Wearable Guide System for Obstacle Avoidance Based on Stereo Computer Vision

DOI

10.2991/icmse-15.2015.329How to use a DOI?

Keywords

computer vision, image processing, random sample consensus (RANSAC), blind guide, wearable

Abstract

ETA (Electronic Travel Aids) is an important method to guide the visual impaired to navigate, in which avoiding the obstacle effectively is the most essential content. A novel wearable ETA system and corresponding algorithms for obstacle avoidance based on binocular stereo computer vision were proposed in this paper. By utilizing RANSAC(Random Sample Consensus) algorithm, the equation of pavement plane is extracted from the images collected by the binocular cameras, and the obstacles are distinguished according to their height relative to the pavement plane, and obstacles coordinates relative to the blind in the world coordinate system are calculated and determined. This presented appliance can provide the information of walkable pavement and safe direction where there is no obstacle. The algorithms were verified by using the experimental prototype. The results show that it can detect obstacles effectively and stably with strong robustness, which provides good foundation for developing blind guide equipment further.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jiexuan Feng
AU  - Tong Wei
PY  - 2015/12
DA  - 2015/12
TI  - Wearable Guide System for Obstacle Avoidance Based on Stereo Computer Vision
BT  - Proceedings of the 2015 6th International Conference on Manufacturing Science and Engineering
PB  - Atlantis Press
SP  - 1811
EP  - 1817
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmse-15.2015.329
DO  - 10.2991/icmse-15.2015.329
ID  - Feng2015/12
ER  -