Adaptive Local Aspect Dictionary Pair Learning for Synthetic Aperture Radar Target Image Classification

作者：Zhang, Xinzheng^*; Tan, Zhiying; Liu, Guo; Liu, Hongqing; Wang, Yijian; Liu, Shujun; Li, Yongming; Xu, Hao; Xia, Jili

来源：Sensors (Switzerland), 2018, 18(9): 2940.

DOI：10.3390/s18092940

• SAR
• images classification
• dictionary learning
• representation learning
• aspect

In this paper, a new target classification algorithm based on adaptive local aspect dictionary pair learning for synthetic aperture radar (SAR) images is developed. To that end, first, the aspect sector of one testing sample is determined adaptively by a regularized non-negative sparse learning method. Second, a synthesis dictionary and an analysis dictionary are jointly learned from the corresponding training subset located in the aspect sector. By doing so, the local aspect dictionary pair is obtained. Finally, the class label of the testing sample is inferred by a use of the minimum reconstruction residual under the representation with the local aspect dictionary pair. Using the local aspect sector training subset rather than the global aspect training set reduces the interference of a large amount of unrelated training samples, which leads to a more discriminative local aspect dictionary pair for target classification. The experiments are conducted with the Moving and Stationary Target Acquisition and Recognition (MSTAR) database, and the results demonstrate that the proposed approach is effective and superior to the state-of-the-art methods.

• 出版日期2018-9
• 单位重庆邮电大学; 中国空间技术研究院; 重庆大学