적외선 영상검지 기술을 활용한 고속도로 버스전용차로 단속시스템 개발
Freeway Bus-Only Lane Enforcement System Using Infrared Image Processing Technique
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
본 연구에서는 고속도로 버스전용차로 단속시스템을 개발하여 현장 성능평가를 수행하였다. 영동고속도로 마성터널 입구 버스전용차로에서 조사한 결과, 버스전용차로를 위반하는 차량의비율이 99%에 달하는 것으로 조사되었다. 하지만 현재의 경찰관에 의한 인력식 단속은 단속율도 낮고 불필요한 안전문제 및 지체를 발생시킨다. 고속도로 버스전용차로는 6인 이상 탑승한9인승 이상 승합차도 통행이 가능하기 때문에 승합차량의 승차인원을 검지하는 기술개발이 필요하다. 조도에 관계없는 승차인원 검지를 위해 적외선 카메라를 사용하였고 짧은 차두시간을감안한 신속한 영상처리 기법으로 YOLOv5 딥러닝 알고리즘을 사용하였다. 개발시스템 성능검증을 위해 테스트베드 및 실 현장 평가를 실시한 결과, 테스트베드와 실 현장에서 각각 7%, 8% 오차를 나타내 만족할 만한 성능을 보였다. 본 연구 결과물을 현장에 적용할 경우 고속도로버스전용차로 운영 효율화 및 단속에 따른 불필요한 지체를 감소시킬 수 있을 것으로 기대된다.
Abstract
An automatic freeway bus-only lane enforcement system was developed and assessed in a real-world environment. Observation of a bus-only lane on the Youngdong freeway, South Korea, revealed that approximately 99% of the vehicles violated the high-occupancy vehicle (HOV) lane regulation. However, the current enforcement by the police not only exhibits a low enforcement rate, but also induces unnecessary safety and delay concerns. Since vehicles with six passengers or higher are permitted to enter freeway bus-only lanes, identifying the number of passengers in a vehicle is a core technology required for a freeway bus-only lane enforcement system. To that end, infrared cameras and the You Only Look Once (YOLOv5) deep learning algorithm were utilized. For assessment of the performance of the developed system, two environments, including a controlled test-bed and a real-world freeway, were used. As a result, the performances under the test-bed and the real-world environments exhibited 7% and 8% errors, respectively, indicating satisfactory outcomes. The developed system would contribute to an efficient freeway bus-only lane operations as well as eliminate safety and delay concerns caused by the current manual enforcement procedures.
참고문헌 (19)
- Cantelli, M., "Xerox Vehicle Occupancy Detection System" (2013), Xerox Innovations Group
- Hao, X., "Occupant Detection through Near-Infrared Imaging", Tamkang Journal of Applied Science and Engineering, 14(3), pp.275~283 (2011)
- He, K., "Deep Residual Learning for Image Recognition", Proceedings of IEEE Conference of Computer Vision and Pattern Recognition (2016)
- "Intelligent Transport Systems Performance Evaluation Guidelines", Ministry of Land, Transport and Infrastructure, ~
- Jang, J., "High-Occupancy Vehicle Lane Enforcement System", The Open Transportation Journal (2021)
- A Review of the Effectiveness and Feasibility of HOV Lane on Freeway, "Jung, K.", Korea Transportation Institute, ~ (2012)
- Automated Vehicle Occupancy Monitoring Systems for HOV, "HOT Facilities", McCormick Rankin Corporation, 2004
- Sensing for HOV, "HOT Lanes Enforcement", Papanikolopoulos, N., 2017, Final Report 2017-05
- Pavlidis, I., "A Vehicle Occupant Counting System Based on Near-Infrared Phenomenology and Fuzzy Neural Classification", IEEE Transaction of Intelligent Transportation Systems, 1(2), pp.72~85 (2000)
- Pavlidis, I., "Automatic Detection of Vehicle Occupants: The Imaging Problem and Its Solution, vol. 11" (2000), Machine Vision and Applications
- Pavlidis, I., "Automatic Passenger Counting in the High Occupancy Vehicle (HOV) Lanes", Proceedings of 1999 Annual Meeting of Intelligent Transportation Society of America (1999)
- Pavlidis, I., "Automatic Detection of Vehicle Passengers through Near-Infrared Fusion", Proceedings of 1999 IEEE, JSAI International Conference of Intelligent Transportation Systems, pp.1999[DOI]
- Redmon, J., "YOLOv3: An Incremental Improvement", arXiv preprint arXiv:1804.02767, ~ (2018)
- Redmon, J., "You Only Look Once: Unified, Real-Time Object Detection", arXiv preprint arXiv:1506.02640, ~ (2015)
- Roulland, F., "Xerox Vehicle Passenger Detection System", Proceedings of 23rd World Congress on Intelligent Transport Systems (2016)
- Schijns, S., "WIT Transactions on The Built Environment vol. 89" (2006)
- Shorten, C., "A Survey on Image Data Augmentation for Deep Learning", Journal of Big Data (2019)
- "Speciality Construction News" (2022)[URL]
- Zhu, X., "TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios", Proceedings of the IEEE, 2021, ~