会议论文

Mei, Xiaoguang

英文

2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019)

2153-6996

2019

294-297

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

IEEE International Symposium on Geoscience and Remote Sensing IGARSS

JUL 28-AUG 02, 2019

Yokohama, JAPAN

[Jin, Qiwen;Ma, Yong;Mei, Xiaoguang;Dai, Xiaobing;Fan, Fan;Huang, Jun] Wuhan Univ, Elect Informat Sch, Wuhan 430072, Peoples R China.^[Ma, Yong;Mei, Xiaoguang;Dai, Xiaobing;Fan, Fan;Huang, Jun] Wuhan Univ, Inst Aerosp Sci & Technol, Wuhan 430072, Peoples R China.^[Li, Hao] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.

Inst Elect & Elect Engineers, Inst Elect & Elect Engineers, Geoscience & Remote Sensing Soc

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

978-1-5386-9154-0

National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61805181, 61705170, 61773295, 61605146]

本校为其他机构

Gaussian mixture model (GMM) can estimate not only the abundances and distribution parameters but also distinct end-member set for each pixel. However, the traditional GMM unmixing model only has proper smoothness and sparsity prior constraints on the abundances and thus cannot excavate the local spatial information in hyperspectral image (HSI). Thus, we propose a new unmixing method with superpixel segmentation (SS) and low-rank representation (LRR) based on GMM called GMM-SS-LRR, which can consider the local spatial correlation of HSI. First, we adopt the principal component analysis (PCA) t...