Real-time traffic light detection using color density

Autonomous driving cars have become a trend in the vehicle industry. Numerous driver assistance systems (DAS) have been introduced to support these automatic cars. Among these DAS methods, traffic light detection (TLD) plays a significant role. This paper proposes a method to detect traffic lights (TLs) using color density identification (CD). The system receives an RGB image as an input and produces the traffic light state (red, yellow, green or no Signal) of the scene. The algorithm has three stages: clustering, filtering, and state identification. Experiments were conducted on both highways and in urban areas in Korea. The results achieved around 95% accuracy on highways and 85% in urban areas. Furthermore, the proposed algorithm is able to run in real-time with 60FPS.

[1]  Zheng Liu,et al.  Traffic light recognition in varying illumination using deep learning and saliency map , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[2]  大町 真一郎,et al.  Traffic Light Detection with Color and Edge Information , 2009 .

[3]  Zheng Liu,et al.  Saliency Map Generation by the Convolutional Neural Network for Real-Time Traffic Light Detection Using Template Matching , 2015, IEEE Transactions on Computational Imaging.

[4]  Gang Tao,et al.  The recognition and tracking of traffic lights based on color segmentation and CAMSHIFT for intelligent vehicles , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[5]  Miguel Angel Ferrer-Ballester,et al.  A Survey on Traffic Light Detection , 2015, ICIAP Workshops.

[6]  Mohan M. Trivedi,et al.  Vision for Looking at Traffic Lights: Issues, Survey, and Perspectives , 2016, IEEE Transactions on Intelligent Transportation Systems.

[7]  Fawzi Nashashibi,et al.  Real time visual traffic lights recognition based on Spot Light Detection and adaptive traffic lights templates , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[8]  Fawzi Nashashibi,et al.  Traffic light recognition using image processing compared to learning processes , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Sebastian Thrun,et al.  Traffic light mapping, localization, and state detection for autonomous vehicles , 2011, 2011 IEEE International Conference on Robotics and Automation.

[10]  Ju H. Park,et al.  Night-Time Traffic Light Detection Based On SVM with Geometric Moment Features , 2013 .

[11]  Chris Urmson,et al.  Traffic light mapping and detection , 2011, 2011 IEEE International Conference on Robotics and Automation.

[12]  Evangelos Dermatas,et al.  Traffic Lights Detection in Adverse Conditions using Color, Symmetry and Spatiotemporal Information , 2012, VISAPP.