Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 382.26 KB
Add to list
  1. Search results
  2. Spectral-spatial classification of hy...

Spectral-spatial classification of hyperspectral images with semi-supervised graph learning

Renbo Luo (UGent) , Wenzhi Liao (UGent) , Hongyan Zhang (UGent) , Youguo Pi and Wilfried Philips (UGent)
(2016) IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXII. In Proceedings of SPIE 10004.
Author
Organization
Abstract
In this paper, we propose a novel semi-supervised graph leaning method to fuse spectral (of original hyperspectral (HS) image) and spatial (from morphological features) information for classification of HS image. In our proposed semi-supervised graph, samples are connected according to either label information (labeled samples) or their k-nearest spectral and spatial neighbors (unlabeled samples). Furthermore, we link the unlabeled sample with all labeled samples in one class which is the closest to this unlabeled sample in both spectral and spatial feature spaces. Thus, the connected samples have similar characteristics on both spectral and spatial domains, and have high possibilities to belong to the same class. By exploiting the fused semi-supervised graph, we then get transformation matrices to project high-dimensional HS image and morphological features to their lower dimensional subspaces. The final classification map is obtained by concentrating the lower-dimensional features together as an input of SVM classifier. Experimental results on a real hyperspectral data demonstrate the efficiency of our proposed semi-supervised fusion method. Compared to the methods using unsupervised fusion or supervised fusion, the proposed semi-supervised fusion method enables improved performances on classification. Moreover, the classification performances keep stable even when a small number of labeled training samples is available.
Keywords
spectral-spatial, semi-supervised, hyperspectral images, Classification, feature extraction, graph

Downloads

  • Download
    (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 382.26 KB

Citation

Please use this url to cite or link to this publication:

MLA
Luo, Renbo, et al. “Spectral-Spatial Classification of Hyperspectral Images with Semi-Supervised Graph Learning.” IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXII, vol. 10004, SPIE, 2016, doi:10.1117/12.2240652.
APA
Luo, R., Liao, W., Zhang, H., Pi, Y., & Philips, W. (2016). Spectral-spatial classification of hyperspectral images with semi-supervised graph learning. IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXII, 10004. https://doi.org/10.1117/12.2240652
Chicago author-date
Luo, Renbo, Wenzhi Liao, Hongyan Zhang, Youguo Pi, and Wilfried Philips. 2016. “Spectral-Spatial Classification of Hyperspectral Images with Semi-Supervised Graph Learning.” In IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXII. Vol. 10004. SPIE. https://doi.org/10.1117/12.2240652.
Chicago author-date (all authors)
Luo, Renbo, Wenzhi Liao, Hongyan Zhang, Youguo Pi, and Wilfried Philips. 2016. “Spectral-Spatial Classification of Hyperspectral Images with Semi-Supervised Graph Learning.” In IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXII. Vol. 10004. SPIE. doi:10.1117/12.2240652.
Vancouver
1.
Luo R, Liao W, Zhang H, Pi Y, Philips W. Spectral-spatial classification of hyperspectral images with semi-supervised graph learning. In: IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXII. SPIE; 2016.
IEEE
[1]
R. Luo, W. Liao, H. Zhang, Y. Pi, and W. Philips, “Spectral-spatial classification of hyperspectral images with semi-supervised graph learning,” in IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXII, Edinburgh, United kingdom, 2016, vol. 10004.
@inproceedings{8100675,
  abstract     = {{In this paper, we propose a novel semi-supervised graph leaning method to fuse spectral (of original hyperspectral (HS) image) and spatial (from morphological features) information for classification of HS image. In our proposed semi-supervised graph, samples are connected according to either label information (labeled samples) or their k-nearest spectral and spatial neighbors (unlabeled samples). Furthermore, we link the unlabeled sample with all labeled samples in one class which is the closest to this unlabeled sample in both spectral and spatial feature spaces. Thus, the connected samples have similar characteristics on both spectral and spatial domains, and have high possibilities to belong to the same class. By exploiting the fused semi-supervised graph, we then get transformation matrices to project high-dimensional HS image and morphological features to their lower dimensional subspaces. The final classification map is obtained by concentrating the lower-dimensional features together as an input of SVM classifier. Experimental results on a real hyperspectral data demonstrate the efficiency of our proposed semi-supervised fusion method. Compared to the methods using unsupervised fusion or supervised fusion, the proposed semi-supervised fusion method enables improved performances on classification. Moreover, the classification performances keep stable even when a small number of labeled training samples is available.}},
  articleno    = {{100040T}},
  author       = {{Luo, Renbo and Liao, Wenzhi and Zhang, Hongyan and Pi, Youguo and Philips, Wilfried}},
  booktitle    = {{IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXII}},
  isbn         = {{978-1-5106-0413-1}},
  issn         = {{0277-786X}},
  keywords     = {{spectral-spatial,semi-supervised,hyperspectral images,Classification,feature extraction,graph}},
  language     = {{eng}},
  location     = {{Edinburgh, United kingdom}},
  pages        = {{5}},
  publisher    = {{SPIE}},
  title        = {{Spectral-spatial classification of hyperspectral images with semi-supervised graph learning}},
  url          = {{http://doi.org/10.1117/12.2240652}},
  volume       = {{10004}},
  year         = {{2016}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: