Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

UNSUPERVISED FEATURE EXTRACTION FOR HYPERSPECTRAL IMAGES USING COMBINED LOW RANK REPRESENTATION AND LOCALLY LINEAR EMBEDDING

Abstract: 

Hyperspectral images(HSIs) provide hundreds of narrow spectral bands for the land-covers, thus can provide more powerful discriminative information for the land-cover classification. However, HSIs suffer from the curse of high dimensionality, therefore dimension reduction and feature extraction are essential for the application of HSIs. In this paper, we propose an unsupervised feature extraction method for HSIs using combined low rank representation and locally linear embedding (LRR LLE). The proposed method can simultaneously use both the spectral and spatial correlation within HSIs, with LRR modelling the intrinsic property of union of low-rank subspaces and LLE considering the correlation within spatial neighbours. Experiments are conducted on real HSI datasets and the classification results demonstrate that the features extracted by LRR LLE are more discriminative than the state-of-art methods.

up
0 users have voted:

Paper Details

Authors:
Mengdi Wang, Jing Yu, Lijuan Niu, Weidong Sun
Submitted On:
8 March 2017 - 3:48am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Mengdi Wang
Paper Code:
IVMSP-L8.5
Document Year:
2017
Cite

Document Files

Unsupervised Feature Extraction for Hyperspectral Images Using Combined Low Rank Representation and Locally Linear Embedding

(57 downloads)

Subscribe

[1] Mengdi Wang, Jing Yu, Lijuan Niu, Weidong Sun, "UNSUPERVISED FEATURE EXTRACTION FOR HYPERSPECTRAL IMAGES USING COMBINED LOW RANK REPRESENTATION AND LOCALLY LINEAR EMBEDDING", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1704. Accessed: Nov. 22, 2017.
@article{1704-17,
url = {http://sigport.org/1704},
author = {Mengdi Wang; Jing Yu; Lijuan Niu; Weidong Sun },
publisher = {IEEE SigPort},
title = {UNSUPERVISED FEATURE EXTRACTION FOR HYPERSPECTRAL IMAGES USING COMBINED LOW RANK REPRESENTATION AND LOCALLY LINEAR EMBEDDING},
year = {2017} }
TY - EJOUR
T1 - UNSUPERVISED FEATURE EXTRACTION FOR HYPERSPECTRAL IMAGES USING COMBINED LOW RANK REPRESENTATION AND LOCALLY LINEAR EMBEDDING
AU - Mengdi Wang; Jing Yu; Lijuan Niu; Weidong Sun
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1704
ER -
Mengdi Wang, Jing Yu, Lijuan Niu, Weidong Sun. (2017). UNSUPERVISED FEATURE EXTRACTION FOR HYPERSPECTRAL IMAGES USING COMBINED LOW RANK REPRESENTATION AND LOCALLY LINEAR EMBEDDING. IEEE SigPort. http://sigport.org/1704
Mengdi Wang, Jing Yu, Lijuan Niu, Weidong Sun, 2017. UNSUPERVISED FEATURE EXTRACTION FOR HYPERSPECTRAL IMAGES USING COMBINED LOW RANK REPRESENTATION AND LOCALLY LINEAR EMBEDDING. Available at: http://sigport.org/1704.
Mengdi Wang, Jing Yu, Lijuan Niu, Weidong Sun. (2017). "UNSUPERVISED FEATURE EXTRACTION FOR HYPERSPECTRAL IMAGES USING COMBINED LOW RANK REPRESENTATION AND LOCALLY LINEAR EMBEDDING." Web.
1. Mengdi Wang, Jing Yu, Lijuan Niu, Weidong Sun. UNSUPERVISED FEATURE EXTRACTION FOR HYPERSPECTRAL IMAGES USING COMBINED LOW RANK REPRESENTATION AND LOCALLY LINEAR EMBEDDING [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1704