Infrared and Laser Engineering, Volume. 51, Issue 3, 20210106(2022)
Infrared dim and small target detection based on YOLO-IDSTD algorithm
Figures & Tables(16)
Fig. 1. YOLO-IDSTD network structure. (a) Feature extraction part; (b) Feature fusion part; (c) Target detection part
Fig. 7. Comparison of detection results of typical infrared dim and small targets. (a) YOLOv3; (b) YOLOv4-tiny; (c) YOLOv3-tiny; (d) YOLO-IDSTD
Table 1. Each layer’s parameters and FLOPs of feature extraction part
View tableView in ArticleTable 1. Each layer’s parameters and FLOPs of feature extraction part
No. Name Parameter FLOPs 1 Focus, 1, 16 224×106 33.0×106 2 Conv, 3/1, 16 2336×106 86.1×106 3 Conv, 3/1, 32 4672×106 43.1×106 4 Conv, 3/1, 64 18560×106 42.8×106 5 PDSCP, 128 38016×106 21.9×106 6 PDSCP, 256 149760×106 21.6×106 7 PDSCP, 512 594432×106 21.4×106
Table 2. Configuration of experimental platform
View tableView in ArticleTable 2. Configuration of experimental platform
Name Related configurations GPU NVIDIA quadro GV100 CPU sInter Xeon silver 4210/128G GPU memory size 32G Operating systems Win10 Computing platform CUDA11.0 CPU(test) Inter Core i7 10700/16G
Table 3. Statistics of extension box
View tableView in ArticleTable 3. Statistics of extension box
Size of extension box Number of datasets Number of images 5 pixel×5 pixel 13 12484 7 pixel×7 pixel 2 798
Table 4. Setting of experimental parameters
View tableView in ArticleTable 4. Setting of experimental parameters
Parameter Infrared dim and small targets datasets Thermal Pedestrian Database FLIR Thermal Datasets Class number 1 1 3 Epoch 500 500 500 Batch size 64 4 64 Image size 384×384 320×320 512×512 Batch size(test) 1 1 1
Table 5. Precision and efficiency of different detection methods
View tableView in ArticleTable 5. Precision and efficiency of different detection methods
Method Precision rate Recall rate AP@0.5 Parameter Model size/MB GFLOPs Detection time/ms YOLOv3-384 0.7371 0.8182 0.8123 61.6×106 117.7 155.2 364.8 SSD300 0.3664 0.7585 0.5170 23.7×106 90.6 35.2 370.4 Mobilenet-SSD 0.5241 0.5111 0.3300 6.3×106 24.0 1.14 66.8 Efficientdet b0 0.5948 0.0589 0.0999 3.9×106 15.1 2.5 73.8 Centernet-ResNet50 0.8323 0.6156 0.6843 32.6×106 124.8 3.8 30.3 YOLOv5s-384 0.7310 0.8029 0.7957 7.3×106 16.6 17.0 98.5 YOLOv4-tiny--384 0.6713 0.7847 0.8195 6.2×106 12.6 16.5 80.1 YOLOv3-tiny-384 0.6780 0.7652 0.8050 8.9×106 14.2 12.9 78.5 YOLO-IDSTD 0.6405 0.8409 0.8242 3.7×106 7.3 3.0 50.2
Table 6. Ablation experiment of YOLO-IDSTD
View tableView in ArticleTable 6. Ablation experiment of YOLO-IDSTD
Improve the detection speed Improve the detection accuracy Recall rate AP@0.5 Model size/MB Detection time/ms YOLOv3-tiny baseline With Focus With PDSCP With PANet With Four-scales prediction With RFB-Small √ 0.7879 0.7771 16.59 78.5 √ √ 0.7576 0.7235 16.59 35.4 √ √ √ 0.7652 0.7342 3.65 26.5 √ √ √ √ 0.7652 0.7604 9.11 31.7 √ √ √ √ √ 0.8258 0.8037 9.22 36.9 √ √ √ √ √ √ 0.8409 0.8242 7.27 50.2
Table 7. Comparative experiments on two sets of infrared small target datasets
View tableView in ArticleTable 7. Comparative experiments on two sets of infrared small target datasets
Method OSU Thermal Pedestrian Database FLIR Thermal Datasets Recall rate AP@0.5 Detection time/ ms Recall rate mAP@0.5 AP@0.5 (person) AP@0.5 (bicycle) AP@0.5 (car) Detection time/ ms Efficientdet b0 0.8723 0.8651 90.5 0.3374 0.4943 0.444 0.435 0.604 160.8 YOLOv5s 0.9909 0.9860 69.6 0.7706 0.7441 0.799 0.563 0.870 122.6 YOLOv3-tiny 1 0.9875 53.2 0.6906 0.6334 0.641 0.449 0.810 98.4 YOLO-IDSTD 1 0.9899 42.9 0.7166 0.6676 0.724 0.448 0.831 60.7
Tools
Get Citation
Copy Citation Text
Xinhao Jiang, Wei Cai, Zhiyong Yang, Peiwei Xu, Bo Jiang. Infrared dim and small target detection based on YOLO-IDSTD algorithm[J]. Infrared and Laser Engineering, 2022, 51(3): 20210106
Paper Information
Category: Image processing
Received: Feb. 20, 2021
Accepted: --
Published Online: Apr. 8, 2022
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20