Hyperspectral Image Classification Using Discriminative Dictionary Learning

35th International Symposium on Remote Sensing of Environment

地球科学;生态环境科学

Zongze, Y.^1 ; Hao, S.^1 ; Kefeng, J.^1 ; Huanxin, Z.^1

College of Electronic Science and Engineering, National University of Defense Technology, Changsha, Hunan 410073, China^1

关键词: Contextual information;    Different class;    Discriminative dictionaries;    Majority voting;    Over-complete dictionaries;    Prediction performance;    Sparse coding;    Sparse representation;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/17/1/012222/pdf
DOI  :  10.1088/1755-1315/17/1/012222

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

The hyperspectral image (HSI) processing community has witnessed a surge of papers focusing on the utilization of sparse prior for effective HSI classification. In sparse representation based HSI classification, there are two phases: sparse coding with an over-complete dictionary and classification. In this paper, we first apply a novel fisher discriminative dictionary learning method, which capture the relative difference in different classes. The competitive selection strategy ensures that atoms in the resulting over-complete dictionary are the most discriminative. Secondly, motivated by the assumption that spatially adjacent samples are statistically related and even belong to the same materials (same class), we propose a majority voting scheme incorporating contextual information to predict the category label. Experiment results show that the proposed method can effectively strengthen relative discrimination of the constructed dictionary, and incorporating with the majority voting scheme achieve generally an improved prediction performance.