Distance Measurement in Visual Navigation of Monocular Autonomous Robots

摘要

Aiming at the drawbacks in traditional visual distance-measurements for autonomous robots,a monocular camera calibration technique based on B-dual-spacial geometry is brought forward and applied to visual distance-measurement of monocular autonomous robots.Compared with OpenCV's calibration technique,the new calibration method can compute camera's inner parameters more veraciously,and it can obviously reduce the total error in monocular visual distance-measurement. Simultaneously,the method combines real-time distance measurement with automatic detection for objective vehicles by incorporating the automatic extration algorithm of moving objects.The validity of the presented method is verified by the actual measurements and contrastive experimentations.