Paper
6 September 2019 Monocular ranging system based on space geometry
Ye Qian, Qian Chen, Wenguang Yang, Fan Wang, Weixian Qian, Zhixiu Li
Author Affiliations +
Abstract
Nowadays, with the boosting incomes and rapid development of science, car has become one of the most important transport vehicle. Driving environment and safety has attracted much attention in the automotive design field. Therefore, it is extremely urgent to develop the intelligent and reliable safety technologies such as vehicle active collision warning system. There are lots of studies focused on the critical research of machine vision ranging technology, however, the installation error of binocular ranging may result in inaccurate measurement accuracy. In this study, we use an improved monocular ranging to measure distance. The traditional monocular ranging models based on the principle of pinhole imaging, static image ranging model and etc. Most of the models require specific prior information of the vehicle, the applicable conditions of the model may be too idealistic and not applicable to general situations. In order to solve the contradiction, our research proposes a creative monocular ranging model to measure the distance between two vehicles. The model is based on the camera space projection relationship taking the factors of the camera's pitch angle into account. Our model has universal application significance using the simple implementation method with residual method. Based on the model, we amended the camera's pitch angle after the experiments. Meanwhile, the accuracy of the model is guaranteed by analyzing the factors affecting the accuracy of the range. The experimental results show that the error is controlled within 10%, which can meet the accuracy requirements of the system.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ye Qian, Qian Chen, Wenguang Yang, Fan Wang, Weixian Qian, and Zhixiu Li "Monocular ranging system based on space geometry", Proc. SPIE 11136, Optics and Photonics for Information Processing XIII, 111360Y (6 September 2019); https://doi.org/10.1117/12.2525418
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Cameras

Ranging

Distance measurement

Imaging systems

Visual process modeling

Data modeling

Machine vision

Back to Top