Kernelized correlation tracking based on point trajectories
Visual tracking is one of the most important directions in computer vision.However,many state-of-the-art algorithms cannot track the interested object reliably due to occlusion during tracking process,which leads to deficiency of object information.In order to solve occlusion problem,a kernelized co...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2018-06-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2018097/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539411790004224 |
|---|---|
| author | Yunqiu LYU Kai LIU Fei CHENG |
| author_facet | Yunqiu LYU Kai LIU Fei CHENG |
| author_sort | Yunqiu LYU |
| collection | DOAJ |
| description | Visual tracking is one of the most important directions in computer vision.However,many state-of-the-art algorithms cannot track the interested object reliably due to occlusion during tracking process,which leads to deficiency of object information.In order to solve occlusion problem,a kernelized correlation tracking method based on point trajectories was proposed.Through analyzing long-term motion cues of the local information,point trajectories were labeled by spectral clustering.These labeled points were used to differentiate the foreground and background objects and thus detect whether the target was occluded or drifts.If drifting and occlusion occur,re-detection was used to detect the re-entering of the target.Experimental results show that the proposed algorithm can handle occlusion and drifting problems effectively. |
| format | Article |
| id | doaj-art-2f40a19392d34b1d9b4b85e8f2064929 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2018-06-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-2f40a19392d34b1d9b4b85e8f20649292025-01-14T07:15:01ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2018-06-013919019859719133Kernelized correlation tracking based on point trajectoriesYunqiu LYUKai LIUFei CHENGVisual tracking is one of the most important directions in computer vision.However,many state-of-the-art algorithms cannot track the interested object reliably due to occlusion during tracking process,which leads to deficiency of object information.In order to solve occlusion problem,a kernelized correlation tracking method based on point trajectories was proposed.Through analyzing long-term motion cues of the local information,point trajectories were labeled by spectral clustering.These labeled points were used to differentiate the foreground and background objects and thus detect whether the target was occluded or drifts.If drifting and occlusion occur,re-detection was used to detect the re-entering of the target.Experimental results show that the proposed algorithm can handle occlusion and drifting problems effectively.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2018097/kernelized correlation filterpoint trajectoriesspectral clustering |
| spellingShingle | Yunqiu LYU Kai LIU Fei CHENG Kernelized correlation tracking based on point trajectories Tongxin xuebao kernelized correlation filter point trajectories spectral clustering |
| title | Kernelized correlation tracking based on point trajectories |
| title_full | Kernelized correlation tracking based on point trajectories |
| title_fullStr | Kernelized correlation tracking based on point trajectories |
| title_full_unstemmed | Kernelized correlation tracking based on point trajectories |
| title_short | Kernelized correlation tracking based on point trajectories |
| title_sort | kernelized correlation tracking based on point trajectories |
| topic | kernelized correlation filter point trajectories spectral clustering |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2018097/ |
| work_keys_str_mv | AT yunqiulyu kernelizedcorrelationtrackingbasedonpointtrajectories AT kailiu kernelizedcorrelationtrackingbasedonpointtrajectories AT feicheng kernelizedcorrelationtrackingbasedonpointtrajectories |