A Self-Adaptive Mean-Shift Segmentation Approach Based on Graph Theory for High-Resolution Remote Sensing Images

摘要

An auto new segmentation approach based on graph theory which named self-adaptive mean-shift for high-resolution remote sensing images was proposed in this paper. This approach could overcome some defects that classic Mean-Shift must determine the fixed bandwidth through trial many times, and could effectively distinguish the difference between different features in the texture rich region. Segmentation experiments were processed with WorldView satellite image. The results show that the presented method is adaptive, and its speed and precision can satisfy application, so it is a robust automatic segmentation algorithm.