Driver Assistance System Based on Monocular Vision

Authors:
Yu-Min Chiang;No-Zen Hsu;Kuan-Liang Lin
Affiliations:
Department of Industrial Engineering and Management, I-Shou University, Taiwan, R.O.C. 840;Department of Industrial Engineering and Management, I-Shou University, Taiwan, R.O.C. 840;Department of Industrial Engineering and Management, I-Shou University, Taiwan, R.O.C. 840
Venue:
IEA/AIE '08 Proceedings of the 21st international conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems: New Frontiers in Applied Artificial Intelligence
Year:
2008

Citing 7
Cited 0

Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects

IEEE Transactions on Pattern Analysis and Machine Intelligence
Architectural issues on vision-based automatic vehicle guidance: the experience of the ARGO project

Real-Time Imaging
Cooperative Fusion for Multi-Obstacles Detection With Use of Stereovision and Laser Scanner

Autonomous Robots
Lane following and lane departure using a linear-parabolic model

Image and Vision Computing
Video-based lane estimation and tracking for driver assistance: survey, system, and evaluation

IEEE Transactions on Intelligent Transportation Systems
The YARF system for vision-based road following

Mathematical and Computer Modelling: An International Journal
GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The rapid growing volume of traffic has a critical affect on economic development but causes large amount of traffic accidents. The paper attempts to develop a driver assistance system based on monocular vision. Main function of the system is to find a collision-free path by lane tracking and obstacle detection. The paper proposes a lane markings detection method which is applicable to variant illumination and complex outdoor environment. The built system will issue a warning signal when it detects a lane departure of the vehicle. For obstacle detection, we use gradient information to find the feature points of the object first and estimate the distance of the object by means of triangulation. Experimental results demonstrate the effectiveness of the proposed approach.