Efficient online subspace learning with an indefinite kernel for visual tracking and recognition

Tracking by Joint Local and Global Search: A Target-Aware Attention-Based Approach

Tracking-by-detection is a very popular framework for single-object tracking that attempts to search the target object within a local search window for each frame. Although such a local search mechanism works well on simple videos, however, it makes the trackers sensitive to extremely challenging scenarios, such as heavy occlusion and fast motion. In this article, we propose a novel and general target-aware attention mechanism (termed TANet) and integrate it with a tracking-by-detection framework to conduct joint local and global search for robust tracking. Specifically, we extract the features of the target object patch and continuous video frames; then, we concatenate and feed them into a decoder network to generate target-aware global attention maps. More importantly, we resort to adversarial training for better attention prediction. The appearance and motion discriminator networks are designed to ensure its consistency in spatial and temporal views. In the tracking procedure, we integrate target-aware attention with multiple trackers by exploring candidate search regions for robust tracking. Extensive experiments on both short- and long-term tracking benchmark datasets all validated the effectiveness of our algorithm.

Visual Object Tracking via Multi-Stream Deep Similarity Learning Networks

Visual tracking remains a challenging research problem because of appearance variations of the object over time, changing cluttered background and requirement for real-time speed. In this paper, we investigate the problem of real-time accurate tracking in a instance-level tracking-by-verification mechanism. We propose a multi-stream deep similarity learning network to learn a similarity comparison model purely off-line. Our loss function encourages the distance between a positive patch and the background patches to be larger than that between the positive patch and the target template. Then, the learned model is directly used to determine the patch in each frame that is most distinctive to the background context and similar to the target template. Within the learned feature space, even if the distance between positive patches becomes large caused by the interference of background clutter, impact from hard distractors from the same class or the appearance change of the target, our method can still distinguish the target robustly using the relative distance. Besides, we also propose a complete framework considering the recovery from failures and the template updating to further improve the tracking performance without taking too much computing resource. Experiments on visual tracking benchmarks show the effectiveness of the proposed tracker when comparing with several recent real-time-speed trackers as well as trackers already included in the benchmarks.

Combining Spatio-Temporal Context and Kalman Filtering for Visual Tracking

As one of the core contents of intelligent monitoring, target tracking is the basis for video content analysis and processing. In visual tracking, due to occlusion, illumination changes, and pose and scale variation, handling such large appearance changes of the target object and the background over time remains the main challenge for robust target tracking. In this paper, we present a new robust algorithm (STC-KF) based on the spatio-temporal context and Kalman filtering. Our approach introduces a novel formulation to address the context information, which adopts the entire local information around the target, thereby preventing the remaining important context information related to the target from being lost by only using the rare key point information. The state of the object in the tracking process can be determined by the Euclidean distance of the image intensity in two consecutive frames. Then, the prediction value of the Kalman filter can be updated as the Kalman observation to the object position and marked on the next frame. The performance of the proposed STC-KF algorithm is evaluated and compared with the original STC algorithm. The experimental results using benchmark sequences imply that the proposed method outperforms the original STC algorithm under the conditions of heavy occlusion and large appearance changes.

Linear Maximum Margin Classifier for Learning from Uncertain Data

In this paper, we propose a maximum margin classifier that deals with uncertainty in data input. More specifically, we reformulate the SVM framework such that each training example can be modeled by a multi-dimensional Gaussian distribution described by its mean vector and its covariance matrix-the latter modeling the uncertainty. We address the classification problem and define a cost function that is the expected value of the classical SVM cost when data samples are drawn from the multi-dimensional Gaussian distributions that form the set of the training examples. Our formulation approximates the classical SVM formulation when the training examples are isotropic Gaussians with variance tending to zero. We arrive at a convex optimization problem, which we solve efficiently in the primal form using a stochastic gradient descent approach. The resulting classifier, which we name SVM with Gaussian Sample Uncertainty (SVM-GSU), is tested on synthetic data and five publicly available and popular datasets; namely, the MNIST, WDBC, DEAP, TV News Channel Commercial Detection, and TRECVID MED datasets. Experimental results verify the effectiveness of the proposed method.

Developmental Approach for Behavior Learning Using Primitive Motion Skills

Imitation learning through self-exploration is essential in developing sensorimotor skills. Most developmental theories emphasize that social interactions, especially understanding of observed actions, could be first achieved through imitation, yet the discussion on the origin of primitive imitative abilities is often neglected, referring instead to the possibility of its innateness. This paper presents a developmental model of imitation learning based on the hypothesis that humanoid robot acquires imitative abilities as induced by sensorimotor associative learning through self-exploration. In designing such learning system, several key issues will be addressed: automatic segmentation of the observed actions into motion primitives using raw images acquired from the camera without requiring any kinematic model; incremental learning of spatio-temporal motion sequences to dynamically generates a topological structure in a self-stabilizing manner; organization of the learned data for easy and efficient retrieval using a dynamic associative memory; and utilizing segmented motion primitives to generate complex behavior by the combining these motion primitives. In our experiment, the self-posture is acquired through observing the image of its own body posture while performing the action in front of a mirror through body babbling. The complete architecture was evaluated by simulation and real robot experiments performed on DARwIn-OP humanoid robot.

A Biologically Inspired Appearance Model for Robust Visual Tracking

In this paper, we propose a biologically inspired appearance model for robust visual tracking. Motivated in part by the success of the hierarchical organization of the primary visual cortex (area V1), we establish an architecture consisting of five layers: whitening, rectification, normalization, coding, and pooling. The first three layers stem from the models developed for object recognition. In this paper, our attention focuses on the coding and pooling layers. In particular, we use a discriminative sparse coding method in the coding layer along with spatial pyramid representation in the pooling layer, which makes it easier to distinguish the target to be tracked from its background in the presence of appearance variations. An extensive experimental study shows that the proposed method has higher tracking accuracy than several state-of-the-art trackers.

A Comprehensive Performance Evaluation of Deformable Face Tracking "In-the-Wild"

Recently, technologies such as face detection, facial landmark localisation and face recognition and verification have matured enough to provide effective and efficient solutions for imagery captured under arbitrary conditions (referred to as "in-the-wild"). This is partially attributed to the fact that comprehensive "in-the-wild" benchmarks have been developed for face detection, landmark localisation and recognition/verification. A very important technology that has not been thoroughly evaluated yet is deformable face tracking "in-the-wild". Until now, the performance has mainly been assessed qualitatively by visually assessing the result of a deformable face tracking technology on short videos. In this paper, we perform the first, to the best of our knowledge, thorough evaluation of state-of-the-art deformable face tracking pipelines using the recently introduced 300 VW benchmark. We evaluate many different architectures focusing mainly on the task of on-line deformable face tracking. In particular, we compare the following general strategies: (a) generic face detection plus generic facial landmark localisation, (b) generic model free tracking plus generic facial landmark localisation, as well as (c) hybrid approaches using state-of-the-art face detection, model free tracking and facial landmark localisation technologies. Our evaluation reveals future avenues for further research on the topic.

View-Invariant Visuomotor Processing in Computational Mirror Neuron System for Humanoid

Mirror neurons are visuo-motor neurons found in primates and thought to be significant for imitation learning. The proposition that mirror neurons result from associative learning while the neonate observes his own actions has received noteworthy empirical support. Self-exploration is regarded as a procedure by which infants become perceptually observant to their own body and engage in a perceptual communication with themselves. We assume that crude sense of self is the prerequisite for social interaction. However, the contribution of mirror neurons in encoding the perspective from which the motor acts of others are seen have not been addressed in relation to humanoid robots. In this paper we present a computational model for development of mirror neuron system for humanoid based on the hypothesis that infants acquire MNS by sensorimotor associative learning through self-exploration capable of sustaining early imitation skills. The purpose of our proposed model is to take into account the view-dependency of neurons as a probable outcome of the associative connectivity between motor and visual information. In our experiment, a humanoid robot stands in front of a mirror (represented through self-image using camera) in order to obtain the associative relationship between his own motor generated actions and his own visual body-image. In the learning process the network first forms mapping from each motor representation onto visual representation from the self-exploratory perspective. Afterwards, the representation of the motor commands is learned to be associated with all possible visual perspectives. The complete architecture was evaluated by simulation experiments performed on DARwIn-OP humanoid robot.

Learning Subspace-Based RBFNN Using Coevolutionary Algorithm for Complex Classification Tasks

Many real-world classification problems are characterized by samples of a complex distribution in the input space. The classification accuracy is determined by intrinsic properties of all samples in subspaces of features. This paper proposes a novel algorithm for the construction of radial basis function neural network (RBFNN) classifier based on subspace learning. In this paper, feature subspaces are obtained for every hidden node of the RBFNN during the learning process. The connection weights between the input layer and the hidden layer are adjusted to produce various subspaces with dominative features for different hidden nodes. The network structure and dominative features are encoded in two subpopulations that are cooperatively coevolved using the coevolutionary algorithm to achieve a better global optimality for the estimated RBFNN. Experimental results illustrate that the proposed algorithm is able to obtain RBFNN models with both better classification accuracy and simpler network structure when compared with other learning algorithms. Thus, the proposed model provides a more flexible and efficient approach to complex classification tasks by employing the local characteristics of samples in subspaces.

Online kernel slow feature analysis for temporal video segmentation and tracking

Slow feature analysis (SFA) is a dimensionality reduction technique which has been linked to how visual brain cells work. In recent years, the SFA was adopted for computer vision tasks. In this paper, we propose an exact kernel SFA (KSFA) framework for positive definite and indefinite kernels in Krein space. We then formulate an online KSFA which employs a reduced set expansion. Finally, by utilizing a special kind of kernel family, we formulate exact online KSFA for which no reduced set is required. We apply the proposed system to develop a SFA-based change detection algorithm for stream data. This framework is employed for temporal video segmentation and tracking. We test our setup on synthetic and real data streams. When combined with an online learning tracking system, the proposed change detection approach improves upon tracking setups that do not utilize change detection.

Indefinite Proximity Learning: A Review

Efficient learning of a data analysis task strongly depends on the data representation. Most methods rely on (symmetric) similarity or dissimilarity representations by means of metric inner products or distances, providing easy access to powerful mathematical formalisms like kernel or branch-and-bound approaches. Similarities and dissimilarities are, however, often naturally obtained by nonmetric proximity measures that cannot easily be handled by classical learning algorithms. Major efforts have been undertaken to provide approaches that can either directly be used for such data or to make standard methods available for these types of data. We provide a comprehensive survey for the field of learning with nonmetric proximities. First, we introduce the formalism used in nonmetric spaces and motivate specific treatments for nonmetric proximity data. Second, we provide a systematization of the various approaches. For each category of approaches, we provide a comparative discussion of the individual algorithms and address complexity issues and generalization properties. In a summarizing section, we provide a larger experimental study for the majority of the algorithms on standard data sets. We also address the problem of large-scale proximity learning, which is often overlooked in this context and of major importance to make the method relevant in practice. The algorithms we discuss are in general applicable for proximity-based clustering, one-class classification, classification, regression, and embedding approaches. In the experimental part, we focus on classification tasks.

Universal blind image quality assessment metrics via natural scene statistics and multiple kernel learning

Universal blind image quality assessment (IQA) metrics that can work for various distortions are of great importance for image processing systems, because neither ground truths are available nor the distortion types are aware all the time in practice. Existing state-of-the-art universal blind IQA algorithms are developed based on natural scene statistics (NSS). Although NSS-based metrics obtained promising performance, they have some limitations: 1) they use either the Gaussian scale mixture model or generalized Gaussian density to predict the nonGaussian marginal distribution of wavelet, Gabor, or discrete cosine transform coefficients. The prediction error makes the extracted features unable to reflect the change in nonGaussianity (NG) accurately. The existing algorithms use the joint statistical model and structural similarity to model the local dependency (LD). Although this LD essentially encodes the information redundancy in natural images, these models do not use information divergence to measure the LD. Although the exponential decay characteristic (EDC) represents the property of natural images that large/small wavelet coefficient magnitudes tend to be persistent across scales, which is highly correlated with image degradations, it has not been applied to the universal blind IQA metrics; and 2) all the universal blind IQA metrics use the same similarity measure for different features for learning the universal blind IQA metrics, though these features have different properties. To address the aforementioned problems, we propose to construct new universal blind quality indicators using all the three types of NSS, i.e., the NG, LD, and EDC, and incorporating the heterogeneous property of multiple kernel learning (MKL). By analyzing how different distortions affect these statistical properties, we present two universal blind quality assessment models, NSS global scheme and NSS two-step scheme. In the proposed metrics: 1) we exploit the NG of natural images using the original marginal distribution of wavelet coefficients; 2) we measure correlations between wavelet coefficients using mutual information defined in information theory; 3) we use features of EDC in universal blind image quality prediction directly; and 4) we introduce MKL to measure the similarity of different features using different kernels. Thorough experimental results on the Laboratory for Image and Video Engineering database II and the Tampere Image Database2008 demonstrate that both metrics are in remarkably high consistency with the human perception, and overwhelm representative universal blind algorithms as well as some standard full reference quality indexes for various types of distortions.

Mean vector component analysis for visualization and clustering of nonnegative data

Mean vector component analysis (MVCA) is introduced as a new method for visualization and clustering of nonnegative data. The method is based on dimensionality reduction by preserving the squared length, and implicitly also the direction, of the mean vector of the original data. The optimal mean vector preserving basis is obtained from the spectral decomposition of the inner-product matrix, and it is shown to capture clustering structure. MVCA corresponds to certain uncentered principal component analysis (PCA) axes. Unlike traditional PCA, these axes are in general not corresponding to the top eigenvalues. MVCA is shown to produce different visualizations and sometimes considerably improved clustering results for nonnegative data, compared with PCA.

Constraint verification with kernel machines

Based on a recently proposed framework of learning from constraints using kernel-based representations, in this brief, we naturally extend its application to the case of inferences on new constraints. We give examples for polynomials and first-order logic by showing how new constraints can be checked on the basis of given premises and data samples. Interestingly, this gives rise to a perceptual logic scheme in which the inference mechanisms do not rely only on formal schemes, but also on the data probability distribution. It is claimed that when using a properly relaxed computational checking approach, the complementary role of data samples makes it possible to break the complexity barriers of related formal checking mechanisms.

Model-based online learning with kernels

New optimization models and algorithms for online learning with Kernels (OLK) in classification, regression, and novelty detection are proposed in a reproducing Kernel Hilbert space. Unlike the stochastic gradient descent algorithm, called the naive online Reg minimization algorithm (NORMA), OLK algorithms are obtained by solving a constrained optimization problem based on the proposed models. By exploiting the techniques of the Lagrange dual problem like Vapnik's support vector machine (SVM), the solution of the optimization problem can be obtained iteratively and the iteration process is similar to that of the NORMA. This further strengthens the foundation of OLK and enriches the research area of SVM. We also apply the obtained OLK algorithms to problems in classification, regression, and novelty detection, including real time background substraction, to show their effectiveness. It is illustrated that, based on the experimental results of both classification and regression, the accuracy of OLK algorithms is comparable with traditional SVM-based algorithms, such as SVM and least square SVM (LS-SVM), and with the state-of-the-art algorithms, such as Kernel recursive least square (KRLS) method and projectron method, while it is slightly higher than that of NORMA. On the other hand, the computational cost of the OLK algorithm is comparable with or slightly lower than existing online methods, such as above mentioned NORMA, KRLS, and projectron methods, but much lower than that of SVM-based algorithms. In addition, different from SVM and LS-SVM, it is possible for OLK algorithms to be applied to non-stationary problems. Also, the applicability of OLK in novelty detection is illustrated by simulation results.