Two Novel Methods for Multiple Kinect v2 Sensor Calibration

Sumit Hazra, Manasa Pisipati, Amrit Puhan, Anup Nandy, Rafal Scherer

Abstract: Camera calibration is an essential step for measuring an instrument’s accuracy by using its parameters. In this paper, we propose two methods for calibrating eight Kinect v2.0 sensors, namely, pairwise and simultaneous single-camera calibration. In the first method, an experimental setup is managed so that the eight Kinect cameras can view a 3D object on a treadmill in consecutive pairs. The novelty of this method infers pairwise calibration of eight Kinects using six steps, specifically: precalibration process, acquiring images from Kinect, exporting the parameters, generation of independent live point clouds, feeding exported parameters for point cloud matching and ensuring successful calibration through merged point clouds. In the second method, a novel octagonal model is developed to calibrate each of the eight cameras on the same experimental setup. We obtain an overall mean reprojection error of 1.37 pixels and 0.42 pixels for the first method and second method, respectively. The smallest reprojection error for the first method is reported to be 0.63 pixels and 0.27 pixels for the second method. The efficiency of the proposed methods is compared with the state-of-art techniques using the root mean square and the reprojection error metrics. We observed that the proposed methods outperform the existing techniques.