Infrared and Laser Engineering, Volume. 50, Issue 4, 20200236(2021)
Multivariate empirical mode decomposition with application to SAR image target recognition
Figures & Tables(9)
Fig. 3. Results of the proposed method for 10-class recognition problem
Fig. 4. Comparison of different methods for recognition problem of depression angle variance
Fig. 5. Comparison of different methods for recognition problem of noise corruption
Fig. 6. Comparison of different methods for recognition problem of target occlusion
Table 1. [in Chinese]
View tableView in ArticleTable 1. [in Chinese]
Class Training set Test set BMP2 233 195 BTR70 233 196 T72 232 196 T62 299 273 BRDM2 298 274 BTR60 256 195 ZSU23/4 299 274 D7 299 274 ZIL131 299 274 2S1 299 274
Table 2. [in Chinese]
View tableView in ArticleTable 2. [in Chinese]
Method type Average recognition rate Proposed 99.28% Monogenic 98.94% BEMD 99.02% CNN 99.08%
Table 3. [in Chinese]
View tableView in ArticleTable 3. [in Chinese]
Depression angle 2S1 BDRM2 ZSU23/4 Training set 17° 299 298 299 Test set 30° 288 287 288 45° 303 303 303
Tools
Get Citation
Copy Citation Text
Youlong Wu. Multivariate empirical mode decomposition with application to SAR image target recognition[J]. Infrared and Laser Engineering, 2021, 50(4): 20200236
Paper Information
Category: Image processing
Received: Jun. 13, 2020
Accepted: --
Published Online: Jul. 30, 2021
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20