Infrared and Laser Engineering, Volume. 50, Issue S2, 20210323(2021)
Evaluation method of laser jamming effect based on deep learning
Figures & Tables(13)
Fig. 2. Flow chart of evaluation algorithm for laser jamming effect
Table 1. Data set division of laser interference detection
View tableView in ArticleTable 1. Data set division of laser interference detection
Parameter Quantity (pieces) Total data set 3 020 Training set 1 812 Validation set 604 Test set 604
Table 2. Experimental parameter configuration
View tableView in ArticleTable 2. Experimental parameter configuration
Parameter Configuration Operating system Linux Language Python 3.6 CUDA 10.2
Table 3. Laser jamming image test results
View tableView in ArticleTable 3. Laser jamming image test results
Network structure YOLOV5s YOLOV5m YOLOV5l YOLOV5x Time/s 1.119 1.208 1.282 1.367 Test results Fig.9 (a) Fig.9 (b) Fig.9 (c) Fig.9 (d) Recognition accuracy 0.86 0.81 0.90 0.92
Table 4. Experimental results of laser interference images with evaluate three algorithms
View tableView in ArticleTable 4. Experimental results of laser interference images with evaluate three algorithms
Algorithm Recognition accuracy Time/s YOLOV3 0.76 3.68 YOLOV4 0.80 2.37 YOLOV5 0.85 1.19
Tools
Get Citation
Copy Citation Text
Youchen Fan, Xu Ma, Shuli Ma, Kechang Qian, Hongxing Hao. Evaluation method of laser jamming effect based on deep learning[J]. Infrared and Laser Engineering, 2021, 50(S2): 20210323
Paper Information
Category: Lasers and laser optics
Received: Apr. 15, 2021
Accepted: --
Published Online: Dec. 3, 2021
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20