Advertisement

DeLTR: A Deep Learning Based Approach to Traffic Light Recognition

  • Yiyang CaiEmail author
  • Chenghua Li
  • Sujuan Wang
  • Jian Cheng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11903)

Abstract

Traffic light recognition is crucial for the intelligent driving system. In the application scenarios, the environment of traffic lights is very complicated, due to different weather, distance and distortion conditions. In this paper, we proposed a Deep-learning based Traffic Light Recognition method, named DeTLR, which can achieve a reliable recognition precision and real-time running speed. Our DeTLR system consists of four parts: a skip sampling system, a traffic light detector (TLD), preprocessing, and a traffic light classifier (TLC). Our TLD combines MobileNetV2 and the Single Stage Detector (SSD) framework, and we design a small convolutional neural network for the TLC. To run our system in real-time, we develop a skip-frames technique and make up the delay of the time in the final response system. Our method could run well in complex natural situations safely, which benefits from both the algorithm and the diversity of the training dataset. Our model reaches a precision of 96.7% on green lights and 94.6% on red lights. The comparison to the one-step method indicates that our two-step method is better both in recall and precision, and running time’s difference is only about 0.7 ms. Furthermore, the experiments on other datasets (LISA, LaRA and WPI) show a good generalization ability of our model.

Keywords

Traffic light recognition Deep learning Convolutional neural network 

References

  1. 1.
    Yu, F., et al.: BDD100K: a diverse driving video database with scalable annotation tooling. arXiv (2018)Google Scholar
  2. 2.
    Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.: MobileNetV2: inverted residual and linear bottlenecks. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4510–4520. IEEE (2017)Google Scholar
  3. 3.
    Behrendt, K., Novak, L., Botros, R.: A deep learning approach to traffic lights: detection, tracking and classification. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 1370–1377. IEEE (2017)Google Scholar
  4. 4.
    Chen, Z., Huang, X.: Accurate. In: IEEE Intelligent Transportation Systems Magazine, pp. 28–42. IEEE (2016)Google Scholar
  5. 5.
    Michael, M., Schlipsing, M.: Extending traffic light recognition: efficient classification of phase and pictogram. In: IEEE International Joint Conference on Neural Network (IJCNN), pp. 1–8. IEEE (2015)Google Scholar
  6. 6.
    Binangkit, J.L., Widyantoro, D.H.: Increasing accuracy of traffic light color detection and recognition using machine learning. In: IEEE International Conference on Telecommunication Systems Services and Applications (TSSA), pp. 1–5. IEEE (2016)Google Scholar
  7. 7.
    Haltakov, V., Mayr, J., Unger, C., Ilic, S.: Semantic segmentation based traffic light detection at day and at night. In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 446–457. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24947-6_37CrossRefGoogle Scholar
  8. 8.
    Charette, R., Nashashibi, F.: Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates. In: IEEE Intelligent Vehicles Symposium, pp. 358–363. IEEE (2009)Google Scholar
  9. 9.
    Cai, Z., Li, Y., Gu, M.: Real-time recognition system of traffic light in urban environment. In: IEEE Symposium on Computational Intelligence for Security and Defence Applications, pp. 1–6. IEEE (2012)Google Scholar
  10. 10.
    Sooksatra, S., Kondo, T.: Red traffic light detection using fast radial symmetry transform. In: IEEE International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), pp. 1–6. IEEE (2014)Google Scholar
  11. 11.
    Jensen, M.B., Philipsen, M.P., Møgelmose, A., Moeslund, T.B. Trivedi, T.M.: Red traffic light detection using fast radial symmetry transform. In: IEEE Transactions on Intelligent Transportation Systems, pp. 1800–1815. IEEE (2016)Google Scholar
  12. 12.
    Philipsen, M.P., Jensen, M.B., Møgelmose, A., Moeslund, T.B., Trivedi, T.M.: Traffic light detection: a learning algorithm and evaluations on challenging dataset. In: IEEE International Conference on Intelligent Transportation Systems, pp. 2341–2345. IEEE (2015)Google Scholar
  13. 13.
    Fairfield, N., Urmson, C.: Traffic light mapping and detection. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 5421–5426. IEEE (2011) Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Yiyang Cai
    • 1
    Email author
  • Chenghua Li
    • 1
  • Sujuan Wang
    • 1
  • Jian Cheng
    • 1
  1. 1.Institute of Automation, Chinese Academy of SciencesBeijingChina

Personalised recommendations