Research Article
Real Time Tracking via Sparse Representation
@INPROCEEDINGS{10.1109/ChinaCom.2013.6694688, author={Hongmei Zhang and xian-sui wei and Tao Huang and Yan He and Xiang Zhang and Jin Ye}, title={Real Time Tracking via Sparse Representation}, proceedings={8th International Conference on Communications and Networking in China}, publisher={IEEE}, proceedings_a={CHINACOM}, year={2013}, month={11}, keywords={l1 tracker; particle filter; spares representation; roi; bomp}, doi={10.1109/ChinaCom.2013.6694688} }- Hongmei Zhang
xian-sui wei
Tao Huang
Yan He
Xiang Zhang
Jin Ye
Year: 2013
Real Time Tracking via Sparse Representation
CHINACOM
IEEE
DOI: 10.1109/ChinaCom.2013.6694688
Abstract
The L1 tracker gains robustness by casting tracking as a sparse approximation problem in a particle filter framework. Unfortunately, the particle filter and solver of norm minimization lead to large amount of calculation as a result that L1 tracker can not achieve real-time tracking. The aim of this paper is to develop a new tracker via sparse representation that not only runs in real time but also has a better robustness than L1 tracker. In our proposed algorithm, candidate targets are sampled in the region of interest(ROI) to increase the tracking speed. Moreover, based on the block orthogonal matching pursuit(BOMP), a very fast solver is developed to solve the resulting norm minimization problem to improve tracking speed and accuracy. We conduct extensive experiment to validate and compare the performance of the BOMP algorithms against six popular -minimization solvers in different challenging sequences. We also implement great experiment to validate the high computational efficiency and tracking accuracy of our proposed tracker compare with four alternative state-of-the-art trackers in six challenging sequences.