File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR.2014.164
- Scopus: eid_2-s2.0-84911375723
- WOS: WOS:000361555601039
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Partial occlusion handling for visual tracking via robust part matching
Title | Partial occlusion handling for visual tracking via robust part matching |
---|---|
Authors | |
Keywords | visual tracking |
Issue Date | 2014 |
Citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014, p. 1258-1265 How to Cite? |
Abstract | Part-based visual tracking is advantageous due to its robustness against partial occlusion. However, how to effectively exploit the confidence scores of individual parts to construct a robust tracker is still a challenging problem. In this paper, we address this problem by simultaneously matching parts in each of multiple frames, which is realized by a locality-constrained low-rank sparse learning method that establishes multi-frame part correspondences through optimization of partial permutation matrices. The proposed part matching tracker (PMT) has a number of attractive properties. (1) It exploits the spatial-temporal localityconstrained property for robust part matching. (2) It matches local parts from multiple frames jointly by considering their low-rank and sparse structure information, which can effectively handle part appearance variations due to occlusion or noise. (3) The proposed PMT model has the inbuilt mechanism of leveraging multi-mode target templates, so that the dilemma of template updating when encountering occlusion in tracking can be better handled. This contrasts with existing methods that only do part matching between a pair of frames. We evaluate PMT and compare with 10 popular state-of-the-art methods on challenging benchmarks. Experimental results show that PMT consistently outperform these existing trackers. |
Persistent Identifier | http://hdl.handle.net/10722/327023 |
ISSN | 2023 SCImago Journal Rankings: 10.331 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhang, Tianzhu | - |
dc.contributor.author | Jia, Kui | - |
dc.contributor.author | Xu, Changsheng | - |
dc.contributor.author | Ma, Yi | - |
dc.contributor.author | Ahuja, Narendra | - |
dc.date.accessioned | 2023-03-31T05:28:14Z | - |
dc.date.available | 2023-03-31T05:28:14Z | - |
dc.date.issued | 2014 | - |
dc.identifier.citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014, p. 1258-1265 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10722/327023 | - |
dc.description.abstract | Part-based visual tracking is advantageous due to its robustness against partial occlusion. However, how to effectively exploit the confidence scores of individual parts to construct a robust tracker is still a challenging problem. In this paper, we address this problem by simultaneously matching parts in each of multiple frames, which is realized by a locality-constrained low-rank sparse learning method that establishes multi-frame part correspondences through optimization of partial permutation matrices. The proposed part matching tracker (PMT) has a number of attractive properties. (1) It exploits the spatial-temporal localityconstrained property for robust part matching. (2) It matches local parts from multiple frames jointly by considering their low-rank and sparse structure information, which can effectively handle part appearance variations due to occlusion or noise. (3) The proposed PMT model has the inbuilt mechanism of leveraging multi-mode target templates, so that the dilemma of template updating when encountering occlusion in tracking can be better handled. This contrasts with existing methods that only do part matching between a pair of frames. We evaluate PMT and compare with 10 popular state-of-the-art methods on challenging benchmarks. Experimental results show that PMT consistently outperform these existing trackers. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.subject | visual tracking | - |
dc.title | Partial occlusion handling for visual tracking via robust part matching | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR.2014.164 | - |
dc.identifier.scopus | eid_2-s2.0-84911375723 | - |
dc.identifier.spage | 1258 | - |
dc.identifier.epage | 1265 | - |
dc.identifier.isi | WOS:000361555601039 | - |