Search

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 [1] 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. [ABSTRACT FROM PUBLISHER]

This paper proposed a hierarchical region merging method that based on the spectral similarity, to optimize the initial segmentation results from watershed transformation, addressing the problem that the existing watershed transformation algorithms are very sensitive to noise and prone to produce over-segmentation. The proposed method was evaluated by comparing with the most widely used watershed segmentation method through visual inspection, quantitative measures and applications in urban land cover classification, using a Quickbird image data of Beijing area and achieved a comparable performance. [ABSTRACT FROM PUBLISHER]