Tracking In Video Sequences Research Articles

A Novel Dynamic System in the Space of SPD Matrices with Applications to Appearance Tracking

In this paper, we address the problem of video tracking using covariance descriptors constructed from simple features extracted from the given image sequence. Theoretically, this can be posed as a tracking problem in the space of ($n \times n$) symmetric positive definite (SPD) matrices denoted by $P_n$. A novel probabilistic dynamic model in $P_n$ based on Riemannian geometry and probability theory is presented in conjunction with a geometric (intrinsic) recursive filter for tracking a time sequence of SPD matrix measurements in a Bayesian framework. This newly developed filtering method can be used for the covariance descriptor updating problem in covariance tracking, leading to new and efficient video tracking algorithms. To show the accuracy and efficiency of our tracker in comparison to the state-of-the-art, we present synthetic experiments on $P_n$ and several real data experiments for tracking in video sequences.

Object Tracking with an Evolutionary Particle Filter Based on Self-Adaptive Multi-Features Fusion

Particle filter algorithms are widely used for object tracking in video sequences, but the standard particle filter algorithm cannot solve the validity of particles ideally. To solve the problems of particle degeneration and sample impoverishment in a particle filter tracking algorithm, an improved object tracking algorithm is proposed, which combines a multi-feature fusion method and a genetic evolution mechanism. The algorithm dynamically computes the feature's fusion weight by the discriminability of each vision feature and then constructs the important density function based on selecting a feature's fusion method adaptively. Moreover, a self-adaptive genetic evolutionary mechanism is introduced into the particle resampling process and makes the particle become an agent with the ability of dynamic self-adaption. With self-adaptive crossover and mutation operators, the evolution system produces a large number of new particles, which can better approximate the true state of the tracking object. The experimental results show that the proposed object tracking algorithm surpasses the conventional particle filter on both robustness and accuracy, even though the tracking object is very challenging regarding illumination variation, structural deformation, the interference of similar targets and occlusion.

Niche PSO Particle Filter with Particles Fusion for Target Tracking

An improved particle filter algorithm is proposed to track a randomly moving target in video. In particle filter framework, a particle swarm optimization improved by niche technique which implemented by restricted competition selection is integrated. It can move particles into high likelihood area of target and form multi-population distribution, so that the searching capability of particles is enhanced and then the adaptation to the change of dynamic target state is improved. The particles of niching particle swarm optimization and the particles of particle filter are integrated for new particle weight calculation and finally realize a new particle filter for target tracking in video sequence.

Efficient object detection and tracking in video sequences

One of the most important problems in computer vision is the computation of the two-dimensional projective transformation (homography) that maps features of planar objects in different images and videos. This computation is required by many applications such as image mosaicking, image registration, and augmented reality. The real-time performance imposes constraints on the methods used. In this paper, we address the real-time detection and tracking of planar objects in a video sequence where the object of interest is given by a reference image template. Most existing approaches for homography estimation are based on two steps: feature extraction (first step) followed by a combinatorial optimization method (second step) to match features between the reference template and the scene frame. This paper has two main contributions. First, we detect both planar and nonplanar objects via efficient object feature classification in the input images, which is applied prior to performing the matching step. Second, for the tracking part (planar objects), we propose a fast method for the computation of the homography that is based on the transferred object features and their associated local raw brightness. The advantage of the proposed schemes is a fast matching as well as fast and robust object registration that is given by either a homography or three-dimensional pose.

Robust Tracking Using Particle Filter with a Hybrid Feature

This paper presents a novel method for robust object tracking in video sequences using a hybrid feature-based observation model in a particle filtering framework. An ideal observation model should have both high ability to accurately distinguish objects from the background and high reliability to identify the detected objects. Traditional features are better at solving the former problem but weak in solving the latter one. To overcome that, we adopt a robust and dynamic feature called Grayscale Arranging Pairs (GAP), which has high discriminative ability even under conditions of severe illumination variation and dynamic background elements. Together with the GAP feature, we also adopt the color histogram feature in order to take advantage of traditional features in resolving the first problem. At the same time, an efficient and simple integration method is used to combine the GAP feature with color information. Comparative experiments demonstrate that object tracking with our integrated features performs well even when objects go across complex backgrounds.

Spatial color histogram based center voting method for subsequent object tracking and segmentation

In this paper, we introduce an algorithm for object tracking in video sequences. In order to represent the object to be tracked, we propose a new spatial color histogram model which encodes both the color distribution and spatial information. Using this spatial color histogram model, a voting method based on the generalized Hough transform is employed to estimate the object location from frame to frame. The proposed voting based method, called the center voting method, requests every pixel near the previous object center to cast a vote for locating the new object center in the new frame. Once the location of the object is obtained, the back projection method is used to segment the object from the background. Experiment results show successful tracking of the object even when the object being tracked changes in size and shares similar color with the background.

A hierarchical feature fusion framework for adaptive visual tracking

A Hierarchical Model Fusion (HMF) framework for object tracking in video sequences is presented. The Bayesian tracking equations are extended to account for multiple object models. With these equations as a basis a particle filter algorithm is developed to efficiently cope with the multi-modal distributions emerging from cluttered scenes. The update of each object model takes place hierarchically so that the lower dimensional object models, which are updated first, guide the search in the parameter space of the subsequent object models to relevant regions thus reducing the computational complexity. A method for object model adaptation is also developed. We apply the proposed framework by fusing salient points, blobs, and edges as features and verify experimentally its effectiveness in challenging conditions.

Object tracking in video by egg shape boundary model and properties of HSV colour space

In this paper, we propose an egg shape boundary model for object tracking in video sequence. The target in the current frame is bounded initially and the features of the target object are extracted. Each pixel in the boundary is transformed either as grey colour or as true colour in the HSV colour space and is used for representing the target pixel inside the boundary. In this model, the acceleration and velocity of the moving target object is considered for forming the egg shape boundary in the next frame by calculating the tangent points. A moving predicted centre technique is proposed for failure detection and recovery. The proposed method is suitable for tracking fast moving target object. For evaluating the performance, we have compared the results with other recently proposed methods in PETS video dataset and the results are found to be encouraging. In addition, it has been noticed that the egg shape boundary model takes less time compared to other model for processing each frame to form the target boundary.

Distributed Markov Chain Monte Carlo kernel based particle filtering for object tracking

Particle filters are computationally intensive and thus efficient parallelism is crucial to effective implementations, especially object tracking in video sequences. Two schemes for pipelining particles under high performance computing environment, including an alternative Markov Chain Monte Carlo (MCMC) resampling algorithm and kernel function, are proposed so as to improve tracking performance and minimize execution time. Experimental results on a network of workstations composed of simple off-the-shelf hardware components show that global parallelizable scheme provides a promising resolution to clearly reduce execution time with increasing particles, compared with generic particle filtering.

Region of Interest Tracking In Video Sequences

Tracking a region-of-interest (ROI) in a video is still a challenging task. Various high level applications rely on tracking. e.g, motion picture indexing, object recognition, video surveillance, audiovisual postproduction etc. Initially ROI is defined in a reference frame and the purpose is to determine the ROI in subsequent target frames in video sequences. The region was detected by determining the similarity measures between the reference and the target frames. Similarity measures between the frames are determined using two classical methods like sum of squared differences(SSD) and sum of absolute differences(SAD). This paper deals with the method of ROI tracking in video sequences by estimating the colour and geometric features between the frames and the similarity measures was determined using the KullbackLeibler Divergence. The increase of description features improves the accuracy. Their combination leads to high dimensional PDFs. Tracking experiments were performed on several standard video sequences and its efficiency was proved.

Joint Compressive Video Coding and Analysis

Traditionally, video acquisition, coding and analysis have been designed and optimized as independent tasks. This has a negative impact in terms of consumed resources, as most of the raw information captured by conventional acquisition devices is discarded in the coding phase, while the analysis step only requires a few descriptors of salient video characteristics. Recent compressive sensing literature has partially broken this paradigm by proposing to integrate sensing and coding in a unified architecture composed by a light encoder and a more complex decoder, which exploits sparsity of the underlying signal for efficient recovery. However, a clear understanding of how to embed video analysis in this scheme is still missing. In this paper, we propose a joint compressive video coding and analysis scheme and, as a specific application example, we consider the problem of object tracking in video sequences. We show that, weaving together compressive sensing and the information computed by the analysis module, the bit-rate required to perform reconstruction and tracking of the foreground objects can be considerably reduced, with respect to a conventional disjoint approach that postpones the analysis after the video signal is recovered in the pixel domain. These findings suggest that considerable gains in performance can be potentially obtained in video analysis applications, provided that a joint analysis-aware design of acquisition, coding and signal recovery is carried out.

On the Optimality of Motion-Based Particle Filtering

Particle filters have revolutionized object tracking in video sequences. The conventional particle filter, also called the CONDENSATION filter, uses the state transition distribution as the proposal distribution, from which the particles are drawn at each iteration. However, the transition distribution does not take into account the current observations, and thus many particles can be wasted in low likelihood regions. One of the most popular methods to improve the performance of particle filters relied on the motion-based proposal density. Although the motivation for motion-based particle filters could be explained on an intuitive level, up until now a mathematical rationale for the improved performance of motion-based particle filters has not been presented. In this letter, we investigate the performance of motion-based particle filters and provide an analytical justification of their superiority over the classical CONDENSATION filter. We rely on the characterization of the optimal proposal density, which minimizes the variance of the particles'weights. However, this density does not admit an analytical expression, making direct sampling from this optimal distribution impossible. We use the Kullback-Leibler (KL) divergence as a similarity measure between density functions and denote a particle filter as superior if the KL divergence between its proposal and the optimal proposal function is lower. We subsequently prove that under mild conditions on the estimated motion vector, the motion-based particle filter outperforms the CONDENSATION filter, in terms of the KL performance measure. Simulation results are presented to support the theoretical analysis.

High-Dimensional Statistical Measure for Region-of-Interest Tracking

This paper deals with region-of-interest (ROI) tracking in video sequences. The goal is to determine in successive frames the region which best matches, in terms of a similarity measure, a ROI defined in a reference frame. Some tracking methods define similarity measures which efficiently combine several visual features into a probability density function (PDF) representation, thus building a discriminative model of the ROI. This approach implies dealing with PDFs with domains of definition of high dimension. To overcome this obstacle, a standard solution is to assume independence between the different features in order to bring out low-dimension marginal laws and/or to make some parametric assumptions on the PDFs at the cost of generality. We discard these assumptions by proposing to compute the Kullback-Leibler divergence between high-dimensional PDFs using the k th nearest neighbor framework. In consequence, the divergence is expressed directly from the samples, i.e., without explicit estimation of the underlying PDFs. As an application, we defined 5, 7, and 13-dimensional feature vectors containing color information (including pixel-based, gradient-based and patch-based) and spatial layout. The proposed procedure performs tracking allowing for translation and scaling of the ROI. Experiments show its efficiency on a movie excerpt and standard test sequences selected for the specific conditions they exhibit: partial occlusions, variations of luminance, noise, and complex motion.

Face detection and tracking using a Boosted Adaptive Particle Filter

A novel algorithm, termed a Boosted Adaptive Particle Filter (BAPF), for integrated face detection and face tracking is proposed. The proposed algorithm is based on the synthesis of an adaptive particle filtering algorithm and the AdaBoost face detection algorithm. An Adaptive Particle Filter (APF), based on a new sampling technique, is proposed. The APF is shown to yield more accurate estimates of the proposal distribution and the posterior distribution than the standard Particle Filter thus enabling more accurate tracking in video sequences. In the proposed BAPF algorithm, the AdaBoost algorithm is used to detect faces in input image frames, whereas the APF algorithm is designed to track faces in video sequences. The proposed BAPF algorithm is employed for face detection, face verification, and face tracking in video sequences. Experimental results show that the proposed BAPF algorithm provides a means for robust face detection and accurate face tracking under various tracking scenarios.

Distance Learning for Similarity Estimation

In this paper, we present a general guideline to find a better distance measure for similarity estimation based on statistical analysis of distribution models and distance functions. A new set of distance measures are derived from the harmonic distance, the geometric distance, and their generalized variants according to the Maximum Likelihood theory. These measures can provide a more accurate feature model than the classical Euclidean and Manhattan distances. We also find that the feature elements are often from heterogeneous sources that may have different influence on similarity estimation. Therefore, the assumption of single isotropic distribution model is often inappropriate. To alleviate this problem, we use a boosted distance measure framework that finds multiple distance measures which fit the distribution of selected feature elements best for accurate similarity estimation. The new distance measures for similarity estimation are tested on two applications: stereo matching and motion tracking in video sequences. The performance of boosted distance measure is further evaluated on several benchmark data sets from the UCI repository and two image retrieval applications. In all the experiments, robust results are obtained based on the proposed methods.

Convergence analysis of active contours

Active contours are very useful tools in image segmentation and object tracking in video sequences. The practical implementations are built with an iterative algorithm based on a second order system defined in the spatial domain, where the elasticity and rigidity are the static parameters for its characterization and mass and damping are the dynamic parameters. In the process, the contour is influenced by external and internal forces varying its shape adaptively. The number of iterations required by the contour to delineate the objects is determined by these forces, by its initialization and by the coefficients of the second order system. This paper analyzes the convergence of active contours using the frequency based formulation and shows that the convergence depends on the dynamic parameters of the second order system and the distance between nodes of the contour attracted by the external forces.

Initialization of Model-Based Vehicle Tracking in Video Sequences of Inner-City Intersections

A fully automatic initialization approach for 3D-model-based vehicle tracking has been developed, based on Edge-Element and Optical-Flow association. An entire automatic initialization and tracking system incorporating this approach achieves results comparable to those obtained by earlier experiments based on semi-interactive initialization, provided the assessment criteria are roughly equivalent. Experiences with a large testing sample--about 15 minutes of inner-city traffic videos--are discussed in detail.

Multiobject tracking in video using a trisection paradigm

This paper proposes a technique for analyzing the following three problems: (a) segmentation of moving objects, (b) feature extraction, and (c) the solution of the correspondence problem in multiobject tracking in video sequences. In (c), we use a paradigm to solve the correspondence problem and to determine a motion trajectory based on a trisectional structure. The paradigm distinguishes between real-world objects, extracts image features such as motion blobs and color patches, and abstracts objects such as meta objects that denote real-world physical objects. The efficiency of the proposed method for determining the motion trajectories of moving objects will be demonstrated in this paper on the basis of the analysis of real image sequences that are subjected to severe disturbances (e.g., increasing congestion, shadow casting, and lighting transitions).

Structural similarity-based object tracking in multimodality surveillance videos

This paper addresses the problem of object tracking in video sequences for surveillance applications by using a recently proposed structural similarity-based image distance measure. Multimodality surveillance videos pose specific challenges to tracking algorithms, due to, for example, low or variable light conditions and the presence of spurious or camouflaged objects. These factors often cause undesired luminance and contrast variations in videos produced by infrared sensors (due to varying thermal conditions) and visible sensors (e.g., the object entering shadowy areas). Commonly used colour and edge histogram-based trackers often fail in such conditions. In contrast, the structural similarity measure reflects the distance between two video frames by jointly comparing their luminance, contrast and spatial characteristics and is sensitive to relative rather than absolute changes in the video frame. In this work, we show that the performance of a particle filter tracker is improved significantly when the structural similarity-based distance is applied instead of the conventional Bhattacharyya histogram-based distance. Extensive evaluation of the proposed algorithm is presented together with comparisons with colour, edge and mean-shift trackers using real-world surveillance video sequences from multimodal (infrared and visible) cameras.

Active contours for video object tracking using region, boundary and shape information

In this paper, we propose a robust model for tracking in video sequences with non-static backgrounds. The object boundaries are tracked on each frame of the sequence by minimizing an energy functional that combines region, boundary and shape information. The region information is formulated by minimizing the symmetric Kullback–Leibler (KL) distance between the local and global statistics of the objects versus the background. The boundary information is formulated using a color and texture edge map of the video frames. The shape information is calculated adaptively to the dynamic of the moving objects and permits tracking that is robust to background distractions and occlusions. Minimization of the energy functional is implemented using the level set method. We show the effectiveness of the approach for object tracking in color, infrared (IR), and fused color-infrared sequences.