A Method for Extracting the Center Coordinates of Camera Calibration Mark

Abstract

The invention discloses a method for extracting the center coordinates of a camera calibration mark. The method for extracting the central coordinates of the calibration mark adopts the following steps: (1) the image is divided into regions, and different parameters are set in different regions to detect the Hough circle to obtain a circular mark image; (2) in the extraction step (1) The inscribed polygon of the circular sign image; (3) carry out Hough straight line detection in the inscribed polygon, extract the intersection coordinates of straight lines; (4) detect the reliability of the intersection coordinates, compare the circle center coordinates obtained in step (1) Set the threshold, delete the intersection points outside the threshold, obtain the intersection points of the straight lines within the threshold, calculate the average value of the intersection points of the straight lines to obtain the center coordinates of the calibration mark. In the circle detection process of the image sub-regions of the present invention, the parameters of different regions are respectively set to perform circle detection, and the center coordinates of the mark are obtained by calculating the average value according to the coordinates of the intersection points of the straight lines, which greatly improves the extraction accuracy of the center coordinates.

Description

technical field [0001] The invention relates to the field of camera calibration, in particular to a method for extracting the center coordinates of a camera calibration mark. Background technique [0002] In modern measurement, non-measurement digital cameras have the characteristics of low cost, easy to carry, and simple operation, making them more and more widely used in the fields of aerial measurement, part inspection, and three-dimensional reconstruction. However, the internal orientation elements of ordinary non-measurement digital cameras are unknown and the distortion difference is relatively large, so they cannot be directly applied to photogrammetry. It is necessary to perform camera calibration on the captured photos to obtain the internal orientation elements and distortion coefficients of the camera. The extraction of the center coordinates of the logo image is a very important step. [0003] The calibration mark is composed of a simple circle and a straight li...

AI Technical Summary

Problems solved by technology

[0009] 1. The method of artificially enhancing a certain color component is not accurate when detecting a circular feature block; and when calculating the precise center coordinates of the mark, use the symmetry principle to find the center of the circular feature block to obtain the center coordinates of the mark. This method requires The obtained features must be fast and accurate, and the calculation process is also somewhat complicated

[0010] 2. The method of obtaining the initial position through direct linear transformation first detects the straight line during detection. In the actual environment, there is a lot of noise in the straight line, resulting in low detection accuracy

Images