Tracking In Video Sequences Research Articles

Parallel implementation of color-based particle filter for object tracking in embedded systems

Recently, embedded systems have become popular because of the rising demand for portable, low-power devices. A common task for these devices is object tracking, which is an essential part of various applications. Until now, object tracking in video sequences remains a challenging problem because of the visual properties of objects and their surrounding environments. Among the common approaches, particle filter has been proven effective in dealing with difficulties in object tracking. In this research, we develop a particle filter based object tracking method using color distributions of video frames as features, and deploy it in an embedded system. Because particle filter is a high-complexity algorithm, we utilize computing power of embedded systems by implementing a parallel version of the algorithm. The experimental results show that parallelization can enhance the performance of particle filter when deployed in embedded systems.

Performance Evaluation of Visual Tracking Algorithms on Video Sequences With Quality Degradation

Recently, there are lots of visual tracking algorithms proposed to improve the performance of object tracking in video sequences with various real conditions, such as severe occlusion, complicated background, fast motion, and so on. In real visual tracking systems, there are various quality degradation occurring during video acquisition, transmission, and processing. However, most existing studies focus on improving the accuracy of visual tracking while ignoring the performance of tracking algorithms on video sequences with certain quality degradation. In this paper, we investigate the performance evaluation of existing visual tracking algorithms on video sequences with quality degradation. A quality-degraded video database for visual tracking (QDVD-VT), including the reference video sequences and their corresponding distorted versions, is constructed as the benchmarking for robustness analysis of visual tracking algorithms. Based on the constructed QDVD-VT, we propose a method for robustness measurement of visual tracking (RMVT) algorithms by accuracy rate and performance stability. The performance of ten existing visual tracking algorithms is evaluated by the proposed RMVT based on the built QDVD-VT. We provide the detailed analysis and discussion on the robustness analysis of different visual tracking algorithms on video sequences with quality degradation from different distortion types. To visualize the robustness of visual tracking algorithms well, we design a robustness pentagon to show the accuracy rate and performance stability of visual tracking algorithms. Our initial investigation shows that it is still challenging for effective object tracking for existing visual tracking algorithms on video sequences with quality degradation. There is much room for the performance improvement of existing tracking algorithms on video sequences with quality degradation in real applications.

People Detection and Tracking in Low Frame-rate Dynamic Scenes

People detection and tracking in video sequences are a crucial step for many applications such as security systems and entertainment. Although humans can easily perform these tasks, detecting and tracking people in dynamic background scenes are not trivial for computer vision systems. Furthermore, the amount of data generated by these applications has become overwhelming. Reducing the video frame rate can be an alternative, mainly in security systems, to reduce the amount of generated data. This paper aims to analyze how much a video frame rate can be reduced without affecting the performance of detection and tracking when people move in scenes with dynamic background. A supervised cascade classifier is used for detection and tracking is performed using the Kalman filter. The analysis is based on video sequences recorded from a vehicle. Results show that tracking is very dependent on the frame rate while detection is much more robust in this scenario.

Review on Kernel based Target Tracking for Autonomous Driving

Significant progress has been made in the field of autonomous driving during the past decades. However, fully autonomous driving in urban traffic is still extremely difficult in the near future. Visual tracking of vehicles or pedestrians is an essential part of autonomous driving. Among these tracking methods, kernel-based object tracking is an effective means of tracking in video sequences. This paper reviews the kernel theory adopted in target tracking of autonomous driving and makes a qualitative and quantitative comparison among several well-known kernel based methods. The theoretical and experimental analysis allow us to conclude that the kernel based online subspace learning algorithm achieves a good trade-off between the stability and real-time processing for target tracking in the practical application environments of autonomous driving. This paper reports on the result of evaluating the performances of five algorithms by using seven video sequences.

A Method of Robust Pedestrian Tracking in Video Sequences Based on Interest Point Description

A Method of Robust Pedestrian Tracking in Video Sequences Based on Interest Point Description

A Fuzzy Aproach For Facial Emotion Recognition

Abstract This article deals with an emotion recognition system based on the fuzzy sets. Human faces are detected in images with the Viola - Jones algorithm and for its tracking in video sequences we used the Camshift algorithm. The detected human faces are transferred to the decisional fuzzy system, which is based on the variable fuzzyfication measurements of the face: eyebrow, eyelid and mouth. The system can easily determine the emotional state of a person.

Diversity-aware classifier ensemble selection via f-score

The primary effect of using a reduced number of classifiers is a reduction in the computational requirements during learning and classification time. In addition to this obvious result, research shows that the fusion of all available classifiers is not a guarantee of best performance but good results on the average. The much researched issue of whether it is more convenient to fuse or to select has become even more of interest in recent years with the development of the Online Boosting theory, where a limited set of classifiers is continuously updated as new inputs are observed and classifications performed. The concept of online classification has recently received significant interest in the computer vision community. Classifiers can be trained on the visual features of a target, casting the tracking problem into a binary classification one: distinguishing the target from the background.Here we discuss how to optimize the performance of a classifier ensemble employed for target tracking in video sequences. In particular, we propose the F-score measure as a novel means to select the members of the ensemble in a dynamic fashion. For each frame, the ensemble is built as a subset of a larger pool of classifiers selecting its members according to their F-score. We observed an overall increase in classification accuracy and a general tendency in redundancy reduction among the members of an f-score optimized ensemble. We carried out our experiments both on benchmark binary datasets and standard video sequences.

Accelerating Particle Filter Using Randomized Multiscale and Fast Multipole Type Methods.

Particle filter is a powerful tool for state tracking using non-linear observations. We present a multiscale based method that accelerates the tracking computation by particle filters. Unlike the conventional way, which calculates weights over all particles in each cycle of the algorithm, we sample a small subset from the source particles using matrix decomposition methods. Then, we apply a function extension algorithm that uses a particle subset to recover the density function for all the rest of the particles not included in the chosen subset. The computational effort is substantial especially when multiple objects are tracked concurrently. The proposed algorithm significantly reduces the computational load. By using the Fast Gaussian Transform, the complexity of the particle selection step is reduced to a linear time in n and k, where n is the number of particles and k is the number of particles in the selected subset. We demonstrate our method on both simulated and on real data such as object tracking in video sequences.

A* algorithm with dynamic weights for multiple object tracking in video sequence

In the clutter environments, persistently tracking multiple objects is still a very challenging problem. In this paper, an A* algorithm with dynamic weights is developed to solve this problem. Firstly, the problem of multiple object tracking is considered as an integer programming of flow network model. Based on this model, afterward, we relax the problem of integer programming problem to a standard linear programming and achieve the global optimal solution with the proposed algorithm, which has been proven in this work. Compared with other advanced methods employed in the modern complex environments, the proposed method is on the merit of lower calculation complexity and better tracking accuracy and robustness. Finally, the simulation result is demonstrated, which reveals that the proposed algorithm saves the time costs vastly.

Moving Object Segmentation in a Video Sequence using Optical Flow and Motion Histogram Technique

The moving object detection and tracking in video sequence is significant research area in the field of computer vision and image processing. Object detection and tracking is key step for object recognition, navigation systems and surveillance systems. An effort has been made to develop an approach for moving object detection in video sequence, based on motion segmentation using optical flow and motion histogram. The algorithm has been described in detail and its competence was checked by performing simulation experiments. ROC comparison shows that this algorithm gives better result than traditional methods.

Performance Analysis of Alpha Beta Filter, Kalman Filter and Meanshift for Object Tracking in Video Sequences

Performance Analysis of Alpha Beta Filter, Kalman Filter and Meanshift for Object Tracking in Video Sequences

Dynamic shortest path association for multiple object tracking in video sequence

Persistently tracking multiple objects in cluttered environments is very challenging. We present a tracking association approach based on the shortest path faster algorithm. We first formulate the multiple object tracking as an integer programming problem of the flow network. Under this framework, the integer assumption is relaxed to a standard linear programming problem. Therefore, the global optimal solution can quickly be obtained using the fast dynamic shortest path algorithm, which highlights the dynamic programming characteristic of the shortest path, thus faster, algorithm. The proposed method avoids the difficulties of integer programming; more importantly, it has a lower worst-case complexity than competing methods but a better tracking accuracy and robustness in complex environments. Simulation results show that our proposed algorithm takes less time than other methods and can operate in real time.

Combinatorial Resampling Particle Filter: An Effective and Efficient Method for Articulated Object Tracking

Particle filter (PF) is a method dedicated to posterior density estimations using weighted samples whose elements are called particles. In particular, this approach can be applied to object tracking in video sequences in complex situations and, in this paper, we focus on articulated object tracking, i.e., objects that can be decomposed as a set of subparts. One of PF's crucial step is a resampling step in which particles are resampled to avoid degeneracy problems. In this paper, we propose to exploit mathematical properties of articulated objects to swap conditionally independent subparts of the particles in order to generate new particle sets. We then introduce a new resampling method called Combinatorial Resampling that resamples over the particle set resulting from all the "admissible" swappings, the so-called combinatorial set. In essence, combinatorial resampling (CR) is quite similar to the combination of a crossover operator and a usual resampling, but there exists a fundamental difference between CR and the use of crossover operators: we prove that CR is sound, i.e., in a Bayesian framework, it is guaranteed to represent without any bias the posterior densities of the states over time. By construction, the particle sets produced by CR better represent the density to estimate over the whole state space than the original set and, therefore, CR produces higher quality samples. Unfortunately, the combinatorial set is generally of an exponential size and, therefore, to be scalable, we show how it can be implicitly constructed and resampled from, thus resulting in both an efficient and effective resampling scheme. Finally, through experimentations both on challenging synthetic and real video sequences, we also show that our resampling method outperforms all classical resampling methods both in terms of the quality of its results and in terms of computation times.

A Survey on Moving Object Tracking in Video

The ongoing research on object tracking in video sequences has attracted many researchers. Detecting the objects in the video and tracking its motion to identify its characteristics has been emerging as a demanding research area in the domain of image processing and computer vision. This paper proposes a literature review on the state of the art tracking methods, categorize them into different categories, and then identify useful tracking methods. Most of the methods include object segmentation using background subtraction. The tracking strategies use different methodologies like Mean-shift, Kalman filter, Particle filter etc. The performance of the tracking methods vary with respect to background information. In this survey, we have discussed the feature descriptors that are used in tracking to describe the appearance of objects which are being tracked as well as object detection techniques. In this survey, we have classified the tracking methods into three groups, and a providing a detailed description of representative methods in each group, and find out their positive and negative aspects.

Manifold Learning for Object Tracking With Multiple Nonlinear Models

This paper presents a novel manifold learning algorithm for high-dimensional data sets. The scope of the application focuses on the problem of motion tracking in video sequences. The framework presented is twofold. First, it is assumed that the samples are time ordered, providing valuable information that is not presented in the current methodologies. Second, the manifold topology comprises multiple charts, which contrasts to the most current methods that assume one single chart, being overly restrictive. The proposed algorithm, Gaussian process multiple local models (GP-MLM), can deal with arbitrary manifold topology by decomposing the manifold into multiple local models that are probabilistic combined using Gaussian process regression. In addition, the paper presents a multiple filter architecture where standard filtering techniques are integrated within the GP-MLM. The proposed approach exhibits comparable performance of state-of-the-art trackers, namely multiple model data association and deep belief networks, and compares favorably with Gaussian process latent variable models. Extensive experiments are presented using real video data, including a publicly available database of lip sequences and left ventricle ultrasound images, in which the GP-MLM achieves state of the art results.

A Novel Fragments-based Similarity Measurement Algorithm for Visual Tracking

V arious adaptive appearance models have been proposed to deal with the challenges in tracking objects such as occlusions, illumination changes, background clutter, and pose variation. In this paper, first, we present a novel Fragments-based Similarity Measurement algorithm for object tracking in video sequence. Both the target and the reference are divided by multiple fragments of the same size. Then, we find the similarity of each fragment with the overlapped smaller patches by comparing the average intensity value of the patches. The accuracy of the tracking results can be improved by adjusting the size of the patches. Finally we incorporate the global similarity measurement using two kinds of distances between them. This method encodes the color and the spatial information so that it can track non-rigid objects under complex scene. We use this coarse-to-fine method to get a balance between the accuracy and the computational cost. Extensive experiments are conducted to verify the efficiency and the reliability of our proposed algorithm in the realistic videos .

A Review on Particle Swarm Optimization Algorithm and Its Variants to Human Motion Tracking

Automatic human motion tracking in video sequences is one of the most frequently tackled tasks in computer vision community. The goal of human motion capture is to estimate the joints angles of human body at any time. However, this is one of the most challenging problem in computer vision and pattern recognition due to the high-dimensional search space, self-occlusion, and high variability in human appearance. Several approaches have been proposed in the literature using different techniques. However, conventional approaches such as stochastic particle filtering have shortcomings in computational cost, slowness of convergence, suffers from the curse of dimensionality and demand a high number of evaluations to achieve accurate results. Particle swarm optimization (PSO) is a population-based globalized search algorithm which has been successfully applied to address human motion tracking problem and produced better results in high-dimensional search space. This paper presents a systematic literature survey on the PSO algorithm and its variants to human motion tracking. An attempt is made to provide a guide for the researchers working in the field of PSO based human motion tracking from video sequences. Additionally, the paper also presents the performance of various model evaluation search strategies within PSO tracking framework for 3D pose tracking.

Improved scale-invariant feature transform feature-matching technique-based object tracking in video sequences via a neural network and Kinect sensor

Object tracking is considered to be a key technique in many computer vision applications, such as video surveillance, object recognition, and robotics. We propose a method that improves the performance of scale-invariant feature transform (SIFT)-based object tracking algorithm to track the object in the subsequent video frames. Recently, many feature-based tracking methods have been proposed. An efficient and improved SIFT feature matching-based tracking method via neural network is provided and compares the outcome of this method with other tracking method outcomes. The tracked object is assigned a distance with the Kinect sensor to determine the depth of the detected object. The experimental results show that the proposed method can track the target object under different situations such as rotation, scaling, and many others with less computation time. Self-organizing map-based improved object tracking method can also estimate the distance between the tracked object and the image sensor. The proposed tracking technique will be useful for the development of many computer vision and robot navigation applications.

An efficient eye detection and tracking system based on particle swarm optimization and adaptive block-matching search algorithm

The problem of eye detection and tracking in video sequences is very important for a large number of applications ranging from face recognition to gaze tracking. Eye detection and tracking are challenging due to a variety of factors such as eye-blinking, partially closed eyes, and oblique face orientations which tend to significantly limit the efficiency of most eye trackers. In this paper, an efficient eye detection and tracking system is presented to overcome these limitations. The proposed system switches between the particle swarm optimization (PSO) based deformable multiple template matching algorithm and the adaptive block-matching search algorithm to improve the efficiency and robustness of the tracking system. For eye detection, PSO-based deformable multiple template matching is employed to estimate the best candidate of the center of the eyes within an image of the video sequence with the highest accuracy. For eye tracking the block-matching algorithm with adaptive search area is utilized to reduce the computational time required to perform the PSO-based algorithm. Experimental results on the standard VidTIMIT database show that the proposed method outperforms the deformable template matching based methods such as genetic and PSO. Moreover, it achieves better performance compared to model-based methods such as the statistical active appearance model (AAM) method and the edge projections based method in terms of accuracy and computational complexity.

Distinguishing Method of Outside Edge in the Tennis Ball-Mean Shift Algorithm

Target tracking is widely applied to monitoring, video coding and military industry. It is a challenge for computer vision that how to conduct effective tracking in video sequences. Of that the main section is to choose proper features and search matching algorithm rapidly. As an effective matching algorithm, due to no exhaustive search required, Mean Shift is successfully applied in target tracking requiring high real-time performance. Motion image detect is applied to industry, military and some important fields such as bank, transportations. This study studies sports target tracking base on Mean Shift. Apply it to outside edge distinguishing in tennis, which has practical significances for high-precision judgment in other sports terms.