Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Circular center detection method based on Gaussian fitting sub-pixel edge detection and improved RANSAC algorithm

A sub-pixel edge, Gaussian fitting technology, applied in computing, image enhancement, image analysis and other directions, can solve the problem of complex process, can not guarantee edge extraction accuracy and so on

Inactive Publication Date: 2018-12-11
HARBIN INST OF TECH
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The algorithm proposed in this paper performs grayscale interpolation on the gradient slope of edge points, and then uses Gaussian fitting to obtain sub-pixel edges. It has better stability and higher precision, but it cannot Guarantee the extraction accuracy of the edge, and need to interpolate the slope of the edge according to the situation, the process is more complicated

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
  • Circular center detection method based on Gaussian fitting sub-pixel edge detection and improved RANSAC algorithm
  • Circular center detection method based on Gaussian fitting sub-pixel edge detection and improved RANSAC algorithm
  • Circular center detection method based on Gaussian fitting sub-pixel edge detection and improved RANSAC algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Embodiment one: if figure 1 As shown, a kind of center detection method based on Gaussian fitting sub-pixel edge detection and improved RANSAC algorithm involved in this embodiment, the specific process of the center detection method is:

[0052] 1. The original image is model-matched and subjected to RIO processing;

[0053] 2. Edge pixel extraction and refinement;

[0054] 3. Sub-pixel edge positioning based on Gaussian fitting;

[0055] 4. Improved RANSAC circle fitting algorithm;

[0056] 5. Calculate the coordinates of the center of the circle.

Embodiment 2

[0057] Embodiment two: if figure 2 As shown, a kind of center detection method based on Gaussian fitting sub-pixel edge detection and improved RANSAC algorithm involved in this embodiment, the specific process of edge pixel extraction and refinement is: 1) using Sobel operator to detect edge; 2) Calculating the gradient value and gradient direction angle of the edge pixels; 3) Thinning the edge by non-maximum suppression method.

[0058] The Sobel operator is used for detection, because the Sobel operator is better than the Prewitt operator and the Robert operator for image processing with grayscale gradients and large noise, but the Sobel operator only considers two directions, so the edge width is detected Larger, there are cases of false edges and edge loss, so the edges must be thinned. The method used for edge refinement is the commonly used non-maximum suppression method. Its principle is to calculate the gradient magnitude and direction of each edge pixel. Amplitude,...

Embodiment 3

[0059] Embodiment three: a kind of center detection method based on Gaussian fitting sub-pixel edge detection and improved RANSAC algorithm involved in this embodiment, the specific process of the sub-pixel edge positioning based on Gaussian fitting is:

[0060] 1) Extraction of Gaussian curve fitting points: Gaussian fitting is performed on the gradient value and gradient direction of the obtained edge points. According to the curve shape of the gradient function, there are the following judgment rules:

[0061] According to the first point, calculate t sequentially i =|g(x i+1 )-g(x i )| value, if t i ε (t ε is a threshold set by oneself), t i+1 >t ε Then write down the x at this time i , which is the starting point;

[0062] if t i >t ε ,t i+1 ε ,t i+2 >t ε , then continue to calculate the following points;

[0063] if t i >t ε ,t i+1 ε ,t i+2 ε , then write down the x at this time i+1 , which is the endpoint value;

[0064] Among them, g(x i ) for x i ...

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 provides a circular center detection method based on Gaussian fitting sub-pixel edge detection and an improved RANSAC algorithm, belonging to the field of aircraft ground simulation. Themethod comprises the follow concrete steps: an original image is matched by a model and RIO processing is conducted on the image; edge pixel extraction and thinning is carried out; sub-pixel edge location based on Gaussian fitting is carried out; an improved RANSAC circle fitting algorithm is provided; the coordinates of the center of a circle are calculated. The invention roughly locates the position of the circular marker through a model matching mode, and performs RIO processing to reduce the size of image processing. Gaussian fitting improves the accuracy and stability of the algorithm. The improved RACNAC algorithm reduces the sampling times, optimizes and screens the candidate circles, reduces the running time and improves the accuracy and stability.

Description

technical field [0001] The invention relates to a circle center detection method based on Gaussian fitting sub-pixel edge detection and an improved RANSAC algorithm, and belongs to the field of aircraft ground simulation. Background technique [0002] The paper "An Improved Gray-scale Moment Sub-pixel Edge Detection Algorithm" (Journal of Chongqing University, Luo Jun, 200805) proposes an improved gray-scale moment sub-pixel edge detection algorithm. The algorithm uses a 7×7 template to move on the image and convolves with the image to find edges. The template is moved pixel by pixel, and the sub-pixel coordinates of the midpoint of the edge are calculated every time it is moved. The algorithm takes the template effect into consideration, and optimizes the calculation formula of the sub-pixel coordinates of the edge, and the experiment verifies that it has good positioning accuracy. Although the algorithm proposed in this paper improves the gray moment and solves the influ...

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 Applications(China)
IPC IPC(8): G06T7/13
CPCG06T2207/10004G06T7/13
Inventor 夏红伟丁致远马广程温奇咏王常虹
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com