Very high resolution Image Segmentation by combined spectral and structural information

Image Segmentation is a key and prerequisite step for object-based analysis using very high resolution (VHR) images. The segmentation method based on morphological profiles proposed in 111 only makes use of the structural information from panchromatic image. This paper proposed a segmentation method for VHR multispectral images by combined spectral and structural information. The proposed method was evaluated by comparing with existing morphological segmentation methods through visual inspection and quantitative measures, using a Quickbird image of Beijing area. The experimental results indicate that the proposed method achieve a better performance.