Small object detection in UAV image based on improved YOLOv5
Less effective information is obtained by the object detection network, due to the small size of the detection object in the entire image, the complex background, and the dense object in unmanned aerial vehicle (UAV) images. In response to the difficulties encountered, a small object detection metho...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Systems Science & Control Engineering |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/21642583.2023.2247082 |
| _version_ | 1797447546624278528 |
|---|---|
| author | Jian Zhang Guoyang Wan Ming Jiang Guifu Lu Xiuwen Tao Zhiyuan Huang |
| author_facet | Jian Zhang Guoyang Wan Ming Jiang Guifu Lu Xiuwen Tao Zhiyuan Huang |
| author_sort | Jian Zhang |
| collection | DOAJ |
| description | Less effective information is obtained by the object detection network, due to the small size of the detection object in the entire image, the complex background, and the dense object in unmanned aerial vehicle (UAV) images. In response to the difficulties encountered, a small object detection method in UAV images is proposed as an improved YOLOv5-based algorithm in this paper. First, the space-to-depth(SPD) conv module is introduced into the basic feature extraction network, to improve significant loss of image information during downsampling. Then, various attention mechanisms are added, to intensify the acquisition of regions of interest in UAV images. Finally, the multiscale detection module is improved, to enhance the network's ability to detect small objects in UAV images. By conducting experiments on the VisDrone-DET2019 dataset, the test results of the established model show. The improved algorithm achieved a Mean Average Precision (mAP) of 41.8%, which is 7.8% better than the baseline network. In addition, the detection performance is better than most current mainstream target detection algorithms and is of some practical value. |
| first_indexed | 2024-03-09T13:57:33Z |
| format | Article |
| id | doaj.art-eb9d9847c2804b8b8e9d06d4cee8a159 |
| institution | Directory Open Access Journal |
| issn | 2164-2583 |
| language | English |
| last_indexed | 2024-03-09T13:57:33Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Systems Science & Control Engineering |
| spelling | doaj.art-eb9d9847c2804b8b8e9d06d4cee8a1592023-11-30T12:45:32ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832023-12-0111110.1080/21642583.2023.2247082Small object detection in UAV image based on improved YOLOv5Jian Zhang0Guoyang Wan1Ming Jiang2Guifu Lu3Xiuwen Tao4Zhiyuan Huang5Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment, Ministry of Education, Anhui Polytechnic University, Wuhu, People’s Republic of ChinaKey Laboratory of Advanced Perception and Intelligent Control of High-End Equipment, Ministry of Education, Anhui Polytechnic University, Wuhu, People’s Republic of ChinaKey Laboratory of Advanced Perception and Intelligent Control of High-End Equipment, Ministry of Education, Anhui Polytechnic University, Wuhu, People’s Republic of ChinaKey Laboratory of Advanced Perception and Intelligent Control of High-End Equipment, Ministry of Education, Anhui Polytechnic University, Wuhu, People’s Republic of ChinaKey Laboratory of Advanced Perception and Intelligent Control of High-End Equipment, Ministry of Education, Anhui Polytechnic University, Wuhu, People’s Republic of ChinaKey Laboratory of Advanced Perception and Intelligent Control of High-End Equipment, Ministry of Education, Anhui Polytechnic University, Wuhu, People’s Republic of ChinaLess effective information is obtained by the object detection network, due to the small size of the detection object in the entire image, the complex background, and the dense object in unmanned aerial vehicle (UAV) images. In response to the difficulties encountered, a small object detection method in UAV images is proposed as an improved YOLOv5-based algorithm in this paper. First, the space-to-depth(SPD) conv module is introduced into the basic feature extraction network, to improve significant loss of image information during downsampling. Then, various attention mechanisms are added, to intensify the acquisition of regions of interest in UAV images. Finally, the multiscale detection module is improved, to enhance the network's ability to detect small objects in UAV images. By conducting experiments on the VisDrone-DET2019 dataset, the test results of the established model show. The improved algorithm achieved a Mean Average Precision (mAP) of 41.8%, which is 7.8% better than the baseline network. In addition, the detection performance is better than most current mainstream target detection algorithms and is of some practical value.https://www.tandfonline.com/doi/10.1080/21642583.2023.2247082UAV image object detectionYOLOv5attention mechanismmultiscale detection |
| spellingShingle | Jian Zhang Guoyang Wan Ming Jiang Guifu Lu Xiuwen Tao Zhiyuan Huang Small object detection in UAV image based on improved YOLOv5 Systems Science & Control Engineering UAV image object detection YOLOv5 attention mechanism multiscale detection |
| title | Small object detection in UAV image based on improved YOLOv5 |
| title_full | Small object detection in UAV image based on improved YOLOv5 |
| title_fullStr | Small object detection in UAV image based on improved YOLOv5 |
| title_full_unstemmed | Small object detection in UAV image based on improved YOLOv5 |
| title_short | Small object detection in UAV image based on improved YOLOv5 |
| title_sort | small object detection in uav image based on improved yolov5 |
| topic | UAV image object detection YOLOv5 attention mechanism multiscale detection |
| url | https://www.tandfonline.com/doi/10.1080/21642583.2023.2247082 |
| work_keys_str_mv | AT jianzhang smallobjectdetectioninuavimagebasedonimprovedyolov5 AT guoyangwan smallobjectdetectioninuavimagebasedonimprovedyolov5 AT mingjiang smallobjectdetectioninuavimagebasedonimprovedyolov5 AT guifulu smallobjectdetectioninuavimagebasedonimprovedyolov5 AT xiuwentao smallobjectdetectioninuavimagebasedonimprovedyolov5 AT zhiyuanhuang smallobjectdetectioninuavimagebasedonimprovedyolov5 |