Journal of Industrial Convergence (산업융합연구)

DAEHAN Society of Industrial Management (대한산업경영학회)
권호 표지
DOI QR코드

DOI QR Code

A Travel Speed Prediction Model for Incident Detection based on Traffic CCTV

돌발상황 검지를 위한 교통 CCTV 기반 통행속도 추정 모델

  • 기용걸 (도로교통공단 ICT융합처) ;
  • 김용호 (도로교통공단 기획본부)
  • Received : 2020.04.27
  • Accepted : 2020.06.20
  • Published : 2020.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Travel speed is an important parameter for measuring road traffic and incident detection system. In this paper I suggests a model developed for estimating reliable and accurate average roadway link travel speeds using image processing sensor. This method extracts the vehicles from the video image from CCTV, tracks the moving vehicles using deep neural network, and extracts traffic information such as link travel speeds and volume. The algorithm estimates link travel speeds using a robust data-fusion procedure to provide accurate link travel speeds and traffic information to the public. In the field tests, the new model performed better than existing methods.

통행속도는 도로의 교통상황을 측정하고, 교통사고와 같은 돌발상황 발생을 검지하는데 활용되는 중요한 정보이다. 본 논문에서 영상처리 기술을 활용하여 도로구간의 통행속도를 정확하게 측정하는 모델을 제안하였다. 제안 모델은 교통 CCTV 영상에서 차량 객체를 추출하고, 딥러닝 기술 등을 활용하여 차량을 추적하여, 도로구간의 통행속도 및 교통량 등과 같은 교통정보를 수집한다. 또한, 새로운 모델은 데이터 융합기술을 활용하여 정확한 구간통행속도를 수집하여 사용자에게 제공하는 것이 가능하다. 제안 모델을 서울시 오금교에서 현장실험한 결과, 기존 교통정보센터 통행속도 정확도(62.8%)보다 새 모델의 정확도가 높은 것(83.6%)을 확인하였다.

Keywords

References

  1. G. H. Ahn, Y. K. Ki & E. J. Kim (2014). Real-time Estimation of Travel Speed Using Urban Traffic Information System and Filtering Algorithm. In IET Intelligent Transport Systems, 8(2), 145-154. https://doi.org/10.1049/iet-its.2012.0051
  2. Y. K. Ki, G. H. Ahn, E. J. Kim & K. S. Bae, (2011). Imputation Model for Link Travel Speed Measurement Using UTIS. Journal of The Korean Institute of Intelligent Transport Systems, 10(6), 63-73.
  3. Y. K. Ki, G. H. Ahn, E. J. Kim & K. S. Bae. (2012). A Study on the construction of Historical Profiles for Travel Speed Prediction Using UTIS. Journal of The Korean Institute of Intelligent Transport Systems, 11(6), 40-48. https://doi.org/10.12815/kits.2012.11.6.40
  4. Chi Xie, Reuy Long Cheu & Der-Horng Lee. (2004, January). Improving Arterial Link Travel Time Estimation by Data Fusion, TRB 2004 Annual Meeting, Washington, D.C. TRB.
  5. Cohn. N. (2009). Real-Time Traffic Information and Navigation. In Transportation Research Record: Journal of the Transportation Research Board, 2129, 129-135. https://doi.org/10.3141/2129-15
  6. John N. Ivan, Joseph L Schofer, Frank s. Koppeleman & Lina L. E. (1997). Real-time Data Fusion for Arterial Street Incident Detection Using neural Networks., In Transportation Research Record: Journal of the Transportation Research Board, (1497).
  7. G. J. Choi & Y. S. Jeong. (1999). A Development of Travel Time Estimation Algorithm Fusing GPS Probe and Loop Detector. Journal of Korea Transportation Research Society, 17(3), 97-116.
  8. Y. C. Kim & T. Y. Kim. (2001). On-Line Travel Time Estimation Methods Using Hybrid Neuro Fuzzy System for Arterial Road. Journal of Korea Transportation Research Society, 19(6), 171-182.
  9. Y. I. Lee & J. H. Lee. (2002). A study on Link Travel Time Estimating Methodology for Traffic Information Service. Journal of Korea Transportation Research Society, 20(3), 55-67.
  10. Y. K. Ki, W. T. Jeong, H. J. Kwon & M. R. Kim, (2019, November). An Algorithm for Incident Detection Using Artificial Neural Networks. In Proc, 25th FRUCT, Finland. FRUCT.
  11. Kenan Mu, Fei Hui & Xiangmo Zhao, (2016). Multiple Vehicle Detection and Tracking in Highway Traffic Surveillance Video Based on SIFT Feature Matching, Journal of Information Processing Systems, 12(2), 183-195. https://doi.org/10.3745/JIPS.02.0040
  12. Y. K. Ki & D. Y. Lee, (2007). A Traffic Accident Recording and Reporting Model at Intersections. IEEE Trans. Intell. Transp. Syst., 8(2), 188-194. https://doi.org/10.1109/TITS.2006.890070