Target Appearance Changes Research Articles

Performance Comparison of Kalman Filter and Mean Shift Algorithm for Object Tracking

Object tracking is one of the important tasks in the field of computer vision. Some of the areas which need Visual object tracking are surveillance, automated video analysis, etc. Mean shift algorithm is one of the popular techniques for this task and is advantageous when compared to some of the other tracking methods. But this method would not be appropriate in the case of large target appearance changes and occlusion. In addition, this method fails when the object is under the action of non-linear forces like that of the gravity e.g. a ball falling under the action of gravity. Another popular method used for tracking is the one that uses Kalman filter, with measurements (often noisy) of position of object to be tracked as input to it. This paper is based on a simulative comparison of both of these algorithms which will give a proper outline of which method will be more appropriate for object tracking, given the nature of motion of object and type of surroundings. Observations based on these methods are present in the literature but there is no evidence based on implementation of these algorithms that shows a quantitative comparison of the said algorithms.

Mean-Shift Guided Particle Filter Tracking Method Based on Layered Dynamic Template Update

Traditional tracking algorithm is not compatible between robustness and efficiency, under complex scenes, the stable template update strategy is not robust to target appearance changes. Therefore, the paper presents a dynamic template-update method that combined with a mean-shift guided particle filter tracking method. By incorporating the original information into the updated template, or according to the variety of each component in template to adjust the updating weights adaptively, the presented algorithm has the natural ability of anti-drift. Besides, the proposed method cope the one-step iteration of mean-shift algorithm with the particle filter, thus boost the performance of efficiency. Experimental results show the feasibility of the proposed algorithm in this paper.

Underwater Target Tracking Algorithm Based on an Improved Color Matching

Owing to fuzzy detail and distortion of underwater image and complex changes of target, the underwater target tracking system requires accuracy and continuity of tracking, and expects that the size of tracking window can adapt to appearance change of target. According to the requirements mentioned above, the underwater target tracking algorithm based on an improved color matching is proposed, which finds the best location of target through tracking accuracy algorithm and calculates width of window on the basis of tracking window size variation algorithm. The experimental results show that this algorithm can adaptively track the real-time target and has higher accuracy than traditional color matching algorithm.

Dynamic appearance model for particle filter based visual tracking

This paper made major research on the target representation problem, which plays a significant role in visual tracking, but has received little attention in most researches. In order to fulfill the requirements of tracking robustness and effectiveness in practical conditions, a dynamic appearance model is constructed. Due to particle filter's excellent characteristics, it is employed in this paper not only to estimate target's state, but also to construct the dynamic observation model integrated by multiple cues. In the proposed method, a dynamic multi-cue integration model is constructed for particle filter framework. And a systematic study is done on evaluating cue's weight. Specially, a particle filter based weight tracker is designed to update multi-cue's integrating manner online, so as to adapt the observation model to target's appearance changes. In such a way, a double-particle-filter based tracking framework is formed, and it is field tested on a variety of videos in different tracking conditions. In the experiments and comparisons, the applicable conditions of the proposed dynamic model are discussed, and its robustness and effectiveness are demonstrated.

Multitarget Tracking of Pedestrians in Video Sequences Based on Particle Filters

Video target tracking is a critical problem in the field of computer vision. Particle filters have been proven to be very useful in target tracking for nonlinear and non-Gaussian estimation problems. Although most existing algorithms are able to track targets well in controlled environments, it is often difficult to achieve automated and robust tracking of pedestrians in video sequences if there are various changes in target appearance or surrounding illumination. To surmount these difficulties, this paper presents multitarget tracking of pedestrians in video sequences based on particle filters. In order to improve the efficiency and accuracy of the detection, the algorithm firstly obtains target regions in training frames by combining the methods of background subtraction and Histogram of Oriented Gradient (HOG) and then establishes discriminative appearance model by generating patches and constructing codebooks using superpixel and Local Binary Pattern (LBP) features in those target regions. During the process of tracking, the algorithm uses the similarity between candidates and codebooks as observation likelihood function and processes severe occlusion condition to prevent drift and loss phenomenon caused by target occlusion. Experimental results demonstrate that our algorithm improves the tracking performance in complicated real scenarios.

Target Tracking Based on Mean Shift and KALMAN Filter with Kernel Histogram Filtering

Visual object tracking is required in many tasks such as video compression, surveillance, automated video analysis, etc. mean shift algorithm is one of popular methods to this task and has some advantages comparing to other tracking methods. This method would not be appropriate in the case of large target appearance changes and occlusion; therefore target model update could actually improve this method. KALMAN filter is a suitable approach to handle model update. We performed mean shift algorithm with model update ability for tracking in this paper and achieve good results.

Online Appearance Model Learning and Generation for Adaptive Visual Tracking

Several adaptive visual tracking algorithms have been recently proposed to capture the varying appearance of target. However, adaptability may also result in the problem of gradual drift, especially when the target appearance changes drastically. This paper gives some theoretical principles for online learning of target model, and then presents a novel adaptive tracking algorithm which is able to effectively cope with drastic variations in target appearance and resist gradual drift. Once target is localized in each frame, the patches sampled from target observation are first classified into foreground and background using an effective classifier. Then the adaptive, pure and time-continuous target model is extracted online through two processes: absorption process and rejection process, through which only the reliable features with high separability are absorbed in the new target model, while the “dangerous” features which may cause interfusion of background patterns are rejected. To minimize the influence of background and keep the temporal continuity of target model, two collaborative models dominant model and continuous model are designed. The proposed learning and generation mechanisms of target model are finally embedded in an adaptive tracking system. Experimental results demonstrate the robust performance of the proposed algorithm under challenging conditions.

Linear Regression and Adaptive Appearance Models for Fast Simultaneous Modelling and Tracking

This work proposes an approach to tracking by regression that uses no hard-coded models and no offline learning stage. The Linear Predictor (LP) tracker has been shown to be highly computationally efficient, resulting in fast tracking. Regression tracking techniques tend to require offline learning to learn suitable regression functions. This work removes the need for offline learning and therefore increases the applicability of the technique. The online-LP tracker can simply be seeded with an initial target location, akin to the ubiquitous Lucas-Kanade algorithm that tracks by registering an image template via minimisation.A fundamental issue for all trackers is the representation of the target appearance and how this representation is able to adapt to changes in target appearance over time. The two proposed methods, LP-SMAT and LP-MED, demonstrate the ability to adapt to large appearance variations by incrementally building an appearance model that identifies modes or aspects of the target appearance and associates these aspects to the Linear Predictor trackers to which they are best suited. Experiments comparing and evaluating regression and registration techniques are presented along with performance evaluations favourably comparing the proposed tracker and appearance model learning methods to other state of the art simultaneous modelling and tracking approaches.

An incremental Bhattacharyya dissimilarity measure for particle filtering

The dissimilarity between a target descriptor and a particle descriptor is a crucial parameter in the particle filtering (PF), while the widely used Bhattacharyya dissimilarity (BD) is not discriminative enough. This paper presents an incremental Bhattacharyya dissimilarity (IBD) for measuring histogram based descriptors (HBDs) used for particle weight estimation. IBD is defined by incorporating an incremental similarity matrix (ISM) into the BD. Such an ISM imposes the incremental similarity beliefs on the matched bin patches of two input histograms and enables a cross-bin interaction during the comparison, which yields the enhanced capability of discriminating the particles located in the object from those positioned in the background. We propose a robust approach to compute the ISM by jointly utilizing the spatial and temporal attributes. Also, to handle target appearance changes and deformations, a classification-inspired target model update strategy is presented. These components lead to an effective and robust tracking algorithm. Experimental results demonstrate that IBD shows promising discriminative capability in comparison with other state of the art dissimilarity measures. Moreover, the IBD based PF-tracker also exhibits competitive tracking performance, especially under scenarios of partial occlusion and background clutter.

基于粒子滤波的红外目标跟踪

To address two challenging problems in infrared target tracking, target appearance changes and unpredictable abrupt motions, a novel particle filtering based tracking algorithm is introduced. In this method, a novel saliency model is proposed to distinguish the salient target from background, and the eigenspace model is invoked to adapt target appearance changes. To account for the abrupt motions efficiently, a two-step sampling method is proposed to combine the two observation models. The proposed tracking method is demonstrated through two real infrared image sequences, which include the changes of luminance and size, and the drastic abrupt motions of the target.