The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Edge Camera based C-ITS Pedestrian Collision Avoidance Warning System

엣지 카메라 기반 C-ITS 보행자 충돌방지 경고 시스템

  • Park, Jong Woo (School of Electronics Engineering, Kyungpook National University) ;
  • Baek, Jang Woon (Artificial Intelligence Application Research Section, ETRI) ;
  • Lee, Sangwon (Research & Development Department, CEST. Co., Ltd.) ;
  • Seo, Woochang (Research & Development Department, CEST. Co., Ltd.) ;
  • Seo, Dae-Wha (School of Electronics Engineering, Kyungpook National University)
  • 박종우 (경북대학교 전자공학부) ;
  • 백장운 (한국전자통신연구원 인공지능응용연구실) ;
  • 이상원 ((주)세스트 연구개발부) ;
  • 서우창 ((주)세스트 연구개발부) ;
  • 서대화 (경북대학교 전자공학부)
  • Received : 2019.11.04
  • Accepted : 2019.11.28
  • Published : 2019.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The prevention of pedestrian accidents in crosswalks and intersections is very important. The C-ITS services provide a warning service for preventing accidents between cars and pedestrians. In the current pedestrian collision prevention warning service according to the C-ITS standard, however, it is difficult to provide real-time service because it detects pedestrians from a video-analysis server in the control center and sends service messages through the ITS system. This paper proposes a pedestrian collision-prevention warning system that detects pedestrians in the local field using an edge camera and sends a warning message directly to the driver through a roadside unit. An evaluation showed that the proposed system could deliver the pedestrian collision prevention-warning message to the driver satisfying the delay time within the 300 ms required by the C-ITS standard, even in the worst case.

최근 횡단보도 및 교차로에서 보행자 충돌사고 예방의 중요성이 증가하고 있다. C-ITS 서비스에서 이러한 사고를 줄이기 위하여 보행자 충돌방지 경고 서비스를 제시하고 있다. 그러나 현재 C-ITS 표준에 따른 보행자 충돌방지 경고 서비스는 현장의 카메라에서 보행자를 바로 검출하여 서비스를 제공하는 것이 아니라 관제 센터의 영상분석 서버에서 보행자를 검출하고 ITS 시스템과 연계하여 서비스를 제공하기 때문에 실시간성을 만족하기 어렵다. 본 논문에서는 엣지 카메라를 이용하여 현장에서 보행자를 검출하고 검출결과를 V2X 인프라를 통해 바로 운전자에게 제공하는 보행자 충돌방지 경고 시스템을 제안하고, 구현한 후 성능 평가를 시행하였다. 평가 결과, 최악의 상황에서도 보행자 충돌방지 경고 메시지를 C-ITS 표준에서 요구하고 있는 300ms 이내의 지연시간을 만족하여 전달할 수 있음을 확인하였다.

Keywords

References

  1. Howard A. G., Zhu M., Chen B., Kalenichenko D., Wang W., Weyand T., Andreetto M. and Adam H.(2017), MobileNets: Efficient Convolution Neural Networks for Mobile Vision Applications, arXiv preprint arXiv: 1704.04861.
  2. Iandola F., Moskewicz M., Karayev S., Girshick R., Darrell T. and Keutzer K.(2014), Densenet: Implementing efficient convnet descriptor pyramids, arXiv preprint arXiv:1404.1869.
  3. Insurance Institute for Highway Safety, Highway Loss Data Institute(2019), Pedestrian crash prevention ratings, https://www.iihs.org/ratings/pedestrian-crash-prevention, 2019.10.29.
  4. Intelligent Transport Society of Korea(2017), Standard of C-ITS Service Specification Part1. Function and Performance Requirement Specification, pp.57-60, p.84.
  5. Intelligent Transport Society of Korea(2017), Standard of C-ITS Service Specification Part2. Data Exchange Specification, pp.48-52, p.70, p.76.
  6. Jung H. G.(2010), "Pedestrian Protection System: Review and Problems," Proceedings in Korean Society of Automotive Engineers(KSAE) 2010 Annual Conference, pp.1820-1826.
  7. Korean National Police Agency(2018), 2018 Traffic Accident Statistics, p.46, p.96.
  8. Lee Y. J., Moon Y. H., Park J. Y. and Min O. G.(2019), "Recent R&D Trends for Lightweight Deep Learning," 2019 Electronics and Telecommunications Trends, vol. 34, no. 2, pp.40-50.
  9. Liu W., Anguelov D., Erhan D., Szegedy C., Reed S., Fu C. Y. and Berg A. C.(2016), "Ssd: Single shot multibox detector," In European Conference on Computer Vision, pp.21-37.
  10. Ministry of Land, Infrastructure and Transport & Korea Expressway Corporation, https://www.c-its.kr/introduction/introduction.do, 2019.8.29.
  11. Ministry of Land, Infrastructure and Transport & Korea Expressway Corporation, https://www.c-its.kr/introduction/service.do, 2019.8.29.
  12. Redmon J. and Farhadi A.(2018), YOLOv3: An Incremental Improvement, arXiv preprint arXiv: 1804.02767.
  13. Sandler M., Howard A. G., Zhu M., Zhmoginov A. and Chen L. C.(2018), MobileNetV2: Inverted Residuals and Linear Bottlenecks, arXiv preprint arXiv:1801.04381.
  14. Shen Z., Liu Z., Li J., Jiang Y. G., Chen Y. and Xue X.(2017), "Dsod: Learning deeply supervised object detectors from scratch," In Proceedings of the IEEE International Conference on Computer Vision, pp.1919-1927.
  15. Szegedy C., Ioffe S., Vanhoucke V. and Alemi A. A.(2017), "Inception-v4, inception-resnet and the impact of residual connections on learning," In Thirty-First AAAI Conference on Artificial Intelligence.
  16. Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhouke V. and Rabinovich A.(2015), "Going deeper with convolutions," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1-9.
  17. Wang R. J., Li X. and Ling C. X.(2018), "Pelee: A real-time object detection system on mobile devices," In Advances in Neural Information Processing Systems, pp.1963-1972.