Lane Departure Identification for Advanced Driver Assistance
- 8 September 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 16 (15249050), 1-9
- https://doi.org/10.1109/tits.2014.2347400
Abstract
In this paper, a technique for the identification of the unwanted lane departure of a traveling vehicle on a road is proposed. A piecewise linear stretching function (PLSF) is used to improve the contrast level of the region of interest (ROI). Lane markings on the road are detected by dividing the ROI into two subregions and applying the Hough transform in each subregion independently. This segmentation approach improves the computational time required for lane detection. For lane departure identification, a distance-based departure measure is computed at each frame, and a necessary warning message is issued to the driver when such measure exceeds a threshold. The novelty of the proposed algorithm is the identification of the lane departure only using three lane-related parameters based on the Euclidean distance transform to estimate the departure measure. The use of the Euclidean distance transform in combination with the PLSF keeps the false alarm around 3% and the lane detection rate above 97% under various lighting conditions. Experimental results indicate that the proposed system can detect lane boundaries in the presence of several image artifacts, such as lighting changes, poor lane markings, and occlusions by a vehicle, and it issues an accurate lane departure warning in a short time interval. The proposed technique shows the efficiency with some real video sequences.Keywords
This publication has 25 references indexed in Scilit:
- Robust Lane Detection in Shadows and Low Illumination Conditions using Local Gradient FeaturesOpen Journal of Applied Sciences, 2013
- A Robust Vision-based Lane Boundaries Detection Approach for Intelligent VehiclesInformation Technology Journal, 2012
- Applying fuzzy method to vision-based lane detection and departure warning systemExpert Systems with Applications, 2010
- A lane-departure identification based on LBPE, Hough transform, and linear regressionComputer Vision and Image Understanding, 2005
- Lane following and lane departure using a linear-parabolic modelImage and Vision Computing, 2005
- Lane detection and tracking using B-SnakeImage and Vision Computing, 2003
- Visually guided manipulation tasksRobotics and Autonomous Systems, 2002
- Invariant characterisation of the Hough transform for pose estimation of arbitrary shapesPattern Recognition, 2002
- A Machine Vision System for Lane-Departure DetectionComputer Vision and Image Understanding, 2002
- Use of the Hough transformation to detect lines and curves in picturesCommunications of the ACM, 1972