Name
Abstract | ||
|---|---|---|
Spatio-temporal context (STC) algorithm transforms the tracking process into a series of processes to find the extremum of the confidence map and fully uses the density context information around the target, which makes the algorithm rapidity and robustness. However, STC cannot deal with the situation of scale variation, motion blur and occlusion, which will cause the spatial model update error and result in the failure of the algorithm to accurately extract the target area. To deal with the problem, an improved spatio-temporal context algorithm is proposed in this paper. Firstly, the target sidelobe ratio (PSR) is used to determine the occlusion of the target. The lower the PSR value is, the more serious the target is blocked. PSR can be obtained by analyzing the response map of the target area. Secondly, the scale correlation filter is used to improve the STC algorithm, so that the algorithm can accurately and completely extract the target area. Thirdly, in order to avoid contamination of the target template when the target is occluded, a template update strategy is introduced to adapt to the appearance change of the target. The template update strategy enables our algorithm to locate the target quickly when the occlusion disappearing. Finally, experiment results on public data set are provided to show the effectiveness and robustness of our proposed algorithm. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/IISR.2018.8535919 | 2018 IEEE International Conference on Intelligence and Safety for Robotics (ISR) |
Keywords | DocType | ISBN |
Visual Tracking,Scale Correlation Filter,Spatial-Temporal Context,Occlusion | Conference | 978-1-5386-5548-1 |
Citations | PageRank | References |
0 | 0.34 | 11 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hao Wan | 1 | 0 | 0.34 |
| Weiguang Li | 2 | 0 | 0.68 |
| Junkuan Cui | 3 | 0 | 0.34 |
| Quanquan Liu | 4 | 7 | 7.90 |
| Chunbao Wang | 5 | 0 | 1.35 |
| Lihong Duan | 6 | 0 | 2.37 |