Segmentation for High Spatial Resolution Remote Sensing Images by Combining Quadtree with Minimum Spanning Tree

摘要

This paper presents a high spatial resolution remote sensing image segmentation method by combining quadtree withminimum spanning tree. Firstly, the improved quadtree segmentation algorithm is used to divide the image iteratively intomany over-segmented objects, which greatly facilitates the selection of initial segmentation parameters. Then the improvedMorton coding is used to construct the spatial index of the generated over-segmented object and form the region adjacencyrelation. Combine spectral and texture features, the similarity between adjacent regions is calculated and the region mergingcriterion is constructed. Based on the idea of minimum spanning tree, the over-segmented objects are merged to generatemultiple minimum spanning trees. During that process, the number of minimum spanning trees can be controlled to obtainideal segmentation results. Compared with two other segmentation algorithms, the method proposed in this paper is moreconvenient to select segmentation parameters and has certain improvement in segmentation accuracy and object integrityof segmentation results.