• Home
  • CODES
    • Classification of Hyperspectral Images
    • Classification of Remote Sensing Data
    • Data fusion: hyperspectral + Lidar
    • Hyperspectral Super Resolution
    • Machine Learning in Remote Sensing
    • Pansharpening
    • Registration
    • Spectral Unmixing
  • DATA
  • About us
  • Home
  • CODES
    • Classification of Hyperspectral Images
    • Classification of Remote Sensing Data
    • Data fusion: hyperspectral + Lidar
    • Hyperspectral Super Resolution
    • Machine Learning in Remote Sensing
    • Pansharpening
    • Registration
    • Spectral Unmixing
  • DATA
  • About us
home/Knowledge Base/CODES/Classification of Hyperspectral Images/SVM-and MRF-Based Method for Accurate Classification of Hyperspectral Images

SVM-and MRF-Based Method for Accurate Classification of Hyperspectral Images

March 5, 2018

SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images
Yuliya Tarabalka, Mathieu Fauvel, Jocelyn Chanussot  and Jón Atli Benediktsson

IEEE Geoscience and Remote Sensing Letters, Vol. 7, no. 4, OCTOBER 2010
DOI: 10.1109/LGRS.2010.2047711

Year: 2010, Volume: 7, Issue: 4, Pages: 736 – 740

Archive 1.zip contains original codes from Dr Tarabalka’s PhD.
Archive 2.zip contains MRF codes using graph-cut which are much more efficient, also provided by Dr Tarabalka.

More code :
You can find a simplified (python) version of the algorithm here
(without gradiant and with ICM rather than Gibs sampler):

https://github.com/mfauvel/SummerSchoolGRSS/blob/master/Codes/script_mrf.py

Tags:classificationhyperspectral imagingMarkov random field (MRF)support vector machine (SVM)
Attached Files
#
File Type
File Size
Download
1 .pdf 341.77 KB 2010_IEEE_GRSL_SVM_MRF
2 .zip 10.88 KB Archive 1
3 .zip 9.68 KB Archive 2
Related Articles
  • More Diverse Means Better: Multimodal Deep Learning Meets Remote-Sensing Imagery Classification
  • Graph Convolutional Networks for Hyperspectral Image Classification
  • CoSpace: Common Subspace Learning from Hyperspectral-Multispectral Correspondences
  • Learnable Manifold Alignment (LeMA) : A Semi-supervised Cross-modality Learning Framework for Land Cover and Land Use Classification
  • Invariant Attribute Profiles: A Spatial-Frequency Joint Feature Extractor for Hyperspectral Image Classification
  • Class-Specific Sparse Multiple Kernel Learning for Spectral–Spatial Hyperspectral Image Classification
Categories
  • CODES
    • Change Detection
    • Classification of Hyperspectral Images
    • Classification of Remote Sensing Data
    • Data fusion: hyperspectral + Lidar
    • Data fusion: Hyperspectral + Multispectral
    • Deep Learning
    • Denoising
    • Graphs, Manifold
    • Hyperspectral
    • Hyperspectral remote sensing
    • Hyperspectral Super Resolution
    • Machine Learning in Remote Sensing
    • Multi-modal
    • Pansharpening
    • Registration
    • Spectral Unmixing
    • Super Resolution
    • Synthetic Aperture Radar and Radar Sounder
  • DATA
Contact

Mail : Jocelyn Chanussot

Like Us On Facebook
Facebook Pagelike Widget
Follow Us On Twitter
Follow @RemoteOpen
Links

http://www.jocelyn-chanussot.net