Traffic Sign Detection and Recognition System for Autonomous RC Cars

Traffic signs play an important role to regulate daily traffic by providing necessary information to the drivers. For unmanned driving systems, real time and robust detection and recognition of traffic signs is one of the main concerns. Therefore, a traffic sign detection and recognition system for autonomous radio controlled cars is proposed. In this work, traditional image processing methods and deep neural networks techniques are combined. First, the online video is streamed from the car camera and the input frame region of interest is detected. Secondly, a convolutional neural network is used to recognize these candidate images. Experimental results show that the proposed system works efficiently up to %87.36 of images. However, calibration is needed for image processing techniques for various environments.

[1]  Francisco López-Ferreras,et al.  Road-Sign Detection and Recognition Based on Support Vector Machines , 2007, IEEE Transactions on Intelligent Transportation Systems.

[2]  Johannes Stallkamp,et al.  Detection of traffic signs in real-world images: The German traffic sign detection benchmark , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[3]  Tao Jin,et al.  Robust and Real-Time Traffic Lights Recognition in Complex Urban Environments , 2011, Int. J. Comput. Intell. Syst..

[4]  Lijuan Liu,et al.  A novel traffic sign detection method via color segmentation and robust shape matching , 2015, Neurocomputing.

[5]  Johannes Stallkamp,et al.  The German Traffic Sign Recognition Benchmark: A multi-class classification competition , 2011, The 2011 International Joint Conference on Neural Networks.

[6]  K. Jo,et al.  Automatic Detection and Recognition of Traffic Signs using Geometric Structure Analysis , 2006, 2006 SICE-ICASE International Joint Conference.

[7]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Mohak Shah,et al.  Comparative Study of Deep Learning Software Frameworks , 2015, 1511.06435.

[9]  M. Benallal,et al.  Real-time color segmentation of road signs , 2003, CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436).

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.