Classification endmember selection with multi-temporal hyperspectral data

Tingxuan Jiang*, H. van der Werff, F. van der Meer

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)
28 Downloads (Pure)

Abstract

In hyperspectral image classification, so-called spectral endmembers are used as reference data. These endmembers are either extracted from an image or taken from another source. Research has shown that endmembers extracted from an image usually perform best when classifying a single image. However, it is unclear if this also holds when classifying multi-temporal hyperspectral datasets. In this paper, we use spectral angle mapper, which is a frequently used classifier for hyperspectral datasets to classify multi-temporal airborne visible/infrared imaging spectrometer (AVIRIS) hyperspectral imagery. Three classifications are done on each of the images with endmembers being extracted from the corresponding image, and three more classifications are done on the three images while using averaged endmembers. We apply image-to-image registration and change detection to analyze the consistency of the classification results. We show that the consistency of classification accuracy using the averaged endmembers (around 65%) outperforms the classification results generated using endmembers that are extracted from each image separately (around 40%). We conclude that, for multi-temporal datasets, it is better to have an endmember collection that is not directly from the image, but is processed to a representative average.

Original languageEnglish
Article number1575
Pages (from-to)1-19
Number of pages19
JournalRemote sensing
Volume12
Issue number10
DOIs
Publication statusPublished - 15 May 2020

Keywords

  • Classification
  • Consistency
  • Cuprite
  • Endmember selection
  • Hyperspectral
  • Multi-temporal
  • ITC-ISI-JOURNAL-ARTICLE
  • ITC-GOLD

Fingerprint Dive into the research topics of 'Classification endmember selection with multi-temporal hyperspectral data'. Together they form a unique fingerprint.

Cite this