Home /Research /A New Method for Error Analysis of Binocular Stereo Vision System
OTHER

A New Method for Error Analysis of Binocular Stereo Vision System

Wenwen Chen, Zhibin Zhang, Hui Li, Shuaimin Hou

Year
2019
Citations
3

Abstract

BSV (Binocular Stereo Vision) system is a simple and efficient approach for robots. However, a BSV system exists to excessive errors during applications. Under the condition of fixed baseline and focal length, two error factors affecting the binocular vision system are analyzed in this paper: (i) the inclination angle of the binocular camera, and (ii) the lateral distance from an object to camera. Then, error analysis was experimentally performed on the calibration board row (X-axis direction) and column (Y-axis direction). The error is corrected by linear fitting, and it is reduced by 2% by correction. Finally, substantial experiments are carried out to verify the correctness of the theoretical.

Keywords

Computer visionArtificial intelligenceStereopsisComputer scienceCorrectnessBinocular visionRobotCamera resectioningCalibrationOrientation (vector space)

Related papers

Browse all OTHER papers