Relevant Traffic Light Localization via Deep Regression

• Rafael de Freitas Universidade Federal do Espírito Santo
• Thiago Paixão Instituto Federal do Espírito Santo
• Rodrigo Berriel Universidade Federal do Espírito Santo
• Alberto De Souza Universidade Federal do Espírito Santo
• Claudine Badue Universidade Federal do Espírito Santo
• Thiago Oliveira-Santos Universidade Federal do Espírito Santo

DOI: https://doi.org/10.5753/eniac.2019.9306

Resumo

Artificial intelligence advances have an important role on self-driving cars development, such as assisting the recognition of traffic lights. However, when relying on images of the scene alone, little progress was observed on selecting the traffic lights defining guidance to the car. Common detection approaches rely on additional high-level decision-making process to select a relevant traffic light. This work address the problem by proposing a deep regression system with an outliers resilient loss to predict the coordinates of a relevant traffic light in the image plane. The prediction can be used as a high-level decision-maker or as an assistant to a cheaper classifier to work on a region of interest. Results for European scenes show success in about 88% of the cases.

Palavras-chave: Traffic Light Recognition, Deep Learning, Self-driving Cars

Referências

Badue, C., Guidolini, R., Carneiro, R. V., Azevedo, P., Cardoso, V. B., Forechi, A., Jesus, L. F. R., Berriel, R. F., Paixão, T. M., Mutz, F., et al. (2019). Self-driving cars: A survey. arXiv preprint arXiv:1901.04407.

Barnes, D., Maddern, W., and Posner, I. (2015). Exploiting 3D Semantic Scene Priors for Online Traffic Light Interpretation. In Intelligent Vehicles Symposium (IV), pages 573–578.

Behrendt, K., Novak, L., and Botros, R. (2017). A deep learning approach to traffic lights: Detection, tracking, and classification. In International Conference on Robotics and Automation (ICRA), pages 1370–1377.

Diaz-Cabrera, M., PietroCerri, and PaoloMedici (2015). Robust real-time traffic light detection and distance estimation using a single camera. Expert Systems with Applications, 42(8):3911–3923.

Franke, U., Pfeiffer, D., Rabe, C., Knoeppel, C., Enzweiler, M., Stein, F., and Herrtwich, R. G. (2013). Making Bertha See. In International Conference on Computer Vision Workshops (ICCVW), pages 214–221.

Fregin, A., Müller, J., Kreβel, U., and Dietmayer, K. (2018). The driveu traffic light dataset: Introduction and comparison with existing datasets. In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages 3376–3383. IEEE.

Gómez, A. E., Alencar, F. A. R., Prado, P. V., Osório, F. S., and Wolf, D. F. (2014). Traffic Lights Detection and State Estimation Using Hidden Markov Models. In Intelligent Vehicles Symposium (IV), pages 750–755.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.

Huber, P. J. (1992). Robust estimation of a location parameter. In Breakthroughs in statistics, pages 492–518. Springer.

Jang, C., Cho, S., Jeong, S., Suhr, J. K., Jung, H. G., and Sunwoo, M. (2017). Traffic light recognition exploiting map and localization at every stage. Expert Systems with Applications, 88:290–304.

Jensen, M. B., Nasrollahi, K., and Moeslund, T. B. (2017). Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data. In Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 882–888.

Jensen, M. B., Philipsen, M. P., Bahnsen, C., Møgelmose, A., Moeslund, T. B., and Trivedi, M. M. (2015). Traffic Light Detection at Night: Comparison of a LearningBased Detector and Three Model-Based Detectors. In International Symposium on Visual Computing (IVSC), pages 774–783.

Jensen, M. B., Philipsen, M. P., Møgelmose, A., Moeslund, T. B., and Trivedi, M. M. (2016). Vision for Looking at Traffic Lights: Issues, Survey, and Perspectives. Transactions on Intelligent Transportation Systems, 17(7):1800–1815.

John, V., Yoneda, K., Qi, B., Liu, Z., and Mita, S. (2014). Traffic Light Recognition in Varying Illumination using Deep Learning and Saliency Map. In International Conference on Intelligent Transportation Systems (ITSC), pages 2286–2291.

Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems (NIPS), pages 1097–1105.

Li, X., Ma, H., Wang, X., and Zhang, X. (2018). Traffic Light Recognition for Complex Scene With Fusion Detections. Transactions on Intelligent Transportation Systems, 19(1):199–208.

Lindner, F., Kressel, U., and Kaelberer, S. (2004). Robust recognition of traffic signals. In Intelligent Vehicles Symposium (IV), pages 49–53.

Mu, G., Xinyu, Z., Deyi, L., Tianlei, Z., and Lifeng, A. (2015). Traffic light detection and recognition for autonomous vehicles. The Journal of China Universities of Posts and Telecommunications, 22(1):50–56.

Müller, J. and Dietmayer, K. (2018). Detecting traffic lights by single shot detection. arXiv preprint arXiv:1805.02523.

Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2017). Automatic differentiation in pytorch.

Philipsen, M. P., Jensen, M. B., Møgelmose, A., Moeslund, T. B., and Trivedi, M. M. (2015). Traffic Light Detection: A Learning Algorithm and Evaluations on Challenging Dataset. In International Conference on Intelligent Transportation Systems (ITSC), pages 2341–2345.

Pon, A. D., Andrienko, O., Harakeh, A., and Waslander, S. L. (2018). A hierarchical deep architecture and mini-batch selection method for joint traffic sign and light detection. arXiv preprint arXiv:1806.07987.

Possati, L. C., Guidolini, R., Cardoso, V. B., Berriel, R. F., Paixão, T. M., Badue, C., Souza, A. F. D., and Oliveira-Santos, T. (2019). Traffic Light Recognition Using Deep Learning and Prior Maps for Autonomous Cars. arXiv preprint arXiv:1906.11886.