On-board video based system for robust road modeling
- 1 January 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
In this paper, a novel road modeling strategy is proposed, defining an accurate and robust system that operates in real-time. The strategy aims to find a trade-off between computational requirements of real systems and accuracy and robustness of the results. The basis of the strategy is an adaptive road segmentation technique which ensures robust detections of lane markings and vehicles. A multiple lane model of the road is obtained by asserting hypotheses of lanes geometry based on perspective analysis and stochastic filtering. This multiple lane approach significantly improves vehicle location compared to other video-based works, as detected vehicles are accurately located within lanes. Tests show the adaptability, robustness and accuracy of the system in daylight situations with severe illumination changes, non-homogeneous color of the pavement of the road, lane markings occlusions, shadows, variable traffic conditions, etc., performing in real-time in all cases.Keywords
This publication has 10 references indexed in Scilit:
- Stabilization of Inverse Perspective Mapping Images based on Robust Vanishing Point Estimation2007 IEEE Intelligent Vehicles Symposium, 2007
- Rear Vehicle Detection and Tracking for Lane Change Assist2007 IEEE Intelligent Vehicles Symposium, 2007
- Robust Vehicle Detection Through Multidimensional Classification for on Board Video Based SystemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Moving Obstacle Detection using Monocular VisionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Increased Accuracy Stereo Approach for 3D Lane DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- High curvature two-clothoid road model estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Lane detection and tracking using B-SnakeImage and Vision Computing, 2003
- Stochastic road shape estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An algorithm for detecting roads and obstacles in radar imagesIEEE Transactions on Vehicular Technology, 2001
- GOLD: a parallel real-time stereo vision system for generic obstacle and lane detectionIEEE Transactions on Image Processing, 1998