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

Method for improving speed of randomized circle detection in specific condition

A technology for detecting speed and random circles, which is applied to computer parts, instruments, character and pattern recognition, etc., and can solve the problems of large calculation and storage requirements

Inactive Publication Date: 2017-01-18
GUANGXI UNIVERSITY OF TECHNOLOGY
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For simple images, RHT is applied to circle detection, which can show good performance; but for complex images, the calculation and storage requirements of RHT will become very large

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
  • Method for improving speed of randomized circle detection in specific condition
  • Method for improving speed of randomized circle detection in specific condition
  • Method for improving speed of randomized circle detection in specific condition

Examples

Experimental program
Comparison scheme
Effect test

experiment example 1

[0059] Table 1 Comparison of execution time of three algorithms

[0060]

[0061] Table 2 The algorithm of this paper figure 2 (b) Test result (unit: pixel)

[0062]

[0063] Table 3 Statistics related to innovation points in the algorithm of this paper

[0064]

experiment example 2

[0067] Table 4 Comparison of the execution time of the three algorithms

[0068]

[0069] Table 5 Algorithm pair in this paper image 3 (b) Test result (unit: pixel)

[0070]

[0071] Table 6 Statistics related to innovation points in the algorithm of this paper

[0072]

experiment example 3

[0074] Figure 4 (a) is an actual image with a size of 140 pixels×140 pixels, and there are 4 circles in the image. The circle detection process is as Figure 4 As shown, where the edge image Figure 4 (b) There are 1688 edge points in total. Use RHT, RCD and the algorithm to Figure 4 (b) The time taken for circle detection is 5.4185 seconds, 2.1138 seconds and 0.4958 seconds, respectively. In the process of 50 inspections, these three algorithms can correctly extract the center coordinates and radius of each circle. The average value of p1, c1, r1, r1 / p1, p2, c2, r2, and r2 / p2 in this algorithm They are 765.88, 561.76, 1.04, 0.001358, 2128706, 16487.58, 2.96, 0.000001.

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 method for improving the speed of randomized circle detection in specific condition. The method comprises the following steps that (1) all edge points in an image are stored in a set V, and the initialized sampling frequency f equals 0; (2) four different points are selected from the V randomly; (3) whether the four points can determine a candidate circle is determined; (4) whether the candidate circle is a true circle is determined; (5) whether the point number positioned in the candidate circle is greater than a threshold Tmin is determined; (6) a step (8) is turned to if the true circle is found, and otherwise, a step (7) is turned to; (7) when f=f+1, if f is greater than Tf, detection ends, and otherwise, the step (2) is returned to; and (8) whether the amount of detected circles reaches a prescribed amount is determined. According to the invention, the success rate in searching the candidate circles and the true circles are improved effectively, and further the detection speed is improved.

Description

Technical field [0001] The invention belongs to the technical field of random circle detection, and in particular relates to a method for improving the speed of random circle detection in a specific situation. Background technique [0002] Fast and accurate detection of circles is widely used in many fields such as target positioning, robotics, and automated inspection. Hough transform is a common method for detecting circles. It has two main advantages: first, it is not sensitive to noise in the image; second, it can be easily calculated in parallel. Because the calculation time and storage space required by Hough transform are too large, a large number of improved Hough transforms have been proposed. The Random Hough Transform (RHT) proposed by Xu et al. is a major improvement to Hough Transform. Compared with Hough Transform, it has the advantages of small storage space requirement, fast, unlimited parameter space and arbitrarily high detection accuracy. For simple images, ...

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): G06K9/46
CPCG06V10/457
Inventor 蒋联源王智文徐奕奕刘美珍何剑
Owner GUANGXI UNIVERSITY OF TECHNOLOGY