The "Low Slow and Small" UAV target detection and tracking algorithm based on improved YOLOv7 and DeepSort
To improve the accuracy of Low altitude unmanned aerial vehicle(UAV) target detection and tracking, an improved UAV detection algorithm based on YOLOv7 and DeepSort framework is proposed. The CBAM attention mechanism is introduced into the backbone network of YOLOv7 algorithm to improve feature extr...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Command Control and Simulation
2025-02-01
|
| Series: | Zhihui kongzhi yu fangzhen |
| Subjects: | |
| Online Access: | https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1737457467353-1413947981.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592283705278464 |
|---|---|
| author | JIAN Yuhong, YANG Huiyue, WANG Xinggang, RONG Yisheng, ZHU Yukun |
| author_facet | JIAN Yuhong, YANG Huiyue, WANG Xinggang, RONG Yisheng, ZHU Yukun |
| author_sort | JIAN Yuhong, YANG Huiyue, WANG Xinggang, RONG Yisheng, ZHU Yukun |
| collection | DOAJ |
| description | To improve the accuracy of Low altitude unmanned aerial vehicle(UAV) target detection and tracking, an improved UAV detection algorithm based on YOLOv7 and DeepSort framework is proposed. The CBAM attention mechanism is introduced into the backbone network of YOLOv7 algorithm to improve feature extraction ability. To improve feature fusion ability at different scales, BiFPN weighted feature pyramid is used to replace PANet, and a small target detection layer is added to improve the detection accuracy of small target UAVs. A "low slow small" human-machine data set is constructed with four types of backgrounds: sky, trees, buildings, and dark conditions. The experimental test is carried out. The results show that the detection part mAP@0.5 of the improved algorithm is improved by 8.6%, and the detection accuracy of small-size and weak-feature targets is improved by about 21%. In the final tracking result, the MOTA index was increased by 24%, and the correct output target box accounted for about 70% of the true target box. |
| format | Article |
| id | doaj-art-52433c01195f4178b5381a79d724098e |
| institution | Kabale University |
| issn | 1673-3819 |
| language | zho |
| publishDate | 2025-02-01 |
| publisher | Editorial Office of Command Control and Simulation |
| record_format | Article |
| series | Zhihui kongzhi yu fangzhen |
| spelling | doaj-art-52433c01195f4178b5381a79d724098e2025-01-21T11:12:00ZzhoEditorial Office of Command Control and SimulationZhihui kongzhi yu fangzhen1673-38192025-02-01471233110.3969/j.issn.1673-3819.2025.01.003The "Low Slow and Small" UAV target detection and tracking algorithm based on improved YOLOv7 and DeepSortJIAN Yuhong, YANG Huiyue, WANG Xinggang, RONG Yisheng, ZHU Yukun0Army Logistics Academy of PLA, Chongqing 401311, ChinaTo improve the accuracy of Low altitude unmanned aerial vehicle(UAV) target detection and tracking, an improved UAV detection algorithm based on YOLOv7 and DeepSort framework is proposed. The CBAM attention mechanism is introduced into the backbone network of YOLOv7 algorithm to improve feature extraction ability. To improve feature fusion ability at different scales, BiFPN weighted feature pyramid is used to replace PANet, and a small target detection layer is added to improve the detection accuracy of small target UAVs. A "low slow small" human-machine data set is constructed with four types of backgrounds: sky, trees, buildings, and dark conditions. The experimental test is carried out. The results show that the detection part mAP@0.5 of the improved algorithm is improved by 8.6%, and the detection accuracy of small-size and weak-feature targets is improved by about 21%. In the final tracking result, the MOTA index was increased by 24%, and the correct output target box accounted for about 70% of the true target box.https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1737457467353-1413947981.pdfanti-drone|machine vision|target detection|target tracking |
| spellingShingle | JIAN Yuhong, YANG Huiyue, WANG Xinggang, RONG Yisheng, ZHU Yukun The "Low Slow and Small" UAV target detection and tracking algorithm based on improved YOLOv7 and DeepSort Zhihui kongzhi yu fangzhen anti-drone|machine vision|target detection|target tracking |
| title | The "Low Slow and Small" UAV target detection and tracking algorithm based on improved YOLOv7 and DeepSort |
| title_full | The "Low Slow and Small" UAV target detection and tracking algorithm based on improved YOLOv7 and DeepSort |
| title_fullStr | The "Low Slow and Small" UAV target detection and tracking algorithm based on improved YOLOv7 and DeepSort |
| title_full_unstemmed | The "Low Slow and Small" UAV target detection and tracking algorithm based on improved YOLOv7 and DeepSort |
| title_short | The "Low Slow and Small" UAV target detection and tracking algorithm based on improved YOLOv7 and DeepSort |
| title_sort | low slow and small uav target detection and tracking algorithm based on improved yolov7 and deepsort |
| topic | anti-drone|machine vision|target detection|target tracking |
| url | https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1737457467353-1413947981.pdf |
| work_keys_str_mv | AT jianyuhongyanghuiyuewangxinggangrongyishengzhuyukun thelowslowandsmalluavtargetdetectionandtrackingalgorithmbasedonimprovedyolov7anddeepsort AT jianyuhongyanghuiyuewangxinggangrongyishengzhuyukun lowslowandsmalluavtargetdetectionandtrackingalgorithmbasedonimprovedyolov7anddeepsort |