In Defense of Sparse Tracking: Circulant Sparse Tracker

In Defense of Sparse Tracking: Circulant Sparse Tracker

Tianzhu Zhang, Adel Bibi, and Bernard Ghanem
"In Defense of Sparse Tracking: Circulant Sparse Tracker"
Conference on Computer Vision and Pattern Recognition (CVPR 2016)
​​​​​​​​
Tianzhu Zhang, Adel Bibi, Bernard Ghanem
visual tracking, circulant sparse tracker
2016
​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.