In this paper, a new method for segmenting multispectral remote sensing image is proposed, which combines spectral properties of the pixels and their spatial properties. Spectral properties are studied by analyzing spectral angle of pixels while spatial properties are studied by morphological method. The spectral angle of each pixel is first computed by taken them as a vector with n-dimension. After an automatic selection of significant minima, an initial segmentation is achieved by applying watershed transformation to spectral angle map. To overcome the over-segmentation problem of watershed transformation, a region merging process using region adjacency graph (RAG) is employed to get the final segmentation result.
Segmentation on Multispectral Remote Sensing Image Using Watershed Transformation
2008 Congress on Image and Signal Processing ; 4 ; 773-777
2008-05-01
379180 byte
Conference paper
Electronic Resource
English
Watershed image segmentation and cloud classification from multispectral MSG–SEVIRI imagery
Online Contents | 2012
|Gray-Scale Image Segmentation by a Watershed Transformation
British Library Online Contents | 2005
|Advanced Multispectral TIR Remote Sensing
British Library Conference Proceedings | 1998
|Multispectral remote sensing of aerosols
Online Contents | 1996
|