Subset-based stereo calibration method optimizing triangulation accuracy

Abstract

Calibration of vision systems is essential for performing measurement in real world coordinates. For stereo vision, one performs stereo calibration, the results of which are used for 3D reconstruction of points imaged in the two cameras. A common and flexible technique for such calibration is based on collection and processing pairs of images of a planar chessboard calibration pattern. The inherent weakness of this approach lies in its reliance on the random nature of data collection, which might lead to better or worse calibration results, depending on the collected set of image pairs. In this paper, a subset-based approach to camera and stereo calibration, along with its implementation based on OpenCV, is presented. It utilizes a series of calibration runs based on randomly chosen subsets from the global set of image pairs, with subsequent evaluation of metrics based on triangulating the features in each image pair. The proposed method is evaluated on a collected set of chessboard image pairs obtained with two identical industrial cameras. To highlight the capabilities of the method to select the best-performing calibration parameters, a principal component analysis and clustering of the transformed data was performed, based on the set of metric measurements per each calibration run.

Dynamic Validation of Calibration Accuracy and Structural Robustness of a Multi-Sensor Mobile Robot

“…According to Equation ( 14), the coordinates of S 2 in the image space coordinate system of camera 1 are (X s21 , Y s21 , Z s21 ), while in the image space coordinate system of camera 1, the coordinates of p ′ are (x 1 , y 1 , − f ). As the coplanarity of points S 2 and p ′ with any point on epipolar line l 11 , in the image space coordinate system of camera 1, the corresponding plane equation can be expressed as Equation (15).…”

“…This is used to assess the precision and accuracy of the calibration parameters by analyzing the differences between the actual projected positions and the theoretically expected positions, as well as the differences in the longitudinal coordinates between the homonymous points, respectively. For example, Semeniuta [ 15 ] evaluated the quality of calibrated camera parameters by assessing the performance of stereo triangulation. Projection error refers to the discrepancy between the actual 2D pixel coordinates and the estimated 2D pixel points.…”

Forward projection multilayer refraction model for underwater camera calibration

“…Notice that the initial values of fx, fy are directly calculated by the ratio between the focal length and the pixel size in the horizontal and vertical directions, respectively. To ensure the solution accuracy, the effect of radial distortion and tangential distortion is taken into consideration and the lens third-order distortion model 26 is employed. Due to the strong nonlinearity introduced by refraction, the Levenberg–Marquardt algorithm 27 is utilized for further nonlinear iterative optimization.…”