined application of local and global search e.g., memetic algorithms, can be more effective. This paper introduces two novel local improvement techniques for the clustered memetic algorithm to incorporate both problem specific and search-space specific knowledge to find one of the optimum structures of a hydrophobic-polar protein sequence on lattice models. Experimental results show the superiority of the proposed techniques against existing EAs on benchmark sequences.

Variation in viewpoints poses significant challenges to action recognition. One popular way of encoding view-invariant action representation is based on the exploitation of epipolar geometry between different views of the same action. Majority of representative work considers detection of landmark points and their tracking by assuming that motion trajectories for all landmark points on human body are available throughout the course of an action. Unfortunately, due to occlusion and noise, detection and tracking of these landmarks is not always robust. To facilitate it, some of the work assumes that such trajectories are manually marked which is a clear drawback and lacks automation introduced by computer vision. In this paper, we address this problem by proposing view invariant action matching score based on epipolar geometry between actor silhouettes, without tracking and explicit point correspondences. In addition, we explore multi-body epipolar constraint which facilitates to work on original action volumes without any pre-processing. We show that multi-body fundamental matrix captures the geometry of dynamic action scenes and helps devising an action matching score across different views without any prior segmentation of actors. Extensive experimentation on challenging view invariant action datasets shows that our approach not only removes long standing assumptions but also achieves significant improvement in recognition accuracy and retrieval.

For cost effective deployment and implementation, mobility is introduced in sensor networks to provide dynamic event coverage. A hybrid network of static and mobile nodes, can yield the same desired accuracy and robustness of a static k-coverage detection model with fewer nodes. Since node movement is a costly operation and the movement strategy has to be decided instantly after event occurrence, it is desirable to have a lightweight distributed node selection and movement scheme. In this work, we propose a game theoretic model to provide dynamic event coverage that achieves the desired detection accuracy with significantly fewer number of nodes while balancing the energy consumption due to mobility and keeping the travelling distance minimum. We address and exploit the spatial clustering nature of events to maximize the overall detection performance over the network lifetime.

Opportunistic access of licensed spectrum using a cognitive radio network (CRN) is getting research attraction due to its ability to improve utilisation of this scarce resource without affecting the primary users (PUs). To improve wide acceptability of CRN, it must be equipped with efficient protocols to deal with multiple primary networks to provision QoS guarantee for demand-driven applications by the secondary users (SUs). In this paper, a novel CSMA/CA-based multichannel cognitive radio medium access control (MCR-MAC) protocol is developed by modifying the 4-way handshaking based IEEE 802.11 DCF to dynamically assign contending SUs to free channels using an innovative random arbitration scheme. The paper also presents a detailed analytical model for cognitive interference to the PUs and SUs. The proposed protocol is designed to keep the interference level in check to remain transparent to the PUs. A throughput analysis at saturation load reveals that this fully ad-hoc MCR-MAC is capable of achieving throughput comparable to the ideal scenario (when SUs are equally divided to the channels) without using any centralised infrastructure or dedicated control channel. Extensive simulation results validate the accuracy of the theoretical analysis and establish MCR-MAC as a highly practical solution to construct a CRN in a region overlapped with multiple primary networks to offer data-rate sensitive applications by the SUs.

Success of participatory sensing system depends on the extent of voluntary participation by users. To increase participation, incentive such as rewards can be used only if reported data has associated user identification. This creates serious threat to participating users' location privacy. Existing techniques tried to solve it with spatial clocking, which suffers from inferior data integrity. In this paper, we present a subset coding based anonymization scheme that can safeguard users' location privacy with k-anonymity while preserving almost lossless data integrity at the destination server. Adversary threats to our scheme are comprehensively analyzed to develop robust strategies and analytical bounds on system parameters for location privacy risk mitigation. Applicability of the proposed scheme is established with extensive simulation results.

Vertical handoff plays an important role in guaranteeing users to be always connected in an overlapped multi-network environment. During the vertical handoff procedure, handoff decision is the most important step that affects the normal working of communication. An incorrect handoff decision or selection of a non-optimal network may result in undesirable effects such as higher costs, poor quality of service (QoS) experience, and even dropped communication. Among the existing vertical handoff decision algorithms, the Markov Decision Process (MDP) based algorithm by Stevens-Navarro et al. is promising due to its ability to achieve the optimal expected reward. However, the reward function used by this algorithm is flawed as it favors reducing expected number of vertical handoffs at the expense of diminished expected values of other QoS parameters. This paper presents an extended MDP based algorithm (EMDP) with novel reward function formulation. Analysis shows that EMDP outperforms the MDP based algorithm in terms of improved expected values of all QoS parameters considered while keeping the vertical handoff number reasonably low.

In this paper, we discuss the challenges associated with integrating multiuser OFDMA in a single cell IEEE 802.11 based wireless ad hoc network and propose a new, dynamic and robust approach to improve it. Our new MAC, using OFDMA in the physical layer, can incorporate multiple concurrent transmissions or receptions in a dynamic manner and can adjust the collision probability based on the traffic load when nodes are endowed with a single half-duplex radio only. Simulation results show that for moderate number of users, our system improves throughput by up to 20%, decreases collision in control messages by up to 45% and reduces the average delay by up to 18%.

Cognitive radio network (CRN) users are inherently expected to experience widely-varied delays due to the uncertainty in wireless channel availability. Supporting delay sensitive real-time services through CRNs, so that visitors are allowed to experience full-scale networking services by opportunistically sharing the spectrum from a number of existing networks without impacting on the primary users, thus remains a challenging task. This paper presents a novel technique to provision QoS guarantee for delay-sensitive services in CRNs having secondary users equipped with multiple radio interfaces. The technique relies on modeling spectrums holes from multiple primary networks through a resultant channel to enable implementing a single server queuing model with random service interruption. Simulation results using ns-2.33 show that using multiple radio interfaces has sheer strength to reduce CRN delay with fewer number of primary channel sensing.

Estimating weight factors for QoS parameters plays an important role in the effectiveness of vertical handoff decision algorithms. This paper presents a novel weight estimation technique, which can adaptively control the spanning of the weights in response to user preference. Simulation results show the supremacy of the technique against the state-of-the-art in achieving wider spanning of the expected values of all QoS parameters under consideration.

Cognitive radio network (CRN) users are inherently expected to experience widely varied delays and jitters due to the uncertainty in channel availability. Supporting delay sensitive real-time services through CRNs thus remains a challenging task. This paper presents a novel technique to provision QoS guarantee in CRNs by modeling the resultant channel of multiple primary networks and finding the optimum number of primary channels to support a desired level of expected latency. In doing so, this paper introduces a cognitive radio based MAC, which can effectively co-exists with primary CSMA/CA networks by accurately estimating the start of the spectrum holes, reliably modeling channel occupation by the primary users, and using event-driven sensing to adaptively control the sensing frequency and interval. Simulation results with ns-2.33 reveal that a CR network based on the proposed MAC can achieve the targeted service delay time by appropriately selecting optimal WLAN primary channels.

Despite recent interests in developing vertical handoff decision algorithms, an essential component of the architecture of the next generation heterogeneous wireless networks, very few studies have so far reported any meaningful comparative performance analysis. This paper attempts to fill this gap in the literature by presenting a comprehensive study on the performance of three vertical handoff decision algorithms, namely, SAW (Simple Additive Weighting), TOPSIS (Technique for Order Preference by Similarity to Ideal Solution), and MDP (Markov Decision Process). We have used both analytical and simulation tools (ns-2.29) to evaluate and compare expected total QoS offerings in the mean duration of a service under different state transition probability distributions, user perception models on the importance of QoS parameters, and network switching costs. To our surprise, we have observed TOPSIS achieving the best performance despite MDP's using the optimal policy. We suspect that the user satisfiability model used in MDP to estimate link rewards might have contradicted the underlying user perception model used to estimate normalised weight of each QoS parameter, which will be investigated in future.

Modern surveillance systems are becoming highly automated in terms of scene understanding and event detection capabilities, and most existing methods rely on track-and motion-based features for event classification and anomaly detection. However, trajectory-based methods fail in public scenarios due to frequently loosing the object tracks, while the capabilities of motion-based methods are limited in detection of direction and velocity related anomalies. In this paper, a novel feature extraction and event detection method is presented without using any track and motion features where event discriminating characteristics are discovered from the dynamics of multiple temporal features extracted from foreground blobs and then confined in support vector machine based models for real-time event detection. Experimental results on benchmark datasets show that the proposed method can successfully discriminate panic-driven events like sudden split, runaway, and fighting from usual events.

A block-based lossless video coding scheme using the notion of binning has been proposed in. To further improve the compression and reduce the complexity, in this paper we investigate the impact of two sub-optimal motion search algorithms on the performance of this lattice-based scheme. While one of the algorithm tries avoiding motion vectors, the other tries to reduce complexity. Our experimental results have demonstrated that the loss due to sub-optimal motion search outweighs the gain when motion vectors are avoided. However, experimental results have shown that there is negligible performance loss when low-complexity sub-optimal three step search is used.

Color image fusion of visible and infra-red imagery can play an important role in multi-sensor night vision systems that are an integral part of modern warfare. Image fusion minimizes the amount of required bandwidth by transmitting the fused image rather than multiple sensor images. Color image fusion can be achieved by combining inputs from original colored sensors or by employing pseudo colorization and color transfer to grayscale images. Various quality measures have been proposed for multi-sensor grayscale image fusion techniques; but no appropriate quality measure has been devised for the quality evaluation of multi-sensor color image fusion. In this paper, we propose a novel color image fusion quality measure, Color Fusion Objective Index (CFOI) based on colorfulness, gradient similarity and mutual information techniques. Experimental results show the effectiveness of CFOI to evaluate the color and salient feature extraction introduced by color fusion techniques into the final fused imagery as well as its consistency with subjective evaluation.

In this paper, we present an automated color transfer based video fusion method to attain real-time color night vision capability for night-time video surveillance. We utilize simple RGB Color transfer technique to fused pseudo colored video frames without conversion to any uncorrelated color space. We investigated that final color fusion results greatly depend on the selection of target color Image. Therefore, rather than using any arbitrary target color image based on mere general visual anticipation, we have automated target color image selection using structural similarity and color saturation. We further apply color enhancement to improve final appearance of color fused images. Subjective and objective quality evaluations greatly indicate the effectiveness of our color video fusion method for nighttime video surveillance applications.

Due to the infrequent medium access in Wireless Sensor Networks (WSN), their MAC protocols are mostly based on CSMA. In this paper we present an efficient contention resolution scheme for CSMA based MAC protocols which is suitable for periodic data collection in WSNs. Taking into account that the number of nodes in a single cluster is fixed, this protocol uses successively decreasing contention window. It is characterized by non-overlapping contention window, that maintains a constant successful transmission rate. It significantly decreases data collection time by minimizing the time wastage due to collisions. At the same time, by using adaptive CW, it reduces the time wastage in empty slots. Experimental results demonstrate that in periodic data collection within a single hop cluster this scheme has performance superior to the recently proposed Synchronous Shared Contention Window (SSCW) based scheme in terms of time wastage and throughput.

In participatory sensing system community people contribute information to be shared by everybody. However, none would be tolerant enough to contribute voluntarily if her privacy is not protected. This has evoked the idea of research in the area of preserving privacy in participatory sensing system. On the other hand, data integrity is desired imperatively to make the service trustworthy and user-friendly. In this paper, we have investigated the performance of a greedy algorithm and its randomized variant to achieve an acceptable tradeoff between these two orthogonal key parameters. We have also analyzed the ability of a third party adversary to decode privacy-sensitive data by eavesdropping. Our experimental results show that the proposed method is performing satisfactorily as an approach of balancing user privacy and data integrity.

In a decentralized sensor network, localization process relies on the integrity of participating sensors. Existence of malicious beacon nodes in the vicinity of non-beacon nodes affects this process. This paper presents a trilateration-based secure localization technique, which is capable of estimating the location of a sensor with high accuracy so long four neighbouring beacon nodes are benign, irrespective of the number of neighbouring liars and without assuming any trust model. In realistic scenarios of wireless environment where transmitted signals attenuate randomly due to fading, the liar-tolerance level of this attack-resistant technique has to be relaxed accordingly. Superiority of this technique against the state-of-the-art has been established with extensive simulation results in terms of location estimation accuracy and liar-filtering probability.

Among the existing block partitioning schemes, the pattern-based video coding (PVC) has already established its superiority at low bit-rate. Its innovative segmentation process with regular-shaped pattern templates is very fast as it avoids handling the exact shape of the moving objects. It also judiciously encodes the pattern-uncovered background segments capturing high level of interblock temporal redundancy without any motion compensation, which is favoured by the rate-distortion optimizer at low bit-rates. The existing PVC technique, however, uses a number of content-sensitive thresholds and thus setting them to any predefined values risks ignoring some of the macroblocks that would otherwise be encoded with patterns. Furthermore, occluded background can potentially degrade the performance of this technique. In this paper, a robust PVC scheme is proposed by removing all the content-sensitive thresholds, introducing a new similarity metric, considering multiple top-ranked patterns by the rate-distortion optimizer, and refining the Lagrangian multiplier of the H.264 standard for efficient embedding. A novel pattern-based residual encoding approach is also integrated to address the occlusion issue. Once embedded into the H.264 Baseline profile, the proposed PVC scheme improves the image quality perceptually significantly by at least 0.5 dB in low bit-rate video coding applications. A similar trend is observed for moderate to high bit-rate applications when the proposed scheme replaces the bi-directional predictive mode in the H.264 High profile.

Pattern-based video coding focusing on moving region in a macroblock has already established its superiority over recent H.264 video coding standard at very low bit rate. Obviously, a large number of pattern templates approximate the moving regions better however, after a certain limit no coding gain is observed due to the increase number of pattern identification bits. Recently, distributed video coding schemes used syndrome coding to predict the original information in decoder using side information. In this paper a novel pattern identification scheme is proposed which predicts the pattern from the syndrome codes and side information in decoder so that actual pattern identification number is not needed in the bitstream. The experimental results confirm that this new scheme successfully improves the rate-distortion performance compared to the existing pattern-based video coding as well as H.264 standard. This new scheme will also open another window of syndrome coding application.

Image sequences of smoke, fire, etc. are known as dynamic textures. Research is mostly limited to characterization of single dynamic textures. In this paper we address the problem of detecting the presence of multiple dynamic textures in an image sequence by establishing a correspondence between the feature space of dynamic textures and that of their mixture in an image sequence. Accuracy of our proposed technique is both analytically and empirically established with detection experiments yielding 92.5% average accuracy on a diverse set of dynamic texture mixtures in synthetically generated as well as real-world image sequences.

Yang proposed the concept of borrow-and-return (BR) to leverage the unused server bandwidth when a group of popular videos being broadcast with the FSFC (first segment on the first channel) broadcasting schemes in order to improve the mean waiting time (MWT) of the viewers with the help of additional receiving bandwidth available at the high-end clients. The BR model borrows the bandwidth of the videos with no new-coming viewers during a timeslot to speed up the transmission of the first segments of some of the remaining videos. In this paper, we first address the relative advantage issue among various possible BR schemes by developing a parametric generic BR (GBR) scheme controlled externally by independent borrow parameters. Later, we propose a new BR (NBR) model by incorporating an efficient transmission strategy to reduce the MWT further. Finally, an optimal NBR scheme is developed by augmenting with the optimal borrow parameters, which significantly outperforms the existing and new BR schemes in terms of overall MWT.

Gaussian mixture models (GMM) is used to represent the dynamic background in a surveillance video to detect the moving objects automatically. All the existing GMM based techniques inherently use the proportion by which a pixel is going to observe the background in any operating environment. In this paper we first show that such a proportion not only varies widely across different scenarios but also forbids using very fast learning rate. We then propose a dynamic background generation technique in conjunction with basic background subtraction which detected moving objects with improved stability and superior detection quality on a wide range of operating environments in two sets of benchmark surveillance sequences.

Pattern-based video coding (PVC) has already established its superiority over recent video coding standard H.264, at low bit rate because of an extra pattern-mode to segment out the arbitrary shape of the moving region within the macroblock (MB). To determine the pattern-mode, the PVC however uses three thresholds to reduce the number of MBs coded using the pattern- mode. By setting these content-sensitive thresholds to any predefined values, the technique risks ignoring some MBs that would otherwise be selected by the rate-distortion optimization function for this mode. Consequently, the ultimate achievable performance is sacrificed to save motion estimation times. In this paper, a novel PVC scheme is proposed by removing all thresholds to determine this mode and hence more efficient performance is achieved without knowing the content of the video sequences. To keep computational complexity in check, pattern motion is approximated from the motion vector of the MB. In addition, efficient pattern similarity metric and new Lagrangian multipliers are also developed. The experimental results confirm that this new scheme improves the image quality by at least 0.5 dB and 1.0 dB compared to the existing PVC and the H.264 respectively.

Adaptive Gaussian mixtures are widely used to model the dynamic background for real-time object detection. Recently the convergence speed of this approach is improved and a relatively robust statistical framework is proposed by Lee (PAMI, 2005). However, object quality still remains unacceptable due to poor Gaussian mixture quality, susceptibility to background/foreground data proportion, and inability to handle intrinsic background motion. This paper proposes an effective technique to eliminate these drawbacks by modifying the new model induction logic and using intensity difference thresholding to detect objects from one or more believe-to-be backgrounds. Experimental results on two benchmark datasets confirm that the object quality of the proposed technique is superior to that of Leepsilas technique at any model learning rate.

Adaptive background modelling based object detection techniques are widely used in machine vision applications for handling the challenges of real-world multimodal background. But they are constrained to specific environment due to relying on environment specific parameters, and their performances also fluctuate across different operating speeds. On the other side, basic background subtraction (BBS) is not suitable for real applications due to manual background initialization requirement and its inability to handle repetitive multimodal background. However, it shows better stability across different operating speeds and can better eliminate noise, shadow, and trailing effect than adaptive techniques as no model adaptability or environment related parameters are involved. In this paper, we propose a hybrid object detection technique for incorporating the strengths of both approaches. In our technique, Gaussian mixture models (GMM) is used for maintaining an adaptive background model and both probabilistic and basic subtraction decisions are utilized for calculating inexpensive neighbourhood statistics for guiding the final object detection decision. Experimental results with two benchmark datasets and comparative analysis with recent adaptive object detection technique show the strength of the proposed technique in eliminating noise, shadow, and trailing effect while maintaining better stability across variable operating speeds.

Very low bit-rate video coding algorithms using content-based generated patterns to segment out moving regions at macroblock level have exhibited good potential for improved coding efficiency when embedded into the H.264 standard as extra mode. This content-based pattern generation (CPG) algorithm provides local optimal result as only one pattern can be optimally generated from a given set of moving regions. But, it failed to provide optimal results for multiple patterns from entire sets. Obviously, a global optimal solution for clustering the set and then generation of multiple patterns enhances the performance farther. But a global optimal solution is not achievable due to the non-polynomial nature of the clustering problem. In this paper, we proposed a near optimal content-based pattern generation (OCPG) algorithm which outperforms the existing approach. Coupling OCPG, generating a set of patterns after clustering the macroblocks into several disjoint sets, with direct pattern selection algorithm by allowing all the macroblocks in multiple pattern modes outperforms the existing pattern-based coding while both embedded into the H.264.

Obstacles present in the line of sight transmission path of a wireless signal severely attenuates the received signal power. Extreme fluctuations of the received signal power caused by shadowing can create "blind spots". Blind spots are areas within the cellular coverage area from where no communication is possible to the base station (BS). For single path packet based services link failures results in total loss of communication. The problem of link failure and blind spots can almost be eliminated in the recently proposed multipath cellular architecture (MCA) which provisions up to three different communication links from the mobile node (MN) to three adjacent BSs through overlapped coverage. Voice and/or multimedia packet delivery can thus benefit by establishing communication from the best interface in terms of received signal power. In this paper, we evaluate the performance of the multi-path MCA model in reducing link failure and blind spot communication problems in presence of multiple obstacles and shadow fading. Obstacle mobility model is utilized as the preferred user mobility model. Video transmission performance improves significantly in terms of reduced packet loss and improved reproduced signal quality at the receiver for the multipath MCA model compared to the existing single path cellular network architecture.

Assuring quality of service (QoS) is an extreme challenge in cellular multimedia delivery especially in single path transmission. One possible way to improve QoS is to provide multipath transmission. In this paper, we introduce a novel multi-path cellular network architecture through placement of additional base stations (BSs), i.e., antennae in the existing cellular architecture. This architecture provides a mobile unit (MU) with more than one communication links from the BSs placed in different locations. The availability of multiple channels allows the implementation of path diversity transmission protocols and improves error resilience capability for multimedia services. The multiple diversified path links reduces outage probability. We show that our proposed architecture provides better reliability and maintains cell capacity for high bandwidth multimedia services while improving signal to interference ratio compared to the existing cellular network model.

Curvature scale-space (CSS) corner detectors look for curvature maxima or inflection points on planar curves. They use arc-length parameterized curvature. Therefore, they are not robust to affine transformations since the arc-length of a curve is not preserved under affine transformations. However, the affine-length of a curve is relatively invariant to affine transformations. This paper presents an improved CSS corner detector by applying the affine-length parameterized curvature to the CSS corner detection technique. A thorough robustness study has been carried out on a large database considering a wide range of affine transformations.

Assuring quality of service (QoS) is an extreme challenge in cellular multimedia delivery. Without appropriate QoS, the content delivered cannot meet consumers' aesthetic demands and thus resulting in revenue loss for the service provider. In this paper, we propose a novel multi-path cellular network architecture through placement of additional base stations (BSs), i.e., antennae in the existing cellular architecture. This architecture provides a MU more than one communication links with the BSs placed in different locations. The availability of multiple channels allows the implementation of path diversity transmission protocols and improves error resilience capability for multimedia services. The problem of link failure and blind spots in the existing cellular networks are handled for voice communications as at least one base station can maintain a line of sight communication path with the MU. The distributed nature of base station placement and multiple diversified path links also reduces outage probability. We show that our proposed architecture provides better reliability and maintains cell capacity for high bandwidth multimedia services while improving signal to interference ratio compared to the existing cellular network model.

Very low bit-rate video coding algorithms using predefined regular-shaped patterns to segment out moving objects at macroblock level have exhibited good potential for improved coding efficiency when embedded in the H.264 standard as an extra mode. Even the best-matched regular-shaped pattern from a predefined codebook cannot approximate the shape of the object well, and there is no guarantee that even a regular-shaped object will have a close match with one of the limited number of predefined patterns. Intuitively, improved coding performance can be achieved if patterns are dynamically extracted from the video content. This letter presents a content-based pattern generation (CPG) algorithm for a set of macro blocks, which is shown optimal when only one pattern is allowed to represent the entire set. Coupling CPG, generating a pattern codebook after clustering the macro blocks into several disjoint sets, with any pattern selection algorithm outperforms the existing regular-shaped pattern-based coding while both embedded in H.264.

Characterized by their distinctive motion patterns, temporal textures are natural phenomenon exhibiting spatio-temporal regularity with indeterminate spatial and temporal extent. This paper presents a real-time motion-based temporal texture characterization technique for the first time using block-based motion measures with very high classification accuracy against the popular opinion that such an accurate characterization is only possible using pixel-based measures. Finding an optimal weight ratio between space and time domain features where the accuracy of this block-based technique peaks has been the essence of this success. Computational complexity analyses and classification results clearly demonstrate the capability of the proposed technique in producing comprehensive classification results comparable to the best pixel-based technique with overwhelming reduction in computational complexity.

Trading off computational complexity and quality is an important performance constraint for real time application of motion estimation algorithm. Previously, the novel concept of a distance-dependent thresholding search (DTS) was introduced for performance scalable motion estimation in video coding applications. This encompassed the full search as well as other fast searching techniques, such as the three-step search, with different threshold settings providing various quality-of-service levels in terms of processing speed and predicted image quality. The main drawback of the DTS was that the threshold values had to be manually defined. In this paper, the DTS algorithm has been extended to a fast and fully adaptive DTS (FADTS), a key feature of which is the automatic adaptation of the threshold using a desired target and the content from the actual video sequence, to achieve either a guaranteed level of quality or processing complexity. Experimental results confirm the performance of the FADTS algorithm in achieving this objective by demonstrating either comparable or improved search speed over existing fast algorithms including the diamond search, hexagon-based search, and enhanced hexagon-based search, while maintaining similar error performance

Information theoretic proof exists to support that independent encoding of distributed sources with a joint decoder by exploiting the correlation among the sources can be as efficient as encoding them jointly. This paper successfully attempts to apply this concept for lossless video coding using lattices to divide the multidimensional integer pixel intensity hyperspace of a block of pixels into a finite number of cosets and encoding each block with its coset index. This radical departure from conventional predictive coding techniques not only offers very low computational complexity by avoiding expensive learning of predictor coefficients but also avoids any coding loss due to rounding of real-valued predictions. On standard test video sequences, this scheme achieved compression within as low as 4.6% of the latest scheme with optimal learning of predictor coefficients. The former, however, outperformed the latter as soon as it started updating the optimal predictor coefficients less frequently to reduce the computational complexity.

The most significant bit (MSB)-plane of an image is least likely to change by the most signal processing operations. Watermarking techniques are, however, unable to exploit the MSB-plane, as embedding any information there introduces the highest distortion. This paper presents a novel rotation, scale, and translation (RST)-resistant multi-bit logo-based copyright protection scheme using the most significant gray-scale bits at the region-of-interest, automatically selected by the invariant centroid (1C) of the image. How the RST-attack can be reversed using the 1C and geometric moments has been proposed. During verification, the test image is restored to its approximate original through reversing any possible RST attack before calculating signature. To avoid any bias, a new MSB-based attack has also been proposed. Experimental results have clearly demonstrated the superiority of the proposed scheme.

The performance of existing copyright protection schemes is questionable due to their vulnerability to geometric transformations. Though a few of them can resist global geometric transformations like rotation and scaling attacks, most of them are vulnerable to rotation-scale and cropping attacks. This paper presents a novel geometric distortion correction scheme robust to global geometric transformations. It restores an attacked image to its approximate original by reversing the attack using the invariant centroid and geometric moments of the image. Experimental results show the effectiveness of the proposed scheme

Computational Grids and peer-to-peer (P2P) networks enable the sharing, selection, and aggregation of geographically distributed resources for solving large-scale problems in science, engineering, and commerce. The management and composition of resources and services for scheduling applications, however, becomes a complex undertaking. We have proposed a computational economy framework for regulating the supply of and demand for resources and allocating them for applications based on the users' quality-of-service requirements. The framework requires economy-driven deadline- and budget-constrained (DBC) scheduling algorithms for allocating resources to application jobs in such a way that the users' requirements are met. In this paper, we propose a new scheduling algorithm, called the DBC cost–time optimization scheduling algorithm, that aims not only to optimize cost, but also time when possible. The performance of the cost–time optimization scheduling algorithm has been evaluated through extensive simulation and empirical studies for deploying parameter sweep applications on global Grids. Copyright © 2005 John Wiley & Sons, Ltd.

Very low bit-rate video coding using regularly shaped patterns to represent moving regions in macroblocks has good potential for improved coding efficiency. This paper presents a real-time pattern selection (RTPS) algorithm, which uses a pattern relevance and similarity metric to achieve faster pattern selection from a large codebook. For each applicable macroblock, the relevance metric is applied to create a customized pattern codebook (CPC) from which the best pattern is selected using the similarity metric. The CPC size is adapted to facilitate real-time selection. Results prove the quantitative and perceptual performance of RTPS is superior to both the Fixed-8 algorithm and H.263.

In the context of very low bit-rate video coding, pattern representations of a moving region (MR) in block-based motion estimation and compensation has become increasingly attractive. Generally, all existing pattern-matching algorithms apply a similarity metric, involving elementary operations, to compute the mismatch between an MR and a particular fixed pattern in order to select the best-matching pattern from a fixed-size codebook of predefined patterns. An efficient similarity metric, together with a new generic computation strategy, is presented by considering only the mismatch areas of MRs. It is theoretically proven that for a specific MR in a macroblock, the new similarity metric selects exactly the same pattern as existing metrics, while the resulting computational coding efficiency is improved by between 21% and 58% compared with the H.263 low bit-rate coding standard.

This paper presents an advanced cell visiting probability estimator for more accurately reserving resources for an estimated time interval to neighbouring cells by exploiting key mobility parameters (speed, direction and distance). The call admission control strategy used allocates bandwidth more efficiently to provide consistent Quality of Service (QoS) guarantees for multimedia traffics. Concomitantly, to ensure continuity of on-going calls with better utilization of resources, bandwidth is borrowed from existing adaptive calls without affecting the minimum QoS guarantee. Simulation results prove that the new scheme offers substantial improvements over the recent existing schemes.

A controlled multicast scheme provides instantaneous service, but limited server bandwidth causes some user requests to be either delayed or rejected when insufficient free bandwidth is available. Two borrowing schemes are proposed for instantaneous video-on-demand (VOD) that reduce the user request blocking rate by borrowing bandwidth from ongoing video streams when there is insufficient free bandwidth for the server to deliver a new video stream. Both these new schemes have proved to be successful in reducing blocking rate and increasing bandwidth utilization at the expense of temporarily degrading the video quality.

This paper proposes a novel velocity support call admission scheme through defining a new directional probability function and a new technique of estimating the reservation time window. The projected velocity-dependent directional probability function, with a negative exponential distribution, is based on the assumption that both the probability of changing direction and the rate of change are higher for slow rather than fast moving mobile units. In this paper, the reservation time window is estimated more accurately through considering the estimated travel distance and average cell dwelling time rather than considering finite number of paths as proposed in many recent studies. The new scheme is compared against the existing predictive mobility support scheme using extensive real-scenario simulations. Results prove the new scheme to be very effective in achieving superior performance in terms of QoS parameters and also reduced number of overhead message transmissions.

Very low bit-rate video coding, using regular shaped patterns to focus on moving regions in macroblocks, has gained significant attention recently. This paper presents a new real-time pattern selection (RTPS) algorithm using a large codebook of thirty two patterns. The algorithm uses a relevance measurement for all the patterns and a moving region, to eliminate a large number of irrelevant patterns prior to the actual best likelihood pattern selection procedure. Both theoretically and empirically it is proven that not only is the computational complexity of the new algorithm comparable to the contemporary algorithm that use a pattern codebook size of only eight patterns but also the new algorithm reduces the bit-rate significantly, while maintaining comparable subjective quality.

Trading-off computational complexity and quality is an important performance constraint for real time application of motion estimation algorithms. To address this issue, a distance dependent thresholding search (DTS) algorithm has been proposed for fast and robust true motion estimation in video coding/indexing applications (Sorwar, G. et al., Proc. ICASSP. 2002; IEEE Asia-Pacific Conf. on Circuits and Systems, 2002; 6th Int. Conf. on Signal Processing, 2002). DTS encompasses both the full search (FS) as well as fast searching modes, with different threshold settings providing various quality-of-service levels. The main drawback of DTS is that the threshold value is defined manually. The DTS algorithm is extended to a fully adaptive distance dependent thresholding search (FADTS), a key feature of which is the automatic adaptation of the threshold using the desired target and the content from the actual video sequence to achieve a guaranteed level of quality or processing complexity. Experimental results confirm the performance of the FADTS algorithm in achieving this objective with minimal additional computational cost.

Most fuzzy rule-based image segmentation techniques to date have been primarily developed for gray level images. In this paper, a new algorithm called fuzzy rule-based colour image segmentation (FRCIS) is proposed by extending the generic fuzzy rule-based image segmentation (GFFUS) algorithm G.C. Karmakar, L.S. Dooley [2002] and integrating a novel algorithm for averaging hue angles. Qualitative and quantitative analysis of the performance of FRCIS is examined and contrasted with the popular fuzzy c-means (FCM) and possibilistic c-means (PCM) algorithms for both the hue-saturation-value (HSV) and RGB colour models. Overall, FRCIS provides considerable improvement for many different image types.

The selection of an optimal regular-shaped pattern set for very low bit-rate video coding, focusing on moving regions has been the objective of much recent research in order to try and improve bit-rate efficiency. Selecting the optimal pattern set however, is an NP hard problem. This paper presents a generic variable pattern selection (GVPS) algorithm, which introduces a pattern selection parameter that is able to control the performance in terms of computational complexity as well as bit-rate and picture quality. While using a sub-optimal variable pattern set, GVPS obtains a coding performance comparable to near-optimal algorithms, such as the k-change neighbourhood solution, while being much less computationally intensive, so that it is able to process all types of video sequences in real-time, with minimal pre-processing overheads.

Very low bit-rate video coding, using regular shaped patterns to focus on moving regions in macroblocks, has gained significant attention. This paper presents a new real-time pattern selection (RTPS) algorithm using a large codebook of thirty two patterns. The algorithm uses a relevance measurement for all the patterns and a moving region, to eliminate a large number of irrelevant patterns prior to the actual best likelihood pattern selection procedure. Both theoretically and empirically it is proven that not only is the computational complexity of the new algorithm comparable to the contemporary algorithm that use a pattern codebook size of only eight patterns but also the new algorithm reduces the bit-rate significantly, while maintaining comparable subjective quality.

The extended fuzzy rules for image segmentation (EFRIS) algorithm initially splits all segmented regions into mutually exclusive 4-connected objects, from which the largest one in each region is designated as its main object. A drawback of this approach is that it is less effective when the main objects are relatively small and some of the minor objects are completely surrounded and connected to the main object of another region. Besides, defining insufficient merging rules, EFRIS also only considers the surrounding main objects in the original order that the regions were segmented, which is undesirable. In this paper, a new general segmentation algorithm called modified extended fuzzy rules for image segmentation (MEFRIS) is presented, which addresses these problems and whose improved segmentation performance is analysed and numerically evaluated. The results are also contrasted with both the original generic fuzzy rule-based image segmentation (GFRIS) and EFRIS algorithms.

A modified full-search (MFS) algorithm is presented for block-based motion estimation applications, which introduces the novel concept of variable distance dependent thresholds. The performance of the MFS algorithm is analyzed and quantitatively compared with both the traditional and exhaustive full-search (FS) technique, and the computationally faster, non-exhaustive three-step-search (TSS) algorithm. Experimental results show that by applying an appropriate threshold function, the MFS algorithm not only matches the speed of the TSS algorithm, but both retains a block distortion error comparable to the global minimum produced by the FS algorithm, and avoids the problem of identifying large numbers of spurious motion vectors in the search process.

The generic fuzzy rule-based image segmentation algorithm (GFRIS) does not produce good results for images containing non-homogeneous regions, as it does not directly consider texture. In this paper a new algorithm called fuzzy rules for image segmentation incorporating texture features (FRIST) is proposed, which includes two additional membership functions to those already defined in GFRIS. FRIST incorporates the fractal dimension and contrast features of a texture by considering image domain specific information. Quantitative evaluation of the performance of FRIST is discussed and contrasted with GFRIS using one of the standard segmentation evaluation methods. Overall, FRIST exhibits considerable improvement in the results obtained compared with the GFRIS approach for many different image types.

Abstract Clusters, Grids, and peer‐to‐peer (P2P) networks have emerged as popular paradigms for next generation parallel and distributed computing. They enable aggregation of distributed resources for solving large‐scale problems in science, engineering, and commerce. In Grid and P2P computing environments, the resources are usually geographically distributed in multiple administrative domains, managed and owned by different organizations with different policies, and interconnected by wide‐area networks or the Internet. This introduces a number of resource management and application scheduling challenges in the domain of security, resource and policy heterogeneity, fault tolerance, continuously changing resource conditions, and politics. The resource management and scheduling systems for Grid computing need to manage resources and application execution depending on either resource consumers' or owners' requirements, and continuously adapt to changes in resource availability. The management of resources and scheduling of applications in such large‐scale distributed systems is a complex undertaking. In order to prove the effectiveness of resource brokers and associated scheduling algorithms, their performance needs to be evaluated under different scenarios such as varying number of resources and users with different requirements. In a Grid environment, it is hard and even impossible to perform scheduler performance evaluation in a repeatable and controllable manner as resources and users are distributed across multiple organizations with their own policies. To overcome this limitation, we have developed a Java‐based discrete‐event Grid simulation toolkit called GridSim. The toolkit supports modeling and simulation of heterogeneous Grid resources (both time‐ and space‐shared), users and application models. It provides primitives for creation of application tasks, mapping of tasks to resources, and their management. To demonstrate suitability of the GridSim toolkit, we have simulated a Nimrod‐G like Grid resource broker and evaluated the performance of deadline and budget constrained cost‐ and time‐minimization scheduling algorithms. Copyright © 2002 John Wiley & Sons, Ltd.

There has recently been an interest in the introduction of reconfigurable buses to existing parallel architectures. Among them Reconfigurable Mesh (RM) draws much attention because of its simplicity. This paper presents two O(1) time algorithms to compute the contour of the maximal elements of N planar points on the RM. The first algorithm employs an RM of size N/spl times/N while the second one uses a 3-D RM of size /spl radic/N/spl times//spl radic/N/spl times//spl radic/N.