Hyperspectral image kernel sparse subspace clustering with spatial max pooling operation
- Author
- Hongyan Zhang (UGent) , Han Zhai, Wenzhi Liao (UGent) , Liqin Cao, Liangpei Zhang and Aleksandra Pizurica (UGent)
- Organization
- 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.
- Keywords
- Hyperspectral image, spatial max pooling, nonlinear, kernel, SSC
Downloads
-
(...).pdf
- full text
- |
- UGent only
- |
- |
- 231.66 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-7189942
- MLA
- Zhang, Hongyan, et al. “Hyperspectral Image Kernel Sparse Subspace Clustering with Spatial Max Pooling Operation.” XXIII ISPRS CONGRESS, COMMISSION III, edited by George Vosselman, vol. 41, no. B3, ISPRS, 2016, pp. 945–48, doi:10.5194/isprsarchives-XLI-B3-945-2016.
- APA
- Zhang, H., Zhai, H., Liao, W., Cao, L., Zhang, L., & Pizurica, A. (2016). Hyperspectral image kernel sparse subspace clustering with spatial max pooling operation. In G. Vosselman (Ed.), XXIII ISPRS CONGRESS, COMMISSION III (Vol. 41, pp. 945–948). https://doi.org/10.5194/isprsarchives-XLI-B3-945-2016
- Chicago author-date
- Zhang, Hongyan, Han Zhai, Wenzhi Liao, Liqin Cao, Liangpei Zhang, and Aleksandra Pizurica. 2016. “Hyperspectral Image Kernel Sparse Subspace Clustering with Spatial Max Pooling Operation.” In XXIII ISPRS CONGRESS, COMMISSION III, edited by George Vosselman, 41:945–48. ISPRS. https://doi.org/10.5194/isprsarchives-XLI-B3-945-2016.
- Chicago author-date (all authors)
- Zhang, Hongyan, Han Zhai, Wenzhi Liao, Liqin Cao, Liangpei Zhang, and Aleksandra Pizurica. 2016. “Hyperspectral Image Kernel Sparse Subspace Clustering with Spatial Max Pooling Operation.” In XXIII ISPRS CONGRESS, COMMISSION III, ed by. George Vosselman, 41:945–948. ISPRS. doi:10.5194/isprsarchives-XLI-B3-945-2016.
- Vancouver
- 1.Zhang H, Zhai H, Liao W, Cao L, Zhang L, Pizurica A. Hyperspectral image kernel sparse subspace clustering with spatial max pooling operation. In: Vosselman G, editor. XXIII ISPRS CONGRESS, COMMISSION III. ISPRS; 2016. p. 945–8.
- IEEE
- [1]H. Zhang, H. Zhai, W. Liao, L. Cao, L. Zhang, and A. Pizurica, “Hyperspectral image kernel sparse subspace clustering with spatial max pooling operation,” in XXIII ISPRS CONGRESS, COMMISSION III, Prague, Czech Republic, 2016, vol. 41, no. B3, pp. 945–948.
@inproceedings{7189942,
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.}},
author = {{Zhang, Hongyan and Zhai, Han and Liao, Wenzhi and Cao, Liqin and Zhang, Liangpei and Pizurica, Aleksandra}},
booktitle = {{XXIII ISPRS CONGRESS, COMMISSION III}},
editor = {{Vosselman, George}},
issn = {{1682-1750}},
keywords = {{Hyperspectral image,spatial max pooling,nonlinear,kernel,SSC}},
language = {{eng}},
location = {{Prague, Czech Republic}},
number = {{B3}},
pages = {{945--948}},
publisher = {{ISPRS}},
title = {{Hyperspectral image kernel sparse subspace clustering with spatial max pooling operation}},
url = {{http://doi.org/10.5194/isprsarchives-XLI-B3-945-2016}},
volume = {{41}},
year = {{2016}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: