A method of target change detection

Abstract

A method for detect a change of an object Firstly, the salient region of the image is extracted by Gabor texture feature, then the fusion image with salient object is obtained by guided filter fusion,and the fusion image is segmented by means of means shift, and then the HOG texture feature is used to compute the variance of the segmented texture, and the final change detection results are compared with each other. The technical proposal of the invention is based on the high-resolution remote sensing satellite image of the image guiding filter fusion and the texture characteristic analysis for the military target change detection technology, which can ensure the change detection precision and improve the change detection efficiency through the image fusion, and truly realizes the automatic, fast and accurate change detection of the military target.

Description

technical field [0001] The invention relates to a target change detection method, in particular to a technique for detecting military target changes based on high-resolution remote sensing satellite images based on image-guided filter fusion and texture feature analysis, and belongs to the technical field of remote sensing image processing. Background technique [0002] As a rising subject with broad application prospects, remote sensing technology is the only means that can provide large-scale dynamic observation data so far. Multitemporal image data for perception and monitoring. Therefore, analyzing the multi-temporal remote sensing images of the same geographic location becomes an effective way to obtain information on changes in the natural environment and military targets. [0003] Some methods of change detection using remote sensing images have been proposed, including pixel-based change detection methods and object-oriented change detection methods. In the case of...

AI Technical Summary

Problems solved by technology

[0004] The current object-oriented change detection algorithms can be generally divided into two categories, one is to segment an image to obtain the object, and search for the object on another image. This type of method only needs to be segmented once, but the segmentation results The accuracy requirement is very high, and when there is a new feature in the search image, it will not be detected; the other is to segment the two images at the same time, and compare the segmentation results. This method requires two segmentations. In addition, complex overlay analysis, region merging and other operations are required after segmentation, and are easily affected by registration errors

For the change detection of military targets, it requires both high precision to ensure the accuracy of information and high efficiency to ensure timeliness. The existing two types of object-oriented change detection algorithms cannot meet these two requirements at the same time.

Images