차량 블랙박스 카메라를 이용한 도시부 교통상태 추정
Estimation of Urban Traffic State Using Black Box Camera
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
도심지역의 교통 상태는 효과적인 교통 운영과 교통 제어를 수행하는 데 필수 요소이다. 하지만 교통 상태를 얻기 위해서 수많은 도로 구간에 교통 센서를 설치하는 것은 막대한 비용이 든다. 이를 해결하기 위해서 시장침투율이 높은 센서인 차량 블랙박스 카메라를 이용하여교통 상태를 추정하는 것이 효과적이다. 하지만 기존의 방법론은 객체 추적 알고리즘이나 광학 흐름과 같이 계산 복잡도가 높고, 연속된 프레임이 있어야 연산을 수행할 수 있다는 단점이존재한다. 이에 본 연구에서는 심층학습 모델로 차량과 차선을 탐지하고, 차선 사이의 공간을관심 영역으로 설정하여 해당 영역의 교통밀도를 추정하는 방법을 제안하였다. 이 방법론은객체 탐지 모델만을 이용해서 연산량이 적고, 연속된 프레임이 아닌 샘플링된 프레임에 대해교통 상태를 추정할 수 있다는 장점이 있기에, 보유하고 있는 컴퓨팅 자원에 맞는 교통 상태추정이 가능하다. 또, 도심지역에서 운행하는 서로 다른 특성의 2개의 버스 노선에서 수집한블랙박스 영상을 검증한 결과, 교통밀도 추정 정확도가 90% 이상인 것을 확인하였다.
Abstract
Traffic states in urban areas are essential to implement effective traffic operation and traffic control. However, installing traffic sensors on numerous road sections is extremely expensive. Accordingly, estimating the traffic state using a vehicle-mounted camera, which shows a high penetration rate, is a more effective solution. However, the previously proposed methodology using object tracking or optical flow has a high computational cost and requires consecutive frames to obtain traffic states. Accordingly, we propose a method to detect vehicles and lanes by object detection networks and set the region between lanes as a region of interest to estimate the traffic density of the corresponding area. The proposed method only uses less computationally expensive object detection models and can estimate traffic states from sampled frames rather than consecutive frames. In addition, the traffic density estimation accuracy was over 90% on the black box videos collected from two buses having different characteristics.
참고문헌 (26)
- Benkraouda, O., "Traffic data imputation using deep convolutional neural networks", IEEE Access, 8, pp.104740~104752 (2020)
- Chen, X., "Vehicle Trajectory Reconstruction at Signalized Intersections Under Connected and Automated Vehicle Environment", IEEE Transactions on Intelligent Transportation Systems, 23(10), pp.17986~18000 (2022)
- Geroliminis, N., "Macroscopic modeling of traffic in cities", Transportation Research Board 86th Annual Meeting (2007)
- Gokasar, I., "Real-time prediction of traffic density with deep learning using computer vision and traffic event information", 2021 International Conference on Innovations in Intelligent Systems and Applications (2021)
- Gupte, S., "Detection and classification of vehicles", IEEE Transactions on Intelligent Transportation Systems, 3(1), pp.37~47 (2002)
- Kar, G., "Real-time traffic estimation at vehicular edge nodes", IEEE, 2017, 1~13
- 김민정, "영상기반 차량인식 기법을 이용한 교통류 추정에 관한 연구", 한국ITS학회 논문지, 18(6), pp.110~123 (2019), 한국ITS학회[DOI]
- Kim, S., "Visual extensions and anomaly detection in the pNEUMA experiment with a swarm of drones", Transportation Research Part C: Emerging Technologies, 147, pp.103966~ (2023)
- Lee, H., "Traffic density estimation using vehicle sensor data", Journal of Intelligent Transportation Systems, 26(6), pp.675~689 (2022)
- Magee, D. R., "Tracking multiple vehicles using foreground, background and motion models", Image and Vision Computing, 22(2), pp.143~155 (2004)
- Mehran, B., "Implementing kinematic wave theory to reconstruct vehicle trajectories from fixed and probe sensor data", Transportation Research Part C : Emerging Technologies, 20(1), pp.144~163 (2012)
- Nantes, A., "Real-time traffic state estimation in urban corridors from heterogeneous data", Transportation Research Part C : Emerging Technologies, 66, pp.99~118 (2016)
- Pandey, A., "Assessment of Level of Service on urban roads: A revisit to past studies", Advances in Transportation Studies, 57 (2022)
- Parisot, C., "Real-time road traffic classification using on-board bus video camera", 2008 11th International IEEE Conference on Intelligent Transportation Systems, pp.189~196 (2008)
- Park, B., "A method for measuring accurate traffic density by aerial photography", Journal of Advanced Transportation, 49(4), pp.568~580 (2015)
- Schuricht, P., "Efficiency-increasing driver assistance at signalized intersections using predictive traffic state estimation", 2011 14th International IEEE Conference on Intelligent Transportation Systems, pp.347~352 (2011)
- Shahrbabaki, M., "A data fusion approach for real-time traffic state estimation in urban signalized links", Transportation Research Part C : Emerging Technologies, 92, pp.525~548 (2018)
- Smulders, S., "Control of freeway traffic flow by variable speed signs", Transportation Research Part B : Methodological, 24(2), pp.111~132 (1990)
- Sun, Z., "Vehicle trajectory reconstruction for signalized intersections using mobile traffic sensors", Transportation Research Part C : Emerging Technologies, 36, pp.268~283 (2013)
- Sun, Z., "Improving the performance of on-road vehicle detection by combining gabor and wavelet features", IEEE 5th International Conference on Intelligent Transportation Systems, pp.130~135 (2002)
- Tabelini, L., "Keep your Eyes on the Lane : Real-time Attention-guided Lane Detection", IEEE, 2021, 294~302
- Thodi, B., "Incorporating kinematic wave theory into a deep learning method for high-resolution traffic speed estimation", IEEE Transactions on Intelligent Transportation Systems, 23(10), pp.17849~17862 (2022)
- "Ultralytics"[URL]
- Umair, M., "Efficient Video-based Vehicle Queue Length Estimation using Computer Vision and Deep Learning for an Urban Traffic Scenario", Processes, 9(10), pp.1786~ (2021)
- Xie, X., "A generic data assimilation framework for vehicle trajectory reconstruction on signalized urban arterials using particle filters", Transportation Research Part C : Emerging Technologies, 92, pp.364~391 (2018)
- Zheng, T., "CLRNet : Cross Layer Refinement Network for Lane Detection", IEEE, 2022, 898~907