Software package for estimation of the stereo camera calibration error in the computer vision system

Abstract

The approach for accuracy assessment of the object model a for the problem of stable grasping in the combined system of the proposal of grasping and the reconstruction of the three-dimensional model of the object was considered. Such a combined system allows stable capture of objects of any shape without restrictions on the types of shapes in the training data set. Novel approaches to surface reconstruction of the object are based on restoring the depth of points from a pair of images from two cameras. The quality of the 3D reconstruction is affected by several factors: the movement of the camera and environmental objects, spatial quantization of the image coordinates, correspondence of key points, camera calibration parameters, unaccounted camera distortions, as well as numerical and statistical properties of the selected reconstruction method. Camera parameter errors can be minimized by improving the calibration procedure, so the impact of errors on the quality of the 3D model was investigated. The deviation of the model from the plane is chosen as a metric for quality assessment. For its calculation, the point cloud is processed by plane identification and segmentation, for which an algorithm based on the RANSAC method is considered. The software package for accuracy estimation was developed. An experiment was conducted to obtain the dependence of the accuracy of the reconstructed planes on the errors of the camera parameters. The impact of calibration errors on 3D reconstruction was evaluated by comparing metrics for individual planes at different levels of artificial error and evaluating the impact of the error on these metrics. Modeling the error of the camera calibration parameters with a given noise level shows that the calibration parameters deteriorate as the noise level increases. In particular, it was established that an increase in error contributes to an increase in the error of estimation of calibration parameters. In addition, orientation parameters (rotation and translation) are more complex and therefore more sensitive to measurement noise than other parameters.

Prombles in programming 2022; 3-4: 469-477