IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Design of Building Dataset and Traffic Light Recognition Module for Domestic Urban Autonomous Driving

국내 도심에서 자율주행을 위한 신호등 인식 모듈 및 데이터 셋 구축 프로세스 설계

  • Jaehyeong Park (DGIST) ;
  • Jin-Hee Lee (DGIST) ;
  • Je-Seok Kim (DGIST) ;
  • Soon Kwon (DGIST)
  • 박재형 ;
  • 이진희 ;
  • 김제석 ;
  • 권순
  • Received : 2024.03.04
  • Accepted : 2024.07.26
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

In the context of urban autonomous driving, where various types of traffic lights are encountered, traffic light recognition technology is of paramount importance. We have designed a high-performance traffic light recognition module tailored to scenarios encountered in domestic urban driving and devised a dataset construction process. In this paper, we focus on minimizing the camera's dependency to enhance traffic light recognition performance. The camera is used solely to distinguish the color information of traffic lights, while accurate location information of the traffic lights is obtained through localization and a map. Based on the information from these components, camera RoIs (Region of Interest) are extracted and transmitted to the embedded board. The transmitted images are then sent back to the main system for autonomous driving control. The processing time for one traffic light RoI averages 43.2 ms. We achieve processing times of average 93.4 ms through batch inference to meet real-time requirements. Additionally, we design a data construction process for collecting, refining, and storing traffic light datasets, including semi-annotation-based corrections.

Keywords

Acknowledgement

본 연구는 과학기술정보통신부에서 지원하는 대구경북과학기술원 기관고유사업 (24-IT-01), 기술사업화 역량강화사업 (2023-DG-RD-0041-02-201), 연구개발특구진흥재단사업 (2023-TB-RD-0017-01) 지원을 받아 수행되었습니다.

References

  1. C. Jung, D. Lee, S. Lee, D. H. Shim, "V2X-communication-aided Autonomous Driving: System Design and Experimental Validation," Sensors Vol. 20, No. 10, pp. 2903, 2020.
  2. M. Weber, P. Wolf, J. M. Zollner, "DeepTLR: A Single Deep Convolutional Network for Detection and Classification of Traffic Lights," 2016 IEEE Intelligent Vehicles Symposium (IV). IEEE, pp. 342-348, 2016.
  3. J. Redmon, S. Divvala, R. Girshick, "You Only Look Once: Unified, Real-time Object Detection," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 779-788, 2016.
  4. Q. Wang, Q. Zhang, X. Liang, Y. Wang, C. Zhou, V. I. Mikulovich, "Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm," Sensors, Vol. 22, No. 1, pp. 200, 2021.
  5. M. Mostafa, M. Ghantous, "A Yolo Based Approach for Traffic Light Recognition for Adas Systems," 2022 2nd International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC). IEEE, pp. 225-229, 2022.
  6. M. Hirabayashi, A. Sujiwo, A. Monrroy, S. Kato, M. Edahiro, "Traffic Light Recognition Using High-definition Map Features," Robotics and Autonomous Systems 111, pp. 62-72, 2019.
  7. S. Kato, E. Takeuchi, Y. Ishiguro, Y. Ninomiya, K. Takeda, T. Hamada, "An Open Approach to Autonomous Vehicles," IEEE Micro, Vol. 35, No. 6, pp. 60-68, 2015.
  8. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, A. C. Berg, "Ssd: Single Shot Multibox Detector," Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part I 14. Springer International Publishing, pp. 21-37, 2016.
  9. Z. Li, Q. Zeng, Y. Liu, J. Liu, L. Li. "An Improved Traffic Lights Recognition Algorithm for Autonomous Driving in Complex Scenarios," International Journal of Distributed Sensor Networks, Vol. 17, No. 5, 15501477211018374, 2021.
  10. K. He, X. Zhang, S. Ren, J. Sun, "Deep Residual Learning for ImageRrecognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Vol. 34. pp. 770-778, 2016.
  11. S. Liu, L. Qi, H. Qin, J. Shi, J. Jia, "Path Aggregation Network for Instance Segmentation," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 8759-8768, 2018.
  12. M. B. Jensen, M. P. Philipsen, A. Mogelmose, T. B. Moeslund, M. M. Trivedi, "Vision for Looking at Traffic Lights: Issues, Survey, and Perspectives," IEEE Transactions on Intelligent Transportation Systems, Vol. 17, No. 7, pp. 1800-1815, 2016
  13. Korean National Police Agency, "Traffic Signal Installation and Operation Manual," 2022.
  14. T. Y. Lin, P. Goyal, R. Girshick, K. He, P. Dollar, "Focal Loss for Dense Object Detection," Proceedings of the IEEE International Conference on Computer Vision. pp. 2980-2988, 2017.
  15. J. H. Lee, J. K. Lee, J. Park, J. S. Kim, S. Kwon, "Construction and Effectiveness Evaluation of Multi Camera Dataset Specialized for Autonomous Driving in Domestic Road Environment," IEMEK J. Embed. Sys. Appl., Vol. 17, No. 5, pp. 273-280, 2022.