Correlation Filter of Multiple Candidates Match for Anti-Obscure Tracking in Unmanned Aerial Vehicle Scenario
Due to the complexity of Unmanned Aerial Vehicle (UAV) target tracking scenarios, tracking drift caused by target occlusion is common and has no suitable solution. In this paper, an occlusion-resistant target tracking algorithm based on the correlated filter tracking model is proposed. First, instea...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/1/163 |
| _version_ | 1797431409963433984 |
|---|---|
| author | Zhen Chen Hongyuan Zheng Xiangping (Bryce) Zhai Kangliang Zhang Hua Xia |
| author_facet | Zhen Chen Hongyuan Zheng Xiangping (Bryce) Zhai Kangliang Zhang Hua Xia |
| author_sort | Zhen Chen |
| collection | DOAJ |
| description | Due to the complexity of Unmanned Aerial Vehicle (UAV) target tracking scenarios, tracking drift caused by target occlusion is common and has no suitable solution. In this paper, an occlusion-resistant target tracking algorithm based on the correlated filter tracking model is proposed. First, instead of the traditional target tracking model that uses single template matching to locate the target, we locate the target by finding the optimal match based on multiple candidates templates matching. Then, in order to increase the accuracy of matching, we use the self-attentive mechanism for feature enhancement. We experiment our proposed algorithm on datasets OTB100 and UAV123, respectively, and the results show that the tracking accuracy of our algorithm outperforms the traditional correlated filtered target tracking model. In addition, we have also tested the anti-occlusion performance of our proposed algorithm on some video sequences in which the target is occluded. The results show that our proposed algorithm has a certain resistance to occlusion, especially in the UAV tracking scenario. |
| first_indexed | 2024-03-09T09:44:33Z |
| format | Article |
| id | doaj.art-4bd3fc552dbb44519daba63df528bd30 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T09:44:33Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-4bd3fc552dbb44519daba63df528bd302023-12-02T00:38:57ZengMDPI AGMathematics2227-73902022-12-0111116310.3390/math11010163Correlation Filter of Multiple Candidates Match for Anti-Obscure Tracking in Unmanned Aerial Vehicle ScenarioZhen Chen0Hongyuan Zheng1Xiangping (Bryce) Zhai2Kangliang Zhang3Hua Xia4College of Computer Science and Technology/College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing 211006, ChinaCollege of Computer Science and Technology/College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing 211006, ChinaCollege of Computer Science and Technology/College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing 211006, ChinaCollege of Computer Science and Technology/College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing 211006, ChinaCollege of Computer Science and Technology/College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing 211006, ChinaDue to the complexity of Unmanned Aerial Vehicle (UAV) target tracking scenarios, tracking drift caused by target occlusion is common and has no suitable solution. In this paper, an occlusion-resistant target tracking algorithm based on the correlated filter tracking model is proposed. First, instead of the traditional target tracking model that uses single template matching to locate the target, we locate the target by finding the optimal match based on multiple candidates templates matching. Then, in order to increase the accuracy of matching, we use the self-attentive mechanism for feature enhancement. We experiment our proposed algorithm on datasets OTB100 and UAV123, respectively, and the results show that the tracking accuracy of our algorithm outperforms the traditional correlated filtered target tracking model. In addition, we have also tested the anti-occlusion performance of our proposed algorithm on some video sequences in which the target is occluded. The results show that our proposed algorithm has a certain resistance to occlusion, especially in the UAV tracking scenario.https://www.mdpi.com/2227-7390/11/1/163target trackingocclusion-resistantmultiple candidatesoptimal match |
| spellingShingle | Zhen Chen Hongyuan Zheng Xiangping (Bryce) Zhai Kangliang Zhang Hua Xia Correlation Filter of Multiple Candidates Match for Anti-Obscure Tracking in Unmanned Aerial Vehicle Scenario Mathematics target tracking occlusion-resistant multiple candidates optimal match |
| title | Correlation Filter of Multiple Candidates Match for Anti-Obscure Tracking in Unmanned Aerial Vehicle Scenario |
| title_full | Correlation Filter of Multiple Candidates Match for Anti-Obscure Tracking in Unmanned Aerial Vehicle Scenario |
| title_fullStr | Correlation Filter of Multiple Candidates Match for Anti-Obscure Tracking in Unmanned Aerial Vehicle Scenario |
| title_full_unstemmed | Correlation Filter of Multiple Candidates Match for Anti-Obscure Tracking in Unmanned Aerial Vehicle Scenario |
| title_short | Correlation Filter of Multiple Candidates Match for Anti-Obscure Tracking in Unmanned Aerial Vehicle Scenario |
| title_sort | correlation filter of multiple candidates match for anti obscure tracking in unmanned aerial vehicle scenario |
| topic | target tracking occlusion-resistant multiple candidates optimal match |
| url | https://www.mdpi.com/2227-7390/11/1/163 |
| work_keys_str_mv | AT zhenchen correlationfilterofmultiplecandidatesmatchforantiobscuretrackinginunmannedaerialvehiclescenario AT hongyuanzheng correlationfilterofmultiplecandidatesmatchforantiobscuretrackinginunmannedaerialvehiclescenario AT xiangpingbrycezhai correlationfilterofmultiplecandidatesmatchforantiobscuretrackinginunmannedaerialvehiclescenario AT kangliangzhang correlationfilterofmultiplecandidatesmatchforantiobscuretrackinginunmannedaerialvehiclescenario AT huaxia correlationfilterofmultiplecandidatesmatchforantiobscuretrackinginunmannedaerialvehiclescenario |