In Defense of Sparse Tracking: Circulant Sparse Tracker
dc.contributor.author | Zhang, Tianzhu | |
dc.contributor.author | Bibi, Adel | |
dc.contributor.author | Ghanem, Bernard | |
dc.date.accessioned | 2017-01-29T13:51:38Z | |
dc.date.available | 2017-01-29T13:51:38Z | |
dc.date.issued | 2016-12-13 | |
dc.identifier.citation | Zhang T, Bibi A, Ghanem B (2016) In Defense of Sparse Tracking: Circulant Sparse Tracker. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/CVPR.2016.421. | |
dc.identifier.doi | 10.1109/CVPR.2016.421 | |
dc.identifier.uri | http://hdl.handle.net/10754/622775 | |
dc.description.abstract | Sparse representation has been introduced to visual tracking by finding the best target candidate with minimal reconstruction error within the particle filter framework. However, most sparse representation based trackers have high computational cost, less than promising tracking performance, and limited feature representation. To deal with the above issues, we propose a novel circulant sparse tracker (CST), which exploits circulant target templates. Because of the circulant structure property, CST has the following advantages: (1) It can refine and reduce particles using circular shifts of target templates. (2) The optimization can be efficiently solved entirely in the Fourier domain. (3) High dimensional features can be embedded into CST to significantly improve tracking performance without sacrificing much computation time. Both qualitative and quantitative evaluations on challenging benchmark sequences demonstrate that CST performs better than all other sparse trackers and favorably against state-of-the-art methods. | |
dc.description.sponsorship | Research in this publication was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research. | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | |
dc.relation.url | http://ieeexplore.ieee.org/document/7780790/ | |
dc.subject | object tracking | |
dc.subject | optimisation | |
dc.subject | particle filtering (numerical methods) | |
dc.subject | Computational modeling | |
dc.subject | Dictionaries | |
dc.subject | Image color analysis | |
dc.subject | Robustness | |
dc.subject | Target tracking | |
dc.subject | Visualization | |
dc.title | In Defense of Sparse Tracking: Circulant Sparse Tracker | |
dc.type | Conference Paper | |
dc.contributor.department | Visual Computing Center (VCC) | |
dc.contributor.department | Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division | |
dc.contributor.department | Electrical Engineering Program | |
dc.identifier.journal | 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) | |
dc.contributor.institution | Institute of Automation, Chinese Academy of Sciences (CASIA), China | |
kaust.person | Zhang, Tianzhu | |
kaust.person | Bibi, Adel Aamer | |
kaust.person | Ghanem, Bernard | |
dc.date.published-online | 2016-12-13 | |
dc.date.published-print | 2016-06 |
This item appears in the following Collection(s)
-
Conference Papers
-
Electrical Engineering Program
For more information visit: https://cemse.kaust.edu.sa/ee -
Visual Computing Center (VCC)
-
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
For more information visit: https://cemse.kaust.edu.sa/