Infrared and Laser Engineering, Volume. 51, Issue 10, 20220029(2022)
SAR ATR method based on canonical correlations analysis of features extracted by 2D random projection
Figures & Tables(7)
Fig. 1. Procedure of ATR based on MCCA of 2D random projection features
Table 1. Sample settings for SOC
View tableView in ArticleTable 1. Sample settings for SOC
Target label Training set (Depression: 17°) Test set (Depression: 15°) Configuration Samples Configuration Samples BMP2 9563 218 9563 9566 c21 180 181 181 BTR70 - 218 - 181 T72 132 217 132 812 s7 181 180 176 T62 - 284 - 258 BRDM2 - 283 - 259 BTR60 - 241 - 180 ZSU23/4 - 284 - 259 D7 - 284 - 259 ZIL131 - 284 - 259 2 S1 - 284 - 180
Table 2. Comparison results under SOC
View tableView in ArticleTable 2. Comparison results under SOC
Method Proposed Random projection 2D random projection Monogenic CNN Average recognition rate 99.08% 97.18% 98.23% 98.64% 98.82%
Table 3. Sample settings for depression angle variance
View tableView in ArticleTable 3. Sample settings for depression angle variance
Target label Training set Test set Depression/(°) Samples Depression/(°) Samples 2 S1 17 284 30 45 283 288 BRDM2 17 283 30 45 272 288 ZSU23/4 17 284 30 45 273 288
Table 4. Comparison results under depression angle variances
View tableView in ArticleTable 4. Comparison results under depression angle variances
Method Average recognition rate 30° 45° Proposed 96.87% 72.19% Random projection 94.72% 68.52% 2D random projection 95.14% 69.52% Monogenic 95.73% 70.42% CNN 95.32% 68.34%
Tools
Get Citation
Copy Citation Text
Zhengwei Li, Xiaobin Huang, Yao Hu. SAR ATR method based on canonical correlations analysis of features extracted by 2D random projection[J]. Infrared and Laser Engineering, 2022, 51(10): 20220029
Paper Information
Category: Image processing
Received: Feb. 12, 2022
Accepted: --
Published Online: Jan. 6, 2023
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20