no code implementations • 1 Jun 2023 • Dunbin Shen, Xiaorui Ma, Wenfeng Kong, Jiacheng Tian, Hongyu Wang
Firstly, to obtain a complete and pure background dictionary, we propose a LRR-based background subspace learning method by jointly mining the low-dimensional structure of all pixels.
no code implementations • 19 Jan 2021 • Sheng Liu, Xiaozhen Xie, Wenfeng Kong
In the Fourier transform domain of HSIs, different frequency slices (FS) contain different information; different singular values (SVs) of each FS also represent different information.