Checkerboard angular point automatic screening method of corner detection

Abstract

The invention discloses a checkerboard angular point automatic screening method of corner detection, which employs a camera to shoot checkerboard images, obtains an angular point set to be identified through routine angular point detection, furthermore searches for a real angular point subset, and finally outputs checkerboard real angular points. The method comprises: designing a rectangular formwork; determining whether an angular point is a checkerboard angular point through calculating the similarity between the shape formed by angular points and the rectangular shape; employing a dioid graph method to describe the position relation among the angular points; and utilizing graph theory knowledge to respectively create distance sub graph and direction sub graph searching angular points. In detecting routine angular points, when a set angular point threshold level is lower and excessive angular point detection exists, the method can automatically determine a real checkerboard angular point subset from a detected angular point set without artificial intervention, remove false angular points, improve angular point detection accuracy, and lay a foundation for subsequent processing such as camera calibration, three-dimensional reconstruction, etc.

Description

technical field [0001] The invention relates to the technical field of checkerboard grid detection, in particular to an automatic screening method for checkerboard grid corner points for edge detection. Background technique [0002] The checkerboard is a kind of calibration board widely used in camera calibration. The corner points of the checkerboard are used as the calibration feature points, and the position accuracy extracted will directly affect the accuracy of the camera calibration, which in turn affects the accuracy of the computer vision system; for the checkerboard At present, there are many methods of corner detection, such as the more classic Harris method, susan method, etc. In conventional corner detection, the corner level is calculated by the corner detection formula, and determined by setting its level threshold Corner points, that is, when the corner point level is greater than a given threshold, it is considered to be a corner point. In the actual checkerb...

AI Technical Summary

Problems solved by technology

[0002] The checkerboard is a kind of calibration board widely used in camera calibration. The corner points of the checkerboard are used as the calibration feature points, and the position accuracy extracted will directly affect the accuracy of the camera calibration, which in turn affects the accuracy of the computer vision system; for the checkerboard At present, there are many methods of corner detection, such as the more classic Harris method, susan method, etc. In conventional corner detection, the corner level is calculated by the corner detection formula, and determined by setting its level threshold Corner points, that is, when the corner point level is greater than a given threshold, it is considered to be a corner point. In the actual checkerboard corner point detection, when the corner point level threshold is set relatively high, corner point leakage detection will occur. When When the horizontal threshold is set low, corner over-detection will occur, that is, some non-checkerboard corners will be detected as corners, resulting in misdetection of corners; The accuracy of point detection is not high, which affects the accuracy of camera calibration. It is urgent to improve the corner detection method of the existing technology to improve the accuracy of corner detection and ensure the accuracy of camera calibration.

Images