Vehicle Tracking on Satellite Video Based on Historical Model
Vehicle tracking on satellite videos poses a challenge for the existing object tracking algorithms due to the few features, object occlusion, and similar objects appearance. To improve the performance of the object tracking algorithm, a historical-model-based tracker intended for satellite videos is...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9847077/ |
| _version_ | 1798035872987217920 |
|---|---|
| author | Shili Chen Taoyang Wang Hongshuo Wang Yunming Wang Jianzhi Hong Tiancheng Dong Zhen Li |
| author_facet | Shili Chen Taoyang Wang Hongshuo Wang Yunming Wang Jianzhi Hong Tiancheng Dong Zhen Li |
| author_sort | Shili Chen |
| collection | DOAJ |
| description | Vehicle tracking on satellite videos poses a challenge for the existing object tracking algorithms due to the few features, object occlusion, and similar objects appearance. To improve the performance of the object tracking algorithm, a historical-model-based tracker intended for satellite videos is proposed in this study. It updates the tracker by using the historical model of each frame in the video, which contains plenty of object information and background information, so as to improve tracking ability on few-feature objects. Furthermore, a historical model evaluation scheme is designed to obtain reliable historical models, which ensures that the tracker is sensitive to the object in the current frame, thus avoiding the impact caused by changes in object appearance and background. Besides, to solve the drift issue of the tracker caused by object occlusion and the appearance of similar objects, an antidrift tracker correction scheme is proposed as well. According to the comparative experiments conducted on satellite videos dataset SatSOT, our tracker produces an excellent performance. Moreover, sensitivity analysis, varying criteria comparative experiments, and ablation experiments are conducted to demonstrate that the proposed schemes are effective in improving the precision and success rate of the tracker. |
| first_indexed | 2024-04-11T21:04:19Z |
| format | Article |
| id | doaj.art-eb0c0a9ddabd4a248cd6d844333fa95e |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-11T21:04:19Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-eb0c0a9ddabd4a248cd6d844333fa95e2022-12-22T04:03:23ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01157784779610.1109/JSTARS.2022.31955229847077Vehicle Tracking on Satellite Video Based on Historical ModelShili Chen0https://orcid.org/0000-0001-7691-0033Taoyang Wang1https://orcid.org/0000-0002-6014-5354Hongshuo Wang2Yunming Wang3https://orcid.org/0000-0002-5109-4217Jianzhi Hong4Tiancheng Dong5Zhen Li6School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaBeijing Aerospace Automatic Control Institute, Beijing, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaInstitute of Remote Sensing Satellite, China Academy of Space Technology, Beijing, ChinaVehicle tracking on satellite videos poses a challenge for the existing object tracking algorithms due to the few features, object occlusion, and similar objects appearance. To improve the performance of the object tracking algorithm, a historical-model-based tracker intended for satellite videos is proposed in this study. It updates the tracker by using the historical model of each frame in the video, which contains plenty of object information and background information, so as to improve tracking ability on few-feature objects. Furthermore, a historical model evaluation scheme is designed to obtain reliable historical models, which ensures that the tracker is sensitive to the object in the current frame, thus avoiding the impact caused by changes in object appearance and background. Besides, to solve the drift issue of the tracker caused by object occlusion and the appearance of similar objects, an antidrift tracker correction scheme is proposed as well. According to the comparative experiments conducted on satellite videos dataset SatSOT, our tracker produces an excellent performance. Moreover, sensitivity analysis, varying criteria comparative experiments, and ablation experiments are conducted to demonstrate that the proposed schemes are effective in improving the precision and success rate of the tracker.https://ieeexplore.ieee.org/document/9847077/Correlation filter (CF)high-confidence trackingmotion estimationobject trackingsatellite video |
| spellingShingle | Shili Chen Taoyang Wang Hongshuo Wang Yunming Wang Jianzhi Hong Tiancheng Dong Zhen Li Vehicle Tracking on Satellite Video Based on Historical Model IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Correlation filter (CF) high-confidence tracking motion estimation object tracking satellite video |
| title | Vehicle Tracking on Satellite Video Based on Historical Model |
| title_full | Vehicle Tracking on Satellite Video Based on Historical Model |
| title_fullStr | Vehicle Tracking on Satellite Video Based on Historical Model |
| title_full_unstemmed | Vehicle Tracking on Satellite Video Based on Historical Model |
| title_short | Vehicle Tracking on Satellite Video Based on Historical Model |
| title_sort | vehicle tracking on satellite video based on historical model |
| topic | Correlation filter (CF) high-confidence tracking motion estimation object tracking satellite video |
| url | https://ieeexplore.ieee.org/document/9847077/ |
| work_keys_str_mv | AT shilichen vehicletrackingonsatellitevideobasedonhistoricalmodel AT taoyangwang vehicletrackingonsatellitevideobasedonhistoricalmodel AT hongshuowang vehicletrackingonsatellitevideobasedonhistoricalmodel AT yunmingwang vehicletrackingonsatellitevideobasedonhistoricalmodel AT jianzhihong vehicletrackingonsatellitevideobasedonhistoricalmodel AT tianchengdong vehicletrackingonsatellitevideobasedonhistoricalmodel AT zhenli vehicletrackingonsatellitevideobasedonhistoricalmodel |