Unsupervised methods for the classification of hyperspectral images with low spatial resolution

  • Authors:

  • A. Villa;J. Chanussot;J. A. Benediktsson;C. Jutten;R. Dambreville

  • Affiliations:

  • Aresys srl, via Bistolfi 49, 20143 Milano, Italy and Dipartimento Elettronica e Informazione, DEI, Politecnico di Milano, Italy;GIPSA-lab, Department Image Signal, Grenoble INP, 38402 Saint Martin d'Héres, France;Faculty of Electrical and Computer Engineering, University of Iceland Hjardarhagi 2-6, 107 Reykjavik, Iceland;GIPSA-lab, Department Image Signal, Grenoble INP, 38402 Saint Martin d'Héres, France;GIPSA-lab, Department Image Signal, Grenoble INP, 38402 Saint Martin d'Héres, France

  • Venue:
  • Pattern Recognition
  • Year:
  • 2013

Quantified Score

Hi-index 0.01

Visualization

Abstract

The problem of structure detection and unsupervised classification of hyperspectral images with low spatial resolution is addressed in this paper. Hyperspectral imaging is a continuously growing area in remote sensing applications. The wide spectral range, providing a very high spectral resolution, allows the detection and classification surfaces and chemical elements of the observed image. The main problem of hyperspectral images is that the spatial resolution can vary from a few to tens of meters. Many factors, such as imperfect imaging optics, atmospheric scattering, secondary illumination effects and sensor noise cause a degradation of the acquired image quality, making the spatial resolution one of the most expensive and hardest to improve in imaging systems. Due to such a constraint, mixed pixels, e.g., pixels containing mixture of different materials, are quite common in hyperspectral images. In this work, we exploit the rich spectral information of hyperspectral images to deal with the problem. Two methods, based on the concept of spectral unmixing and unsupervised classification, are proposed to obtain thematic maps at a finer spatial scale in a totally unsupervised way. Experiments are carried out on one simulated and two real hyperspectral data sets and clearly show the comparative effectiveness of the proposed method with respect to traditional unsupervised methods, both for classification and detection of spatial structures.