Flexible calibration method for binocular vision system based on one-dimensional coding target

Abstract

The invention discloses a flexible calibration method for binocular vision system based on one-dimensional coding target, and the method comprises the following steps: (1) processing an annular coding mark point on a one-dimensional target to form a one-dimensional coding target, randomly placing the one-dimensional coding target in a binocular system view field, and obtaining a plurality of images; (2) carrying out decoding and sub-pixel accurate positioning on the coded mark point image; (3) estimating an essential matrix of the binocular vision system by using a weighted translation normalization algorithm; and (4) optimizing and calculating internal and external parameter matrixes of the binocular vision system. According to the method, the coding mark points and the simply calibrated one-dimensional target are fused to replace traditional circular mark points, so that the recognition precision and the universality and flexibility of a matching algorithm are improved; and meanwhile, an essential matrix is estimated by using a weighted translation normalization algorithm, so that the interference of noise is eliminated, and the matching precision is further improved.

Description

technical field [0001] The invention relates to a binocular vision system calibration method, in particular to a binocular vision system calibration method for a one-dimensional coded target. Background technique [0002] Camera calibration refers to the establishment of the relationship between the pixel position of the camera image and the position of the scene point. The method is to solve the internal and external parameters of the camera from the image coordinates and world coordinates of known feature points according to the camera model. At present, there are many methods of camera calibration to improve the accuracy and efficiency of camera calibration. Among them, the one-dimensional target method is easy to operate and widely used. However, only collinear dots are used as the one-dimensional target for calibration. Although the round points are easy to identify, the recognition accuracy is not high, and it is not convenient for stereo matching, and different algori...

AI Technical Summary

Problems solved by technology

At present, there are many methods of camera calibration to improve the accuracy and efficiency of camera calibration. Among them, the one-dimensional target method is easy to operate and widely used. However, only collinear dots are used as the one-dimensional target for calibration. Although the round points are easy to identify, the recognition accuracy is not high, and it is not convenient for stereo matching, and different algorithms must be used for matching according to the specific form of feature point settings, resulting in the algorithm not being universal and flexible.

Images