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

Checkerboard corner detection method and device

A checkerboard and point detection technology, applied in the image field, can solve the problems of insufficient determination of each candidate corner point, inaccurate analysis results, and low efficiency of corner point detection, so as to reduce the amount of calculation, improve calculation efficiency, and improve accuracy. efficiency and robustness

Active Publication Date: 2018-10-16
SPREADTRUM COMM (SHANGHAI) CO LTD
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the prior art, it takes a lot of computing resources to determine the corner point score of each candidate corner point, resulting in low corner detection efficiency, and the corner point score is only used in the corner point detection stage, not for subsequent In the checkerboard generation stage, the utilization rate is low
[0005] Furthermore, in the prior art, in order to reduce the amount of calculation, the corner peaks are only analyzed within the range of 0 to π in the boundary direction, resulting in insufficient determination of each candidate corner point, which easily leads to inaccurate analysis results based on the corner peaks

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
  • Checkerboard corner detection method and device
  • Checkerboard corner detection method and device
  • Checkerboard corner detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In the existing checkerboard corner detection method, it is necessary to spend a lot of computing resources to determine the corner score of each candidate corner, and then determine whether to keep the candidate corner based on the corner score, resulting in the existing corner Point detection is less efficient.

[0038] The inventors of the present invention have found through research that the corner point score of each candidate corner point is not a necessary parameter, and can also be compared by comparing the peak values ​​of different corner points of the candidate corner points, and the different corner points of the candidate corner points The directional relationship of the point peaks is analyzed to determine the candidate corner points to be retained.

[0039] In the embodiment of the present invention, an image is acquired, and candidate corner points in the image are determined; within the range of 0 to 2π in the boundary direction, the number of corner p...

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 checkerboard corner detection method and device. The method comprises the steps that an image is acquired, and candidate corners in the image are determined; within a 0-2pi range of a boundary direction, the number of corner peaks of each candidate corner and the size and direction of each corner peak are determined; the candidate corners with the number of corner peaks smaller than 4 are removed; and for each candidate corner with the number of corner peaks greater than or equal to 4, whether the candidate corner is reserved is determined according to a comparison result of sizes and a direction relation of different corner peaks of the candidate corner. Through the scheme, the calculation amount in the detection process can be reduced, and the detection efficiency of the candidate corners is effectively improved.

Description

technical field [0001] The invention relates to the field of image technology, in particular to a checkerboard corner detection method and device. Background technique [0002] In the application of mobile camera equipment, camera calibration is an important and indispensable step. The step of calibration is mainly to detect corner points (triples) based on the pattern of square checkerboard or circular checkerboard, and then calculate internal parameters, external parameters, lens distortion parameters, etc. according to the positions of the corner points. [0003] In the existing checkerboard corner detection method, the candidate corners are first determined based on the Harris isocorner detection algorithm, and then the number of corner peaks of each candidate corner is determined within the range of 0 to π in the boundary direction, and each The magnitude and direction of the corner peaks. Then, for the candidate corner points where the number of peaks is greater than...

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): G06T7/80G06T7/73
CPCG06T7/73G06T7/80G06T2207/30208G06T2207/30244
Inventor 徐海燕刘阳林福辉
Owner SPREADTRUM COMM (SHANGHAI) CO LTD
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