Abstract | ||
---|---|---|
Robust visual tracking, as a critical problem in community of computer vision, is still knotty, especially in challenging scenarios. In this paper, using the nature of low-rank matrix recovery, we propose a tracker with structured appearance model consisting of multiple representative models. By exploring the signal recovery power of Low-Rank matrix, we get effective representation of target and background for tracking; at the same time maintain a robust appearance model with multiple representative templates. Benefitting from low-rank recovery power, the representation matrix of candidates w.r.t the low-rank dictionary shows low-rank and sparse. Meanwhile, by our update strategy, a novel dictionary is maintained with low-rank models derived from multiple representative templates, which further encourages the sparse representation of particles. The proposed algorithm is demonstrated by extensive experiments on several challenging databases. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1145/2513228.2513231 | RACS |
Keywords | Field | DocType |
effective representation,low-rank matrix,low-rank model,low-rank matrix recovery,multiple representative template,low-rank recovery power,signal recovery power,low-rank dictionary,multiple representative model,visual tracking,representation matrix | Computer vision,Matrix (mathematics),Computer science,Sparse approximation,Signal recovery,Active appearance model,Low-rank approximation,Eye tracking,Artificial intelligence,Template | Conference |
Citations | PageRank | References |
0 | 0.34 | 9 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Deqian Fu | 1 | 7 | 4.51 |
Shunbo Hu | 2 | 1 | 2.05 |
Seong Tae Jhang | 3 | 20 | 8.59 |