Infrared and Laser Engineering, Volume. 50, Issue 8, 20210138(2021)
Combination of multiple decision principles based on sparse representation-based classification for target recognition of SAR image
Figures & Tables(9)
Table 1. Typical experimental setup based on the MSTAR dataset
View tableView in ArticleTable 1. Typical experimental setup based on the MSTAR dataset
Class Training Test Configuration Number of images Configuration Number of images BMP2 9 563 233 9 563 195 9 566 196 c21 196 BTR70 c71 233 c71 196 T72 132 232 132 196 812 195 s7 191 T62 A51 299 A51 273 BRDM2 E-71 298 E-71 274 BTR60 7 532 256 7 532 195 ZSU23/4 d08 299 d08 274 D7 13 015 299 13 015 274 ZIL131 E12 299 E12 274 2S1 B01 299 B01 274
Table 2. Results comparison under SOC
View tableView in ArticleTable 2. Results comparison under SOC
Method type Average recognition rate Proposed 98.52% SRC+Principle 1 96.54% SRC+Principle 2 95.88% SRC+Principle 3 97.06% CNN 98.14%
Table 3. Experimental setup under depression angle differences
View tableView in ArticleTable 3. Experimental setup under depression angle differences
Class Configuration Depression angle Training Test 17° 30° 45° 2S1 B01 299 288 303 BRDM2 E-71 298 287 303 ZSU23/4 d08 299 288 303
Tools
Get Citation
Copy Citation Text
Yajuan Li. Combination of multiple decision principles based on sparse representation-based classification for target recognition of SAR image[J]. Infrared and Laser Engineering, 2021, 50(8): 20210138
Paper Information
Category: Image processing
Received: Apr. 6, 2021
Accepted: --
Published Online: Nov. 2, 2021
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20