Road Segmentation in Reflectance Maps Using Neural Networks

• Ludmila Dias IFES
• Eduardo O. Ferreira IFES
• Francisco de Assis Boldt IFES
• Marcos V. Faria IFES
• Thiago M. Paixão IFES

DOI: https://doi.org/10.5753/eries.2024.244707

Abstract

Advances in perception for autonomous driving have been driven by deep learning, which uses various sensors such as cameras, LiDARs, and radars to obtain a precise understanding of the environment. In this context, our work focuses on the semantic segmentation of roads in remission maps generated by LiDAR. We compare four convolutional neural network architectures—U-Net, PSPNet, FPN, and LinkNet—with the ENet model. Our goal is to evaluate the performance of these models in terms of average accuracy compared to ENet and to analyze them using other standard metrics.

References

Badue, C., Guidolini, R., Carneiro, R. V., Azevedo, P., Cardoso, V. B., Forechi, A., Jesus, L., Berriel, R., Paixão, T. M., Mutz, F., de Paula Veronese, L., Oliveira-Santos, T., and De Souza, A. F. (2021). Self-driving cars: A survey. Expert Systems with Applications, 165:113816.

Bolimera, A., Muthalagu, R., Kalaichelvi, V., and Singh, A. (2023). Ego vehicle lane detection and key point determination using deep convolutional neural networks and inverse projection mapping. Transport and Telecommunication Journal, 24(2):110–119.

Carneiro, R. V., Nascimento, R. C., Guidolini, R., Cardoso, V. B., Oliveira-Santos, T., Badue, C., and De Souza, A. F. (2018). Mapping road lanes using laser remission and deep neural networks. In 2018 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE.

Chaurasia, A. and Culurciello, E. (2017). Linknet: Exploiting encoder representations for efficient semantic segmentation. CoRR, abs/1707.03718.

Fagnant, D. J. and Kockelman, K. (2015). Preparing a nation for autonomous vehicles: Opportunities, barriers and policy recommendations. Transportation Research Part A: Policy and Practice, 77:167–181.

Hao, S., Zhou, Y., and Guo, Y. (2020). A brief survey on semantic segmentation with deep learning. Neurocomputing, 406:302–321.

Kingma, D. P. and Ba, J. (2017). Adam: A method for stochastic optimization.

Lin, T., Dollár, P., Girshick, R. B., He, K., Hariharan, B., and Belongie, S. J. (2016). Feature pyramid networks for object detection. CoRR, abs/1612.03144.

Lin, T., Goyal, P., Girshick, R. B., He, K., and Dollár, P. (2017). Focal loss for dense object detection. CoRR, abs/1708.02002.

Martínez-Díaz, M. and Soriguera, F. (2018). Autonomous vehicles: theoretical and practical challenges. Transportation Research Procedia, 33:275–282.

Organização Pan-Americana da Saúde (2021). Oms lança década de ação pela segurança no trânsito 2021-2030. OPAS.

Paden, B., Cap, M., Yong, S. Z., Yershov, D., and Frazzoli, E. (2016). A survey of motion planning and control techniques for self-driving urban vehicles.

Paszke, A., Chaurasia, A., Kim, S., and Culurciello, E. (2016). Enet: A deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147.

Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. CoRR, abs/1505.04597.

Schrank, D., Eisele, B., Lomax, T., and Bak, J. (2019). Urban mobility report.

Singh, R. and Rani, R. (2020). Semantic segmentation using deep convolutional neural network: A review. SSRN Electronic Journal, pages 1–8.

Wong, K., Gu, Y., and Kamijo, S. (2021). Mapping for autonomous driving: Opportunities and challenges. IEEE Intelligent Transportation Systems Magazine, 13(1):91–106.

Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2016). Pyramid scene parsing network. CoRR, abs/1612.01105.