Real-Time Lane Departure Warning System on a Lower Resource Platform

Real-time lane detection and tracking is one of the most reliable approaches to prevent road accidents by alarming the driver of the excessive lane changes. This paper addresses the problem of correct lane detection and tracking of the current lane of a vehicle in real-time. We propose a solution that is computationally efficient and performs better than previous approaches. The proposed algorithm is based on detecting straight lines from the captured road image, marking a region of interest, filtering road marks and detecting the current lane by using the information gathered. This information is obtained by analyzing the geometric shape of the lane boundaries and the convergence point of the lane markers. To provide a feasible solution, the only sensing modality on which the algorithm depends on is the camera of an off-the-shelf mobile device. The proposed algorithm has a higher average accuracy of 96.87% when tested on the Caltech Lanes Dataset as opposed to the state-of-the-art technology for lane detection. The algorithm operates on three frames per second on a 2.26 GHz quad-core processor of a mobile device with an image resolution of 640×480 pixels. It is tested and verified under various visibility and road conditions.

[1]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[3]  Cuneyt Akinlar,et al.  Video-Based Lane Detection Using a Fast Vanishing Point Estimation Method , 2012, 2012 IEEE International Symposium on Multimedia.

[4]  Dinggang Shen,et al.  Lane detection and tracking using B-Snake , 2004, Image Vis. Comput..

[5]  Mohamed Aly,et al.  Real time detection of lane markers in urban streets , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[6]  Shuai Di,et al.  Lane Detection Based on Machine Learning Algorithm , 2014 .

[7]  Silvio Savarese,et al.  Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection , 2016, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[8]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[9]  Christopher M. Kreucher,et al.  LANA: a lane extraction algorithm that uses frequency domain features , 1999, IEEE Trans. Robotics Autom..

[10]  Rama Chellappa,et al.  A Learning Approach Towards Detection and Tracking of Lane Markings , 2012, IEEE Transactions on Intelligent Transportation Systems.

[11]  Dibo Hou,et al.  A Novel Lane Detection Algorithm Based on Support Vector Machine , 2005 .

[12]  C. Kreucher,et al.  A DRIVER WARNING SYSTEM BASED ON THE LOIS LANE DETECTION ALGORITHM , 1998 .

[13]  Ronen Lerner,et al.  Recent progress in road and lane detection: a survey , 2012, Machine Vision and Applications.

[14]  Fernando A. Mujica,et al.  An Empirical Evaluation of Deep Learning on Highway Driving , 2015, ArXiv.

[15]  Steven C. H. Hoi,et al.  Face Detection using Deep Learning: An Improved Faster RCNN Approach , 2017, Neurocomputing.

[16]  Massimo Bertozzi,et al.  GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection , 1998, IEEE Trans. Image Process..

[17]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[18]  Li Sha Sha.  The Research of the Lane Detection Algorithm Base on Vision Sensor , 2013 .

[19]  Sheroz Khan,et al.  A Hyperbola-Pair Based Lane Detection System for Vehicle Guidance , 2010 .

[20]  S. Khan,et al.  Real time lane detection for autonomous vehicles , 2008, 2008 International Conference on Computer and Communication Engineering.

[21]  Rafael Grompone von Gioi,et al.  LSD: a Line Segment Detector , 2012, Image Process. Line.