One‐step backtracking for occlusion detection in real‐time visual tracking
Occlusion is a challenging problem in real‐time visual object tracking. Most state‐of‐the‐art methods learn the inaccurate appearance of the target when it becomes occluded by other objects in the scene. To address this issue, a novel one‐step backtracking (OB) tracker for occlusion detection is pro...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-03-01
|
| Series: | Electronics Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/el.2016.4183 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832096701393928192 |
|---|---|
| author | Yulong Xu Jiabao Wang Yang Li Zhuang Miao Yafei Zhang |
| author_facet | Yulong Xu Jiabao Wang Yang Li Zhuang Miao Yafei Zhang |
| author_sort | Yulong Xu |
| collection | DOAJ |
| description | Occlusion is a challenging problem in real‐time visual object tracking. Most state‐of‐the‐art methods learn the inaccurate appearance of the target when it becomes occluded by other objects in the scene. To address this issue, a novel one‐step backtracking (OB) tracker for occlusion detection is proposed, which backtracks to one previous frame and detects occlusion by comparing the tracking result with OB result in each frame. An adaptive learning model update scheme is further proposed by computing the peak‐to‐sidelobe ratio of the response maps to improve the tracking performance. Experiments on several benchmark sequences show that the proposed tracker outperforms state‐of‐the‐art approaches and achieves real‐time visual tracking. |
| format | Article |
| id | doaj-art-c3683e241ece4ea29f02a5091eef8850 |
| institution | Kabale University |
| issn | 0013-5194 1350-911X |
| language | English |
| publishDate | 2017-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Electronics Letters |
| spelling | doaj-art-c3683e241ece4ea29f02a5091eef88502025-02-05T12:30:42ZengWileyElectronics Letters0013-51941350-911X2017-03-0153531832010.1049/el.2016.4183One‐step backtracking for occlusion detection in real‐time visual trackingYulong Xu0Jiabao Wang1Yang Li2Zhuang Miao3Yafei Zhang4College of Command Information SystemsPLA University of Science and TechnologyNanjing210007People's Republic of ChinaCollege of Command Information SystemsPLA University of Science and TechnologyNanjing210007People's Republic of ChinaCollege of Command Information SystemsPLA University of Science and TechnologyNanjing210007People's Republic of ChinaCollege of Command Information SystemsPLA University of Science and TechnologyNanjing210007People's Republic of ChinaCollege of Command Information SystemsPLA University of Science and TechnologyNanjing210007People's Republic of ChinaOcclusion is a challenging problem in real‐time visual object tracking. Most state‐of‐the‐art methods learn the inaccurate appearance of the target when it becomes occluded by other objects in the scene. To address this issue, a novel one‐step backtracking (OB) tracker for occlusion detection is proposed, which backtracks to one previous frame and detects occlusion by comparing the tracking result with OB result in each frame. An adaptive learning model update scheme is further proposed by computing the peak‐to‐sidelobe ratio of the response maps to improve the tracking performance. Experiments on several benchmark sequences show that the proposed tracker outperforms state‐of‐the‐art approaches and achieves real‐time visual tracking.https://doi.org/10.1049/el.2016.4183one‐step backtrackingocclusion detectionreal‐time visual object trackingOB trackeradaptive learning model update schemepeak‐to‐sidelobe ratio |
| spellingShingle | Yulong Xu Jiabao Wang Yang Li Zhuang Miao Yafei Zhang One‐step backtracking for occlusion detection in real‐time visual tracking Electronics Letters one‐step backtracking occlusion detection real‐time visual object tracking OB tracker adaptive learning model update scheme peak‐to‐sidelobe ratio |
| title | One‐step backtracking for occlusion detection in real‐time visual tracking |
| title_full | One‐step backtracking for occlusion detection in real‐time visual tracking |
| title_fullStr | One‐step backtracking for occlusion detection in real‐time visual tracking |
| title_full_unstemmed | One‐step backtracking for occlusion detection in real‐time visual tracking |
| title_short | One‐step backtracking for occlusion detection in real‐time visual tracking |
| title_sort | one step backtracking for occlusion detection in real time visual tracking |
| topic | one‐step backtracking occlusion detection real‐time visual object tracking OB tracker adaptive learning model update scheme peak‐to‐sidelobe ratio |
| url | https://doi.org/10.1049/el.2016.4183 |
| work_keys_str_mv | AT yulongxu onestepbacktrackingforocclusiondetectioninrealtimevisualtracking AT jiabaowang onestepbacktrackingforocclusiondetectioninrealtimevisualtracking AT yangli onestepbacktrackingforocclusiondetectioninrealtimevisualtracking AT zhuangmiao onestepbacktrackingforocclusiondetectioninrealtimevisualtracking AT yafeizhang onestepbacktrackingforocclusiondetectioninrealtimevisualtracking |