Deep nonnegative matrix factorization with dual-factor hierarchical constraints for hyperspectral unmixing
Image Processing|更新时间:2025-10-15
|
Deep nonnegative matrix factorization with dual-factor hierarchical constraints for hyperspectral unmixing
“In the field of hyperspectral unmixing, researchers have proposed a deep NMF framework that significantly improves unmixing accuracy and robustness by enhancing spectral nonlinear feature expression and improving spatial consistency of abundance estimation.”
Chinese Journal of Liquid Crystals and DisplaysVol. 40, Issue 10, Pages: 1490-1508(2025)
作者机构:
北方民族大学 计算机科学与工程学院, 宁夏 银川 750021
作者简介:
基金信息:
National Natural Science Foundation of China(62461001);Natural Science Foundation of Ningxia(2024AAC02035);Innovation Project for Postgraduates of North Minzu University(YCX24365)
QU Kewen, LUO Xiaojuan, BAO Wenxing. Deep nonnegative matrix factorization with dual-factor hierarchical constraints for hyperspectral unmixing[J]. Chinese journal of liquid crystals and displays, 2025, 40(10): 1490-1508.
DOI:
QU Kewen, LUO Xiaojuan, BAO Wenxing. Deep nonnegative matrix factorization with dual-factor hierarchical constraints for hyperspectral unmixing[J]. Chinese journal of liquid crystals and displays, 2025, 40(10): 1490-1508. DOI: 10.37188/CJLCD.2025-0122. CSTR: 32172.14.CJLCD.2025-0122.
Deep nonnegative matrix factorization with dual-factor hierarchical constraints for hyperspectral unmixing