High-Accuracy and Low-Latency Tracker for UAVs Monitoring Tibetan Antelopes
As the habitat areas of Tibetan antelopes usually exhibit poaching and unpredictable risks, combining target recognition and tracking with intelligent Unmanned Aerial Vehicle (UAV) technology is necessary to obtain the real-time location of injured Tibetan antelopes to better protect and rescue them...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/2/417 |
| _version_ | 1827622257861591040 |
|---|---|
| author | Wei Luo Xiaofang Li Guoqing Zhang Quanqin Shao Yongxiang Zhao Denghua Li Yunfeng Zhao Xuqing Li Zihui Zhao Yuyan Liu Xiaoliang Li |
| author_facet | Wei Luo Xiaofang Li Guoqing Zhang Quanqin Shao Yongxiang Zhao Denghua Li Yunfeng Zhao Xuqing Li Zihui Zhao Yuyan Liu Xiaoliang Li |
| author_sort | Wei Luo |
| collection | DOAJ |
| description | As the habitat areas of Tibetan antelopes usually exhibit poaching and unpredictable risks, combining target recognition and tracking with intelligent Unmanned Aerial Vehicle (UAV) technology is necessary to obtain the real-time location of injured Tibetan antelopes to better protect and rescue them. (1) Background: The most common way to track an object is to detect each frame of it, and it is not necessary to run the object tracker and classifier at the same rate, because the speed for them to change class is slower than objects move. Especially in the edge reasoning scene, UAV real-time monitoring requires to seek a balance between the frame rate, latency, and accuracy. (2) Methods: A backtracking tracker is proposed to recognize Tibetan antelopes which generates motion vectors through stored optical flow, achieving faster target detection. The lightweight You Only Look Once X (YOLOX) is selected as the baseline model to reduce the dependence on hardware configuration and calculation cost while ensuring detection accuracy. Region-of-Interest (ROI)-to-centroid tracking technology is employed to reduce the processing cost of motion interpolation, and the overall processing frame rate is smoothed by pre-calculating the motions of different objects recognized. The On-Line Object Tracking (OLOT) system with adaptive search area selection is adopted to dynamically adjust the frame rate to reduce energy waste. (3) Results: using YOLOX to trace back in the native Darkenet can reduce latency by 3.75 times, and the latency is only 2.82 ms after about 10 frame hops, with the accuracy being higher than YOLOv3. Compared with traditional algorithms, the proposed algorithm can reduce the tracking latency of UAVs by 50%. By running and comparing in the onboard computer, although the proposed tracker is inferior to KCF in FPS, it is significantly higher than other trackers and is obviously superior to KCF in accuracy. (4) Conclusion: A UAV equipped with the proposed tracker effectively reduces reasoning latency in monitoring Tibetan antelopes, achieving high recognition accuracy. Therefore, it is expected to help better protection of Tibetan antelopes. |
| first_indexed | 2024-03-09T11:20:03Z |
| format | Article |
| id | doaj.art-3c00dada0f334d8789d2577e5f4b8cfb |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T11:20:03Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-3c00dada0f334d8789d2577e5f4b8cfb2023-12-01T00:20:27ZengMDPI AGRemote Sensing2072-42922023-01-0115241710.3390/rs15020417High-Accuracy and Low-Latency Tracker for UAVs Monitoring Tibetan AntelopesWei Luo0Xiaofang Li1Guoqing Zhang2Quanqin Shao3Yongxiang Zhao4Denghua Li5Yunfeng Zhao6Xuqing Li7Zihui Zhao8Yuyan Liu9Xiaoliang Li10North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Architecture and Civil Engineering, Langfang Normal University, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, Langfang 065000, ChinaKey Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaNorth China Institute of Aerospace Engineering, Langfang 065000, ChinaAgricultural Information Institute of Chinese Academy of Agricultural Sciences, Key Laboratory of Agricultural Monitoring and Early Warning Technology, Ministry of Agriculture and Rural Affairs, Beijing 100081, ChinaNorth China Institute of Aerospace Engineering, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, Langfang 065000, ChinaAs the habitat areas of Tibetan antelopes usually exhibit poaching and unpredictable risks, combining target recognition and tracking with intelligent Unmanned Aerial Vehicle (UAV) technology is necessary to obtain the real-time location of injured Tibetan antelopes to better protect and rescue them. (1) Background: The most common way to track an object is to detect each frame of it, and it is not necessary to run the object tracker and classifier at the same rate, because the speed for them to change class is slower than objects move. Especially in the edge reasoning scene, UAV real-time monitoring requires to seek a balance between the frame rate, latency, and accuracy. (2) Methods: A backtracking tracker is proposed to recognize Tibetan antelopes which generates motion vectors through stored optical flow, achieving faster target detection. The lightweight You Only Look Once X (YOLOX) is selected as the baseline model to reduce the dependence on hardware configuration and calculation cost while ensuring detection accuracy. Region-of-Interest (ROI)-to-centroid tracking technology is employed to reduce the processing cost of motion interpolation, and the overall processing frame rate is smoothed by pre-calculating the motions of different objects recognized. The On-Line Object Tracking (OLOT) system with adaptive search area selection is adopted to dynamically adjust the frame rate to reduce energy waste. (3) Results: using YOLOX to trace back in the native Darkenet can reduce latency by 3.75 times, and the latency is only 2.82 ms after about 10 frame hops, with the accuracy being higher than YOLOv3. Compared with traditional algorithms, the proposed algorithm can reduce the tracking latency of UAVs by 50%. By running and comparing in the onboard computer, although the proposed tracker is inferior to KCF in FPS, it is significantly higher than other trackers and is obviously superior to KCF in accuracy. (4) Conclusion: A UAV equipped with the proposed tracker effectively reduces reasoning latency in monitoring Tibetan antelopes, achieving high recognition accuracy. Therefore, it is expected to help better protection of Tibetan antelopes.https://www.mdpi.com/2072-4292/15/2/417Tibetan antelope protectionintelligent UAVSOTYOLOXoptical flowlatency |
| spellingShingle | Wei Luo Xiaofang Li Guoqing Zhang Quanqin Shao Yongxiang Zhao Denghua Li Yunfeng Zhao Xuqing Li Zihui Zhao Yuyan Liu Xiaoliang Li High-Accuracy and Low-Latency Tracker for UAVs Monitoring Tibetan Antelopes Remote Sensing Tibetan antelope protection intelligent UAV SOT YOLOX optical flow latency |
| title | High-Accuracy and Low-Latency Tracker for UAVs Monitoring Tibetan Antelopes |
| title_full | High-Accuracy and Low-Latency Tracker for UAVs Monitoring Tibetan Antelopes |
| title_fullStr | High-Accuracy and Low-Latency Tracker for UAVs Monitoring Tibetan Antelopes |
| title_full_unstemmed | High-Accuracy and Low-Latency Tracker for UAVs Monitoring Tibetan Antelopes |
| title_short | High-Accuracy and Low-Latency Tracker for UAVs Monitoring Tibetan Antelopes |
| title_sort | high accuracy and low latency tracker for uavs monitoring tibetan antelopes |
| topic | Tibetan antelope protection intelligent UAV SOT YOLOX optical flow latency |
| url | https://www.mdpi.com/2072-4292/15/2/417 |
| work_keys_str_mv | AT weiluo highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes AT xiaofangli highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes AT guoqingzhang highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes AT quanqinshao highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes AT yongxiangzhao highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes AT denghuali highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes AT yunfengzhao highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes AT xuqingli highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes AT zihuizhao highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes AT yuyanliu highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes AT xiaoliangli highaccuracyandlowlatencytrackerforuavsmonitoringtibetanantelopes |