A recently developed sparse representation algorithm, has been proved to be useful for multi‐object tracking and this study is a proposal for developing its parallelisation. An online dictionary learning is used for object recognition. After detection, each moving object is represented by a descriptor containing its appearance features and its position feature. Any detected object is classified and indexed according to the sparse solution obtained by an orthogonal matching pursuit (OMP) algorithm. For a real‐time tracking, the visual information needs to be processed very fast without reducing the results accuracy. However, both the large size of the descriptor and the growth of the dictionary after each detection, slow down the system process. In this work, a novel accelerating OMP algorithm implementation on a graphics processing unit is proposed. Experimental results demonstrate the efficiency of the parallel implementation of the used algorithm by significantly reducing the computation time.

This letter studies the sensing performance of random Bernoulli matrices with column size$n$much larger than row size$m$. It is observed that as the compression ratio$n/m$increases, this kind of matrices tends to present a performance floor regarding the guaranteed signal sparsity. The performance floor is effectively estimated with the formula${1 \over 2}(\sqrt {\pi m/2} + 1)$. To the best of our knowledge, it is the first time in compressed sensing, a theoretical estimation is successfully proposed to reflect the real performance.

This paper presents a novel unsupervised algorithm to detect salient regions and to segment out foreground objects from background. In contrast to previous unidirectional saliency-based object segmentation methods, in which only the detected saliency map is used to guide the object segmentation, our algorithm mutually exploits detection/segmentation cues from each other. To achieve this goal, an initial saliency map is generated by the proposed segmentation driven low-rank matrix recovery model. Such a saliency map is exploited to initialize object segmentation model, which is formulated as energy minimization of Markov random field. Mutually, the quality of saliency map is further improved by the segmentation result, and serves as a new guidance for the object segmentation. The optimal saliency map and the final segmentation are achieved by jointly optimizing the defined objective functions. Extensive evaluations on MSRA-B and PASCAL-1500 datasets demonstrate that the proposed algorithm achieves the state-of-the-art performance for both the salient region detection and the object segmentation.

This paper addresses the problem of automatic figure-ground segmentation, which aims at automatically segmenting out all foreground objects from background. The underlying idea of this approach is to transfer segmentation masks of globally and locally (glocally) similar exemplars into the query image. For this purpose, we propose a novel high-level image representation method named as object-oriented descriptor. Using this descriptor, a set of exemplar images glocally similar to the query image is retrieved. Then, using over-segmented regions of these retrieved exemplars, a discriminative classifier is learned on-the-fly and subsequently used to predict foreground probability for the query image. Finally, the optimal segmentation is obtained by combining the online prediction with typical energy optimization of Markov random field. The proposed approach has been extensively evaluated on three datasets, including Pascal VOC 2010, VOC 2011 segmentation challenges, and iCoseg dataset. Experiments show that the proposed approach outperforms state-of-the-art methods and has the potential to segment large-scale images containing unknown objects, which never appear in the exemplar images.

Low-rank matrix recovery (LRMR) model, aiming at decomposing a matrix into a low-rank matrix and a sparse one, has shown the potential to address the problem of saliency detection, where the decomposed low-rank matrix naturally corresponds to the background, and the sparse one captures salient objects. This is under the assumption that the background is consistent and objects are obviously distinctive. Unfortunately, in real images, the background may be cluttered and may have low contrast with objects. Thus directly applying the LRMR model to the saliency detection has limited robustness. This paper proposes a novel approach that exploits bottom-up segmentation as a guidance cue of the matrix recovery. This method is fully unsupervised, yet obtains higher performance than the supervised LRMR model. A new challenging dataset PASCAL-1500 is also introduced to validate the saliency detection performance. Extensive evaluations on the widely used MSRA-1000 dataset and also on the new PASCAL-1500 dataset demonstrate that the proposed saliency model outperforms the state-of-the-art models.

Recently sparse representation has been successfully applied to single object tracking by observing the reconstruction error of candidate object with sparse representation. In practice, sparse representation also shows competitive performance on multi-class classification, and thus is potential for multi-object tracking. In this paper we explore this technique for on-line multi-object tracking through a simple tracking-by-detection scheme, with background subtraction for object detection and sparse representation for object recognition. Final experiments demonstrate that the proposed approach only combining color histogram and 2-dimensional coordinates as features, achieves favorable performance over state-of-the-art work in persistent identity tracking.

We present the sparse binary matrix defined by low-density parity-check (LDPC) codes as measurement matrix in compressed sensing. This kind of matrix owns much stronger orthogonality than current other main measurement matrices. In practice, for a matrix given size, the optimal column degree for high orthogonality can also be determined by progressive edge-growth (PEG) algorithm.

The purpose of this paper is segmenting objects in an image and assigning a predefined semantic label to each object. There are two contributions in this paper. On one hand, semantic segmentation is guided by hierarchical regions instead of by single-level regions or multi-scale regions generated by multiple segmentations. On the other hand, sparse coding is introduced as high level description of the regions, which contributes to reduction of quantization error compared to traditional bag-of-visual-words method. Experiments on the challenging Microsoft Research Cambridge dataset (MSRC 21) show that our algorithm achieves state-of-the-art performance.

In IKONOS imagery, both multispectral (MS) and panchromatic data are provided, with different spatial resolutions. IKONOS images can be fused or pan-sharpened for the visual interpretation of large-area-scale applications. To date, many image fusion techniques have been developed. In particular, the intensity-hue-saturation (IHS)-based methods are well known in quick image pan-sharpening. However, most of these processes produce color distortion due to the unnatural spectral response of IKONOS sensors, particularly in vegetated areas. Hence, many recent methods make use of vegetation enhancement in order to correct the unnatural color appearance. Generally, this enhancement is accomplished using vegetation indexes (VIs). A new fusion approach that produces images with natural colors is proposed. Moreover, in this technique, a high-resolution normalized difference VI is also proposed and used in delineating the vegetation. The procedure is performed in two steps: MS fusion using the IHS technique and vegetation enhancement. Vegetation enhancement is a correction step, and it depends on the considered application. The new approach provides very good results in terms of objective quality measures. In addition, visual analysis proves that the concept of the proposed approach is promising, and it improves well the fusion quality by enhancing the vegetated zones.

We present an efficient content-based image coding called locally adaptive resolution (LAR) offering advanced scalability at different semantic levels, i.e., pixel, block, and region. A local analysis of image activity leads to a nonuniform block representation supporting two layers of image description. The first layer provides global information encoded in the spatial domain enabling a low bit rate while preserving contours. The second layer holds texture information encoded in the spectral domain, enabling scalable bitstream in accordance with the required quality. This basic LAR coding leads to an efficient progressive compression, evaluated through subjective quality tests. Its nonuniform block representation also allows a hierarchical region representation providing higher semantic functionalities. More precisely, the segmentation process can be simultaneously performed at both the coder and the decoder from only the luminance component highly compressed by the first coding layer. This solution provides a representation at a region level while avoiding any contour encoding overhead. Region enhancement can then be realized through the second layer. Furthermore, very high compression of the chromatic components is achieved thanks to this region representation. In this scheme, a low-cost chromatic control, which was first introduced during the segmentation process, increases the consistency of region representation in terms of color.

Scalability and others functionalities such as the region of interest encoding become essential properties of an efficient image coding scheme. Within the framework of lossless compression techniques, S+P and CALIC represent the state-of-the-art. The proposed interleaved S+P algorithm outperforms these method while providing the desired properties. Based on the LAR (locally adaptive resolution) method, an original pyramidal decomposition combined with a DPCM scheme is elaborated. This solution uses the S-transform in such a manner that a refined prediction context is available for each estimation steps. The image coding is done in two main steps, so that the first one supplies a LAR low-resolution image of good visual quality, and the second one allows a lossless reconstruction. The method exploits an implicit context modelling, intrinsic property of our content-based quad-tree like representation.

In this paper, we present some preliminary results obtained with the MSGPR method in the context of pattern recognition: this new method is based on the analysis of closed contour of planar objects. The contour C/sub 0/ of a planar object is parameterised by its curvilinear abscissa u and separated into two signals x(u) and y(u) corresponding to its coordinates x and y. These signals are then filtered with a Gaussian low-pass filter. The size of the sub-consequent contour C/sub /spl sigma// is then adjusted so that it has the same size as the original contour C/sub 0/. Then the contour C/sub GC/(/spl sigma/) thus obtained and the original contour C/sub 0/ yield intersection points that give intersection points map (IPM) which is used to characterise the pattern. By construction, this method is invariant under translation. The results of analysis have shown its invariance under rotation and its resistance against scale change for a large range of scaling. It is a fast and simple algorithm that can be successfully applied in the context of pattern recognition dedicated to planar non-occluded objects. The application of this method in the research of a query pattern in a database has given very encouraging results.

This paper deals with a major problem encountered in the area of remote sensing consisting of the registration of multitemporal and/or multisensor images. In general, such images have different gray-level characteristics, and simple techniques such as those based on correlation cannot be applied directly. In this work, a new automatic satellite image registration approach is proposed. This technique exploits the invariant relations between regions of a reference and a sensed image, respectively. It involves an edge-based selection of the most distinctive control points (CPs) in the reference image. The search for the corresponding CPs in the sensed image is based on local similarity detection by means of template matching according to a combined invariants-based similarity measure. The final warping of the images according to the selected CPs is performed by using the thin-plate spline interpolation. The procedure is fully automatic and computationally efficient. The proposed algorithm for this technique has been successfully applied to register multitemporal SPOT and synthetic aperture radar images from urban and agricultural areas. The experimental results demonstrate the robustness, efficiency and accuracy of the algorithm.

We present a new coding scheme providing compression efficiency (better subjective quality than JPEG2000) and region-level functionalities at low bit-rates for both the sender and the receiver. A contourless coding region description is obtained by a segmentation process at the sender and receiver, supervised by chromatic consistency and operating on a well adapted low resolution Y image. Chromatic images can then be region-based encoded at very low cost. As the region topology fully matches the representation used to encode the content, further enhancement can be globally applied over the whole image or limited to a region of interest.

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.

In the present paper, a set of robust texture features based on morphological residues of opening or closing by reconstruction is introduced. This set of features is proven much more robust to noise than those based on traditional morphological residues. The robustness to noise of this set of features is investigated in detail. An algorithm is constructed to select the most discriminating feature subset. In texture classification experiments, it is found that this feature subset bears high robustness to various noises even when the noise levels are quite high.

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.

In this paper, a quantitative evaluation methodology for morphological filters is presented. The goal of this evaluation scheme is to measure simultaneously the ability of morphological filters in edge sharpness preservation and noise suppression. A general morphological gradient criterion is proposed to divide an image into a series of regions according to its local spatial activity levels. The local mean-square-error (MSE) and local mean-absolute-error (MAE) are used to verify and compare performances of different tested filters. Several efficient and simple structured detail-preserving and noise-removal morphological filters are proposed and tested on simulated images by this scheme to prove its efficiency. For real image processing procedures, a combined filter structure is proposed to improve filter results.

In this work we present a method for multiresolution texture image segmentation via supervised Bayesian classification. This method takes into account a function called classification index CI (or Indice de Classification IC3). This function measures the accuracy rate of a pixel classification after it has been classified. The CI measure is based on the location of the pixel attribute vector in the observation space relative to the classes to which it must be classified. To reduce the time used in the classification process, we propose a new method (ASH: Algorithme de Segmentation Hierarchique3) that segments hierarchically the multiresolution images.

The author describes a coding scheme for color television signals over 34 Mb/s channels. Spatio-temporal blocks are used to reduce both the spatial and temporal redundancies within the blocks; the blocks are independent of one another and of fixed size (5*3*4). Spatial interpolation and temporal prediction are used, along with luminance masking on itself as well as on the chrominance signals. Quantization is adaptive under the visual threshold with a kind of multilevel block transform coding. Color coding is by block-adaptive DPCM (differential pulse code modulation).>

B.T.C. (Block Truncation Coding) is a recent coding scheme for T.V. pictures producing compressed images with less than 2 bits/pixel. B.T.C. divides a picture into small blocks of fixed size : 4×4 pixels. The transmitter computes a two level representation of each block, preserving its local sample moments. Its essential artifact is that edges have tendency to be ragged. We thus propose a modified coding scheme based on statistical edge properties. An edge following algorithm is applied to the transmitted part of the picture. According to the position of edges in adjacent blocks to the transmitted one, a class of its pixels may be reconstructed by a third level issued from the mean of the block. Thus, our solution needs only few additional bits (0.18 bits/pixel) achieving fixed date rate of 2 bits/pixel.