关键词: 主成分分析, 彩色区域生长, 水平集方法, 高分辨率遥感影像, 道路提取

Abstract: A color region growing algorithm based on PCA (Principal Component Analysis) was proposed. Level set method was employed to extract urban roads from high-resolution remote sensing images. Firstly, the region growing algorithm was applied to the preliminary road segmentation, and then the roughly obtained road region was used to construct the initial level set function, which then evolved stably according to a level set evolution equation without re-initialization. Finally, a regularizing local edge algorithm based on level set without re-initialization was presented, and utilized to regularize the local erroneous road curve due to obstacles. Experimental results show that the method is efficient and practical for extracting complete roads from high-resolution remote sensing images, with less manual intervention and stronger anti-noise ability.

Key words: Principal Component Analysis (PCA), color region growing, level set method, high-resolution remote sensing image, road extraction