Abstract In wireless networks, the Contention Window (CW) is a crucial parameter for wireless channel sharing among numerous stations, directly influencing overall network performance. With the rapid growth and increasing diversity of traffic in wireless networks, differentiating and serving various types of traffic to enhance network performance has become a pressing issue that needs to be addressed. Deep Reinforcement Learning (DRL) optimizes decision-making through the interaction between an agent and its environment, enabling it to handle complex state spaces and high-dimensional data, making it particularly suitable for dynamically adjusting the contention window and adapting to environmental changes in real time. Access Category (AC) is used to differentiate various types of traffic to support different quality of service (QoS) requirements. Therefore, this paper proposes the integration of DRL techniques into the EDCA mechanism, utilizing AC to differentiate network traffic, while the DRL technology adjusts the contention window to adequately ensure QoS for different types of traffic and enhance overall network performance. This paper proposes a CW back off scheme based on DRL for differentiating ACs. The scheme uses DRL technology to observe the channel collision rate and sense the current network conditions, thereby adaptively adjusting the CW size for ACs. In addition, it dynamically adjusts the back off strategy according to the perceived current network conditions to optimize the data transmission process. In the range of 20–120 stations, the scheme was tested in both single AC and multiple AC traffic scenarios, demonstrating excellent performance. The collision rate consistently remained below 18%, while the normalized throughput was maintained above 76%. Additionally, there is a significant improvement compared to existing deep reinforcement learning-based optimization schemes. Experimental results show that this scheme effectively discriminates between different ACs, resulting in lower latency and higher throughput for high-priority traffic. Furthermore, adaptively adjusting the CW size and improving the back off strategy maintains a low collision rate and stable throughput even under heavy load conditions, significantly improving the overall network performance.

Distributed video coding paradigm aims at transferring the major part of the processing computation effort from the encoder to the decoder. Motion interpolation is done at the decoder to generate side information (SI) through motion compensated temporal interpolation (MCTI). SI is considered as a noisy version of the original data: channel control coding schemes, such as turbo coding, are used to eliminate the errors (SI inaccuracies). The video data is turbo encoded and the parity bits are sent to the decoder. The systematic bits, however, are discarded since the decoder already disposes of SI that can be used for the channel likelihood ratio calculations. However, when the MCTI generation of SI is highly corrupted, the channel likelihood ratios based on the SI are inefficient and even misleading. A number of parity bits number exceeding the original data length may then be required, thus leading to an undesirable expansion effect. In this paper, we propose a method to detect adaptively the situations where the SI is of lower quality. Then puncturing matrices, enabling systematic bits, are used to help computing reliable channel likelihood ratios. An improvement up to 0.5 dB is reported for PSNRs vs bit rate performances.

Automatic monitoring of image/video quality is very important in modern multimedia communication services. We are interested in digital watermarking as a promising approach to image quality assessment without reference to the original image. The proposed methodology makes use of wavelet-based embedding of multiple watermarks with robustness control in order to capture the degree of the degradation undergone by a received image. The watermark robustness is controlled through 1) embedding and detection of multiple watermarks, 2) multi-resolution and directional subband selection, 3) perceptual watermark weighting and 4) fine watermark strength adjustment process. At the receiver end, the detection or lack of detection of the watermarks in a received image are used to estimate image's PSNR range and determine its associated quality attribute. Simulation results show the efficiency of such watermarking scheme in assessing the quality level of test images under JPEG compression.

This paper presents an on-the-fly model-driven validation of data points for random sample consensus methods (RANSAC). The novelty resides in the idea that an analysis of the outcomes of previous random model samplings can benefit subsequent samplings. Given a sequence of successful model samplings, information from the inlier sets and the model errors is used to provide a validness of a data point. This validness is used to guide subsequent model samplings, so that the data point with a higher validness has more chance to be selected. To evaluate the performance, the proposed method is applied to the problem of the line model fitting and the estimation of the fundamental matrix. Experimental results confirm that the proposed algorithm improves the performance of RANSAC in terms of the estimate accuracy and the number of samplings.

In the last few years distributed video coding (DVC) has become a new paradigm for video compression where the encoding process needs to be simple. DVC allows for the development of new applications where the computational complexity and the amount of memory inside the video encoder are limited. In this paper, we introduce a new data representation and coding method for DVC systems. The proposed method consists of an adaptive binary representation based on the maximum difference between the source picture and the side information. This adaptive representation provides a reduction of bitrate without any loss of information, while maintaining the low complexity of the encoder. Experimental results show a significant increase in performance over conventional DVC methods.

The curved wavelet transform (CWT) was developed to enhance compactness of the wavelet transform (WT) representation. Curve determination is critical for the CWT because a well-defined curve set can increase the performance gain in terms of the rate-distortion (R-D). Conventionally, the image to be encoded is divided into blocks and the curve orientation in each block is independently determined through the minimization of its high-pass CWT energy. In this paper, we propose an R-D optimization algorithm for the curve determination, in which variable block size and the impact of neighboring blocks are taken into account. To reduce the computational cost, an alternative sampling strategy is exploited. Experiment results with natural images show that the proposed algorithm can provide better image quality, measured objectively or subjectively, compared to the conventional CWT coding algorithm. Importantly, the proposed approach overcomes the hurdles of computational cost and optimization at the global level opens the door for further performance enhancements of applications with the CWT.

Localization algorithm continues to be an important and challenging topic in today's wireless sensor networks (WSNs). In this paper, a novel range-free localization algorithm using expected hop progress (LAEP) to predict the location of any sensor in a WSN is proposed. This algorithm is based on an accurate analysis of hop progress in a WSN with randomly deployed sensors and arbitrary node density. By deriving the expected hop progress from a network model for WSNs in terms of network parameters, the distance between any pair of sensors can be accurately computed. Since the distance estimation is a key issue in localization systems for WSNs, the proposed range-free LAEP achieves better performance and less communication overhead as compared to some existent schemes like DV-Hop and RAW. In addition, we study the effect of anchor placement on the algorithm performance by deriving the corresponding mean position error range. Extensive simulations are performed and the results are observed to be in good agreement with the theoretical analysis.

A novel data structure is proposed for magnitude-ordering 4D wavelet coefficients of wavelet-based multiview video coding. This data structure consists of temporal-view 2D zerotree data structures followed by spatial 2D zerotree data structures. Based on this 4D data structure, an algorithm is developed for the coding of 4D wavelet coefficients. Experiment results confirm that the proposed coding algorithm outperforms conventional algorithms that do not use the 4D zerotree data structure.

This paper presents an extension to the maximum likelihood estimation sample consensus (MLESAC) algorithm by estimating the prior validity of correspondences using both the measured data and a model hypothesis. Validity is determined based on the data set associated with the model that is considered as the best one so far in the previous random trials. The proposed robust algorithm is applied to estimate the fundamental matrix using randomly generated synthetic test data. Experiment results show that at various outlier ratios the proposed algorithm reduces the Sampson error and is also faster (in terms of the number of trials) in comparison to other conventional algorithms.

Intrusion detection in Wireless Sensor Network (WSN) is of practical interest in many applications such as detecting an intruder in a battlefield. The intrusion detection is defined as a mechanism for a WSN to detect the existence of inappropriate, incorrect, or anomalous moving attackers. For this purpose, it is a fundamental issue to characterize the WSN parameters such as node density and sensing range in terms of a desirable detection probability. In this paper, we consider this issue according to two WSN models: homogeneous and heterogeneous WSN. Furthermore, we derive the detection probability by considering two sensing models: single-singing detection and multiple-sensing detection. In addition, we discuss the network connectivity and broadcast reachability, which are necessary conditions to ensure the corresponding detection probability in a WSN. Our simulation results validate the analytical values for both homogeneous and heterogeneous WSNs.

A wireless sensor network (WSN) has to maintain a desirable sensing coverage and periodically report sensed data to the administrative center (i.e., base station) and the reporting period may range from months to years. Coverage and lifetime are two paramount problems in a WSN due to constraint of associated battery power. All previous theoretical analysis on the coverage and lifetime is primarily focused on the random uniform distribution of sensors or some specific network scenarios (e.g., a controllable WSN). In this paper, we provide an analytical framework for the coverage and lifetime of a WSN that follows a two-dimensional Gaussian distribution. We also study the coverage and lifetime when the dimensions of Gaussian dispersion (i.e., x, y) admit different Gaussian parameters (i.e., standard deviation, $\sigma_x \neq\sigma_y$). We identify intrinsic properties of coverage/lifetime in terms of Gaussian distribution parameters, which is a fundamental issue in designing a WSN. Following the results obtained, we further determine the sensor deployment strategies for a WSN that could satisfy a predefined coverage and lifetime. Two deployment algorithms are developed based on using our analytical models and are shown to effectively increase the WSN lifetime.

We propose a polynomial-based scheme that addresses the problem of event region detection (PERD) for wireless sensor networks (WSNs). Nodes of an aggregation tree perform function approximation of the event using multivariate polynomial regression. Only the coefficients of this polynomial are then transmitted up the tree instead of aggregated data. PERD includes two components: event recognition and event report with boundary detection. In addition, PERD is capable of detecting single event or multiple events simultaneously occurring in the WSN. Since PERD is implemented over a polynomial tree on a WSN in a distributed manner, it is easily scalable and computation overhead is very light. Results reveal that event(s) can be detected by PERD with error in detection remaining almost constant achieving a percentage error within a threshold of 10% with increase in communication range.

The problems of energy efficient sensor network configuration and local fusion of sensed data have been addressed separately in the previous works. In this paper, we propose to analyze the sensing accuracy with the consideration of the node distribution and fusion overhead in terms of the energy consumption. By extending existing sensing model in the literature, we quantify how the sensing ranges and node densities of sensor nodes impact the sensing accuracy, and how it affects the fusion overhead and the sensing lifetime of the network. We identify the tradeoff between sensing accuracy and energy consumption in an analytical framework. It can be used to choose optimal parameters of sensor networks to meet the specified sensing or lifetime requirements.

A wireless sensor network (WSN) is composed of wireless sensors using batteries with energy constraints, which limits the network lifetime. How to maximize the network lifetime is an important issue in the design of WSNs. We establish a relationship between node density and network lifetime in a periodically data delivery scenario of WSNs with sensors transmitting data to the sink node periodically. Based on our analysis, we propose a sensor node density deployment method that could implement a differential node density in WSNs so that the lifetime of the network could be maximized. Both theoretic analysis and simulation results show that our method outperforms the uniform node distribution method in terms of the network lifetime

In this paper, we study the node sleep scheduling scheme in the commonly used static disk model for sensor networks, where homogenous sensors are uniformly distributed in a circular area with a stationary sink located at the center. Then, we introduce and analyze a hops-based sleeping scheduling algorithm (HSS) for enhancing the lifetime and energy efficiency of the sensor networks. The HSS divides the circular sensor network into several levels according to the average hop distance based on certain network parameters. By assigning hops-based sleeping probabilities to each sensor, and the network lifetime as well as energy efficiency can be greatly improved. Simulations are performed to compare our proposed HSS scheme with the traditional randomized sleeping scheduling (RSS) scheme, where all the nodes have the uniform sleeping probability. The results demonstrate that our HSS scheme can enhance network lifetime greatly, provide desired QoS requirement effectively, and drastically outperform the RSS scheme

In this paper, we propose a novel localization algorithm using expected hop progress (LAEP) to predict the positions of sensor nodes in WSNs. Our algorithm is based on a hop progress analytical model for a given network topology. By deriving relationship between node connectivity and expected-hop progress from the model, the distance between any two nodes can be accurately computed. As the distance estimation is a key issue in positioning system of WSNs, our expected-hop progress based localization algorithm also achieves reasonable performance in anchor-based WSNs with very few anchors. In addition, we considered the impact of deterministic anchor placement on the algorithm performance when the sensors are random deployed. Both grid and triangular placement of anchor nodes have been examined in this paper. Simulation results are seen to be in good agreement with the theoretical analysis and substantiate the validity of our proposed scheme LAEP

This paper deals with disparity estimation and the reconstruction of intermediate views from stereoscopic images. Using block-wise maximum-likelihood (ML) disparity estimation, it was found that the Laplacian model outperformed the Cauchy and Gaussian models in terms of disparity compensation errors and the number of correspondence matches. The disparity values in occluded regions were then determined using both object-based and reliability-based interpolation. Finally, an adaptive technique was used to interpolate the intermediate views. One distinguishing characteristic of this algorithm is that the left and right-eye images were projected onto the plane of the intermediate view to be reconstructed. This resulted in two projected images. The intermediate view was created using a weighted average of these two projected images with the weights based on the quality of the corresponding areas of the projected images. Subjective examination of the reconstructed images indicate that they have high image quality and good stable depth when viewed stereoscopically. An objective evaluation with the test image sequence "Flower Garden" shows that the proposed algorithm can achieve a peak signal-to-noise ratio gain of around 1 dB, when compared to a reference algorithm.

The conventional two-dimensional wavelet transform used in existing image coders is usually performed through one-dimensional (1-D) filtering in the vertical and horizontal directions, which cannot efficiently represent edges and lines in images. The curved wavelet transform presented in this paper is carried out by applying 1-D filters along curves, rather than being restricted to vertical and horizontal straight lines. The curves are determined based on image content and are usually parallel to edges and lines in the image to be coded. The pixels along these curves can be well represented by a small number of wavelet coefficients. The curved wavelet transform is used to construct a new image coder. The code-stream syntax of the new coder is the same as that of JPEG2000, except that a new marker segment is added to the tile headers. Results of image coding and subjective quality assessment show that the new image coder performs better than, or as well as, JPEG2000. It is particularly efficient for images that contain sharp edges and can provide a PSNR gain of up to 1.67 dB for natural images compared with JPEG2000.

The wavelet transform in JPEG2000 is performed using one-dimensional (1D) filtering in the vertical and horizontal directions. This conventional wavelet transform is not effective to represent edges and lines in images. In this paper we present a curved wavelet transform that improves the performance of JPEG200. The curved wavelet transform is performed using 1D filtering along curves that are usually parallel to edges and lines in images. The pixels along these curves can be well represented by a small number of wavelet coefficients. A simple algorithm is proposed in this paper to determine the curves according to image content. Experimental results show that the curved wavelet transform can significantly improve the compression efficiency of JPEG2000, especially for images that contain sharp edges and lines. The coding gain can be up to 1.6 dB in the terms of PSNR.

For the purpose of temporally scalable video coding and multi-dimensional bit rate control, we conducted experiments of subjective quality assessment for video sequences encoding with variable frame rates and quantization parameters. The experimental results show that the correlation between the PSNR and the subjective quality becomes very low when the two coding parameters vary simultaneously. Then, we propose a new quality metric that takes into account the quantization errors, frame rates, and motion speeds. This metric has a higher correlation with the subjective quality. The average correlation coefficient for five video sequences is as high as 0.93, whereas that of the PSNR is only 0.70.

This paper presents a hybrid de-interlacing algorithm that converts video from interlaced format to progressive format. This hybrid algorithm effectively combines two existing de-interlacing techniques: one that offers high vertical resolution and the other that is robust to erroneous motion vectors. The combination is based on a new measurement of motion vector reliability, so that the hybrid algorithm is dominated by the high-resolution technique if motion vectors are reliable; otherwise, it approaches the robust technique. Motion vector reliability is measured using the a posteriori probability of motion vectors. Experimental results show that this is an effective measure of motion vector reliability. The hybrid algorithm offers high spatial resolution without artifacts caused by erroneous motion vectors, and outperforms four of the best existing techniques in terms of peak signal-to-noise ratio.

The conventional 2D wavelet transform for image coding is performed using a symmetric extension and 1D filtering in the vertical and horizontal directions. In this paper, we present a curved wavelet transform and a method called overlapped extension. The curved wavelet transform is performed using 1D filtering along curves that are usually parallel to edges and lines in images. The pixels along these curves can be well represented using a small number of wavelet coefficients. The overlapped extension is proposed to prevent coding artifacts around the ends of the curves. Experimental results show that, compared with the conventional wavelet transform, the curved wavelet transform with overlapped extension significantly improves the subjective quality of decoded images, and the coding gain in PSNR can be up to 1.5 dB.

A depth-image-based rendering system for generating new views is proposed. One important aspect of the proposed system is that the depth maps are pre-processed using an asymmetric filter to smoothen the sharp changes in depth at object boundaries. In addition to ameliorating the effects of blocky artifacts and other distortions contained in the depth maps, the smoothing reduces or completely removes disocclusion areas where potential artifacts can arise from image warping which is needed to generate images from new viewpoints. The asymmetric nature of the filter reduces the amount of geometric distortion that might be perceived otherwise. We present some results to show that the proposed system provides an improvement in image quality of stereoscopic virtual views while maintaining reasonably good depth quality.

Proposes an algorithm for improving the image quality of disparity-based intermediate view reconstruction by introducing a reliability measurement for disparity estimates. The reliability of disparity estimates is measured with a criterion based on a-posteriori probability of disparity estimates, in which the displaced image intensity difference and the variation of disparity estimates are taken into account. This reliability measurement is then integrated into an intermediate view reconstruction approach, which guides the recovery of disparity values in occluded areas and the reconstruction of the intermediate views. Experimental results with natural stereoscopic sequences show that the disparity reliability measurement is quite effective. The proposed algorithm improves the image quality of reconstructed intermediate views.

An intermediate view reconstruction is required in many applications. In this contribution, an adaptive object-based algorithm for intermediate view reconstruction of stereoscopic images is proposed. The disparity fields between the left-eye and the right-eye images are first estimated and then post-processed for recovering the disparity values in occluded areas. After that, the intermediate view is adaptively interpolated from the stereoscopic images using object-based disparity compensation. Tests with natural stereoscopic sequences show that the reconstructed views have high image quality and create very clean and stable depth when viewed stereoscopically.

This paper presents a technique for unsupervised video segmentation. This technique consists of two phases: initial segmentation and temporal tracking, similar to a number of existing techniques. However, new algorithms for spatial segmentation, marker extraction, and modified watershed transformation are proposed for the present technique. The new algorithms make this technique differ from existing techniques by the following features: (1) it can effectively track fast moving objects, (2) it can detect the appearance of new objects as well as the disappearance of existing objects, and (3) it is computationally efficient because of the use of watershed transformations and a fast motion estimation algorithm. Simulation results demonstrate that the proposed technique can efficiently segment video sequences with fast moving, newly appearing, or disappearing objects in the scene.

The number of regions and length of contour are two basic constraints in segmentation-based motion-compensated video coding. This paper presents a coding scheme which focuses on region number reduction, contour coding, and displaced frame difference (DFD) compression. One of the important features of the proposed scheme is a spatio-temporal simplification algorithm based on morphological filters, with which an image can be segmented into a small number of regions. Another important feature of the scheme is a segmentation map sampling technique which reduces contour length by about 50% with a very small reconstruction error. Experimental results show that, using the proposed scheme, a high compression ratio can be achieved with a small coding error for video sequences such as Miss America and Foreman.

The main difficulty in global motion parameters estimation resides in the disturbance of independently moving objects. The algorithm presented in this letter exploits global motion information not only from stationary objects and the image background, but also from independently moving objects. Simulation results show that the new algorithm is computationally fast and robust to the disturbance caused by independently moving objects.

Morphological skeletonization and decomposition are two well-known schemes for binary image representation, but they are not compact for gray-level images. In this correspondence, bounded gray-level morphology is used to improve their performances for gray-level image representation. Experimental results show that bounded gray-level morphology efficiently reduces the number of skeleton points and the entropy of morphological decomposition.

Character recognition and texture segmentation are performed by a filter based on morphological opening. The filter is characterized by two shape patterns, one of them being larger than the other. If it is applied to an image, the output image will keep only the image objects which are smaller than the large shape pattern but larger that the small one. Thus, the filter has shape band-pass characteristics. It is used for character recognition and texture segmentation. Experimental results show the good performance of the filter for these purposes.

Compression of segmented images is an essential step in segmentation-based approaches for image and video coding. This paper presents a lossless morphological sampling scheme for this purpose. With this sampling scheme, an image can be exactly reconstructed from its samples if it has been filtered by a morphological filter, but removal of any one sample would violate the exact reconstruction. Based on the sampling scheme, a new technique for segmented image compression is then developed. This technique can easily control coding errors and bit rates in the coding or decoding procedure.

The authors define a recursive morphological decomposition algorithm using a group of structuring elements of different sizes. The algorithm decomposes a texture image into a series of images according to their primitive sizes and gray levels. In order to segment accurately the boundaries of adjacent regions, an adaptive technique is proposed based on Bayes error estimation to determine the size of the window over which texture features are extracted. Thus, window size varies according to its position in image and to the textures to be segmented. Experimental results are given.>