关键词: 水平集, 主动轮廓模型, 曲线演化, 建筑物检测, 图像分割

Abstract: By analyzing traditional level set methods based on gradient and Chan-Vese model based on regions，a double level set model for remote sensing image segmentation is proposed.This method combines local gradients and global regions average values，and uses variational methods to get the associated curve evolution equation.An internal energy term is introduced to force the level set function to be closed to a signed distance function，which can completely eliminate the need of the costly re-initialization procedure.Therefore，it can speed up the curve evolution.At the same time，the model can segment more than two targets simultaneity.In remote sensing image，this method can detect the area with a sunny exposure，shadow region and the roof of the building at one time.The experimental results show that it is an effective approach to building detection.

Key words: level set, active contour, curve evolving, building detection, image segmentation