Classificação de Sinais de Trânsito para Direção Autônoma via Rede Neural Convolucional
Resumo
Sinais de trânsito são elementos fundamentais que servem de alerta e orientação à direção autônoma de veículos. Nesse sentido, um dos principais problemas de pesquisa abordados na literatura relacionada é o de classificação automática de sinais de trânsito. Uma vez que veículos autônomos podem ser utilizados em diferentes países, onde os sinais de trânsito podem ter diferentes símbolos e significados, e necessário que os classificadores sejam capazes de se adaptar de acordo com o conjunto de sinais de cada país. Dado isso, este trabalho propõe o treinamento de modelos de aprendizado de máquina utilizando datasets públicos de placas de trânsito de diferentes países, com o objetivo de gerar classificadores suficientemente robustos para utiliza-ção nesses diversos países. Assim sendo, são apresentadas algumas estratégias para treinamento dos modelos de classificação, bem como uma avaliação experimental dessas diferentes estratégias, sendo destacada aquela que levou aos melhores resultados.
Palavras-chave:
Sinais de Trânsito, Aprendizado Profundo, Classificação, Direção Autônoma, Aprendizado de Máquina
Referências
A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, Eds. Curran Associates, Inc., 2012, pp. 1097-1105. [Online]. Available: http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," in Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, Eds. Curran Associates, Inc., 2014, pp. 2672-2680. [Online]. Available: http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf
S. M. Weiss and C. A. Kulikowski, Computer systems that learn: classification and prediction methods from statistics, neural nets, machine learning, and expert systems. Morgan Kaufmann Publishers Inc., 1991.
A. Qayyum, M. Usama, J. Qadir, and A. Al-Fuqaha, "Securing connected & autonomous vehicles: Challenges posed by adversarial machine learning and the way forward," arXiv preprint arXiv:1905.12762, 2019.
F. Jurisic, I. Filkovic, and Z. Kalafatic, "Multiple-dataset traffic sign classification with onecnn," in 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR). IEEE, 2015, pp. 614-618.
Y. Yang, H. Luo, H. Xu, and F. Wu, "Towards real-time traffic sign detection and classification," IEEE Transactions on Intelligent transportation systems, vol. 17, no. 7, pp. 2022-2031, 2015.
"Dataset alemão de sinais de trânsito," http://benchmark.ini.rub.de/?section=gtsrbsubsection=dataset, accessed: 29/03/2020.
D. Cires¸An, U. Meier, J. Masci, and J. Schmidhuber, "Multi-column deep neural network for traffic sign classification," Neural networks, vol. 32, pp. 333-338, 2012.
C. G. Serna and Y. Ruichek, "Classification of traffic signs: The european dataset," IEEE Access, vol. 6, pp. 78 136-78 148, 2018.
D. Cires¸an, U. Meier, J. Masci, and J. Schmidhuber, "A committee of neural networks for traffic sign classification," in The 2011 international joint conference on neural networks. IEEE, 2011, pp. 1918-1921.
J. Jin, K. Fu, and C. Zhang, "Traffic sign recognition with hinge loss trained convolutional neural networks," IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 5, pp. 1991-2000, 2014.
H. H. Aghdam, E. J. Heravi, and D. Puig, "A practical and highly optimized convolutional neural network for classifying traffic signs in real-time," International Journal of Computer Vision, vol. 122, no. 2, pp. 246-269, 2017.
S. Saha, M. S. Islam, M. A. B. Khaled, and S. Tairin, "An efficient traffic sign recognition approach using a novel deep neural network selection architecture," in Emerging Technologies in Data Mining and Information Security. Springer, 2019, pp. 849-862.
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going deeper with convolutions," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1-9.
K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
J. Cao, C. Song, S. Peng, F. Xiao, and S. Song, "Improved traffic sign detection and recognition algorithm for intelligent vehicles," Sensors, vol. 19, no. 18, p. 4021, 2019.
D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, "Backpropagation applied to handwritten zip code recognition," Neural Computation, vol. 1, no. 4, pp. 541-551, 1989.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
"Dataset belga de sinais de trânsito," https://btsd.ethz.ch/shareddata/, accessed: 29/03/2020.
"Dataset croata de sinais de trânsito," http://www.zemris.fer.hr/kalfa/Datasets/rMASTIF/, accessed: 29/03/2020.
I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," in Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, Eds. Curran Associates, Inc., 2014, pp. 2672-2680. [Online]. Available: http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf
S. M. Weiss and C. A. Kulikowski, Computer systems that learn: classification and prediction methods from statistics, neural nets, machine learning, and expert systems. Morgan Kaufmann Publishers Inc., 1991.
A. Qayyum, M. Usama, J. Qadir, and A. Al-Fuqaha, "Securing connected & autonomous vehicles: Challenges posed by adversarial machine learning and the way forward," arXiv preprint arXiv:1905.12762, 2019.
F. Jurisic, I. Filkovic, and Z. Kalafatic, "Multiple-dataset traffic sign classification with onecnn," in 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR). IEEE, 2015, pp. 614-618.
Y. Yang, H. Luo, H. Xu, and F. Wu, "Towards real-time traffic sign detection and classification," IEEE Transactions on Intelligent transportation systems, vol. 17, no. 7, pp. 2022-2031, 2015.
"Dataset alemão de sinais de trânsito," http://benchmark.ini.rub.de/?section=gtsrbsubsection=dataset, accessed: 29/03/2020.
D. Cires¸An, U. Meier, J. Masci, and J. Schmidhuber, "Multi-column deep neural network for traffic sign classification," Neural networks, vol. 32, pp. 333-338, 2012.
C. G. Serna and Y. Ruichek, "Classification of traffic signs: The european dataset," IEEE Access, vol. 6, pp. 78 136-78 148, 2018.
D. Cires¸an, U. Meier, J. Masci, and J. Schmidhuber, "A committee of neural networks for traffic sign classification," in The 2011 international joint conference on neural networks. IEEE, 2011, pp. 1918-1921.
J. Jin, K. Fu, and C. Zhang, "Traffic sign recognition with hinge loss trained convolutional neural networks," IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 5, pp. 1991-2000, 2014.
H. H. Aghdam, E. J. Heravi, and D. Puig, "A practical and highly optimized convolutional neural network for classifying traffic signs in real-time," International Journal of Computer Vision, vol. 122, no. 2, pp. 246-269, 2017.
S. Saha, M. S. Islam, M. A. B. Khaled, and S. Tairin, "An efficient traffic sign recognition approach using a novel deep neural network selection architecture," in Emerging Technologies in Data Mining and Information Security. Springer, 2019, pp. 849-862.
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going deeper with convolutions," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1-9.
K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
J. Cao, C. Song, S. Peng, F. Xiao, and S. Song, "Improved traffic sign detection and recognition algorithm for intelligent vehicles," Sensors, vol. 19, no. 18, p. 4021, 2019.
D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, "Backpropagation applied to handwritten zip code recognition," Neural Computation, vol. 1, no. 4, pp. 541-551, 1989.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
"Dataset belga de sinais de trânsito," https://btsd.ethz.ch/shareddata/, accessed: 29/03/2020.
"Dataset croata de sinais de trânsito," http://www.zemris.fer.hr/kalfa/Datasets/rMASTIF/, accessed: 29/03/2020.
Publicado
23/11/2020
Como Citar
OLIVEIRA, Nicomar; MOURA, Pedro; CAMPOS, Carlos.
Classificação de Sinais de Trânsito para Direção Autônoma via Rede Neural Convolucional. In: TRABALHOS EM ANDAMENTO - SIMPÓSIO BRASILEIRO DE ENGENHARIA DE SISTEMAS COMPUTACIONAIS (SBESC), 10. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 157-162.
ISSN 2763-9002.
DOI: https://doi.org/10.5753/sbesc_estendido.2020.13106.
