Detection of Sand and Dust Storms from MERIS Image Using FE-Otsu Alogrithm
Authors:
- Kaiping WeiKWKaiping Wei
- Tao ZhangTZTao Zhang
- Bin HeBHBin He
- 1 May 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21517614,p. 3852-3855
Abstract
Aiming at resolving the issue of Sand and Dust Storm (SDS) location in a remote sensing image, a new method is proposed in this paper to detect the center and intensity of a SDS automatically. First, SDS coverage area is extracted from remote sensing images by 2D-Otsu algorithm combined with fuzzy entropy, and the PSO algorithm is implemented to accelerate the process of global threshold selection. And then SDS intensity is evaluated according to the area ratio of SDS in an image. Based on implementation of morphological operations, major region of SDS is confirmed and the SDS center is detected using mass searching algorithm. Experimental result shows that the center and intensity of SDS can be detected rapidly and efficiently.Keywords
This publication has 7 references indexed in Scilit:
- Automatic thresholding of gray-level pictures using two-dimension Otsu method2002
- A new optimizer using particle swarm theory2002
- Morphological Image Analysis1999
- Threshold selection based on fuzzy c-partition entropy approachPattern Recognition, 1998
- Remote sensing aerosols using satellite infrared observationsJournal of Geophysical Research: Atmospheres, 1997
- Automatic segmentation of ultrasound images using morphological operatorsIEEE Transactions on Medical Imaging, 1991
- Automatic thresholding of gray-level pictures using two-dimensional entropyComputer Vision, Graphics, and Image Processing, 1989