Advanced search
1 file | 3.02 MB Add to list

Hyperspectral and LiDAR classification with semisupervised graph fusion

Author
Organization
Abstract
To fuse hyperspectral and Light Detection And Ranging (LiDAR), we propose a semisupervised graph fusion (SSGF) approach. We apply morphological filters to LiDAR and the first few components of hyperspectral data to model the height and spatial information, respectively. Then, the proposed SSGF is used to project the spectral, elevation, and spatial features onto a lower subspace to obtain the new features. In particular, the objective of SSGF is to maximize the class separation ability and preserve the local neighborhood structure by using both labeled and unlabeled samples. Experimental results on the hyperspectral and LiDAR data from the 2013 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest demonstrated the superiority of the SSGF.
Keywords
Feature extraction, Hyperspectral imaging, Laser radar, Training, Data mining, Distance measurement, Graph fusion, hyperspectral, Light Detection And Ranging (LiDAR), semisupervised, FOREST, PROFILES, IMAGERY

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 3.02 MB

Citation

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

MLA
xia, Junshi, et al. “Hyperspectral and LiDAR Classification with Semisupervised Graph Fusion.” IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, vol. 17, no. 4, 2020, pp. 666–70, doi:10.1109/LGRS.2019.2928009.
APA
xia, J., Liao, W., & Du, P. (2020). Hyperspectral and LiDAR classification with semisupervised graph fusion. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 17(4), 666–670. https://doi.org/10.1109/LGRS.2019.2928009
Chicago author-date
xia, Junshi, Wenzhi Liao, and Peijun Du. 2020. “Hyperspectral and LiDAR Classification with Semisupervised Graph Fusion.” IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 17 (4): 666–70. https://doi.org/10.1109/LGRS.2019.2928009.
Chicago author-date (all authors)
xia, Junshi, Wenzhi Liao, and Peijun Du. 2020. “Hyperspectral and LiDAR Classification with Semisupervised Graph Fusion.” IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 17 (4): 666–670. doi:10.1109/LGRS.2019.2928009.
Vancouver
1.
xia J, Liao W, Du P. Hyperspectral and LiDAR classification with semisupervised graph fusion. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS. 2020;17(4):666–70.
IEEE
[1]
J. xia, W. Liao, and P. Du, “Hyperspectral and LiDAR classification with semisupervised graph fusion,” IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, vol. 17, no. 4, pp. 666–670, 2020.
@article{8661484,
  abstract     = {To fuse hyperspectral and Light Detection And Ranging (LiDAR), we propose a semisupervised graph fusion (SSGF) approach. We apply morphological filters to LiDAR and the first few components of hyperspectral data to model the height and spatial information, respectively. Then, the proposed SSGF is used to project the spectral, elevation, and spatial features onto a lower subspace to obtain the new features. In particular, the objective of SSGF is to maximize the class separation ability and preserve the local neighborhood structure by using both labeled and unlabeled samples. Experimental results on the hyperspectral and LiDAR data from the 2013 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest demonstrated the superiority of the SSGF.},
  author       = {xia, Junshi and Liao, Wenzhi and Du, Peijun},
  issn         = {1545-598X},
  journal      = {IEEE GEOSCIENCE AND REMOTE SENSING LETTERS},
  keywords     = {Feature extraction,Hyperspectral imaging,Laser radar,Training,Data mining,Distance measurement,Graph fusion,hyperspectral,Light Detection And Ranging (LiDAR),semisupervised,FOREST,PROFILES,IMAGERY},
  language     = {eng},
  number       = {4},
  pages        = {666--670},
  title        = {Hyperspectral and LiDAR classification with semisupervised graph fusion},
  url          = {http://dx.doi.org/10.1109/LGRS.2019.2928009},
  volume       = {17},
  year         = {2020},
}

Altmetric
View in Altmetric
Web of Science
Times cited: