Traffic sign detection by template matching based on multi-level chain code histogram

This paper proposes a real-time system for traffic signs detection, which features of template matching based on a new feature expression for geometric shapes, namely, multi-level chain code histogram (MCCH). For all of the different shapes associated with Chinese traffic signs, e.g., circle, triangle, inverted triangle and octagon, MCCH is a robust feature expression with remarkable low computational cost, which is particularly important for real-time applications. The proposed system consists of three stages: 1) segmentation based on color; 2) MCCH extraction; 3) template matching. Extensive experiments were conducted using different datasets, demonstrating outstanding performance with regard to high processing speed and accuracy. The system robustness to rotation, scale, and illumination has also been illustrated.

[1]  Luc Van Gool,et al.  Traffic sign recognition — How far are we from the solution? , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[2]  Ari Visa,et al.  Shape recognition of irregular objects , 1996, Other Conferences.

[3]  Jordi Vitrià,et al.  Traffic Sign Recognition Using Evolutionary Adaboost Detection and Forest-ECOC Classification , 2009, IEEE Transactions on Intelligent Transportation Systems.

[4]  Zhilu Wu,et al.  A robust, coarse-to-fine traffic sign detection method , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[5]  Xiaolin Hu,et al.  Traffic sign detection by ROI extraction and histogram features-based recognition , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[6]  Trevor Darrell,et al.  The pyramid match kernel: discriminative classification with sets of image features , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

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

[8]  Rachid Belaroussi,et al.  Angle vertex and bisector geometric model for triangular road sign detection , 2009, 2009 Workshop on Applications of Computer Vision (WACV).

[9]  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).

[10]  T. Kanade,et al.  Color information for region segmentation , 1980 .

[11]  Changshui Zhang,et al.  Traffic Sign Recognition With Hinge Loss Trained Convolutional Neural Networks , 2014, IEEE Transactions on Intelligent Transportation Systems.

[12]  Mirko Meuter,et al.  A Decision Fusion and Reasoning Module for a Traffic Sign Recognition System , 2011, IEEE Transactions on Intelligent Transportation Systems.

[13]  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.

[14]  Jürgen Schmidhuber,et al.  A committee of neural networks for traffic sign classification , 2011, The 2011 International Joint Conference on Neural Networks.

[15]  Ignacio Parra,et al.  Automatic Traffic Signs and Panels Inspection System Using Computer Vision , 2011, IEEE Transactions on Intelligent Transportation Systems.

[16]  Luke Fletcher,et al.  Real-Time Speed Sign Detection Using the Radial Symmetry Detector , 2008, IEEE Transactions on Intelligent Transportation Systems.

[17]  Yann LeCun,et al.  Traffic sign recognition with multi-scale Convolutional Networks , 2011, The 2011 International Joint Conference on Neural Networks.

[18]  Saturnino Maldonado-Bascón,et al.  Goal Evaluation of Segmentation Algorithms for Traffic Sign Recognition , 2010, IEEE Transactions on Intelligent Transportation Systems.