Field Of Object Tracking Research Articles

Dynamic and robust method for detection and locating vehicles in the video images sequences with use of image processing algorithm

There are various methods in the field of moving-object tracking in the video images that each of them implies on the specific features of object. Among tracking methods based on features, algorithms based on color are able to provide a precise description of the object and track the object with high speed. One of the efficient methods in the field of object tracking based on color information is mean-shift algorithm. If the color of moving object approaches toward a background model or image background has a low contrast and brightness, then the color information is not enough for target tracking. In this paper, the new tracking method is proposed which with combination of moved object information with color information, the new proposed method will be capable to track object under condition that color information is not enough for tracking. With use of background subtraction method based on Gaussian combination, the binary image which includes moving information will use in the mean-shift algorithm. Usage of object movement information will compensate the lack of spatial information and will increase robustness of algorithm especially in the complicated conditions. Also in order to achieve the robust algorithm against changes in shapes, size, and rotation of object, extended mean-shift algorithm is used. Results show the robustness of proposed algorithm in object tracking especially under conditions which object color is same as background color and have better results in the low contrast condition in comparison to mean-shift and extended mean-shift algorithms.

Unscented information filtering phase unwrapping algorithm for interferometric fringe patterns.

This paper proposes a new phase unwrapping (PU) algorithm based on an unscented information filter for interferometric fringes. The proposed algorithm is the result of combining an unscented information filter with a Levenberg-Marquardt method, a robust phase gradient estimator called the amended matrix pencil model, and an efficient quality-guided strategy based on heapsort. The unscented information filter, a new type of filter that has recently been well applied to traditional nonlinear object tracking fields, is introduced to estimate the unambiguous unwrapped phase of wrapped phase images for the first time, to the best of our knowledge. First, a recursive PU procedure based on an unscented information filter is established to perform PU and noise filtering at the same time by combining the unscented information filter and the amended matrix pencil model, where the amended matrix pencil model is applied to acquire phase gradient information needed for the recursive PU procedure. Second, the above recursive PU procedure is further optimized to improve the accuracy of the phase estimate by inserting the Levenberg-Marquardt method. This is also the first time that the Levenberg-Marquardt method is combined with the unscented information filter for the unwrapping of interferometric fringes, to the best of our knowledge. Finally, the efficient quality-guided strategy based on heapsort is used to efficiently route the path of the unwrapping procedure and to guide the proposed method to efficiently unwrap wrapped pixels along the path from the high-reliance region to the low-reliance region of the wrapped fringes. Results obtained with synthetic data and real data show more acceptable solutions with the proposed method, compared to some of the most used algorithms.

A hierarchical clustering of features approach for vehicle tracking in traffic environments

Purpose Developing algorithms for automated detection and tracking of multiple objects is one challenge in the field of object tracking. Especially in a traffic video monitoring system, vehicle detection is an essential and challenging task. In the previous studies, many vehicle detection methods have been presented. These proposed approaches mostly used either motion information or characteristic information to detect vehicles. Although these methods are effective in detecting vehicles, their detection accuracy still needs to be improved. Moreover, the headlights and windshields, which are used as the vehicle features for detection in these methods, are easily obscured in some traffic conditions. The paper aims to discuss these issues. Design/methodology/approach First, each frame will be captured from a video sequence and then the background subtraction is performed by using the Mixture-of-Gaussians background model. Next, the Shi-Tomasi corner detection method is employed to extract the feature points from objects of interest in each foreground scene and the hierarchical clustering approach is then applied to cluster and form them into feature blocks. These feature blocks will be used to track the moving objects frame by frame. Findings Using the proposed method, it is possible to detect the vehicles in both day-time and night-time scenarios with a 95 percent accuracy rate and can cope with irrelevant movement (waving trees), which has to be deemed as background. In addition, the proposed method is able to deal with different vehicle shapes such as cars, vans, and motorcycles. Originality/value This paper presents a hierarchical clustering of features approach for multiple vehicles tracking in traffic environments to improve the capability of detection and tracking in case that the vehicle features are obscured in some traffic conditions.

Object Tracking in Wireless Sensor Networks: Challenges and Solutions

Wireless Sensor Networks (WSNs) are small, inexpensive and battery-operated sensor nodes that are deployed over a geographical area. WSNs are used in many applications such border patrolling, military intrusion detection, wildlife animal monitoring, surveillance of natural disasters and healthcare systems. Mobile object tracking is a vital task in all these applications. The goal of this work is to highlight the most important challenges in the field of object tracking and provide a survey of the WSN architectural design and implementation approaches for tackling this problem. To that end, we analyze how each approach responds to each challenge and where it falls short. This analysis should provide researchers with a state-of-the-art review and inspire them to propose novel solutions.

Discriminative descriptors for object tracking

Object tracking is one of the most challenging problems in computer vision. Only Fast trackers can satisfy the real-time requirements and can be used in many artificial intelligence applications. Due to the impressive high-speed, correlation filters have received much attention within the field of object tracking. Recently, trackers using luminance information or color names for image description have been performed in a correlation filters framework. In this paper, we propose the usage of discriminative color descriptors to improve the tracking performance of the traditional correlation filters tracker. Discriminative color descriptors are compact and efficient. Moreover, our tracker incorporates scale estimation into the traditional correlation filters, which results in increased tracking performance. Extensive experiments demonstrate that the proposed tracker can obtain superior results compared to existing trackers using correlation filters and it is also able to outperform state-of-the-art trackers on the CVPR2013 object tracking benchmark.

Study on the Comparison of Two Metrics Used in the Fields of Object Tracking

The paper researches on the comparison of two metrics methods under Riemannian metric and under Log-Euclidean metric respectively. Firstly, Experiments are done for comparing the distance and mean values worked out under the two metrics. And the time required for computing under these two metrics is also shown. Lastly, the two methods are applied to the field of image tracking. The performance of the two methods is compared, and the time required for tracking each frame is gained. Experiments results show that the two methods can gain similar distance and mean values, and similar tracking results, while the time required under Log-Euclidean metric is less than under Riemannian metric.

Improvement of mean shift tracking performance using a convex kernel function and extracting motion information

Color feature is now taken into real consideration as one of the important cues in the area of objects tracking, in image sequences. This feature has attracted considerable attention, in recent years. One of the well-known tools in color feature extraction is to use mean shift (MS) tracking algorithm. The probability of finding the object location in line with this tracking algorithm is somehow desirable, in image sequences, by maximizing the Bhattacharyya coefficient between both objects and corresponding candidate models. Even though the MS tracking algorithm is just known as a popular tool in the field of object tracking, it does not have sufficient merit to be realized in complex environments, i.e., background with object’s similar color, sudden light changes, occlusion types and so on. In such a case, the amount of the present coefficient could truly be decreased, during the tracking process, because of the mentioned environmental problems. A convex kernel function in association with the motion information of video sequences is used in this investigation to improve the MS tracking algorithm for the purpose of overcoming the existing problems. The proposed approach is employed to present the MS kernel function, directly. Thus, by using the investigation in its present form, the capability of the MS kernel is increased. Moreover, by using both color feature and motion information, simultaneously, in comparison with single color feature, noises and also uninterested regions can actually be eliminated. Experimental results on data set illustrate that the proposed approach has an optimum performance in real-time object tracking under the severe conditions.

Mean-Shift object tracking based on scale invariant feature transform

Mean-Shift algorithm performs well in object tracking field because of its advantages of fast pattern matching and non-parametric estimation.However,this algorithm has its inherent deficiencies.In order to improve the robustness of Mean-Shift algorithm,the target was divided into a number of sub-regions in this paper,each sub-region individually used Mean-Shift tracking,and those whose iterations are more than eight times quit.And Scale Invariant Feature Transform(SIFT) was employed to exclude those sub-regions with smaller matching key points.Finally,the object location was obtained according to the sub-regions with more matching key points.Experiments show that the proposed method is of high robustness in situations of occlusion,scale change,rotation,scene change,etc.

Dynamic tracking re-adjustment: a method for automatic tracking recovery in complex visual environments

Detection and analysis of events from video sequences is probably one of the most important research issues in computer vision and pattern analysis society. Before, however, applying methods and tools for analyzing actions, behavior or events, we need to implement robust and reliable tracking algorithms able to automatically monitor the movements of many objects in the scene regardless of the complexity of the background, existence of occlusions and illumination changes. Despite the recent research efforts in the field of object tracking, the main limitation of most of the existing algorithms is that they are not enriched with automatic recovery strategies able to re-initialize tracking whenever its performance severely deteriorates. This is addressed in this paper by proposing an automatic tracking recovery tool which improves the performance of any tracking algorithm whenever the results are not acceptable. For the recovery, non-linear object modeling tools are used which probabilistically label image regions to object classes. The models are also time varying. The first property is implemented in our case using concepts from functional analysis which allow parametrization of any arbitrary non-linear function (with some restrictions on its continuity) as a finite series of known functional components but of unknown coefficients. The second property is addressed by proposing an innovative algorithm that optimally estimates the non-linear model at an upcoming time instance based on the current non-linear models that have been already approximated. The architecture is enhanced by a decision mechanism which permits verification of the time instances in which tracking recovery should take place. Experimental results on a set of different video sequences that present complex visual phenomena (full and partial occlusions, illumination variations, complex background, etc) are depicted to demonstrate the efficiency of the proposed scheme in proving tracking in very difficult visual content conditions. Additionally, criteria are proposed to objectively evaluate the tracking performance and compare it with other strategies.

2D Articulated Pose Tracking Using Particle Filter with Partitioned Sampling and Model Constraints

In this paper, we develop a two-dimensional articulated body tracking algorithm based on the particle filtering method using partitioned sampling and model constraints. Particle filtering has been proven to be an effective approach in the object tracking field, especially when dealing with single-object tracking. However, when applying it to human body tracking, we have to face a "particle-explosion" problem. We then introduce partitioned sampling, applied to a new articulated human body model, to solve this problem. Furthermore, we develop a propagating method originated from belief propagation (BP), which enables a set of particles to carry several constraints. The proposed algorithm is then applied to tracking articulated body motion in several testing scenarios. The experimental results indicate that the proposed algorithm is effective and reliable for 2D articulated pose tracking.