Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
6-2015
Abstract
Most modern trackers typically employ a bounding box given in the first frame to track visual objects, where their tracking results are often sensitive to the initialization. In this paper, we propose a new tracking method, Reliable Patch Trackers (RPT), which attempts to identify and exploit the reliable patches that can be tracked effectively through the whole tracking process. Specifically, we present a tracking reliability metric to measure how reliably a patch can be tracked, where a probability model is proposed to estimate the distribution of reliable patches under a sequential Monte Carlo framework. As the reliable patches distributed over the image, we exploit the motion trajectories to distinguish them from the background. Therefore, the visual object can be defined as the clustering of homo-trajectory patches, where a Hough voting-like scheme is employed to estimate the target state. Encouraging experimental results on a large set of sequences showed that the proposed approach is very effective and in comparison to the state-of-the-art trackers. The full source code of our implementation will be publicly available.
Keywords
visual object tracking, machine learning
Discipline
Databases and Information Systems
Research Areas
Data Science and Engineering
Publication
CVPR 2015: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition: June 7-12, Boston, MA: Proceedings
First Page
353
Last Page
361
ISBN
9781467369640
Identifier
10.1109/CVPR.2015.7298632
Publisher
IEEE
City or Country
Piscataway, NJ
Citation
LI, Yang; ZHU, Jianke; and HOI, Steven C. H..
Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches. (2015). CVPR 2015: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition: June 7-12, Boston, MA: Proceedings. 353-361.
Available at: https://ink.library.smu.edu.sg/sis_research/2927
Copyright Owner and License
Publisher
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/CVPR.2015.7298632