Abstract
Traffic signs support road safety and managing the flow of traffic, hence are an integral part of any vision system for autonomous driving. While the use of deep learning is well-known in traffic signs classification due to the high accuracy results obtained using convolutional neural networks (CNNs) (state of the art is 99.46%), little is known about binarized neural networks (BNNs). Compared to CNNs, BNNs reduce the model size and simplify convolution operations and have shown promising results in computationally limited and energy-constrained devices which appear in the context of autonomous driving.
This work presents a bottom-up approach for architecturing BNNs by studying characteristics of the constituent layers. These constituent layers (binarized convolutional layers, max pooling, batch normalization, fully connected layers) are studied in various combinations and with different values of kernel size, number of filters and of neurons by using the German Traffic Sign Recognition Benchmark (GTSRB) for training. As a result, we propose BNNs architectures which achieve an accuracy of more than \(90\%\) for GTSRB (the maximum is \(96.45\%\)) and an average greater than \(80\%\) (the maximum is \(88.99\%\)) considering also the Belgian and Chinese datasets for testing. The number of parameters of these architectures varies from 100k to less than 2M. The accompanying material of this paper is publicly available at https://github.com/apostovan21/BinarizedNeuralNetwork.
This work was supported by a grant of the Romanian National Authority for Scientific Research and Innovation, CNCS/CCCDI - UEFISCDI, project number PN-III-P1-1.1-TE-2021-0676, within PNCDI III.
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
Belgian Traffic Sign Database. www.kaggle.com/datasets/shazaelmorsh/trafficsigns. Accessed March 25 2023
Benchmarks of the 3rd International Verification of Neural Networks Competition (VNN-COMP’22). www.github.com/ChristopherBrix/vnncomp2022_benchmarks. Accessed Feb 22 2023
Chinese Traffic Sign Database. www.kaggle.com/datasets/dmitryyemelyanov/chinese-traffic-signs. Accessed March 25 2023
German Traffic Sign Recognition Benchmark. www.kaggle.com/datasets/meowmeowmeowmeowmeow/gtsrb-german-traffic-sign?datasetId=82373 &language=Python. Accessed March 25 2023
Amir, G., Wu, H., Barrett, C., Katz, G.: An SMT-based approach for verifying binarized neural networks. In: TACAS 2021. LNCS, vol. 12652, pp. 203–222. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72013-1_11
Chen, E.H., Röthig, P., Zeisler, J., Burschka, D.: Investigating low level features in CNN for traffic sign detection and recognition. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 325–332. IEEE (2019)
Chen, E.H., et al.: Investigating Binary Neural Networks for Traffic Sign Detection and Recognition. In: 2021 IEEE Intelligent Vehicles Symposium (IV), pp. 1400–1405. IEEE (2021)
Ciregan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3642–3649. IEEE (2012)
Courbariaux, M., Bengio, Y., David, J.P.: BinaryConnect: Training deep neural networks with binary weights during propagations. Adv. Neural Inform. Process. Syst. 28 (2015)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. Ieee (2009)
Geiger, L., Team, P.: Larq: an open-source library for training binarized neural networks. J. Open Source Softw. 5(45), 1746 (2020)
Guo, X., Zhou, Z., Zhang, Y., Katz, G., Zhang, M.: OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks. arXiv preprint arXiv:2301.11912 (2023)
Houben, S., Stallkamp, J., Salmen, J., Schlipsing, M., Igel, C.: Detection of traffic signs in real-world images: the German traffic sign detection benchmark. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2013)
Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. Adv. Neural Inform. Process. Syst. 29 (2016)
Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Quantized neural networks: training neural networks with low precision weights and activations. J. Mach. Learn. Res. 18(1), 6869–6898 (2017)
Ioffe, S., Szegedy, C.: Batch Normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456. PMLR (2015)
Katz, G., Barrett, C., Dill, D.L., Julian, K., Kochenderfer, M.J.: Reluplex: an efficient SMT solver for verifying deep neural networks. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 97–117. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63387-9_5
Krishnamoorthi, R.: Quantizing Deep Convolutional Networks for Efficient Inference: A whitepaper. arXiv preprint arXiv:1806.08342 (2018)
Krizhevsky, A., Hinton, G., et al.: Learning Multiple Layers of Features from Tiny Images (2009)
LeCun, Y.: The MNIST Database of Handwritten Digits. www.yann.lecun.com/exdb/mnist/ (1998)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal Loss for Dense Object Detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
de Moura, L., Bjørner, N.: Z3: an efficient SMT solver. In: Ramakrishnan, C.R., Rehof, J. (eds.) TACAS 2008. LNCS, vol. 4963, pp. 337–340. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-78800-3_24
Narodytska, N.: Formal analysis of deep binarized neural networks. In: IJCAI, pp. 5692–5696 (2018)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading Digits in Natural Images with Unsupervised Feature Learning (2011)
Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: ImageNet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525–542. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_32
Ruder, S.: An Overview of Gradient Descent Optimization Algorithms. arXiv preprint arXiv:1609.04747 (2016)
Sermanet, P., LeCun, Y.: Traffic sign recognition with multi-scale convolutional networks. In: The 2011 International Joint Conference on Neural Networks, pp. 2809–2813. IEEE (2011)
Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., et al.: Intriguing Properties of Neural Networks. arXiv preprint arXiv:1312.6199 (2013)
Zhang, J., Wang, W., Lu, C., Wang, J., Sangaiah, A.K.: Lightweight deep network for traffic sign classification. Ann. Telecommun. 75, 369–379 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Postovan, A., Eraşcu, M. (2023). Architecturing Binarized Neural Networks for Traffic Sign Recognition. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14254. Springer, Cham. https://doi.org/10.1007/978-3-031-44207-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-44207-0_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44206-3
Online ISBN: 978-3-031-44207-0
eBook Packages: Computer ScienceComputer Science (R0)