Research on PolSAR Image Classification Method Based on Vision Transformer Considering Local Information  

作　　者：Mingxia Zhang Aichun Wang Xiaozheng Du Xinmeng Wang Yu Wu Mingxia Zhang;Aichun Wang;Xiaozheng Du;Xinmeng Wang;Yu Wu(China Center for Resources Satellite Data and Application, Beijing, China)

机构地区：[1]China Center for Resources Satellite Data and Application, Beijing, China

出　　处：《Journal of Computer and Communications》2024年第9期22-38,共17页电脑和通信（英文）

摘　　要：In response to the problem of inadequate utilization of local information in PolSAR image classification using Vision Transformer in existing studies, this paper proposes a Vision Transformer method considering local information, LIViT. The method replaces image patch sequence with polarimetric feature sequence in the feature embedding, and uses convolution for mapping to preserve image spatial detail information. On the other hand, the addition of the wavelet transform branch enables the network to pay more attention to the shape and edge information of the feature target and improves the extraction of local edge information. The results in Wuhan, China and Flevoland, Netherlands show that considering local information when using Vision Transformer for PolSAR image classification effectively improves the image classification accuracy and shows better advantages in PolSAR image classification.In response to the problem of inadequate utilization of local information in PolSAR image classification using Vision Transformer in existing studies, this paper proposes a Vision Transformer method considering local information, LIViT. The method replaces image patch sequence with polarimetric feature sequence in the feature embedding, and uses convolution for mapping to preserve image spatial detail information. On the other hand, the addition of the wavelet transform branch enables the network to pay more attention to the shape and edge information of the feature target and improves the extraction of local edge information. The results in Wuhan, China and Flevoland, Netherlands show that considering local information when using Vision Transformer for PolSAR image classification effectively improves the image classification accuracy and shows better advantages in PolSAR image classification.

关 键 词：Vision Transformer POLSAR Image Classification LIViT 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]