Abstract
This study proposes a synthetic aperture radar (SAR) target recognition method via sparse representation of multi-view images with correlation analysis. The multi-view SAR images are first clustered into several view sets and in each set the included SAR images share high correlations. For the view set with only one SAR image, the sparse representation-based classification (SRC) is used for classification. The joint sparse representation (JSR) is employed to classify the view sets with more than one images in order to exploit their correlations. The decisions from different view sets are then fused based on the Bayesian theory. Therefore, both the independency and inner correlations in the multi-view SAR images can be better exploited to improve the target recognition performance. Experiments are conducted on the moving and stationary target acquisition and recognition (MSTAR) data set. The results show the superiority of the proposed approach over some other methods.
Disclosure statement
No potential conflict of interest was reported by the authors.
Additional information
Notes on contributors
Xinying Miao
Xinying Miao received her PhD from Dalian University of Technology in 2013. Currently, she is an associate professor at Dalian Ocean University. Her present research interests include wireless sensor network, IOT and automation.
Yupeng Shan
Yupeng Shan received his master degree from Gansu Agricultural University in 2007. Currently, he is a research assistant at Dalian Ocean University. His present research interest is automation of food processing.