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

A Research on Improving the Shape of Korean Road Signs to Enhance LiDAR Detection Performance

LiDAR 시인성 향상을 위한 국내 교통안전표지 형상개선에 대한 연구

  • 김지윤 (한국건설기술연구원 도로교통연구본부) ;
  • 김지수 (한국건설기술연구원 도로교통연구본부) ;
  • 박범진 (한국건설기술연구원 도로교통연구본부)
  • Received : 2023.05.16
  • Accepted : 2023.06.07
  • Published : 2023.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

LiDAR plays a key role in autonomous vehicles, and to improve its visibility, it is necessary to improve its performance and the detection objects. Accordingly, this study proposes a shape for traffic safety signs that is advantageous for self-driving vehicles to recognize. Improvement plans are also proposed using a shape-recognition algorithm based on point cloud data collected through LiDAR sensors. For the experiment, a DBSCAN-based road-sign recognition and classification algorithm, which is commonly used in point cloud research, was developed, and a 32ch LiDAR was used in an actual road environment to conduct recognition performance tests for 5 types of road signs. As a result of the study, it was possible to detect a smaller number of point clouds with a regular triangle or rectangular shape that has vertical asymmetry than a square or circle. The results showed a high classification accuracy of 83% or more. In addition, when the size of the square mark was enlarged by 1.5 times, it was possible to classify it as a square despite an increase in the measurement distance. These results are expected to be used to improve dedicated roads and traffic safety facilities for sensors in the future autonomous driving era and to develop new facilities.

자율주행차량에서 핵심적인 역할을 수행하는 LiDAR의 주변 환경 검지 시인성을 향상시키기 위해서는 LiDAR 성능의 개선 뿐만 아니라, 검지 물체의 개선도 필요하다. 이에 본 연구는 LiDAR 센서를 통해 수집되는 point cloud 데이터 기반의 형상인식 알고리즘을 활용하여 자율주행차량이 인식하기에 유리한 교통안전표지 형상과 개선방안을 제시하였다. 실험을 위해 point cloud 활용 연구에서 보편적으로 활용되는 DBSCAN 기반의 도로표지 인식·분류 알고리즘을 개발하고 실도로 환경에서 32ch LiDAR를 활용, 도로표지 5종에 대한 인식 성능 실험을 수행하였다. 연구결과, 정사각형이나 원형보다는 상하 비대칭이 있는 정삼각형, 직사각형과 같은 형상이 보다 적은 점군의 수로도 검지가 가능하고, 83% 이상의 높은 분류 정확도를 보였다. 또한, 정사각형 표지의 크기를 1.5배 확대할 경우, 분류 정확도를 향상시킬 수 있었다. 이러한 결과는 미래 자율주행 시대의 센서를 위한 전용 도로·교통안전시설물 개선 및 신규 시설물 개발에 활용될 수 있을 것으로 기대된다.

Keywords

Acknowledgement

본 연구는 국토교통부/국토교통과학기술진흥원의 지원으로 수행되었음(과제번호 21AMDP-C161924-01, 주관연구기관 과제명: 크라우드 소싱 기반의 디지털 도로교통 인프라 융합플랫폼 기술 개발 / 공동연구기관 과제명: 도로·교통 인프라 성능평가 방법론 개발 및 자율차 기반의 개발 인프라 검증)

References

  1. Beraldin, J. and Blais, F.(2010), Laser scanning technology: In Airborne and Terrestrial Laser Scanning, Whittles Publishing, pp.1-42.
  2. Chen, C., Fragonara, L. Z. and Tsourdos, A.(2021), "RoIFusion: 3D Object Detection From LiDAR and Vision", IEEE Access, vol. 9, pp.51710-51721. https://doi.org/10.1109/ACCESS.2021.3070379
  3. Goodin, C., Carruth, D., Doude, M. and Hudson, C.(2019), "Predicting the Influence of Rain on LiDAR in ADAS", Electronics, vol. 8, no. 1, p.89. doi: 10.3390/electronics8010089
  4. GSA Global(n.d.), Autonomous driving and sensor fusion SoCs, Available online: https://www.gsaglobal.org/forums/autonomous-driving-and-sensor-fusion-socs/, 2022.10.05.
  5. Jeon, H. and Kim, J.(2021), "Analysis on Handicaps of Automated Vehicle and Their Causes using IPA and FGI", Journal of Korea Institute Intelligent Transportation System, vol. 20, no. 3, pp.34-46. https://doi.org/10.12815/kits.2021.20.3.34
  6. Kim, J. and Park, B.(2022a), "A Research of Factors Affecting LiDAR's Detection on Road Signs: Focus on Shape and Height of Road Sign", Journal of Korea Institute Intelligent Transportation System, vol. 21, no. 4, pp.34-46. https://doi.org/10.12815/kits.2022.21.4.190
  7. Kim, J. and Park, B.(2022b), "A Study of LiDAR's Detection Performance Degradation in Fog and Rain Climate", Journal of Korea Institute Intelligent Transportation System, vol. 21, no. 2, pp.101-115. https://doi.org/10.12815/kits.2022.21.2.101
  8. Kim, J., Park, B. and Kim, J.(2023), "Empirical Analysis of Autonomous Vehicle's LiDAR Detection Performance Degradation for Actual Road Driving in Rain and Fog", Sensors, vol. 23, no. 6, p.2972. doi: 10.3390/s23062972
  9. Kim, J., Park, B., Roh, C. and Kim, Y.(2021), "Performance of Mobile LiDAR in the Real Road Driving Conditions", Sensors, vol. 21, no. 22, p.7461. doi: 10.3390/s2201010
  10. Kim, S., Ha, J. and Jo, K.(2021), "Semantic Point Cloud-Based Adaptive Multiple Object Detection and Tracking for Autonomous Vehicles", IEEE Access, vol. 9, pp.157550-157562. doi: 10.1109/ACCESS.2021.3130257
  11. Korea Institute of Civil Engineering and Building Technology(KICT)(2021), Improved Road Infrastructures to Strengthen Driving Safety of Automated Driving Car Final Report.
  12. Kutila, M., Pyykonen, P., Ritter, W., Sawade, O. and Schaufele, B.(2016), "Automotive LIDAR sensor development scenarios for harsh weather conditions", Proceedings of the 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazil, 1-4 November 2016, IEEE, New York, NY, USA, 2016, pp.265-270.
  13. Li, Y. and Ibanez-Guzman, J.(2020), "LiDAR for autonomous driving: The principles, challenges, and trends for automotive LiDAR and perception systems", IEEE Signal Processing Magazine, vol. 37, no. 4, pp.50-61. https://doi.org/10.1109/MSP.2020.2973615
  14. Park, B. and Kim, J.(2021), "A Study of LiDAR's Performance Change by Road Sign's Color and Climate", Journal of Korea Institute Intelligent Transportation System, vol. 20, no. 6, pp.228-241. https://doi.org/10.12815/kits.2021.20.6.228
  15. Park, B.(2022), "Method of improvements for autonomous vehicle road-traffic facilities using LiDAR", The Korea Institute of Intelligent Transportation Systems(KITS) International Conference Special Session B-5.
  16. Tang, L., Shi, Y., He, Q., Sadek, A. W. and Qiao, C.(2020), "Performance Test of Autonomous Vehicle LiDAR Sensors Under Different Weather Conditions", Transportation Research Record, vol. 2674, no. 1, pp.319-329. https://doi.org/10.1177/0361198120901681
  17. Yan, X., Gao, J., Zheng, C., Zheng, C., Zhang, R., Cui, S. and Li, Z.(2022), "2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds", Computer Vision, ECCV 2022-17th European Conference, Part XXVIII, pp.677-695. doi: 10.1007/978-3-031-19815-1_39
  18. Zamanakos, G., Tsochatzidis, L., Amanatiadis, A. and Pratikakis, I.(2021), "A comprehensive survey of LIDAR-based 3D object detection methods with deep learning for autonomous driving", Computers & Graphics, vol. 99, pp.153-181. doi: 10.1016/j.cag.2021.07.003