Infrared and Laser Engineering, Volume. 51, Issue 5, 20210459(2022)
J-MSF：A new infrared dim and small target detection algorithm based on multi-channel and multiscale
Figures & Tables(15)
Fig. 7. (a) Mark contrast box; (b) YOLO-Tiny detection result; (c) YOLOv3 detection result; (d) YOLOv3+SPP detection result; (e) Gaussian YOLOv3+SPP detection result; (f) YOLOv4 detection result; (g) J-MSF detection result
Fig. 8. (a) YOLO-Tiny Precision
Table 1. Dimensions of network parameters
View tableView in ArticleTable 1. Dimensions of network parameters
Fusion map/layer Kernel size Output size Stride Channel Basic-feature map - 8×8 - 1024 Artery-feature map - 16×16 - 768 Detection map 1 - 32×32 - 30 Detection map 2 - 64×64 - 30 Detection map 3 - 128×128 - 30 Maxpooling 1 3 32×32 1 128 Maxpooling 2 5 32×32 1 128 Maxpooling 3 7 32×32 1 128
Table 2. SNR data distribution table of test set
View tableView in ArticleTable 2. SNR data distribution table of test set
SNR region 3.26-3 3-2 2-1 1-0 0-(−1.97) −3-(−20) Data4 0 5 209 379 204 2 Data8 2 39 108 94 101 55 Data12 5 84 407 424 341 238 Data16 5 247 214 15 1 12 Data20 0 12 155 197 29 8 Total 12 387 1093 1109 676 315
Table 3. Contrast experiment of JAnet network
View tableView in ArticleTable 3. Contrast experiment of JAnet network
Model $\mathop X\nolimits_{FN} $ R AP Darknet-53 458 87.2% 86.38% Darknet-53-JA 343 90.0% 88.43% J-MSF 217 94.0% 93.13%
Table 4. Ablation study
View tableView in ArticleTable 4. Ablation study
Darknet53 J-MSF Loss Fusion Precision R AP FPS √ - D - 86% 87.20% 86.38% 66.3 √ - D √ 92% 92.20% 92.74% 57.5 √ - M - 89% 94.04% 93.88% 71.9 √ - M √ 82% 95.00% 93.47% 71.6 - √ D - 90% 94.00% 93.13% 59.0 - √ D √ 90% 94.10% 93.46% 73.4 - √ M - 86% 95.85% 94.80% 66.8 - √ M √ 88% 96.27% 96.29% 67.6
Table 5. Results of infrared target detection by YOLO serial model
View tableView in ArticleTable 5. Results of infrared target detection by YOLO serial model
Detection algorithm $\mathop X\nolimits_{TP} $ $\mathop X\nolimits_{FP} $ $\mathop X\nolimits_{FN} $ Precision R AP YOLO-Tiny 2389 1355 1203 59% 64% 45.32% YOLOv3 3309 435 283 88% 92% 86.38% YOLOv3+SPP[17] 3318 283 274 92% 92% 92.74% Gaussian YOLOv3[18]+SPP 3407 758 185 78% 95% 93.60% YOLOv4 3397 446 195 88% 95% 93.13% J-MSF 3443 451 149 88% 96% 96.29%
Table 6. Comparison of mainstream algorithms
View tableView in ArticleTable 6. Comparison of mainstream algorithms
Detection algorithm AP FPS Faster R-CNN[ 20 ]43.7% 35.2 SSD300[ 21 ]52.3% 154.7 RefineDet[ 22 ]63.9% 70.1 RetinaNet[ 23 ]65.4% 80.3 YOLOv3 86.4% 66.3 YOLOv4 93.1% 66.8 J-MSF 96.3% 67.6
Tools
Get Citation
Copy Citation Text
Guogang Wang, Zhaojin Sun, Yunpeng Liu. J-MSF：A new infrared dim and small target detection algorithm based on multi-channel and multiscale[J]. Infrared and Laser Engineering, 2022, 51(5): 20210459
Paper Information
Category: Infrared technology and application
Received: Jul. 6, 2021
Accepted: --
Published Online: Jun. 14, 2022
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20