干旱区生态环境知识资源中心

Vegetation often exists as patch in arid and semi-arid region. Numbers and areas and locations and spatial structure characteristics of vegetation patch are the important parameters for vegetation function and structure researches in landscape ecology. Visual interpretation of high spatial resolution remote sensing image to study landscape structure characters is often used, which needs lot of time and labours. In this paper, vegetation patches are detected using the canny edge detector and ellipticity measurement based on ALOS fusion image, and the whole processing steps were given. The detection accuracy of the patches is about 89.3%, which is better than that of the methods that only used the spectral difference between vegetation patches and background. The experiments show that integration the canny edge detector with the algorithm for extracting circle and ellipse objects is simple and effective for detecting vegetation patches. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of Conference ESIAT2011 Organization Committee.