Abstract
Traffic sign recognition is an important research area in intelligent transportation, which is especially important in autopilot system. Convolutional Neural Network (CNN) is the main research method of traffic sign recognition. However, the convolution neural network is easily affected by the spatial diversity of the image. With regard to this, in this paper, a multi-column spatial transformer convolution neural network named MC-STCNN is proposed to solve the problem when Convolutional Neural Network (CNN) can’t adapt to the spatial diversity of the image very well. The MC-STCNN network consisted of CNN and STN is formed by training pictures of different sizes. It can be well adapted to the spatial diversity and the images input of different sizes. It achieves an accuracy of 99.75% on GTSRB traffic sign recognition, exceeding the current highest accuracy of 99.65%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhao, G.F.: Traffic Sign Recognition Based on Machine Learning. Electronic University Of Science & Technology Of Hangzhou (2015)
Akatsuka, H., Imai, S.: Road signposts recognition system. In: The International Conference on SAE Vehicle Highway Infrastructure: Safety Compatibility, pp. 189–196 (1987)
Kellmeyer, D.L., Zwahlen, H.T.: Detection of highway warning signs in natural video images using color image processing and neural networks. In: IEEE World Congress on Computational Intelligence, vol. 7, pp. 4226–4231 (1994)
Ren, F.X., Huang, J.S., Jiang, R.Y., Klette, R.: General traffic sign recognition by feature matching. In: Proceedings of the 24th International Conference Image and Vision Computing, pp. 409–414 (2009)
Prisacariu, V.A., Timofte, R., Zimmermann, K., Reid, I., Van Gool, L.J.: Integrating object detection with 3D tracking towards a better driver assistance system. In: 20th International Conference on Pattern Recognition (ICPR), pp. 3344–3347 (2010)
Liu, B., Liu, H., Luo, X., Sun, F.C.: Speed limit sign recognition using log-polar mapping and visual codebook. In: 9th International Symposium on Neural Networks (ISNN), pp. 247–256 (2012)
Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: The German traffic sign recognition benchmark: a multi-class classification competition. In: IEEE International Joint Conference on Neural Networks, pp. 1453–1460 (2011)
Ciresan, D., Meier, U., Masci, J., Schmidhuber, J.: Multi-column deep neural network for traffic sign classification. Neural Netw. 32, 333–338 (2012)
Jin, J.Q., Fu, K., Zhang, C.S.: Traffic sign recognition with hinge loss trained convolutional neural networks. IEEE Trans. Intell. Transp. Syst. 15(5), 1991–2000 (2014)
Huang, Z.Y., Yu, Y.L., Gu, J.S.: An efficient method for traffic sign recognition based on extreme learning machine. IEEE Trans. Cybern. 47(4), 920–933 (2016)
Aghdam, H.H., Heravi, E.J., Puig, D.: A practical and highly optimized convolutional neural network for classifying traffic signs in real-time. Int. J. Comput. Vis. 122(2), 246–269 (2017)
Jaderberg, M., Simonvan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Advances in Neural Information Processing Systems (2015)
Mishkin, D., Sergievskiy, N., Matas, J.: Systematic evaluation of CNN advances on the ImageNet. In: arXiv (2016)
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant 61571372, 61672436, 61372139 and 61601376, the Natural Science Foundation of Chongqing under Grant cstc2017jcyjBX0050, and the Fundamental Research Funds for the Central Universities under Grant XDJK2017A005 and XDJK2016A001.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Zhang, J., Duan, S., Wang, L., Zou, X. (2018). Multi-column Spatial Transformer Convolution Neural Network for Traffic Sign Recognition. In: Huang, T., Lv, J., Sun, C., Tuzikov, A. (eds) Advances in Neural Networks – ISNN 2018. ISNN 2018. Lecture Notes in Computer Science(), vol 10878. Springer, Cham. https://doi.org/10.1007/978-3-319-92537-0_68
Download citation
DOI: https://doi.org/10.1007/978-3-319-92537-0_68
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92536-3
Online ISBN: 978-3-319-92537-0
eBook Packages: Computer ScienceComputer Science (R0)