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

Multi-scale SAR image edge detection method

An image edge and detection method technology, applied in the field of image processing, can solve the problems of a single-sized detection window, unable to meet the requirements, etc., to achieve the effect of ensuring accuracy and overcoming texture-rich areas and weak edge areas

Pending Publication Date: 2020-02-11
CHINA UNIV OF MINING & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the defect that conventional ROA edge detectors cannot meet the requirements with a single-sized detection window, and propose a multi-scale SAR image edge detection method that comprehensively utilizes different-sized detection windows

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
  • Multi-scale SAR image edge detection method
  • Multi-scale SAR image edge detection method
  • Multi-scale SAR image edge detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0037] Such as figure 1 As shown, a kind of multi-scale SAR image edge detection method described in the present invention comprises the following steps:

[0038] Step 1: Set the maximum detection window W max and the minimum detection window W min , get N W =(W max –W min ) / 2+1 windows W of different sizes;

[0039] This embodiment sets W max = 7, W min = 3, then there are N W = 3 windows of different sizes, that is, W takes 3, 5, 7.

[0040] Step 2: For three windows of different sizes, set their template parameters l, w, d, θ respectively, such as figure 2 shown; each window of size W can obtain N θ =π / θ templates, then a total of N=N W *N θ Templates with different sizes W and different directions θ; where l is the template length, w is the template width, and d is the template area R 1 and R 2 The distance...

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 multi-scale SAR image edge detection method. The method comprises the following steps of calculating edge gradients in different directions in the image by using windows withdifferent sizes; then, reserving the maximum value in all gradients with different sizes and different directions and the corresponding direction information. A ccording to the method, the windows with different sizes and different directions can be used for detecting edges, and the defect that the edge position obtained during single window edge detection is inaccurate is effectively overcome.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a multi-scale SAR image edge detection method. Background technique [0002] The edge in the image is the most basic and difficult to change feature in the image. It is the most concentrated place in the image and the basis for image feature extraction, target recognition, image segmentation and other processing. Therefore, edge detection is the most important in the field of image processing. One of the basic questions. However, due to the influence of factors such as sensors, imaging principles, imaging positions, and imaging objects in the imaging process, the edge information in the image varies greatly in the image, which makes it difficult to detect the edge accurately. [0003] The current image edge detection algorithms can be roughly divided into: 1) edge detection algorithms based on spatial gradient; 2) wavelet edge detection algorithms based on frequency dom...

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
IPC IPC(8): G06T7/13G06T7/136
CPCG06T2207/10044G06T7/13G06T7/136
Inventor 郎丰铠
Owner CHINA UNIV OF MINING & TECH