A novel region-merging approach guided by priority for high resolution image segmentation

In order to improve the segmentation accuracy for high resolution remote sensing image, merging priority is modeled and used to guide merging process. Within-segment spectral variance and inter-segment edge strength are exploited for model construction. In the proposed approach, the segment with the lowest model value is prioritized for processing. Local-mutual-best-fitting rule is then used to find the appropriate neighbor of the segment under processing. Two scenes of GF-2 multi-spectral images were adopted for algorithm validation. The results indicated that the proposed method outperformed some competitive approaches.