会议论文详细信息
35th International Symposium on Remote Sensing of Environment
Hyperspectral Image Classification Using Discriminative Dictionary Learning
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
PDF
【 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.

【 预 览 】
附件列表
Files Size Format View
Hyperspectral Image Classification Using Discriminative Dictionary Learning 831KB PDF download
  文献评价指标  
  下载次数:15次 浏览次数:12次