Abstract | ||
---|---|---|
This paper proposes a new approach based on object sparse representation (OSR) for object tracking. The OSR method implemented by L1-norm minimization is robust to the partial occlusion and deterioration in object images. Firstly, we dynamically construct a set of samples in a predicted searching window in a new video frame, on which the sparse representation of the tracked object can be calculated by the OSR method. This procedure can automatically select the subset of the samples as a basis which most compactly expresses the object with small residuals and rejects all other possible but less compact representations. In terms of this sparse and compact representation, the instantaneous tracking result is achieved in the new video frame. Extensive comparative experiments demonstrate the effectiveness of the proposed approach especially in occlusion context. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICIP.2011.6115831 | ICIP |
Keywords | Field | DocType |
image representation,l1-norm minimization,osr,object sparse representation,object tracking,object image deterioration,sparse representation,video frame,vectors,kalman filter,robustness,minimization,visualization,kalman filters | Computer vision,Pattern recognition,Computer science,Image representation,Sparse approximation,Video tracking,Minification,Artificial intelligence | Conference |
Volume | Issue | ISSN |
null | null | 1522-4880 E-ISBN : 978-1-4577-1302-6 |
ISBN | Citations | PageRank |
978-1-4577-1302-6 | 1 | 0.37 |
References | Authors | |
6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhenjun Han | 1 | 176 | 16.40 |
Jianbin Jiao | 2 | 367 | 32.61 |
Qixiang Ye | 3 | 913 | 64.51 |