Laser & Optoelectronics Progress, Volume. 58, Issue 4, 0407001(2021)
Application of Deep Learning in Data Processing of Satellite Laser Ranging
Figures & Tables(9)
Fig. 3. Results of Ajisai laser ranging satellite. (a) Original data; (b)result after treatment by proposed algorithm; (c) zoomed result
Fig. 4. Results of space debris 001575. (a) Original data; (b)result after treatment by proposed algorithm; (c) zoomed result
Fig. 5. Results of space debris 20580. (a) Original data; (b)result after treatment by proposed algorithm; (c) zoomed result
Table 1. Performance of deep neural networks under different numbers of ranging residual images
View tableTable 1. Performance of deep neural networks under different numbers of ranging residual images
Number of images Training accuracy /% Test accuracy /% F1-score 200 0.9999 0.8296 0.7731 500 0.9999 0.8471 0.8385 700 0.9999 0.8917 0.8649 1000 0.9999 0.8854 0.8636 1500 0.9999 0.8933 0.8651 1774 0.9994 0.8933 0.8615
Table 2. Recognization result comparison of proposed algorithm and Graz method
View tableTable 2. Recognization result comparison of proposed algorithm and Graz method
Target name NC number Graz number Cross number Cross rate /% Ajisai 45292 45201 45073 99.72 001575 31 7 7 100 20580 216 123 100 81.30
Table 3. Comparison of batch ranging results
View tableTable 3. Comparison of batch ranging results
Image number NC number Graz number Cross number Cross rate /% 472 4368 5293 4272 89.80
Tools
Get Citation
Copy Citation Text
Kaibin Feng, Rufeng Tang, Rongwang Li, Yuqiang Li. Application of Deep Learning in Data Processing of Satellite Laser Ranging[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0407001
Paper Information
Category: Fourier Optics and Signal Processing
Received: Jul. 27, 2020
Accepted: Aug. 13, 2020
Published Online: Feb. 24, 2021
The Author Email: Li Rongwang (lirw@ynao.ac.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20