교통류에서는 거시적인 지표로 속도, 교통량, 밀도가 중요한 파라미터로 활용되고 있으며, 미시적인 지표로는 가속도와 차두거리가 중요한 파라미터로 활용되고 있다. 속도와 교통량은 현재 설치된 교통정보 수집장치로 수집이 가능하지만 가속도와 차두거리는 안전과 자율주행분야 등에 필요성이 있지만 현재 교통정보 수집장치로는 수집이 불가능한 실정이다. 객체인식 기법인 YOLO는 정확도와 실시간성이 우수하여 교통분야를 포함하여 다양한 분야에서 활용되고 있다. 본 연구에서는 YOLO를 활용하여 가속도와 차두거리를 측정하기 위해 측정 간격을 조밀하게 설정하여 간격별 차량의 속도 변화와 차량 간 통행시간 차이를 통해 가속도와 차두거리를 측정하는 모델을 개발하였다. 지점별 교통특성에 따라 가속도와 차두거리의 범위가 다름을 확인하였고, 측정률 확보를 위한 기준거리와 화면각도에 따른 비교분석을 수행하다. 측정간격은 20m, 각도는 직각에 가까울수록 측정률이 높아짐을 분석하였다. 이를 통해 교차로별 안전도 분석과 국내 차량행태모델 분석에 기여할 수 있을 것이다.
교통류에서는 거시적인 지표로 속도, 교통량, 밀도가 중요한 파라미터로 활용되고 있으며, 미시적인 지표로는 가속도와 차두거리가 중요한 파라미터로 활용되고 있다. 속도와 교통량은 현재 설치된 교통정보 수집장치로 수집이 가능하지만 가속도와 차두거리는 안전과 자율주행분야 등에 필요성이 있지만 현재 교통정보 수집장치로는 수집이 불가능한 실정이다. 객체인식 기법인 YOLO는 정확도와 실시간성이 우수하여 교통분야를 포함하여 다양한 분야에서 활용되고 있다. 본 연구에서는 YOLO를 활용하여 가속도와 차두거리를 측정하기 위해 측정 간격을 조밀하게 설정하여 간격별 차량의 속도 변화와 차량 간 통행시간 차이를 통해 가속도와 차두거리를 측정하는 모델을 개발하였다. 지점별 교통특성에 따라 가속도와 차두거리의 범위가 다름을 확인하였고, 측정률 확보를 위한 기준거리와 화면각도에 따른 비교분석을 수행하다. 측정간격은 20m, 각도는 직각에 가까울수록 측정률이 높아짐을 분석하였다. 이를 통해 교차로별 안전도 분석과 국내 차량행태모델 분석에 기여할 수 있을 것이다.
While analyzing traffic flow, speed, traffic volume, and density are important macroscopic indicators, and acceleration and spacing are the important microscopic indicators. The speed and traffic volume can be collected with the currently installed traffic information collection devices. However, ac...
While analyzing traffic flow, speed, traffic volume, and density are important macroscopic indicators, and acceleration and spacing are the important microscopic indicators. The speed and traffic volume can be collected with the currently installed traffic information collection devices. However, acceleration and spacing data are necessary for safety and autonomous driving but cannot be collected using the current traffic information collection devices. 'You Look Only Once'(YOLO), an object recognition technique, has excellent accuracy and real-time performance and is used in various fields, including the transportation field. In this study, to measure acceleration and spacing using YOLO, we developed a model that measures acceleration and spacing through changes in vehicle speed at each interval and the differences in the travel time between vehicles by setting the measurement intervals closely. It was confirmed that the range of acceleration and spacing is different depending on the traffic characteristics of each point, and a comparative analysis was performed according to the reference distance and screen angle to secure the measurement rate. The measurement interval was 20m, and the closer the angle was to a right angle, the higher the measurement rate. These results will contribute to the analysis of safety by intersection and the domestic vehicle behavior model.
While analyzing traffic flow, speed, traffic volume, and density are important macroscopic indicators, and acceleration and spacing are the important microscopic indicators. The speed and traffic volume can be collected with the currently installed traffic information collection devices. However, acceleration and spacing data are necessary for safety and autonomous driving but cannot be collected using the current traffic information collection devices. 'You Look Only Once'(YOLO), an object recognition technique, has excellent accuracy and real-time performance and is used in various fields, including the transportation field. In this study, to measure acceleration and spacing using YOLO, we developed a model that measures acceleration and spacing through changes in vehicle speed at each interval and the differences in the travel time between vehicles by setting the measurement intervals closely. It was confirmed that the range of acceleration and spacing is different depending on the traffic characteristics of each point, and a comparative analysis was performed according to the reference distance and screen angle to secure the measurement rate. The measurement interval was 20m, and the closer the angle was to a right angle, the higher the measurement rate. These results will contribute to the analysis of safety by intersection and the domestic vehicle behavior model.
Ha, T. J., Park, J. J. and Kim, Y. C.(2003), "Development of Highway Safety Evaluation Considering Design Consistency using Acceleration", Journal of Korea Society of Transportation, vol. 21, no. 1, pp.127-136.
Jeng, S. Y., Lioa, H. W. and Lin, C. J.(2021), "A Real-Time Vehicle Counting, Speed Estimation, and Classification System Based on Virtual Detection Zone and YOLO", Hindawi Mathematical Problems in Engineering, vol. 2021, p.1577614.
Jeong, M. S.(2014), A Study on Accident Severity Analysis Using Acceleration Noise, Seoul National University Graduate School.
Lakshmanan, V., Gorner, M. and Gillard, R.(2023), Practical! Machine Learning for Computer Vision, Wiki Books, pp.121-159.
Ministry of Land, Infrastructure and Transport(2023), ITS Performance Evaluation Standards in the Automobile and Road Traffic Sector, Ministry of Land, Infrastructure and Transport Notice No. 2023-21, pp.46-50.
Park, J. H., Oh, C. and Kang, K. P.(2011), "Assessment of Freeway Crash Risk using Probe Vehicle Accelerometer", Journal of Korean Society of Road Engineers, vol. 13, no. 2, pp.49-56.
Rais, A. H. and Munir, R.(2021) "Vehicle Speed Estimation Using YOLO, Kalman Filter, and Frame Sampling", ICAICTA(2021 8th International Conference on Advanced Informatics: Concepts, Theory and Applications), vol. 2021, no. 8, pp.1-6.
Redmon, J., Divvala, S., Girshick, R. and Farhadi, A.(2016), "You Only Look Once: Unified, Real-Time Object Detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp.779-788.
Wallace, B., Rockwood, M., Goubran, R., Knoefel, F., Marchall, S. and Porter, M.(2015), "Measurement of vehicle acceleration in studies of older drivers from GPS position and OBDII velocity sensors", 2015 IEEE International Symposium on Medical Measurement and Applications, pp.391-396.
AI-Helper
※ AI-Helper는 부적절한 답변을 할 수 있습니다.