Classification of Hyperspectral Images Using SVM with Shape-Adaptive Reconstruction and Smoothed Total Variation

Ruoning LI, Kangning CUI, Raymond H. CHAN*, Robert J. PLEMMONS

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

3 Citations (Scopus)

Abstract

In this work, a novel algorithm called SVM with Shape-adaptive Reconstruction and Smoothed Total Variation (SaR-SVM-STV) is introduced to classify hyperspectral images, which makes full use of spatial and spectral information. The Shape-adaptive Reconstruction (SaR) is introduced to preprocess each pixel based on the Pearson Correlation be-tween pixels in its shape-adaptive (SA) region. Support Vector Machines (SVMs) are trained to estimate the pixel-wise probability maps of each class. Then the Smoothed Total Variation (STV) model is applied to denoise and generate the final classification map. Experiments show that SaR-SVM-STY outperforms the SVM-STV method with a few training labels, demonstrating the significance of reconstructing hy-perspectral images before classification.

Original languageEnglish
Title of host publicationIGARSS 2022: 2022 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PublisherIEEE
Pages1368-1371
Number of pages4
ISBN (Electronic)9781665427920
ISBN (Print)9781665427937
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022 - Kuala Lumpur, Malaysia
Duration: 17 Jul 202222 Jul 2022

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2022-July

Conference

Conference2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022
Country/TerritoryMalaysia
CityKuala Lumpur
Period17/07/2222/07/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

  • Hyperspectral Image Classification
  • Image Reconstruction
  • Semi-supervised Learning
  • Smoothed To-tal Variation
  • Support Vector Machines

Fingerprint

Dive into the research topics of 'Classification of Hyperspectral Images Using SVM with Shape-Adaptive Reconstruction and Smoothed Total Variation'. Together they form a unique fingerprint.

Cite this