Laser & Optoelectronics Progress, Volume. 59, Issue 4, 0415004(2022)
Lightweight Target Detection Algorithm Based on Adaptive Spatial Feature Fusion
Figures & Tables(14)
Fig. 1. Standard convolution and depth separable convolution. (a) Standard convolution; (b) deep convolution; (c) point convolution
Fig. 8. Comparison of training effect between proposed algorithm and YOLOv4 under a small amount of data samples
Fig. 9. Comparison of training effect between proposed algorithm and YOLOv4 under a large number of data samples
Fig. 10. Comparison of detection effect between proposed algorithm and YOLOv4.(a)(c)(e)(g) YOLOv4 algorithm;(b)(d)(f)(h) proposed algorithm
Table 1. MobileNet structure
View tableTable 1. MobileNet structure
Type Number of filters Size Output Conv 32 3×3 416×416 Conv dw 32 3×3/2 208×208 Conv 64 1×1 208×208 Conv dw 64 3×3/2 104×104 Conv 128 1×1 104×104 Conv dw 128 3×3 104×104 Conv 128 1×1 104×104 Conv dw 128 3×3/2 52×52 Conv 256 1×1 52×52 Conv dw 256 3×3 52×52 Conv 256 1×1 52×52 Conv dw 256 3×3/2 26×26 Conv 512 1×1 26×26 5× Conv dw 512 3×3 26×26 Conv 512 1×1 26×26 Conv dw 512 3×3/2 13×13 Conv 1024 1×1 13×13 Conv dw 1024 3×3 13×13 Conv 1024 1×1 13×13
Table 2. CSPDarkNet-53 structure
View tableTable 2. CSPDarkNet-53 structure
Type Number of filters Size Output Convolutional 32 3×3 416×416 Convolutional 64 3×3/2 208×208 1× Convolutional 32 1×1 Convolutional 64 3×3 Residual 208×208 Convolutional 128 3×3/2 104×104 2× Convolutional 64 1×1 Convolutional 128 3×3 Residual 104×104 Convolutional 256 3×3/2 52×52 8× Convolutional 128 1×1 Convolutional 256 3×3 Residual 52×52 Convolutional 512 3×3/2 26×26 8× Convolutional 256 1×1 Convolutional 512 3×3 Residual 26×26 Convolutional 1024 3×3/2 13×13 4× Convolutional 512 1×1 Convolutional 1024 3×3 Residual 13×13
Table 3. Performance comparison of different algorithms
View tableTable 3. Performance comparison of different algorithms
Algorithm AP /% mAP /% Detection speed /（frame·s-1） Mask No_mask No_mask_well Faster-RCNN 97.77 97.56 95.33 96.88 2 RetinaFace 74.51 97.35 70.45 80.77 6 Attention-RetinaFace 75.76 98.67 73.89 82.77 8 SSD 77.33 75.55 73.34 74.07 9 YOLOv3 81.62 80.96 77.65 80.07 11 YOLOv3-tiny 78.67 77.92 75.33 77.30 15 YOLOv4 88.92 87.34 85.84 87.36 13 Improved_YOLOv4 96.38 96.96 94.44 95.92 19
Table 4. Comparison of ablation experiments
View tableTable 4. Comparison of ablation experiments
Grouping MobileNet ASFF Modify_loss AP /% mAP /% Detection speed /（frame·s-1） Mask No_mask No_mask_well G1 88.92 87.34 85.84 87.36 13 G2 √ 86.75 86.02 83.98 85.58 21 G3 √ √ 91.88 92.32 89.45 91.21 20 G4 √ √ √ 96.38 96.96 94.44 95.92 19
Tools
Get Citation
Copy Citation Text
Yujie Luo, Jian Zhang, Liang Chen, Lü Zhang, Wanqing Ouyang, Daiqin Huang, Yuyi Yang. Lightweight Target Detection Algorithm Based on Adaptive Spatial Feature Fusion[J]. Laser & Optoelectronics Progress, 2022, 59(4): 0415004
Paper Information
Category: Machine Vision
Received: Feb. 18, 2021
Accepted: Apr. 6, 2021
Published Online: Feb. 15, 2022
The Author Email: Jian Zhang (jzhang@hnust.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20