Check patentability & draft patents in minutes with Patsnap Eureka AI!

SAR image change detection method based on superpixel saliency analysis

A super pixel, remarkable technology, applied in the field of image processing, can solve the problem of long running time, achieve the effect of improving the change effect, reducing the computing time, and occupying less memory

Active Publication Date: 2019-10-11
XIDIAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The change detection method based on the saliency map invented by Yang Chuan is based on the pixel feature, using the saliency map as a guide for change detection, and combining the spatial information of the image to improve the detection accuracy, but this method is calculated in units of pixels, resulting in long running time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • SAR image change detection method based on superpixel saliency analysis
  • SAR image change detection method based on superpixel saliency analysis
  • SAR image change detection method based on superpixel saliency analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Refer to attached figure 1 , the implementation steps of the present invention are as follows:

[0043] Step 1. Input the data graph to obtain the logarithmic ratio graph c1.

[0044] Input the SAR images G1 and G2 to be detected at two different moments in the same scene to obtain the SAR image

[0045] The logarithmic ratio plot c1=log(G1+1)-log(G2+1).

[0046] Step 2. Obtain the filter map of the logarithmic ratio map c1.

[0047] Set the filter graph p to be input, where p=c1, the radius r1 of the local window and the conventional coefficient e, call the guided filter function GD to filter the logarithmic ratio graph c1, and obtain the filter graph c: c=GD(c1,p, r1,e);

[0048] Step 3: Carry out superpixel segmentation on the filtered image c to obtain a segmented image L.

[0049] (3.1) Convert the filter image c into a color image;

[0050] (3.2) Set the number k of superpixel blocks, the balance weight coefficient m between color and space, the radius r of ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a SAR image change detection method based on superpixel saliency analysis, which mainly solves the problem of low detection accuracy of the traditional technology. The scheme is: 1) Input two images at different moments in the same scene to obtain a logarithmic ratio image of the image; perform guided filtering on the logarithmic ratio image to obtain a filtered image; 2) perform superpixel segmentation on the filtered image to obtain a segmented image ; 3) Use the saliency method to calculate the saliency map from the segmentation map; perform threshold processing on the saliency map, and combine two images at different times to obtain the difference map; 4) Use the fuzzy local information C-means clustering method to cluster the difference map , to get the change map. The invention introduces superpixel segmentation and guided filtering, which not only reduces the noise of the SAR image, but also effectively improves the accuracy of the SAR image through the obtained saliency map, which can be used to detect the change area.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for SAR image change detection, which can be used for change region detection. Background technique [0002] Image change detection technology is used to detect changes in the same place at different times, which has important application value. Synthetic Aperture Radar (SAR) has the characteristics of all-weather and all-time, and it is a good source of change detection information. The research on SAR image change detection technology has a very broad application prospect. Multi-temporal SAR image data contains more information than single SAR image data. Change detection technology has been widely studied in this area. It can obtain the required ground object change information through the difference analysis of SAR images in different periods. Change detection is mainly used for land use and land cover changes in resource and environmental monit...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/10G06T3/40G06K9/00G06K9/46G06K9/62
CPCG06T3/4053G06T7/0002G06T7/10G06T2207/10044G06V20/13G06V10/462G06F18/23
Inventor 曹向海王林冀雅梅吉贝贝焦李成
Owner XIDIAN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com