Method for determining the optimal segmentation scale of satellite image segmentation based on information gain ratio

Abstract

The invention discloses a method for determining the optimal segmentation scale of satellite image segmentation based on information gain rate, includes obtaining high-resolution satellite remote sensing image, preprocessing, selecting representative region as sample region determined by optimal segmentation scale, classifying surface features of sample region, obtaining image classification result of sample region as reference image determined by optimal segmentation scale, and obtaining image classification result of sample region as reference image determined by optimal segmentation scale;setting a series of segmentation scale parameters from small to large, using multi-scale segmentation technology, the sample image is segmented in multi-scale to obtain a series of segmented object vectors; Based on Shannon information entropy formula, the information entropy of reference image and segmentation vector is calculated, and the conditional entropy of reference image with segmentationvector is calculated, then the information gain and information gain ratio of segmentation vector are calculated. The optimal segmentation scale is selected according to the principle of maximum information gain rate. Finally, based on the optimal segmentation scale, the original image is segmented at multiple scales.

Description

technical field [0001] The invention relates to the technical field of object-oriented image segmentation parameter selection, in particular to a method for determining the optimal segmentation scale of satellite image segmentation based on information gain ratio. Background technique [0002] In recent years, with the continuous launch of various satellites, the available data sources for crop monitoring are increasing, and crop identification based on multi-source satellite remote sensing data has become a new trend, which better solves the defect of insufficient temporal resolution of a single satellite image. (Sharma et al. 2017; Colkesen and Kavzoglu 2017; Morton et al. 2011; Novelli et al. 2016). However, the spatial resolution of different satellite data is often inconsistent. The traditional pixel-based method needs to use resampling to make the resolution consistent (Mansaray et al.2017; Sharma et al.2017), but mixed pixel and scale effects The existence of restric...

AI Technical Summary

Problems solved by technology

However, the supervised optimal segmentation scale determination method that is currently widely used is mainly based on topological or geometric metrics to evaluate the degree of agreement between the reference object and the segmentation object. The application of the method is relatively complicated, which limits its application.

Images