结合视觉显著模型与水平集算法的建筑物立面图像轮廓快速提取

iming at the time-consuming problem of traditional contour extraction method in building facade image processing, a building elevation contour extraction algorithm combined with visual saliency model and level set algorithm is proposed. First of all, using visual salient features and super pixel information to filter out the irrelevant background; secondly, it selects the significant blocks according to the buildings texture feature, with each super pixel block as a processing unit; finally, using the level set algorithm optimizes the resulting building area to obtain the final contour. The experimental results show that the processing speed of the proposed algorithm is effectively improved when the processing effect is equivalent, compared with the traditional contour extraction method.