Share Email Print

Proceedings Paper

Semi-supervised hyperspectral image segmentation using regionalized stochastic watershed
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Stochastic watershed is a robust method to estimate the probability density function (pdf) of contours of a multi-variate image using MonteCarlo simulations of watersheds from random markers. The aim of this paper is to propose a stochastic watershed-based algorithm for segmenting hyperspectral images using a semi-supervised approach. Starting from a training dataset consisting in a selection of representative pixel vectors of each spectral class of the image, the algorithm calculate for each class a membership probability map (MPM). Then, the MPM of class k is considered as a regionalized density function which is used to simulate the random markers for the MonteCarlo estimation of the pdf of contours of the corresponding class k. This pdf favours the spatial regions of the image spectrally close to the class k. After applying the same technique to each class, a series of pdf are obtained for a single image. Finally, the pdf's can be segmented hierarchically either separately for each class or after combination, as a single pdf function. In the results, besides the generic spatial-spectral segmentation of hyperspectral images, the interest of the approach is also illustrated for target segmentation.

Paper Details

Date Published: 12 May 2010
PDF: 12 pages
Proc. SPIE 7695, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVI, 76951F (12 May 2010); doi: 10.1117/12.850187
Show Author Affiliations
Jesús Angulo, MINES ParisTech (France)
Santiago Velasco-Forero, MINES ParisTech (France)

Published in SPIE Proceedings Vol. 7695:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVI
Sylvia S. Shen; Paul E. Lewis, Editor(s)

© SPIE. Terms of Use
Back to Top