Remote Sensing Data Feature Analysis Using Spatial Linear Embedding (SLE)

DOI

10.2991/icmmcce-15.2015.17How to use a DOI?

Keywords

Spatial linear embedding; Remote sensing data feature analysis; Manifold learning.

Abstract

Dimensionality reduction has been used to reduce the complexity of the representation of remote sensing data. In this paper, a novel remote sensing data feature analysis method is proposed based on an improved manifold learning algorithm--spatial linear embedding. The purpose of feature extraction is to reduce the dimensionality of the remote sensing data while preserving the significant information. Compared with LLE, spatial linear embedding method emphasizes the relation of neighboring pixels spatially to increase system efficiency.The method makes up the shortage that LLE ignores the relation of neighboring pixels spatially which is extremely important for remote sensing data. In this paper we have obtain experiment results from the analysis of remote sensing data using PCA and spatial linear embedding. The results show that the SLEcan give significantly higher accuracies than the linear method of PCA.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lifang Xue
AU  - Xiushuang Yi
AU  - Xiumei Liu
AU  - Jie Li
PY  - 2015/12
DA  - 2015/12
TI  - Remote Sensing Data Feature Analysis Using Spatial Linear Embedding (SLE)
BT  - Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015
PB  - Atlantis Press
SP  - 91
EP  - 94
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmcce-15.2015.17
DO  - 10.2991/icmmcce-15.2015.17
ID  - Xue2015/12
ER  -