Particle PHD filter based multi-target tracking using discriminative group-structured dictionary learning

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

Multiple target tracking requires data association that operates in conjunction with filtering. When multiple targets are closely spaced, the conventional approaches (as, e.g., MHT/assignment) may not give satisfactory results. This is mainly because of the difficulty in deciding what the number of targets is. Recently, the probability hypothesis density (PHD) filter has been proposed and particle filtering techniques have been developed to implement the PHD filter. In the particle PHD filter, the track labeling problem is not considered, i.e., the PHD is obtained only for a frame at a time, and it is very difficult to perform the multipeak extraction, particularly in high clutter environments. A track labeling method combined with the PHD approach, as well as considering the finite resolution, is proposed here for multitarget tracking, i.e., we keep a separate tracker for each target, use the PHD in the resolution cell to get the estimated number and locations of the targets at each time step, and then perform the track labeling ("peak-to-track" association), whose results can provide information for PHD peak extraction at the next time step. Besides, by keeping a separate tracker for each target, our approach provides more information than the standard particle PHD filter. For example, in group target tracking, if we are interested in the motion of a specific target, we can track this target, which is not possible for the standard particle PHD filter, since the standard particle PHD filter does not keep track labels. Using our approach, multitarget tracking can be performed with automatic track initiation, maintenance, spawning, merging, and termination

For the distance and velocity deception from the new towed decoy, echo signal from the target and decoy appear as one target on time domain and frequency domain because of aliasing. Therefore, independent measurements for the decoy and aircraft are unavailable for conventional algorithm, neither identification and tracking. In this paper is proposed a new algorithm for joint identification and tracking of the decoy and aircraft which are unresolved within radar beam, innovations for which include: First, construction of echo signal model in the three interfering stages. Once stage decided with the decoy presence detection algorithm, the proposed particle filter based measurement generating algorithm sequentially estimates the aircraft and decoy character parameters on different stages, separating the aircraft signal and decoy signal. Secondly, based on the improved labeled particle probability hypothesis density (IL-P-PHD) filter, an algorithm for joint identification and tracking of vertically the unresolved aircraft and decoy is proposed, realizing real time identification and sequential estimation of movement state. Simulation experiment demonstrates that the proposed algorithm behaves in a manner consistent with our expectations.

Multi-target tracking in distributed sensor networks using particle PHD filters

Both interclass variances and intraclass similarities are crucial for improving the classification performance of discriminative dictionary learning (DDL) algorithms. However, existing DDL methods often ignore the combination between the interclass and intraclass properties of dictionary atoms and coding coefficients. To address this problem, in this paper, we propose a discriminative Fisher embedding dictionary learning (DFEDL) algorithm that simultaneously establishes Fisher embedding models on learned atoms and coefficients. Specifically, we first construct a discriminative Fisher atom embedding model by exploring the Fisher criterion of the atoms, which encourages the atoms of the same class to reconstruct the corresponding training samples as much as possible. At the same time, a discriminative Fisher coefficient embedding model is formulated by imposing the Fisher criterion on the profiles (row vectors of the coding coefficient matrix) and coding coefficients, which forces the coding coefficient matrix to become a block-diagonal matrix. Since the profiles can indicate which training samples are represented by the corresponding atoms, the proposed two discriminative Fisher embedding models can alternatively and interactively promote the discriminative capabilities of the learned dictionary and coding coefficients. The extensive experimental results demonstrate that the proposed DFEDL algorithm achieves superior performance in comparison with some state-of-the-art dictionary learning algorithms on both hand-crafted and deep learning-based features.

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.

Exploiting class-wise coding coefficients: Learning a discriminative dictionary for pattern classification

We address the problem of sparse channel representation for downlink channel estimation in multi-user frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems. Existing methods typically adopt discrete Fourier transform (DFT) matrix as a sparse basis to represent sparse channels. However, a sparse basis constructed through dictionary learning method has proven to have strong sparse channel representation. In this work, we develop a discriminative dictionary learning-based sparse channel representation for downlink channel estimation in a multi-user FDD massive MIMO systems. Considering partially shared support between near users, we present a new discriminative dictionary learning (DDL) method for sparse channel representation, based on which the channel estimation scheme is developed. Compared with learning a shared dictionary for all users, it can provide a better representation, thus improving the performance of recovery in the compressive sensing process. Numerical results demonstrate the superior performance of discriminative dictionary as compared to the shared dictionary in terms of normalized mean square error (NMSE) and symbol error rate (SER).

In visual tracking, developing an efficient appearance model is a challenging task due to the influence of various factors, such as illumination variation, occlusion, background clutter, and so on. Existing tracking algorithms use appearance samples from previous frames to form a template set upon which target appearance models are built. However, these appearance models are data-dependent, so they may be corrupted by significant appearance variation. It is difficult to update the templates in challenging environments. In this paper, we propose a robust visual tracking algorithm with an adaptive appearance model using a point-to-set metric learning technique. To do this, we first model a target representation using a set of target templates and a regularized affine hull (RAH) spanned by the target templates. Then, we learn a point-to-set distance metric, which is incorporated into the optimization process to obtain an adaptive target representation. The RAH model covers unseen target appearances by affine combinations of the target templates. Based on the proposed target appearance model, we design an effective template update scheme by adjusting the weights of the target templates. Experimental results on challenging video sequences with comparisons to several state-of-the-art tracking algorithms demonstrate the effectiveness and robustness of the proposed tracking algorithm.

Wild animal detection is an active research area since last many decades among wildlife researchers to study and analyze wild animals and their behavior. This paper presents sparse representation based wild animal detection system using Discriminative Feature-oriented Dictionary Learning (DFDL). DFDL extracts discriminative class-specific features and shows a low complexity method for animal detection. We acquired class-specific dictionaries allowed to represent a new image to identity of the class of the image. Concurrently, these dictionaries are incapable of representing the samples of other classes. The experiments are performed over in-house database compiled by us. We achieved promising results using DFDL with 93% accuracy.

Robust discriminative nonnegative dictionary learning for occluded face recognition

Sparse representation (SR)-based tracking systems have become popular in the past recent years for its effectiveness. However, the underlying assumption of these tracking systems is that the target appearance can be linearly represented by a sparse approximation over a set of templates and a residual term, which usually needs to solve $\ell_1$ norm minimization for many times and brings a heavy computational cost. This paper introduces an efficient tracking system by discovering orthogonalized templates. By orthogonalizing templates from previous frames and removing their correlation, we show that the sparsity of template weights is not necessary in target appearance modeling and thus a least squares regularization can be employed. We also decompose the residual term into two components in observation model to take occlusion cases into consideration. We demonstrate that, in comparison with the SR-based tracking systems that use $\ell_1$ learning, our tracking system is much more computationally efficient while getting an even better performance. Experiments on a variety of challenging video sequences demonstrate both the effectiveness and efficiency of the system.

In deep dictionary learning multiple dictionaries are learned based on information at various levels of abstraction. We propose a novel hierarchical discriminative dictionary learning layer embedded within a neural network with an image classification objective. Discrimination is induced in the learned synthesis dictionaries at multiple hierarchical levels in a simple way by a one-hot-code representation of the class labels during the training backward pass. In addition, local sparse representation objectives are approximated during the forward pass, introducing local regularization. We evaluate our proposal on five known datasets and we either outperform state-of-the-art methods or achieve competitive classification results.

In recent years, online building an adaptive target appearance model has been investigated for robust visual tracking in a dynamic environment. However one inherent problem of adaptive appearance trackers is drift, a gradual adaptation of the tracker to non-targets. To alleviate this problem, we consider visual tracking in a novel online manifold regularization (Online-MR) setting where labeled and unlabeled data arrive sequentially in large volume for tracker update. A discriminative target appearance model based on Haar wavelet is learned at each frame and its output score is used as the input sample feature for Online-MR tracker learning. Such a combination of Online-MR semi-supervised learning and online appearance model adaptation results in a robust tracking scheme that can prevent the tracker from drifting while retain its adaptation to appearance changing. Experimental results demonstrate the effectiveness of the proposed method from comparisons with adaptive appearance model based trackers on several challenging video sequences.

The probability hypothesis density (PHD) filter has emerged as a promising tool for dealing with the multi-target tracking problem in recent years. However, except in some special situations, closed-form recursive update equations for the PHD filter do not exist and the particle filter approaches have to be used. The output of the particle filter at each step is the particle clouds approximation of the PHD. Thus, some special algorithms are needed to extract the target states from those particles. Utilising the information of both particles’ weight and their spatial distribution, an improved algorithm named C-Clean is proposed in this study. This algorithm is comprised of two steps. First, clustering techniques are used to exploit the spatial distribution of particles. Then, within those clusters whose corresponding PHD weight is beyond some predefined threshold, the peak extraction procedure modified from the CLEAN technique is taken to extract the multi-target state. Simulation results demonstrate that its performance is better than those algorithms using the information of particles’ spatial distribution or weight only.