Laser & Optoelectronics Progress, Volume. 59, Issue 8, 0810006(2022)
Lightweight Target Detection Algorithm for Small and Weak Drone Targets
Figures & Tables(14)
Fig. 2. Analysis of size of drone targets in two datasets. (a) Dataset A; (b) Dataset B
Fig. 3. Structure diagram of YOLOv4-tiny algorithm. (a) YOLOv4-tiny; (b) CSPBlock
Fig. 5. ShuffleNetV2 and improved backbone network structure. (a) ShuffleV2Block; (b) backbone network of ShuffleNetV2; (c) backbone network of proposed algorithm
Fig. 6. FPN structure comparison of different detection models. (a) YOLOv4-tiny; (b) YOLOv4-tiny (YOLO-Head enhancement); (c) DTD-YOLOv4-tiny
Fig. 8. Working principles of sub-pixel Conv and sub-pixel. (a) Sub-pixel Conv; (b) sub-pixel
Fig. 9. Comparison of accuracy and detection speed of different target detection models under different datasets. (a) Dataset A; (b) Dataset B
Fig. 10. Comparison of partial detection results of test set on different datasets. (a) YOLOv4-tiny (Dataset A); (b) DTD-YOLOv4-tiny (Dataset A); (c) YOLOv4-tiny (Dataset B); (d) DTD-YOLOv4-tiny (Dataset B)
Table 1. Performance comparison of different algorithms in MS COCO dataset
View tableTable 1. Performance comparison of different algorithms in MS COCO dataset
Algorithm Image size mAP@50 /% GFLOPs Detection speed /（frame·s-1） YOLOv4 416 65.7 60.1 55 YOLOv3-tiny 416 33.1 5.6 345 YOLOv4-tiny 416 40.2 6.9 330
Table 2. Ablation experiment results of DTD-YOLOv4-tiny algorithm
View tableTable 2. Ablation experiment results of DTD-YOLOv4-tiny algorithm
Model Head improve Neck improve Backbone Improve AP /% Parameters GFLOPs Anchor box imporve YOLO-Head enhancement ShuffleV2
Block（B）
reorg
layer
sub
pixel
Shufflev2
Block（B）
ShuffleNetv2 Backbone Proposed Backbone YOLOv4-tiny （Baseline） 43.1 5.8×106 12.1 Imporve A √ 84.1 5.8×106 12.1 Imporve B √ √ 91.3 6.1×106 14.3 Imporve C √ √ √ 93.6 6.8×106 17.1 Imporve D √ √ √ √ 94.5 6.5×106 16.1 Imporve E √ √ √ √ √ 87.1 0.65×106 1.9 Imporve F √ √ √ √ √ 87.4 0.64×106 2.2 Imporve G √ √ √ √ √ √ 85.3 0.27×106 0.9 DTD-
YOLOv4-tiny
√ √ √ √ √ √ √ 89.4 0.32×106 1.1
Table 3. 4 Performance comparison of different algorithms on Dataset A
View tableTable 3. 4 Performance comparison of different algorithms on Dataset A
Algorithm Image size P /% R /% AP /% Parameters GFLOPs GPU /GB YOLOv3-SPP 416×234 93.5 96.2 96.8 625×106 116.9 3.85 YOLOv4 416×234 85.6 96.6 95.5 639×106 105.9 5.6 YOLOv4-tiny 416×234 81.5 87.6 84.1 5.87×106 12.1 0.7 DTD-YOLOv4-tiny 416×234 83.5 86.7 89.4 0.327×106 1.1 0.52 DTD-YOLOv4-tiny 608×342 88.3 93.9 94.2 0.327×106 1.1 0.583 DTD-YOLOv4-tiny 960×540 87.8 95.6 95.0 0.327×106 1.1 1.3
Table 4. Performance comparison of different algorithms on Dataset B
View tableTable 4. Performance comparison of different algorithms on Dataset B
Model Image size AP /% Model size YOLOv3［ 18 ］1333×800 84.9 234.1 MB Fast RCNN（MobileNet）［ 18 ］1333×800 67.5 162.5 MB Casacade RCNN（MobileNet）［ 18 ］1333×800 78.0 384.9 MB TIB-Net［ 18 ］1333×800 89.2 697.0 KB YOLOv4-tiny 1344×756 78.5 23 MB DTD-YOLOv4-tiny 960×540 80.3 1.4 MB DTD-YOLOv4-tiny 1344×756 83.3 1.4 MB DTD-YOLOv4-tiny 1920×1080 85.1 1.4 MB
Tools
Get Citation
Copy Citation Text
Rongqi Jiang, Zecong Ye, Yueping Peng, Guorong Xie, Heng Du. Lightweight Target Detection Algorithm for Small and Weak Drone Targets[J]. Laser & Optoelectronics Progress, 2022, 59(8): 0810006
Paper Information
Category: Image Processing
Received: Mar. 16, 2021
Accepted: Apr. 27, 2021
Published Online: Apr. 11, 2022
The Author Email: Jiang Rongqi (jjqqjjqq163@163.com), Peng Yueping (percy001@163.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20