Advanced search
1 file | 1.73 MB

Combining feature fusion and decision fusion for classification of hyperspectral and LiDAR data

Wenzhi Liao (UGent) , Rik Bellens (UGent) , Aleksandra Pizurica (UGent) , Sidharta Gautama (UGent) and Wilfried Philips (UGent)
Author
Organization
Project
SBO-IWT project Chameleon: Domain-specific Hyperspectral Imaging Systems for Relevant Industrial Applications
Abstract
This paper proposes a method to combine feature fusion and decision fusion together for multi-sensor data classification. First, morphological features which contain elevation and spatial information, are generated on both LiDAR data and the first few principal components (PCs) of original hyperspectral (HS) image. We got the fused features by projecting the spectral (original HS image), spatial and elevation features onto a lower subspace through a graph-based feature fusion method. Then, we got four classification maps by using spectral features, spatial features, elevation features and the graph fused features individually as input of SVM classifier. The final classification map was obtained by fusing the four classification maps through the weighted majority voting. Experimental results on fusion of HS and LiDAR data from the 2013 IEEE GRSS Data Fusion Contest demonstrate effectiveness of the proposed method. Compared to the methods using single data source or only feature fusion, with the proposed method, overall classification accuracies were improved by 10% and 2%, respectively.
Keywords
remote sensing, hyperspectral image, Data fusion, AREAS, PROFILES, LiDAR data, graph-based

Downloads

  • IGARSS Wenzhi2014.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.73 MB

Citation

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

Chicago
Liao, Wenzhi, Rik Bellens, Aleksandra Pizurica, Sidharta Gautama, and Wilfried Philips. 2014. “Combining Feature Fusion and Decision Fusion for Classification of Hyperspectral and LiDAR Data.” In IEEE International Symposium on Geoscience and Remote Sensing IGARSS, ed. Monique Bernier, Josée Lévesque, Jean-Marc Garneau, and Ellsworth LeDrew, 1241–1244. IEEE.
APA
Liao, Wenzhi, Bellens, R., Pizurica, A., Gautama, S., & Philips, W. (2014). Combining feature fusion and decision fusion for classification of hyperspectral and LiDAR data. In M. Bernier, J. Lévesque, J.-M. Garneau, & E. LeDrew (Eds.), IEEE International Symposium on Geoscience and Remote Sensing IGARSS (pp. 1241–1244). Presented at the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IEEE.
Vancouver
1.
Liao W, Bellens R, Pizurica A, Gautama S, Philips W. Combining feature fusion and decision fusion for classification of hyperspectral and LiDAR data. In: Bernier M, Lévesque J, Garneau J-M, LeDrew E, editors. IEEE International Symposium on Geoscience and Remote Sensing IGARSS. IEEE; 2014. p. 1241–4.
MLA
Liao, Wenzhi, Rik Bellens, Aleksandra Pizurica, et al. “Combining Feature Fusion and Decision Fusion for Classification of Hyperspectral and LiDAR Data.” IEEE International Symposium on Geoscience and Remote Sensing IGARSS. Ed. Monique Bernier et al. IEEE, 2014. 1241–1244. Print.
@inproceedings{5663198,
  abstract     = {This paper proposes a method to combine feature fusion and decision fusion together for multi-sensor data classification. First, morphological features which contain elevation and spatial information, are generated on both LiDAR data and the first few principal components (PCs) of original hyperspectral (HS) image. We got the fused features by projecting the spectral (original HS image), spatial and elevation features onto a lower subspace through a graph-based feature fusion method. Then, we got four classification maps by using spectral features, spatial features, elevation features and the graph fused features individually as input of SVM classifier. The final classification map was obtained by fusing the four classification maps through the weighted majority voting. Experimental results on fusion of HS and LiDAR data from the 2013 IEEE GRSS Data Fusion Contest demonstrate effectiveness of the proposed method. Compared to the methods using single data source or only feature fusion, with the proposed method, overall classification accuracies were improved by 10\% and 2\%, respectively.},
  author       = {Liao, Wenzhi and Bellens, Rik and Pizurica, Aleksandra and Gautama, Sidharta and Philips, Wilfried},
  booktitle    = {IEEE International Symposium on Geoscience and Remote Sensing IGARSS},
  editor       = {Bernier, Monique  and L{\'e}vesque, Jos{\'e}e  and Garneau, Jean-Marc  and LeDrew, Ellsworth },
  isbn         = {9781479957743},
  language     = {eng},
  location     = {Quebec, Canada},
  pages        = {1241--1244},
  publisher    = {IEEE},
  title        = {Combining feature fusion and decision fusion for classification of hyperspectral and LiDAR data},
  year         = {2014},
}

Web of Science
Times cited: