The Method of Real-Time Distance Measurement Based on Monocular Vision

Abstract

The paper proposes a real-time monocular vision-based algorithm that can be applied to robot tracking. Unlike the models used in other papers, the model used in this paper is suitable for the condition that the camera is looking up. There is a common deficiency existing in previous models that the target point is constrained to some areas of the camera field. To overcome the shortcomings, the camera field of view is divided into three regions which also reduces the computational complexity. The intrinsic parameters of camera can be obtained by calibration. Pitch angle rectification, together with camera calibration, improves the ranging accuracy.