The study of stereo vision technique for the autonomous vehicle

Pei Li; Xi Wang; Jiang-feng Wang

doi:10.1117/12.2197837

22 August 2015 The study of stereo vision technique for the autonomous vehicle

Pei Li, Xi Wang, Jiang-feng Wang

Proceedings Volume 9656, International Symposium on Photonics and Optoelectronics 2015; 96560Y (2015) https://doi.org/10.1117/12.2197837
Event: International Symposium on Photonics and Optics, 2015, Shanghai, China

Abstract

The stereo vision technology by two or more cameras could recovery 3D information of the field of view. This technology can effectively help the autonomous navigation system of unmanned vehicle to judge the pavement conditions within the field of view, and to measure the obstacles on the road. In this paper, the stereo vision technology in measuring the avoidance of the autonomous vehicle is studied and the key techniques are analyzed and discussed. The system hardware of the system is built and the software is debugged, and finally the measurement effect is explained by the measured data. Experiments show that the 3D reconstruction, within the field of view, can be rebuilt by the stereo vision technology effectively, and provide the basis for pavement condition judgment. Compared with unmanned vehicle navigation radar used in measuring system, the stereo vision system has the advantages of low cost, distance and so on, it has a good application prospect.

Citation Download Citation

Pei Li, Xi Wang, and Jiang-feng Wang "The study of stereo vision technique for the autonomous vehicle", Proc. SPIE 9656, International Symposium on Photonics and Optoelectronics 2015, 96560Y (22 August 2015); https://doi.org/10.1117/12.2197837

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available