Object-based remote sensing image super-resolution charting method

Abstract

The invention discloses an object-based remote sensing image super-resolution charting method. Object-based soft classification is carried out by aiming at a mixed object problem with which an object-based remote sensing classification process is faced so as to obtain the category ratio of each object on the basis of the object-based soft classification; and a spatial relationship between the mixed object and a neighborhood object thereof is utilized, on the basis of the first law of geography, i.e., a spatial correlation principle, the spatial correlation feature of each sub pixel in the mixed object is estimated by virtue of a deconvolution and surface to point kriging interpolation technology in statistics, and an object-based linear optimization model is constructed under the ratio constraint of each category of the mixed object to determine the optimal category attribute of the sub-pixel so as to finish the remote sensing image super-resolution charting. The method has the advantages of high practicality, high simulation accuracy and the like and is suitable for ground surface information extraction and geoscience data mining works including remote sensing data classification, land coverage / utilization, change detection and the like.

Description

technical field [0001] The invention relates to the technical field of geospatial information, in particular to an object-based remote sensing image super-resolution mapping method. Background technique [0002] Extracting land cover / use basic data from remote sensing images through classification technology is a hot field in the research of remote sensing information extraction. However, the mixed pixels that commonly exist in remote sensing images are the main factors that affect the classification results. Super-resolution mapping technology (also known as sub-pixel mapping or sub-pixel positioning) is a new technology for solving mixed pixel classification (Atkinson, 1997), which is a soft classification of low spatial resolution images (also known as Mixed pixel decomposition) is downscaled to a multi-level higher spatial resolution hard classification map (Ge et al., 2016; Ling et al., 2014; Zhong and Zhang, 2012), that is, sub Marker map of ground object categories ...

AI Technical Summary

Problems solved by technology

However, due to the constraints of ubiquitous mixed pixels and image segmentation methods (Clinton et al., 2010; Han Peng et al., 2010), the results of image segmentation include both pure objects and "mixed objects", which are different from those based on The mixed pixel problem faced by pixel classification is similar to

In addition, as the spatial resolution of the image increases, the details of the ground objects that can be expressed by the image also increase, which causes the spectral heterogeneity within the same type of ground objects to increase, and the spectral difference between different ground objects to decrease. After image segmentation, it will face more complex mixed object problems (Blaschke et al., 2014)

[0004] At present, super-resolution mapping research mainly uses pixel-based soft classification results to solve the classification problem of mixed pixels (Ge et al., 2016; Tong et al., 2013), and there is no super-resolution mapping method that can solve Mixed Object Problems Faced During Object-Based Classification

Images