Camera calibration error compensation method based on multi-dimensional characteristics

Abstract

A camera calibration error compensation method based on multi-dimensional characteristics includes the following steps: (1) preparing data: collecting p images of standard targets, obtaining p images with errors, selecting q key points through each images, obtaining p*q key points; (2) extracting the characteristics of the key points: extracting the characteristics of each key point; (3) calculating the actual errors of the p*q key points (delta x, delta y) p*q; (4) conducting simulated training: conducting a support vector regression model training by using support vector machine (SVM) light tools; and (5) estimating errors: obtaining the actual position (x, y) q of q key points, then extracting the characteristics of the q key points according to step (2), storing the characteristics of the q key points in a to-be-regressed characteristic file, and calculating the compensation value (delta x, delta y) of each key point. According to the camera calibration error compensation method based on the multi-dimensional characteristics, association characteristics of a scene image are used, the compensation value of each collected image estimated in support vector regression is adopted, and by means of the camera calibration error compensation method based on the multi-dimensional characteristics, compensated light target center is close to an ideal light target center.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a camera calibration error compensation method based on multi-dimensional features. Background technique [0002] Camera calibration is one of the important problems in machine vision. For the pinhole model camera, the calibration process is mainly to solve the camera intrinsic parameters (Intrinsic parameters) and extrinsic parameters (Extrinsic parameters). Solve the transformation from target pixel coordinates (image coordinate system) to scene coordinates (world coordinate system) through these internal and external parameters. The calibration process can use direct linear method, Tsai method, Zhang Zhengyou method, etc. However, no matter which calibration method is used, there is an error between the actual calculated target coordinates and the ideal coordinates due to the radial distortion of the lens, the geometric deformation of the tilt, and the change of the on-site e...

AI Technical Summary

Problems solved by technology

[0004] The above compensation methods have achieved certain effects, but there are still two aspects that can still be improved

First, high-degree polynomials are used to model the compensation value. As the number increases, the amount of calculation increases exponentially, and it is difficult to balance the contradiction between calculation time and compensation quality; second, camera distortion not only causes local area pixels to The deviation of the point position also affects the imaging of the whole picture

Images