The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Reliable and repeatable evaluation of low-level (tracking) and high-level (behavior analysis) vision tasks require annotation of ground-truth information in videos. Depending on the scenarios, ground-truth annotation may be required for individual targets and/or groups of targets. Unlike the existing tools that generally allow an explicit annotation for individual targets only, we propose a tool that...
Correlation filters have recently been popular due to their success in short-term single-object tracking as well as their computational efficiency. Nevertheless, the appearance model of a single correlation filter based tracking algorithm quickly forgets the past poses of the target object due to the updates over time. To overcome this undesired forgetting, our approach is to run trackers with separate...
To overcome the real-time and robust problem of visual tracking, a visual tracking algorithm based on a fusion of multi cue and particle filter was proposed. Firstly, the integrating formula was transmuted on the framework of particle filter base on multi-cues which integrated multi-cues based on cues rather than feature points so that it could be used for parallel computing. Secondly, the EM algorithm...
Humans have the capability to quickly prioritize external visual stimuli and localize their most interest in a scene. Inspired by this mechanism, we propose a robust object tracking algorithm based on visual attention. We fuse motion feature and color feature to estimate the target state under the guidance of saliency map. Principal Component Analysis method is used to compute saliency feature based...
In this paper, we propose an approach for improving the object tracking accuracy in video surveillance scenarios by estimating and compensating the occlusion introduced by static scene objects. Specifically, the scene occluder map is first estimated by analyzing the gradient of a normalized cumulative motion map from the frames of the first several minutes of a surveillance video. Then, a scene occlusion...
An efficient gyro-aided iterative Earth Mover's Distance (iEMD) algorithm for visual tracking is proposed in this paper. The Earth Mover's Distance (EMD) is used as the similarity measure to search the optimal template candidates in color-spatial space in a video sequence. The computation of the EMD is formulated as the transportation problem from linear programming. The efficiency of this optimization...
According to the requirement of high precision and dexterous visual tracking system for the humanoid robot, a development of three degrees of freedom head robot is proposed, and the design principle is described in detail. The modular joint design method is adopted to reduce the complexity of the mechanism design effectively, and the control principle of the double closed loop of the joint is also...
Occlusion is a thorny issue in visual tracking, which may lead to serious drift to the tracking result. In this paper, a new tracker is proposed to deal with occlusion in tracking. Background surroundings to the object are divided into patches as supplementary information for occlusion detection. When the object is partially occluded, compensation will be made to the estimated position thus ensuring...
In this paper, a model based on weighted extreme learning machine (weighted ELM) is proposed for visual tracking. The weighted ELM considers different class distributions both of the positive and negative classes, where extra weights are utilized in the framework. The proposed model simultaneously trains a certain number of weighted ELMs with different feature blocks. Moreover, the weighted multiple...
The Kanade-Lucas-Tomasi(KLT) method is a classictracking algorithm, which however suffers from a longexisting gradual template drift problem. In this paper, wepresent an improved tracking algorithm which can sustain thetracking performance for a long term against drift. In thisapproach, we formulate the tracking over a state comprisingof a template with kinematic motion. Based on the sparsemotion...
Sample quality plays an important role in tracking-by-learning strategies, but the reliable online samples are hard to be obtained due to challenges of variational environments. By modeling how human visual interest actively guiding the seek of salient regions and movements in video sequences, in this paper, a compositional tracking strategy is proposed based on an integrated saliency map, which is...
Object tracking usually suffers from the geometrical deformations and occlusions of objects. This paper presents a new method for accurate object tracking by combining the multi-angle discriminative correlation filters and key-points under the framework of Discriminative Scale Space Tracker (DSST) tracker. Experimental results demonstrate that the proposed method can produce promising tracking results...
To solve the problem of poor robustness and low effectiveness of visual tracking in complex scenes, a novel target tracking algorithm based on adaptive observation weight is proposed in this paper. First of all, a weighted observation model is established by linear visual tracking representation. Then an iterative optimization algorithm is proposed to obtain the parameters of the model, and adaptively...
Developing an effective target appearance model is a challenging task due to the influence of factors such as partial occlusion, illumination variations, fast motion, etc. Existing appearance models usually utilize the tracking results from previous frames as target templates upon which the target appearance model is built by linear combinations of the templates. With such kind of representation,...
Achieving precise and robust human detection and tracking over camera networks is a very challenging task in the research of intelligent video surveillance. Its difficulties mainly result from abrupt human object motion, object occlusion and object scale change, and changing object appearance due to changes in illumination and viewpoint, non-rigid deformations, intra-class variability in shape and...
In this paper, a new visual tracking approach via the local patches and the contextual information of the target is presented. In the tracking procedure, the target object is decomposed into a set of patches of equal size and each patch is represented by using intensity and gradient histograms. Then, the likelihood of local patches is defined as the weighted sum of reliability and stability indices,...
In this paper, we propose a robust visual tracking method based on a temporal ensemble framework. Different from conventional ensemble-based trackers, which combine weak classifiers into a strong one using AdBoost in spatial fusion manners, our method adopts a powerful and efficient tracker integrated with its snapshots in different temporal windows of online tracking process to construct a temporal...
We propose a nonlinear metric learning (NML) method for visual tracking. Instead of utilizing the hand-crafted similarity measures, the NML tracker can automatically learn distance metrics from training data itself to categorize object and backgrounds in visual tracking. To exploit the nonlinear structures of samples, the NML tracker seeks several hierarchical nonlinear transformations by adopting...
Most existing discriminative tracking methods model a target object as a whole and train a tracker based on holistic templates, which cannot effectively deal with partial occlusions. Instead, in this paper, by treating the target as a collection of local patches, we propose a novel tracking approach based on boosted local classifiers. Initially, a set of local patches are sampled to train a set of...
Visual tracking plays a fundamental role in many applications, such as video surveillance, image compression and three-dimensional reconstruction. From the perspective of accuracy and complexity, correlation filter for target tracking has been proved to be one of the most efficient algorithms. However, it suffers from some difficulties when tracking complex objects with rotations, occlusions and other...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.