Optics and Precision Engineering, Volume. 31, Issue 18, 2723(2023)
Joint self-attention and branch sampling for object detection on drone imagery
Figures & Tables(12)
Fig. 5. Comparison of detection results of different algorithms on VisDrone2019
Fig. 6. Comparison of detection results of different algorithms on UAVDT
Table 1. Comparison of the results of the baseline and the algorithm in this paper on VisDrone2019
View tableView in ArticleTable 1. Comparison of the results of the baseline and the algorithm in this paper on VisDrone2019
Method 指标 Pedestrian People Bicycle Car Van Truck Tricycle Awning-tricycle Bus Motor ALL Baseline-s mAP50 66.8 53.7 35.8 88.4 56.3 45.2 42.4 21.5 64.6 64.3 53.9 mAP 33.9 22.5 16.6 57.7 39.9 30.6 24.3 13.6 46.8 31.6 31.7 Ours-s mAP50 72.1 58.0 42.7 90.5 61.0 53.8 48.6 25.2 72.4 68.8 59.3 mAP 38.4 26.1 21.6 67.6 45.0 36.0 29.2 16.0 54.6 36.4 37.1 Baseline-m mAP50 69.4 56.0 39.7 89.4 59.1 52.6 46.8 26.3 71.4 66.0 57.7 mAP 34.2 24.5 19.7 67.5 44.2 34.3 28.4 16.2 51.9 33.8 35.4 Ours-m mAP50 73.6 60.3 45.4 91.1 62.0 55.2 50.6 29.7 79.4 70.3 61.8 mAP 39.4 27.1 23.2 69.1 46.5 39.1 30.4 18.3 59.2 36.9 38.9
Table 2. Comparison of results of different algorithm models on VisDrone2019
View tableView in ArticleTable 2. Comparison of results of different algorithm models on VisDrone2019
Method mAP50 mAP mAP75 Ap-small AP-mid AP-large ClusDet［ 10 ］56.2 32.4 31.6 - - - DSHNet［ 11 ］51.8 30.3 30.9 - - - HRDNet［ 12 ］62.0 35.5 35.1 - - - Yolov5-s 53.7 31.7 31.4 22.0 43.7 49.5 Yolov5-m 58.6 35.4 36.8 27.6 47.6 52.4 Yolov7［ 22 ］57.3 35.6 37.1 26.5 46.0 50.3 YoloX 53.5 31.4 31.7 22.5 41.5 48.5 MobileNetv3 55.4 32.9 32.9 24.5 44.3 49.5 MobileViT 55.5 33.3 33.7 24.9 44.2 41.8 mSODANet［ 27 ］55.9 36.9 37.4 - - - Ours-s 59.3 37.1 38.3 29.2 48.5 51.6 Ours-m 62.1 38.9 39.5 31.2 51.3 52.5
Table 3. Comparison of the results of the baseline and the algorithm in this paper on UAVDT
View tableView in ArticleTable 3. Comparison of the results of the baseline and the algorithm in this paper on UAVDT
Method 指标 Car Truck Bus All Baseline-s mAP50 73.0 15.2 26.6 38.3 mAP 41.2 8.1 15.9 21.7 Ours-s mAP50 73.3 19.4 39.7 44.1 mAP 40.9 10.9 23.0 24.9 Baseline-m mAP50 72.1 8.55 40.5 40.4 mAP 39.6 4.86 22.9 22.5 Ours-m mAP50 73.7 18.0 40.9 44.2 mAP 42.3 11.2 24.1 25.8
Table 4. Comparison of results of different algorithm models on UAVDT
View tableView in ArticleTable 4. Comparison of results of different algorithm models on UAVDT
Method mAP50 mAP mAP75 ClusDet［ 10 ］26.5 13.9 12.5 DMNet［ 28 ］24.6 14.7 16.3 GLSAN［ 29 ］30.5 19.0 21.7 CDMNet［ 30 ］29.1 16.8 18.5 DSHNet［ 11 ］30.4 17.8 19.7 Yolov5-s 38.3 21.7 22.6 Yolov5-m 41.4 22.6 24.1 PRDet［ 31 ］34.1 19.8 21.3 UFPMP-Det［32］ 38.7 24.6 28.0 Ours-s 44.1 24.9 27.3 Ours-m 44.7 25.3 28.1
Table 5. Performance comparison of different sampling methods
View tableView in ArticleTable 5. Performance comparison of different sampling methods
Method Up-sampling Down-sampling Nearest Bilinear DBUS Conv Pooling DBDS mAP50 53.7 54.1 54.5 53.7 53.5 54.8 mAP 31.7 32.1 32.8 31.7 32.0 33.2
Table 6. Ablation experiment result
View tableView in ArticleTable 6. Ablation experiment result
Baseline Fourhead Our-Fourhead NRCS DBUS DBDS FE-IR（3） Parm GFLOPs mAP50（%） mAP（%） FPS 1 √ 7.028M 16.0 53.7 31.7 35.6 2 √ √ 7.262M 19.3 54.8 32.4 24.7 3 √ √ 6.911M 19.1 56.1 34.3 25.6 4 √ √ √ 6.583M 19.3 56.9 35.1 27.1 5 √ √ √ 6.942M 21.4 56.3 34.6 27.1 6 √ √ √ 6.982M 21.6 56.8 35.2 26.9 7 √ √ √ √ 7.013M 23.4 57.1 35.2 26.5 8 √ √ √ √ √ 6.686M 23.6 58.3 35.9 26.9 9 √ √ √ √ √ √ 7.875M 26.8 59.7 37.1 22.1
Tools
Get Citation
Copy Citation Text
Yunzuo ZHANG, Cunyu WU, Yameng LIU, Tian ZHANG, Yuxin ZHENG. Joint self-attention and branch sampling for object detection on drone imagery[J]. Optics and Precision Engineering, 2023, 31(18): 2723
Paper Information
Category: Information Sciences
Received: Dec. 29, 2022
Accepted: --
Published Online: Oct. 12, 2023
The Author Email: ZHANG Yunzuo (zhangyunzuo888@sina.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20