Detection method for construction change of remote-sensing image based on DSM and kernel density estimation

Abstract

The invention relates to a detection method for a construction change of a remote-sensing image based on a DSM and a kernel density estimation. The detection method comprises the following steps that a first image and a second image of the panchromatic remote-sensing image are preprocessed; angular points are extracted respectively; the center point of a candidate construction is searched, and the kernel density estimation is conducted by using a symmetrical Gaussian probability-density function; results of the kernel density estimation are overlapped, and two time phase kernel density estimation images are obtained; a difference algorithm is carried out on the kernel density estimation images, and a difference image Pdif is obtained; the difference image Pdif is labeled, and a change region CH is obtained; purification is carried out on the change region CH. The problems that a false detection rate and a missing detection rate of the construction change of the high spatial resolution remote-sensing image are high, the algorithm is complex are solved, and the method can be used in update of an urban geography database and fast recognition of illegal constructions.

Description

technical field [0001] The invention relates to the field of remote sensing image processing, in particular to a method for detecting building changes in remote sensing images based on DSM and kernel density estimation. Background technique [0002] Building change detection in remote sensing images is a technique to quantitatively analyze and determine building change information from remote sensing data in different periods. At present, many experts and scholars in the world are trying to find fast and automatic change detection methods. Although researchers have proposed many building change detection methods, these methods often lack powerful mathematical theory derivation and digital model establishment. The specific implementation process Many steps in the process still rely on human experience guidance, and most methods have strict requirements on the image data used for change detection, are sensitive to the influence of factors such as noise and radiation difference...

AI Technical Summary

Problems solved by technology

At present, many experts and scholars in the world are trying to find fast and automatic change detection methods. Although researchers have proposed many building change detection methods, these methods often lack powerful mathematical theory derivation and digital model establishment. The specific implementation process Many steps in the process still rely on human experience guidance, and most methods have strict requirements on the image data used for change detection, are sensitive to the influence of factors such as noise and radiation differences between different time periods, and lack automatic and efficient change information extraction and analysis methods. Moreover, most of them are designed for optical remote sensing images obtained by the same sensor, and it is difficult to effectively use remote sensing image data obtained by different sensors.

Although many building change detection technologies and methods have emerged and have been applied in many aspects, the following difficulties still exist in remote sensing image building change detection to be further studied and solved: (1) high data quality requirements; (2) Insufficient practicability of the algorithm; (3) The degree of automation of change detection is low

Images