Sparse coding based visual tracking: Review and experimental comparison

Sparse coding has been used for target appearance modeling and applied successfully in visual tracking. However, noise may be inevitably introduced into the representation due to background clutter. To cope with this problem, we propose a saliency weighted sparse coding appearance model for visual tracking. Firstly, a spectral filtering based visual attention computational model, which combines both bottom-up and top-down visual attention, is proposed to calculate saliency map. Secondly, pooling operation in sparse coding is weighted by calculated saliency map to help target representation focus on distinctive features and suppress background clutter. Extensive experiments on a recently proposed tracking benchmark demonstrate that the proposed algorithm outperforms state-of-the-art methods in tracking objects under background clutter.

Correlation filter (CF) based trackers have gained significant attention in the field of visual single-object tracking, owing to their favorable performance and high efficiency; however, existing trackers still suffer from model drift caused by boundary effects and filter degradation. In visual tracking, long-term occlusion and large appearance variations easily cause model degradation. To remedy these drawbacks, we propose a sparse adaptive spatial-temporal context-aware method that effectively avoids model drift. Specifically, a global context is explicitly incorporated into the correlation filter to mitigate boundary effects. Subsequently, an adaptive temporal regularization constraint is adopted in the filter training stage to avoid model degradation. Meanwhile, a sparse response constraint is introduced to reduce the risk of further model drift. Furthermore, we apply the alternating direction multiplier method (ADMM) to derive a closed-solution of the object function with a low computational cost. In addition, an updating scheme based on the APCE-pool and Peak-pool is proposed to reveal the tracking condition and ensure updates of the target’s appearance model with high-confidence. The Kalam filter is adopted to track the target when the appearance model is persistently unreliable and abnormality occurs. Finally, extensive experimental results on OTB-2013, OTB-2015 and VOT2018 datasets show that our proposed tracker performs favorably against several state-of-the-art trackers.

Automatic prostate segmentation from MR images is an important task in various clinical applications such as prostate cancer staging and MR-guided radiotherapy planning. However, the large appearance and shape variations of the prostate in MR images make the segmentation problem difficult to solve. Traditional Active Shape/Appearance Model (ASM/AAM) has limited accuracy on this problem, since its basic assumption, i.e., both shape and appearance of the targeted organ follow Gaussian distributions, is invalid in prostate MR images. To this end, the authors propose a sparse dictionary learning method to model the image appearance in a nonparametric fashion and further integrate the appearance model into a deformable segmentation framework for prostate MR segmentation. To drive the deformable model for prostate segmentation, the authors propose nonparametric appearance and shape models. The nonparametric appearance model is based on a novel dictionary learning method, namely distributed discriminative dictionary (DDD) learning, which is able to capture fine distinctions in image appearance. To increase the differential power of traditional dictionary-based classification methods, the authors' DDD learning approach takes three strategies. First, two dictionaries for prostate and nonprostate tissues are built, respectively, using the discriminative features obtained from minimum redundancy maximum relevance feature selection. Second, linear discriminant analysis is employed as a linear classifier to boost the optimal separation between prostate and nonprostate tissues, based on the representation residuals from sparse representation. Third, to enhance the robustness of the authors' classification method, multiple local dictionaries are learned for local regions along the prostate boundary (each with small appearance variations), instead of learning one global classifier for the entire prostate. These discriminative dictionaries are located on different patches of the prostate surface and trained to adaptively capture the appearance in different prostate zones, thus achieving better local tissue differentiation. For each local region, multiple classifiers are trained based on the randomly selected samples and finally assembled by a specific fusion method. In addition to this nonparametric appearance model, a prostate shape model is learned from the shape statistics using a novel approach, sparse shape composition, which can model nonGaussian distributions of shape variation and regularize the 3D mesh deformation by constraining it within the observed shape subspace. The proposed method has been evaluated on two datasets consisting of T2-weighted MR prostate images. For the first (internal) dataset, the classification effectiveness of the authors' improved dictionary learning has been validated by comparing it with three other variants of traditional dictionary learning methods. The experimental results show that the authors' method yields a Dice Ratio of 89.1% compared to the manual segmentation, which is more accurate than the three state-of-the-art MR prostate segmentation methods under comparison. For the second dataset, the MICCAI 2012 challenge dataset, the authors' proposed method yields a Dice Ratio of 87.4%, which also achieves better segmentation accuracy than other methods under comparison. A new magnetic resonance image prostate segmentation method is proposed based on the combination of deformable model and dictionary learning methods, which achieves more accurate segmentation performance on prostate T2 MR images.

Structured sparse representation has been recently found to achieve better efficiency and robustness in exploiting the target appearance model in tracking systems with both holistic and local information. Therefore, to better simultaneously discriminate multi-targets from their background, we propose a novel video-based multi-target tracking system that combines the particle probability hypothesis density (PHD) filter with discriminative group-structured dictionary learning. The discriminative dictionary with group structure learned by the hierarchical K-means clustering algorithm implicitly associates the dictionary atoms with the group labels, simultaneously enforcing the target candidates from the same group (class) to share the same structured sparsity pattern. Furthermore, we propose a new joint likelihood calculation by relating the discriminative sparse codes with the maximum voting technique to enhance the particle PHD updating step. Experimental results on two publicly available benchmark video sequences confirm the improved performance of our proposed method over other state-of-the-art techniques in video-based multi-target tracking.

An efficient iterative Earth Mover's Distance (iEMD) algorithm for visual tracking is proposed in this paper. The Earth Mover's Distance (EMD) is used as the similarity measure to search for the optimal template candidates in feature-spatial space in a video sequence. The local sparse representation is used as the appearance model for the iEMD tracker. The maximum-alignment-pooling method is used for constructing a sparse coding histogram which reduces the computational complexity of the EMD optimization. The template update algorithm based on the EMD is also presented. When the camera is mounted on a moving robot, e.g., a flying quadcopter, the camera could experience a sudden and rapid motion leading to large inter-frame movements. To ensure that the tracking algorithm converges, a gyro-aided extension of the iEMD tracker is presented, where synchronized gyroscope information is utilized to compensate for the rotation of the camera. The iEMD algorithm's performance is evaluated using eight publicly available videos from the CVPR 2013 dataset. The performance of the iEMD algorithm is compared with eight state-of-the-art tracking algorithms based on relative percentage overlap. Experimental results show that the iEMD algorithm performs robustly in the presence of illumination variation and deformation. The robustness of this algorithm for large inter-frame displacements is also illustrated.

Appearance change of moving targets is a challenging problem in visual tracking. In this paper, we present a novel visual object tracking algorithm based on the observation dependent hidden Markov model (OD-HMM) framework. The observation dependency is computed by structure complexity coefficients (SCC) which is defined to predict the target appearance change. Unlike conventional methods addressing the appearance change problem by investigating different online appearance models, we handle this problem by addressing the fundamental reason of motion -related appearance change during visual tracking. Based on the analysis of motion-related appearance change, we investigate the relationship between the structure of the object surface and the appearance stability. The appearance of complex structural regions is easier to change compared with that of smooth structural regions with object moving. Based on this, we define SCC to predict the appearance stability of moving objects. Different from the standard HMM-based tracking algorithms where observations between different frames are assumed to be independent, we consider the observation dependency between consecutive frames with the information provided by SCC. Moreover , we present a novel outlier removing method in appearance model updating which helps to avoid error accumulation. Experimental results on challenging video sequences demonstrate that the proposed visual tracking algorithm with OD-HMM and SCC achieves better performance than existing related tracking algorithms.

Effective representation methods and proper signal priors are crucial in most signal processing applications. In this thesis we focus on different structured models and we design appropriate schemes that allow the discovery of low dimensional latent structures that characterise and identify the signals. Motivated by the highly non-linear structure of most datasets, we firstly investigate the geometry of manifolds. Manifolds are low dimensional, non-linear structures that are naturally employed to describe sets of strongly related signals such as the images of a 3-D object captured from different viewpoints. However, the use of manifolds in applications is not straightforward due to their usually non-analytic and non-linear form. We propose here a way to `disassemble' a manifold into simpler components by approximating it with affine subspaces. Our objective is to discover a set of low dimensional affine subspaces that can represent manifold data accurately while preserving the manifold's structure. To this end, we employ a greedy technique that iteratively merges manifold samples into groups based on the difference of local tangents. We use our algorithm to approximate synthetic and real manifolds and to demonstrate that it is competitive to state-of-the-art techniques. Then, we consider structured sparse representations of signals and we propose a new sparsity model, where signals are essentially composed of a small number of structured {\it molecules }. We define the molecules to be linear combinations of a small number of atoms in a redundant dictionary. Our multi-level model takes into account the energy distribution of the significant signal components in addition to their support. It permits to define typical visual patterns and recognise them in prototypical or deformed form. We define a new structural difference measure between molecules and their deformed versions, which is based on their sparse codes and we create an algorithm for decomposing signals into molecules that can account for different deviations in the internal molecule structure. Our experiments verify the benefits of the new image model in various restoration tasks and they confirm that the development of proper models that extend the mere notion of sparsity can be very useful for various inverse problems in imaging. Finally, we investigate the problem of learning molecule representations directly in the sparse code domain. We constrain sparse codes to be linear combinations of a few, possibly deformed, molecules and we design an algorithm that can learn the structure from the codes without transforming them back into the signal domain. To this end, we take advantage of our structural difference which is based on the sparse codes and we devise a scheme for representing the codes with molecules and learn the molecules at the same time. To illustrate the effectiveness of our proposed algorithm we apply it to various synthetic and real datasets and we compare the results with traditional sparse coding and dictionary learning techniques. From the experiments, we verify the superior performance of our scheme in interpreting and recognising correctly the underlying structure. In short, in this thesis we are interested in low-dimensional, structured models. Among the various choices, we focus on manifolds and sparse representations and we propose schemes that enhance their structural properties and highlight their effectiveness in signal representations.

Intelligent video surveillance is currently one of the most active research topics in computer vision, especially when facing the explosion of video data captured by a large number of surveillance cameras. As a key step of an intelligent surveillance system, robust visual tracking is very challenging for computer vision. However, it is a basic functionality of the human visual system (HVS). Psychophysical findings have shown that the receptive fields of simple cells in the visual cortex can be characterized as being spatially localized, oriented, and bandpass, and it forms a sparse, distributed representation of natural images. In this article, motivated by these findings, we propose an effective appearance model based on sparse coding and apply it in visual tracking. Specifically, we consider the responses of general basis functions extracted by independent component analysis on a large set of natural image patches as features and model the appearance of the tracked target as the probability distribution of these features. In order to make the tracker more robust to partial occlusion, camouflage environments, pose changes, and illumination changes, we further select features that are related to the target based on an entropy-gain criterion and ignore those that are not. The target is finally represented by the probability distribution of those related features. The target search is performed by minimizing the Matusita distance between the distributions of the target model and a candidate using Newton-style iterations. The experimental results validate that the proposed method is more robust and effective than three state-of-the-art methods.

Image representation based on sparse coding generalizes the bag of words model. Although it reduces the reconstruction error for local features to achieve the state-of-the-art image classification performance, the large computational cost hinders the application of sparse coding-based image features. In this paper, we propose approximating a sparse code using the output of a simple neural network. The resulting parameter learning model for the neural network automatically incorporates non-negative and shift-invariant constraints, leading to an efficient normalized non-negative sparse coding (N <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> SC) sparse encoder. Without the use of the traditional iterative process to solve the sparse coding objective, the sparse encoder directly “converts” each local feature into a sparse code. We also introduce a method for training the encoder based on the auto-encoder method. In addition, we formally propose the corresponding sparse coding scheme called N <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> SC, which enforces both the non-negative constraint and the shift-invariant constraint in addition to the traditional sparse coding criteria. As demonstrated by several experiments, the obtained N <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> SC encoder requires only 3%-10% of the processing time for image feature extraction compared with the standard sparse coding scheme. At the same time, the features extracted using the exact solutions of the N <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> SC coding scheme and the N <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> SC encoder offer superior image classification accuracy compared to the accuracy of many existing sparse coding-based representations.

Joint discriminative and shared dictionary learning with dictionary extension strategy for bearing fault classification

Effective object appearance model is one of the key issues for the success of visual tracking. Since the appearance of a target and the environment changes dynamically, the majority of existed visual tracking algorithms tend to drift away from targets. To address this issue, we propose a robust tracking algorithm by integrating the generative and discriminative model. The object appearance model is made up of generative target model and a discriminative classifier. For the generative target model, we adopt the weighted structural local sparse appearance model combining patch based gray value and Histogram of Oriented Gradients feature as the patch dictionary. By sampling positives and negatives, alignment-pooling features are obtained based on the patch dictionary through local sparse coding, then we use support vector machine to train the discriminative classifier. The proposed method is embedded into a Bayesian inference framework for visual tracking. A combined matching method is adopted to improve the proposal distribution of the particle filter. Moreover, in order to adapt the situation change, the patch dictionary and discriminative classifier are updated by incremental learning every five frames. Experimental results on some publicly available benchmarks of video sequences demonstrate the accuracy and effectiveness of our tracker.

Airplane detection based on rotation invariant and sparse coding in remote sensing images

While many visual tracking methods have been proposed, the challenges such as severe deformation, cluttered background and heavy occlusion are still under well solved. This paper proposed a new visual tracking method by combing the sparse representation and global measure. We flrst construct an appearance model by sparse representation with the patches from target rectangles and their surrounding backgrounds. With this appearance model, we successfully identify the patches of target undergoing heavy occlusion or severe deformation. Then, we deflne a global measure based on the cues of saliency and color contrast to detect the tracking object. This measure performs well in distinguishing object from background especially in cluttered background. Many experiments on difierent challenge image sequences demonstrate that our method is much more robust and stable in tracking.

Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this paper, we propose a novel top-down saliency model that jointly learns a Conditional Random Field (CRF) and a discriminative dictionary. The proposed model is formulated based on a CRF with latent variables. By using sparse codes as latent variables, we train the dictionary modulated by CRF, and meanwhile a CRF with sparse coding. We propose a max-margin approach to train our model via fast inference algorithms. We evaluate our model on the Graz-02 and PASCAL VOC 2007 datasets. Experimental results show that our model performs favorably against the state-of-the-art top-down saliency methods. We also observe that the dictionary update significantly improves the model performance.

This paper proposes a new approach based on object sparse representation (OSR) for object tracking. The OSR method implemented by L1-norm minimization is robust to the partial occlusion and deterioration in object images. Firstly, we dynamically construct a set of samples in a predicted searching window in a new video frame, on which the sparse representation of the tracked object can be calculated by the OSR method. This procedure can automatically select the subset of the samples as a basis which most compactly expresses the object with small residuals and rejects all other possible but less compact representations. In terms of this sparse and compact representation, the instantaneous tracking result is achieved in the new video frame. Extensive comparative experiments demonstrate the effectiveness of the proposed approach especially in occlusion context.