Unlock instant, AI-driven research and patent intelligence for your innovation.

SAR Image Change Detection Method Based on Stereographic Model

A technology of image change detection and stereo map, applied in the field of image processing, can solve the problems of unsatisfactory representation and detection out of bounds, so as to achieve smooth and accurate results and reduce redundancy.

Active Publication Date: 2020-11-06
HEFEI UNIV OF TECH
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the characterization of this method at the edge of the change area is not satisfactory, and the phenomenon of over-detection often occurs

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 Stereographic Model
  • SAR Image Change Detection Method Based on Stereographic Model
  • SAR Image Change Detection Method Based on Stereographic Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] refer to figure 1 As shown, the specific implementation of the SAR image change detection method based on the stereographic model includes the following steps:

[0046] Step 1. Input two-time SAR images: Input two SAR images of the same area at different times after registration and geometric correction X 1 and x 2 .

[0047] Step 2. Gaussian filtering: set the Gaussian filtering scale parameter σ=0.5, and then the SAR image X 1 Perform Gaussian filtering to obtain the filtered SAR image X' 1 .

[0048] Step 3. Key point extraction: Use a local window of size 3×3 in the filtered SAR image X' 1 Roaming in the middle, extract the pixel point with the highest intensity in the window as the key point of the research.

[0049] Step 4. Stereoscopic model construction: the extracted key point set S ω (X' 1 ) as the vertex V of the graph, and calculate the Euclidean distance between each vertex; then according to the K nearest neighbor rule, connect the K nearest neighb...

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 a stereographic model. The realization process is as follows: firstly, Gaussian filtering is performed on a single-time SAR image, and then the local maximum point in the filtered image is extracted as the key point of change detection research ;According to the location attributes of the key points, construct a stereographic model on the two-time SAR image, and then obtain the multi-span neighborhood and spatial information between the two-time key points; The changes of the key points on the image are measured; finally, the K-means clustering algorithm is used to perform cluster analysis on the change measurement results to separate the changed areas from the non-changed areas. Due to the introduction of multi-span neighborhood and spatial information, the method of the present invention can further improve the accuracy of the change detection method while effectively suppressing coherent speckle noise.

Description

technical field [0001] The present invention belongs to the field of image processing, which relates to the change detection of synthetic aperture radar (Synthetic Aperture Radar, SAR) image, and can be widely applied to natural disaster monitoring, land cover and utilization, resource and environment monitoring, urban development and planning, and military reconnaissance and Evaluation of strike effects and many other fields. Background technique [0002] SAR image change detection is an important technology to obtain surface change information by using two-time SAR images of the same geographical area at different times. Due to the special mechanism of SAR microwave imaging, it can perform active imaging under any atmospheric and sunlight conditions, and has the characteristics of all-weather and all-day work; Therefore, the development of high-precision and high-efficiency SAR image change detection methods has become a research hotspot among scholars at home and abroad....

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): G06K9/00G06K9/62
CPCG06V20/13G06F18/23213G06F18/24147
Inventor 杨学志汪骏贾璐
Owner HEFEI UNIV OF TECH