Abstract
Traffic signs convey information, an instruction, or a warning to the driver. Recognizing these traffic signs and classifying them into their appropriate classes is an imperative task for autonomous driving assistant systems. Each country has its own traffic signs which vary much in their physical appearance, thus it is much more difficult to design classification systems that succeed. Since it is a real time problem, along with the recognition accuracy of the algorithm, its real-time performance is also much desirable. In this work, the Belgium traffic sign dataset has been used in which the traffic signs have been segmented into 62 classes. It is a subset of the European traffic sign dataset that includes traffic signs from 6 countries, namely, Germany, Belgium, France, Croatia, Netherlands, and Sweden with 162 classes. We have used the Keras library (provided by TensorFlow) to build the neural network. The model uses Softmax activation along with ReLu function. A dropout of 15% has been used to avoid over fitting. A fully connected neural network with five layers which employs Adam optimizer and cross entropy has been used in the model to train the given images. Our experimental trials, by varying different parameters, have resulted an accuracy of 91.35%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Liu, C., Li, S., Chang, F., Wang, Y.: Machine vision based traffic sign detection methods: review, analyses and perspectives. IEEE Access 7, 86578–86596 (2019)
Zhou, S., Deng, C., Piao, Z., Zhao, B.: Few-shot traffic sign recognition with clustering inductive bias and random neural network. Pattern Recogn. 100, 107160 (2020)
Liang, Z., Shao, J., Zhang, D., Gao, L.: Traffic sign detection and recognition based on pyramidal convolutional networks. Neural Comput. Appl. 32, 1–11 (2019)
Piccioli, G., De Micheli, E., Parodi, P., Campani, M.: Robust method for road sign detection and recognition. Image Vision Comput. 14(3), 209–223 (1996)
Yang, Y., Luo, H., Xu, H., Wu, F.: Towards real-time traffic sign detection and classification. IEEE Trans. Intell. Transp. Syst. 17(7), 2022–2031 (2015)
Bascón, S.M., RodrÃguez, J.A., Arroyo, S.L., Caballero, A.F., López-Ferreras, F.: An optimization on pictogram identification for the road-sign recognition task using svms. Comput. Vision Image Underst. 114(3), 373–383 (2010)
Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: Man vs computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw. 32, 323–332 (2012)
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. Vision 122(2), 246–269 (2017)
Zaklouta, F., Stanciulescu, B., Hamdoun, O.: Traffic sign classification using kd trees and random forests. In: The 2011 International Joint Conference on Neural Networks, pp. 2151–2155. IEEE, 2011
Wang, G., Ren, G., Wu, Z., Zhao, Y., Jiang, L.: A hierarchical method for traffic sign classification with support vector machines. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2013)
Jin, J., Fu, K., Zhang, C.: Traffic sign recognition with hinge loss trained convolutional neural networks. IEEE Trans. Intell. Transp. Syst. 15(5), 1991–2000 (2014)
Zhu, Z., Liang, D., Zhang, S., Huang, X., Li, B., Hu, S.: Traffic-sign detection and classification in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2110–2118 (2016)
Mathias, M., Timofte, R., Benenson, R., Van Gool, L.: Traffic sign recognition—how far are we from the solution? In: The 2013 International Joint Conference on Neural networks (IJCNN), pp. 1–8. IEEE (2013)
Ayachi, R., Afif, M., Said, Y., Atri, M.: Traffic signs detection for real-world application of an advanced driving assisting system using deep learning. Neural Process. Lett. 51(1), 837–851 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kavati, I., Babu, E.S., Cheruku, R. (2021). Real-Time Traffic Sign Recognition and Classification Using Deep Learning. In: Abraham, A., et al. Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2020). SoCPaR 2020. Advances in Intelligent Systems and Computing, vol 1383. Springer, Cham. https://doi.org/10.1007/978-3-030-73689-7_60
Download citation
DOI: https://doi.org/10.1007/978-3-030-73689-7_60
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73688-0
Online ISBN: 978-3-030-73689-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)