The bioinspired traffic sign classifier
-
Dominika Przewlocka-Rus
und
Tomasz Kryjak
Abstract
Objectives
In this paper the research on developing convolutional spiking neural networks for traffic signs classification is presented. Unlike classical ones, spiking networks reflect the behaviour of biological neurons much more closely, by taking into account the time dimension and event-based operation. Spiking networks running on dedicated neuromorphic platforms, such as Intel Loihi, can operate with greater energy efficiency, hence they are an interesting approach for embedded solutions.
Methods
For convolutional spiking neural networks' design and simulation, Nengo and NengoDL libraries for Python language were used. Numerous experiments using the Leaky-Integrate-and-Fire (LIF) neuron model were conducted. The training results, with different augmentation methods and number of time steps for input image presentation were compared.
Results
Finally, an accuracy of up to 97% on the test set was achieved, depending on the number of time steps the input was presented to the SNN.
Conclusions
The proposed experiments show that using simple convolutional spiking neural network, one can achieve accuracy comparable to the classical network with the same architecture and trained on the same dataset. At the same time, running on dedicated neuromorphic hardware, such solution should be characterized by low latency and low energy consumption.
Acknowledgments
We would also like to thank Mr. Aleksander Orlikowski for his help with the initial experiments.
-
Research funding: The work presented in this paper was supported by the AGH University of Science and Technology Project No. 16.16.120.773.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: Authors state no conflict of interest.
-
Informed consent: Informed consent was obtained from all individuals included in this study.
-
Ethical approval: Not applicable.
References
1. Paugam-Moisy, H, Bohte, S. Computing with Spiking Neuron Networks. In: Handbook of Natural Computing. Springer-Verlag; 2012:335–76 pp.10.1007/978-3-540-92910-9_10Suche in Google Scholar
2. Hunsberger, E, Eliasmith, C. Training Spiking Deep Networks for Neuromorphic Hardware. CoRR. abs/1611.05141; 2016.Suche in Google Scholar
3. O’Connor, P, Welling, M. Deep Spiking Networks. CoRR. abs/ 1602.08323; 2016.Suche in Google Scholar
4. Lee, J, Delbruck, T, Pfeiffer, M. Training Deep Spiking Neural Networks Using Backpropagation. Front Neurosci 2016;10:508. https://doi.org/10.3389/fnins.2016.00508.Suche in Google Scholar PubMed PubMed Central
5. Diehl, P, Neil, D, Binas, J, Cook, M, Liu, S, Pfeiffer, M. Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In: 2015 International Joint Conference On Neural Networks (IJCNN); 2015:1–8 pp.10.1109/IJCNN.2015.7280696Suche in Google Scholar
6. Ranjan, J, Sigamani, T, Barnabas, J. A novel and efficient classifier using spiking neural network. J Supercomput 2020;76:6545–60, https://doi.org/10.1007/s11227-019-02881-y.Suche in Google Scholar
7. Rasmussen, D. NengoDL: combining deep learning and neuromorphic modelling methods. CoRR. abs/18052018.11144.10.1007/s12021-019-09424-zSuche in Google Scholar PubMed
8. 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; 2011:1453–60 pp.10.1109/IJCNN.2011.6033395Suche in Google Scholar
9. Cireşan, D, Meier, U, Masci, J, Schmidhuber, J. Multi-column deep neural network for traffic sign classification. Neural Networks 2012;32:333–8, https://doi.org/10.1016/j.neunet.2012.02.023.Suche in Google Scholar PubMed
10. Sermanet, P, LeCun, Y. Traffic sign recognition with multi-scale Convolutional Networks. In: The 2011 International Joint Conference On Neural Networks; 2011:2809–13 pp.10.1109/IJCNN.2011.6033589Suche in Google Scholar
11. Zaklouta, F, Stanciulescu, B, Hamdoun, O. Traffic sign classification using K-d trees and Random Forests. In: The 2011 International Joint Conference On Neural Networks; 2011:2151–5 pp.10.1109/IJCNN.2011.6033494Suche in Google Scholar
12. Arcos-García, Á, Á lvarez-García, J, Soria-Morillo, L. Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods. Neural Networks 2018;99:158–65.10.1016/j.neunet.2018.01.005Suche in Google Scholar PubMed
13. Zuiderveld, K. Contrast Limited Adaptive Histogram Equalization. In: Graphics Gems. Academic Press; 1994:474–85 pp.10.1016/B978-0-12-336156-1.50061-6Suche in Google Scholar
14. Lecun, Y, Bottou, L, Bengio, Y, Haffner, P. Gradient-based learning applied to document recognition. Proc IEEE 1998;86:2278–324, https://doi.org/10.1109/5.726791.Suche in Google Scholar
15. Springenberg, J, Dosovitskiy, A, Brox, T, Riedmiller, M. Striving for Simplicity: The All Convolutional Net. CoRR; 2015.Suche in Google Scholar
16. Intel. Lava Tool. https://github.com/lava-nc/lava.Suche in Google Scholar
17. Kim, S, Park, S, Na, B, Yoon, S.: Spiking Neural Network for Real-time Object Detection. CoRR. abs/1903.06530; 2019.Suche in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- Research Article
- Development and implementation of an online platform for curriculum mapping in medical education
- Review
- Book review “Process maturity of hospitals and the quality of medical services” by Beata Detyna
- Research Articles
- Image processing algorithms in the assessment of grain damage degree
- The bioinspired traffic sign classifier
- islEHR, a model for electronic health records interoperability
Artikel in diesem Heft
- Frontmatter
- Research Article
- Development and implementation of an online platform for curriculum mapping in medical education
- Review
- Book review “Process maturity of hospitals and the quality of medical services” by Beata Detyna
- Research Articles
- Image processing algorithms in the assessment of grain damage degree
- The bioinspired traffic sign classifier
- islEHR, a model for electronic health records interoperability
