Effective Road Lane Detection and Tracking Method Using Line Segment Detector

In this paper, we present an effective lane detection and tracking system using a fusion of Line Segment Detector (LSD) and Kalman filter. We employ line segment as low-level features to detect lane markings on structured road. Firstly, we segment the road surface region through adaptive method, and then a different grayscale method is used to achieve strong contrast than the previous studies. Secondly, we apply LSD algorithm on them and remove incorrect line segments in an adaptive way. Finally, two Kalman filters are used to track the virtual boundary points, which also be applied to predict the next processed region of interests (ROIs). Meanwhile, real-time performance can be better achieved. Experiments are conducted on several open datasets which are collected in real-world scenarios, such as Caltech dataset. The results demonstrate the efficiency and the robustness of our proposed method.

[1]  Dong Hwan Kim,et al.  A Robust Lane Detection Method Based on Vanishing Point Estimation Using the Relevance of Line Segments , 2017, IEEE Transactions on Intelligent Transportation Systems.

[2]  Xu Huang,et al.  Extraction of lane markings using orientation and vanishing point constraints in structured road scenes , 2014, Int. J. Comput. Math..

[3]  Kwanghoon Sohn,et al.  Gradient-Enhancing Conversion for Illumination-Robust Lane Detection , 2013, IEEE Transactions on Intelligent Transportation Systems.

[4]  Monson H. Hayes,et al.  Robust lane detection and tracking with ransac and Kalman filter , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[5]  Dacheng Tao,et al.  Deep Neural Network for Structural Prediction and Lane Detection in Traffic Scene , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[6]  Antonio M. López,et al.  Road Detection Based on Illuminant Invariance , 2011, IEEE Transactions on Intelligent Transportation Systems.

[7]  Qingquan Li,et al.  A Sensor-Fusion Drivable-Region and Lane-Detection System for Autonomous Vehicle Navigation in Challenging Road Scenarios , 2014, IEEE Transactions on Vehicular Technology.

[8]  Youngjoon Han,et al.  A real-time system of lane detection and tracking based on optimized RANSAC B-spline fitting , 2013, RACS.

[9]  Azzedine Boukerche,et al.  Lane detection and tracking system based on the MSER algorithm, hough transform and kalman filter , 2014, MSWiM '14.

[10]  Rafael Grompone von Gioi,et al.  LSD: A Fast Line Segment Detector with a False Detection Control , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Bin Dai,et al.  Vision-based long-distance lane perception and front vehicle location for full autonomous vehicles on highway roads , 2012 .

[12]  Qingxuan Jia,et al.  Road lane modeling based on RANSAC algorithm and hyperbolic model , 2016, 2016 3rd International Conference on Systems and Informatics (ICSAI).

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

[14]  Azzedine Boukerche,et al.  A real-time lane marking localization, tracking and communication system , 2016, Comput. Commun..

[15]  Kang Ryoung Park,et al.  Road Lane Detection by Discriminating Dashed and Solid Road Lanes Using a Visible Light Camera Sensor , 2016, Sensors.

[16]  Huifang Li,et al.  Study on a robust approach of lane departure warning algrithm , 2010, 2010 2nd International Conference on Signal Processing Systems.

[17]  Nanning Zheng,et al.  Springrobot: a prototype autonomous vehicle and its algorithms for lane detection , 2004, IEEE Transactions on Intelligent Transportation Systems.

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

[19]  Kwanghoon Sohn,et al.  Real-time illumination invariant lane detection for lane departure warning system , 2015, Expert Syst. Appl..