A system-on-chip FPGA design for real-time traffic signal recognition system

Traffic signal detection has long been an important function in an advanced driver assistance system (ADAS). This paper presents a complete system design based on the techniques of blob detection, histogram of oriented gradients (HOG) and support vector machine (SVM). Blob detection is applied to detect potential candidates, and then HOG and SVM is for feature classification. A novel hardware/software co-design architecture is developed for traffic light recognition at real-time. With well-balanced workload on FPGA fabric and the on-chip ARM processor, the entire system-on-chip can achieve a processing rate of 60 fps for XGA 1024-by-768 video. The system can achieve an accuracy rate of over 90% on both red lights and green lights. The proposed system can be improved by replacing HOG with more advanced feature algorithm to obtain higher accuracy.

[1]  Kazuaki Terashima,et al.  A survey of technical trend of ADAS and autonomous driving , 2014, Proceedings of Technical Program - 2014 International Symposium on VLSI Technology, Systems and Application (VLSI-TSA).

[2]  Manuela Pereira,et al.  Detection and classification of peer-to-peer traffic: A survey , 2013, CSUR.

[3]  Hiroyuki Tanabe,et al.  Development of a Generic RGB to HSV Hardware , 2013 .

[4]  Y. Chung,et al.  A Vision-Based Traffic Light Detection System at Intersections , 2002 .

[5]  Umit Ozguner,et al.  A robust video based traffic light detection algorithm for intelligent vehicles , 2009, 2009 IEEE Intelligent Vehicles Symposium.

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

[7]  Xinming Huang,et al.  A pipeline architecture for traffic sign classification on an FPGA , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[8]  Thomas B. Moeslund,et al.  Vision-Based Traffic Sign Detection and Analysis for Intelligent Driver Assistance Systems: Perspectives and Survey , 2012, IEEE Transactions on Intelligent Transportation Systems.

[9]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[10]  M. Omachi,et al.  Traffic light detection with color and edge information , 2009, 2009 2nd IEEE International Conference on Computer Science and Information Technology.