Optoelectronics Letters

, Volume 13, Issue 6, pp 476–480 | Cite as

Traffic sign recognition based on deep convolutional neural network

  • Shi-hao Yin (尹世豪)
  • Ji-cai Deng (邓计才)
  • Da-wei Zhang (张大伟)
  • Jing-yuan Du (杜靖远)
Article
First Online:
Received:
  • 108 Downloads

Abstract

Traffic sign recognition (TSR) is an important component of automated driving systems. It is a rather challenging task to design a high-performance classifier for the TSR system. In this paper, we propose a new method for TSR system based on deep convolutional neural network. In order to enhance the expression of the network, a novel structure (dubbed block-layer below) which combines network-in-network and residual connection is designed. Our network has 10 layers with parameters (block-layer seen as a single layer): the first seven are alternate convolutional layers and block-layers, and the remaining three are fully-connected layers. We train our TSR network on the German traffic sign recognition benchmark (GTSRB) dataset. To reduce overfitting, we perform data augmentation on the training images and employ a regularization method named “dropout”. The activation function we employ in our network adopts scaled exponential linear units (SELUs), which can induce self-normalizing properties. To speed up the training, we use an efficient GPU to accelerate the convolutional operation. On the test dataset of GTSRB, we achieve the accuracy rate of 99.67%, exceeding the state-of-the-art results.

Document code

A 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Nguwi Y.Y. and Kouzani A.Z., Neural Computing and Applications 17, 265 (2008).CrossRefGoogle Scholar
  2. [2]
    Mogelmose A., Trivedi M.M. and Moeslund T.B., IEEE Transactions on Intelligent Transportation Systems 13, 1484 (2012).CrossRefGoogle Scholar
  3. [3]
    Lu X., Wang Y., Zhou X., Zhang Z. and Ling Z., IEEE Transactions on Intelligent Transportation Systems 18, 960 (2017).CrossRefGoogle Scholar
  4. [4]
    Lim K.H., Seng K.P. and Ang L.M., Intra Color-shape Classification for Traffic Sign Recognition, 2010 International Computer Symposium (ICS2010), 642 (2010).Google Scholar
  5. [5]
    Madani A. and Yusof R., Neural Computing and Applications, 1 (2017).Google Scholar
  6. [6]
    Lau M.M., Lim K.H. and Gopalai A.A., Malaysia Traffic Sign Recognition with Convolutional Neural Network, 2015 IEEE International Conference on Digital Signal Processing (DSP), 1006 (2015).Google Scholar
  7. [7]
    Glorot X., Bordes A. and Bengio Y., Deep Sparse Rectifier Neural Networks, Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, 315 (2011).Google Scholar
  8. [8]
    Maas A.L., Hannun A.Y. and Ng A.Y., Rectifier Nonlinearities Improve Neural Network Acoustic Models, Proceedings of the 30th International Conference on Machine Learning (ICML13) 28, 6 (2013).Google Scholar
  9. [9]
    Xu B., Wang N., Chen T. and Li M., Empirical Evaluation of Rectified Activations in Convolutional Network, arXiv preprint arXiv:1505.00853 (2015).Google Scholar
  10. [10]
    Klambauer G., Unterthiner T., Mayr A. and Hochreiter S., Self-Normalizing Neural Networks, arXiv preprint arXiv:1706.02515 (2017).Google Scholar
  11. [11]
    LeCun Y., Bottou L., Bengio Y. and Haffner P., Proceedings of the IEEE 86, 2278 (1998).CrossRefGoogle Scholar
  12. [12]
    Krizhevsky A., Sutskever I. and Hinton G.E., Advances in Neural Information Processing Systems 25, 1097 (2012).Google Scholar
  13. [13]
    Simonyan K. and Zisserman A., Very Deep Convolutional Networks for Large-scale Image Recognition, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.Google Scholar
  14. [14]
    Lin M., Chen Q. and Yan S., Network in Network, Proc. ICLR, 2014.Google Scholar
  15. [15]
    Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhoucke V. and Rabinovich A., Going Deeper with Convolutions, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1 (2015).Google Scholar
  16. [16]
    He K., Zhang X., Ren S. and Sun J., Deep Residual Learning for Image Recognition, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770 (2016).Google Scholar
  17. [17]
    Szegedy C., Ioffe S., Vanhoucke V. and Alemi A.A., Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, AAAI, 4278 (2017).Google Scholar
  18. [18]
    Stallkamp J., Schlipsing M., Salmen J. and Igel C., Neural Networks 32, 323 (2012).CrossRefGoogle Scholar
  19. [19]
    Abadi M., Agarwal A., Barham P. and Brevdo E., Tensorflow: Large-scale Machine Learning on Heterogeneous Distributed Systems, arXiv preprint arXiv:1603.04467 (2016).Google Scholar
  20. [20]
    Kingma D. and Ba J., Adam: A Method for Stochastic Optimization, arXiv preprint arXiv:1412.6980 (2014).Google Scholar
  21. [21]
    Hinton G.E., Srivastava N., Krizhevsky A., Sutskever I. and Salakhutdinov R.R., Improving Neural Networks by Preventing Co-adaptation of Feature Detectors, arXiv preprint arXiv:1207.0580 (2012).MATHGoogle Scholar
  22. [22]
    Glorot X. and Bengio Y., Understanding the Difficulty of Training Deep Feedforward Neural Networks, Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 249 (2010).Google Scholar

Copyright information

© Tianjin University of Technology and Springer-Verlag GmbH Germany, part of Springer Nature 2017

Authors and Affiliations

  • Shi-hao Yin (尹世豪)
    • 1
  • Ji-cai Deng (邓计才)
    • 1
  • Da-wei Zhang (张大伟)
    • 1
  • Jing-yuan Du (杜靖远)
    • 1
  1. 1.School of Information EngineeringZhengzhou UniversityZhengzhouChina

Personalised recommendations