Abstract
The detection of traffic lights is an indispensable part of advanced driver assistance systems. This paper presents a new two-stage detection framework which is able to recognize various types of traffic signals. Different from the techniques based on the direct detection of traffic lights, we consider the individual signal bulbs as targets for detection and recognition. In our two-stage approach, the first detection stage aims to achieve a very low miss rate on the traffic signal bulbs with possibly high false positives. It is then followed by the second recognition stage to single out the correct traffic signals using a classification network. The proposed method overcomes the diverse traffic light detection problem due to various arrangements of signal bulbs in different countries. It is also capable of simultaneously detecting individual traffic signals including the arrow lights. Thus, the categories of traffic light states for classification and training can be reduced. The experiments carried out using our road scene images and public datasets have demonstrated the feasibility of the proposed technique.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bach, M., Stumper, D., Dietmayer, K.: Deep convolutional traffic light recognition for automated driving. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 851–858. IEEE (2018)
Behrendt, K., Novak, L., Botros, R.: A deep learning approach to traffic lights: detection, tracking, and classification. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 1370–1377 (2017). https://doi.org/10.1109/ICRA.2017.7989163
Behrendt, K., Novak, L., Botros, R.: A deep learning approach to traffic lights: detection, tracking, and classification. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 1370–1377. IEEE (2017)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)
Chaudhury, K., DiVerdi, S., Ioffe, S.: Auto-rectification of user photos. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 3479–3483 (2014). https://doi.org/10.1109/ICIP.2014.7025706
Chen, Z., Huang, X.: Accurate and reliable detection of traffic lights using multiclass learning and multiobject tracking. IEEE Intell. Transp. Syst. Mag. 8(4), 28–42 (2016). https://doi.org/10.1109/MITS.2016.2605381
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Fregin, A., Muller, J., Krebel, U., Dietmayer, K.: The driveu traffic light dataset: introduction and comparison with existing datasets. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 3376–3383 (2018). https://doi.org/10.1109/ICRA.2018.8460737
Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Jensen, M.B., Philipsen, M.P., Møgelmose, A., Moeslund, T.B., Trivedi, M.M.: Vision for looking at traffic lights: issues, survey, and perspectives. IEEE Trans. Intell. Transp. Syst. 17(7), 1800–1815 (2016). https://doi.org/10.1109/TITS.2015.2509509
John, V., Zheming, L., Mita, S.: Robust traffic light and arrow detection using optimal camera parameters and gps-based priors. In: 2016 Asia-Pacific Conference on Intelligent Robot Systems (ACIRS), pp. 204–208. IEEE (2016)
Lin, T., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936–944 (2017). https://doi.org/10.1109/CVPR.2017.106
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Weber, M., Huber, M., Zöllner, J.M.: Hdtlr: a CNN based hierarchical detector for traffic lights. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 255–260. IEEE (2018)
Weber, M., Wolf, P., Zöllner, J.M.: Deeptlr: a single deep convolutional network for detection and classification of traffic lights. In: 2016 IEEE Intelligent Vehicles Symposium (IV), pp. 342–348. IEEE (2016)
Yeh, T.W., Lin, H.Y.: Detection and recognition of arrow traffic signals using a two-stage neural network structure. In: The 6th International Conference on Vehicle Technology and Intelligent Transport Systems (VEHITS) (2020)
Yeh, T.W., Lin, S.Y., Lin, H.Y., Chan, S.W., Lin, C.T., Lin, Y.Y.: Traffic light detection using convolutional neural networks and lidar data. In: 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), pp. 1–2. IEEE (2019)
Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 418–434. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_25
Acknowledgment
The support of this work in part by the Ministry of Science and Technology of Taiwan under Grant MOST 106-2221-E-194-004 and the Advanced Institute of Manufacturing with High-tech Innovations (AIM-HI) from The Featured Areas Research Center Program within the framework of the Higher Education Sprout Project by the Ministry of Education (MOE) in Taiwan is gratefully acknowledged.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, SY., Lin, HY. (2022). A Two-Stage Framework for Diverse Traffic Light Recognition Based on Individual Signal Detection. In: Djeddi, C., Siddiqi, I., Jamil, A., Ali Hameed, A., Kucuk, İ. (eds) Pattern Recognition and Artificial Intelligence. MedPRAI 2021. Communications in Computer and Information Science, vol 1543. Springer, Cham. https://doi.org/10.1007/978-3-031-04112-9_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-04112-9_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-04111-2
Online ISBN: 978-3-031-04112-9
eBook Packages: Computer ScienceComputer Science (R0)