Automatic scale segmentation parameter selection method for object remote sensing image analysis

Abstract

The invention discloses an automatic scale segmentation parameter selection method for object remote sensing image analysis. Optimum space scale segmentation parameters are determined through calculating an average local variance curve range method; optimum attribute scale segmentation parameter are determined through a local variance histogram estimation method; optimum merging threshold parameters are determined by employing anisotropy space correlation statistics to calculate horizontal and vertical ranges; scale effect evaluation and scale segmentation parameter optimization adjustment on a segmentation result are carried out by employing an index evaluation method. In combination with the geological spatial statistics and a mode identification theory method, the automatic scale segmentation parameter selection method realizes automatic selection of the optimum scale segmentation parameters before segmentation, can clearly explain the determined optimum scale segmentation parameters based on statistics theories, has higher theory credibility and improves information extraction and analysis efficiency and precision for object remote sensing images.

Description

technical field [0001] The invention relates to the field of remote sensing geoscience analysis methods, in particular to an automatic selection method of scale segmentation parameters in object-oriented remote sensing image analysis. Background technique [0002] The research on Object-Oriented Remote Sensing Image Processing and Analysis (GEOBIA) is still in its infancy, and the academic community has not yet clearly defined the concept of object-oriented scale. According to the definition of image objects in mainstream object-oriented commercial software—an image object is a connected region composed of pixels with the same attributes, the superficial meaning of scale in object-oriented image processing and analysis is the size of image objects or object details in terms of spatial span; From the perspective of image object extraction algorithm, that is, image segmentation algorithm, the scale selection in object-oriented image processing and analysis mainly corresponds t...

AI Technical Summary

Problems solved by technology

In addition, the surface system is a complex system composed of different levels of subsystems. Since the objects contained in the images are of different sizes, they need to be reflected at different processing scales. However, the current object-oriented remote sensing image analysis is often based on discrete or With a single scale, it is difficult to achieve a global understanding of the image

Images