The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-4/W4
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W4, 91–96, 2017
https://doi.org/10.5194/isprs-archives-XLII-4-W4-91-2017
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W4, 91–96, 2017
https://doi.org/10.5194/isprs-archives-XLII-4-W4-91-2017

  26 Sep 2017

26 Sep 2017

GRAPH-BASED SEMI-SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION USING SPATIAL INFORMATION

N. Jamshidpour1, S. Homayouni2, and A. Safari1 N. Jamshidpour et al.
  • 1Dept. of Geomatics Engineering, College of Engineering, U. of Tehran, Tehran, Iran
  • 2Dept. of Geography, Environmental Studies, and Geomatics, U. of Ottawa, Ottawa, Canada

Keywords: hyperspectral classification, semi-supervised learning, graph construction, spatial information

Abstract. Hyperspectral image classification has been one of the most popular research areas in the remote sensing community in the past decades. However, there are still some problems that need specific attentions. For example, the lack of enough labeled samples and the high dimensionality problem are two most important issues which degrade the performance of supervised classification dramatically. The main idea of semi-supervised learning is to overcome these issues by the contribution of unlabeled samples, which are available in an enormous amount. In this paper, we propose a graph-based semi-supervised classification method, which uses both spectral and spatial information for hyperspectral image classification. More specifically, two graphs were designed and constructed in order to exploit the relationship among pixels in spectral and spatial spaces respectively. Then, the Laplacians of both graphs were merged to form a weighted joint graph. The experiments were carried out on two different benchmark hyperspectral data sets. The proposed method performed significantly better than the well-known supervised classification methods, such as SVM. The assessments consisted of both accuracy and homogeneity analyses of the produced classification maps. The proposed spectral-spatial SSL method considerably increased the classification accuracy when the labeled training data set is too scarce.When there were only five labeled samples for each class, the performance improved 5.92% and 10.76% compared to spatial graph-based SSL, for AVIRIS Indian Pine and Pavia University data sets respectively.