A Method of Spatial Salient Structure Extraction UsingLocal Spatial Statistics in High Resolution Images

Objective Homogeneous regions or edges are important structural information for object recognitionand extraction in high resolution remote sensing images.This paper considers the homogeneous re-gions and edges from the perspective of spatial dependence,which is a measure of the spatial associa-tion between the pixel values in the image.Spatial dependence is one of the spatial characteristics ofhigh resolution images.Based on the measure to spatial dependence using local spatial statistics(localMoran’s I,local Geary’s C and Getis),this paper proposes a simple,effective method of extractingspatial salient structures(homogeneous regions or edges)which adopts a new technique of 3Dthresh-olding for spatial dependence intensity.Comparative experiments show the potential and performancedifferences of three statistics in modeling spatial dependence and extracting spatial salient structures.