CNN based Traffic Sign Classification using Adam Optimizer

An automatic detection and classification of traffic signs is an important task in Advanced Driver Assistance System (ADAS).Convolutional Neural Network (CNN) has surpassed the human performance and shown the great success in detection and classification of traffic signs. The paper proposes an approach based on the deep convolutional network for classifying traffic signs. The Belgium traffic sign dataset (BTSD) is used for evaluation and experiment results shows that the proposed method can achieve competitive results compared with state of the art approaches. Different activations and optimizers are used to evaluate the performance of proposed architecture and it is observed that Adam (Adaptive Moment Estimation) optimizer and softmax activation performs well.

[1]  Wenyu Liu,et al.  Traffic sign detection and recognition using fully convolutional network guided proposals , 2016, Neurocomputing.

[2]  Cui-Hua Li,et al.  Unifying visual saliency with HOG feature learning for traffic sign detection , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[3]  C. Bahlmann,et al.  Real-time recognition of U.S. speed signs , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[4]  Chandan Chakraborty,et al.  Batch Normalization in Convolutional Neural Networks — A comparative study with CIFAR-10 data , 2018, 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT).

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

[6]  Xiaohui Liu,et al.  Real-time traffic sign recognition from video by class-specific discriminative features , 2010, Pattern Recognit..

[7]  Sven Behnke,et al.  Hierarchical Neural Networks for Image Interpretation (Lecture Notes in Computer Science) , 2003 .

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

[9]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[10]  Domenec Puig,et al.  A practical approach for detection and classification of traffic signs using Convolutional Neural Networks , 2016, Robotics Auton. Syst..

[11]  Luis Moreno,et al.  Road traffic sign detection and classification , 1997, IEEE Trans. Ind. Electron..

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

[13]  Cuneyt Akinlar,et al.  On circular traffic sign detection and recognition , 2016, Expert Syst. Appl..

[14]  Luc Van Gool,et al.  Multi-view traffic sign detection, recognition, and 3D localisation , 2014, Machine Vision and Applications.

[15]  David Shaw,et al.  Regular polygon detection , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Bo Li,et al.  Data Dropout: Optimizing Training Data for Convolutional Neural Networks , 2018, 2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI).

[18]  Sven Behnke,et al.  Hierarchical Neural Networks for Image Interpretation , 2003, Lecture Notes in Computer Science.

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

[20]  Jürgen Schmidhuber,et al.  Multi-column deep neural network for traffic sign classification , 2012, Neural Networks.

[21]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.