Abstract
In this paper, we present a kernel sparse subspace clustering with spatial max pooling operation (KSSC-SMP) algorithm for hyperspectral remote sensing imagery. Firstly, by mapping the feature points into a higher dimensional space from the original space with the kernel strategy, the sparse subspace clustering (SSC) model is extended to nonlinear manifolds, which can better explore the complex nonlinear structure of hyperspectral images (HSIs) and obtain a much more accurate representation coefficient matrix. Secondly, through the spatial max pooling operation, the spatial contextual information is integrated to obtain a smoother clustering result. Through experiments, it is verified that the KSSC-SMP algorithm is a competitive clustering method for HSIs and outperforms the state-of-the-art clustering methods.
Original language | English |
---|---|
Title of host publication | XXIII ISPRS Congress, Commission III |
Subtitle of host publication | International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences |
Pages | 945-948 |
Number of pages | 4 |
Volume | XLI-B3 |
DOIs | |
Publication status | Published - 2016 |
Event | 23rd Congress of the International-Society-for-Photogrammetry-and-Remote-Sensing (ISPRS) - Prague, Czech Republic Duration: 11 Jul 2016 → 19 Jul 2016 |
Conference
Conference | 23rd Congress of the International-Society-for-Photogrammetry-and-Remote-Sensing (ISPRS) |
---|---|
Abbreviated title | ISPRS2016 |
Country/Territory | Czech Republic |
City | Prague |
Period | 11/07/16 → 19/07/16 |
Keywords
- hyperspectral image
- spatial max pooling
- nonlinear
- kernel
- SSC