SAR Image Target Recognition Method Combining Multi-Resolution Representation and Complex Domain CNN

Liangcai Qiao

doi:10.3788/LOP57.241007

Laser & Optoelectronics Progress, Volume. 57, Issue 24, 241007(2020)

SAR Image Target Recognition Method Combining Multi-Resolution Representation and Complex Domain CNN

Liangcai Qiao^*

Author Affiliations

School of Information Engineering (College of Big Data), Xuzhou University of Technology, Xuzhou, Jiangsu 221018, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(15)

Fig. 1. Flow chart of multi-resolution representation algorithm

Download full size

Fig. 2. SAR image targets under different resolutions. (a) Original image; (b) 0.4m; (c) 0.5m; (d) 0.6m

Download full size

Fig. 3. Flow chart of obtaining label distribution

Download full size

Fig. 4. Convergence curve of network training process

Download full size

Fig. 5. Feature maps of proposed network output. (a) Input image; (b) first convolutional layer

Download full size

Fig. 6. Flow chart of SAR image target recognition process combining multi-resolution representation and complex domain CNN

Download full size

Fig. 7. Schematic of target to be identified. (a) BMP2; (b) BRT70; (c) T72; (d) T62; (e) BRDM2; (f) BTR60; (g) ZSU23/4; (h) D7; (i) ZIL131; (j) 2S1

Download full size

Fig. 8. Identification results of 10 categories of targets under standard operating conditions

Download full size

Fig. 9. Comparison curves of different methods under random noise identification problem

Download full size

Table 1. Number of images for training and test samples under standard operating conditions
View table
Table 1. Number of images for training and test samples under standard operating conditions
Class Training set(depression angle 17°) Test set(depression angle 15°)
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. Average recognition rates of different methods under standard operating conditions
View table
Table 2. Average recognition rates of different methods under standard operating conditions
Method Average recognition rate/%
Proposed method 99.42
MR 1 98.78
MR 2 99.02
CNN 99.08
CCNN 99.16

Table 3. Number of images for training and test samples in model identification problems
View table
Table 3. Number of images for training and test samples in model identification problems
Class Training set(depression angle 17°) Test set(depression angle 15°)
BMP2 233 (Sn_9563) 196 (Sn_9566)196 (Sn_c21)
BTR70 233 (Sn_c71) 196 (Sn_c71)
T72 232 (Sn_132) 195 (Sn_812)191 (Sn_s7)

Table 4. Average recognition rates of different methods under model recognition problem
View table
Table 4. Average recognition rates of different methods under model recognition problem
Method Average recognition rate /%
Proposed method 98.92
MR 1 97.64
MR 2 98.08
CNN 97.26
CCNN 98.23

Table 5. Number of images for training and test samples in pitch angle recognition problem
View table
Table 5. Number of images for training and test samples in pitch angle recognition problem
Sample Depressionangle 2S1 BDRM2 ZSU23/4
Training set 17° 299 298 299
Test set 30° 288 287 288
45° 303 303 303

Table 6. Average recognition rates of different methods under pitch angle recognition problem
View table
Table 6. Average recognition rates of different methods under pitch angle recognition problem
Method Average recognition rate/%
30° 45°
Proposed method 98.56 73.62
MR 1 97.54 69.56
MR 2 97.82 71.08
CNN 97.43 67.92
CCNN 98.02 72.02

Tools

Get Citation

Copy Citation Text

Liangcai Qiao. SAR Image Target Recognition Method Combining Multi-Resolution Representation and Complex Domain CNN[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241007

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: May. 14, 2020

Accepted: Jun. 4, 2020

Published Online: Dec. 2, 2020

The Author Email: Qiao Liangcai (qiaolc@xzit.edu.cn)

DOI:10.3788/LOP57.241007

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Number of images for training and test samples under standard operating conditions

Table 1. Number of images for training and test samples under standard operating conditions

Table 2. Average recognition rates of different methods under standard operating conditions

Table 2. Average recognition rates of different methods under standard operating conditions

Table 3. Number of images for training and test samples in model identification problems

Table 3. Number of images for training and test samples in model identification problems

Table 4. Average recognition rates of different methods under model recognition problem

Table 4. Average recognition rates of different methods under model recognition problem

Table 5. Number of images for training and test samples in pitch angle recognition problem

Table 5. Number of images for training and test samples in pitch angle recognition problem

Table 6. Average recognition rates of different methods under pitch angle recognition problem

Table 6. Average recognition rates of different methods under pitch angle recognition problem