Automated Detection Algorithm for Traffic Incident in Urban Expressway Based on Lengthways Time Series
The paper proposes an automatic traffic accident detection algorithm for the urban expressway. The algorithm is established on longitudinal time series theory based on catastrophe theory and statistics theory. The results: (1) the lengthways time series of traffic parameters data manifests a good stability than the transverse time series and it can detect accident when the losing data are more; (2) no matter what traffic flow stats are, the model can detect accident accurately. The model developed in the study can be directly used by traffic engineers and managers to detect traffic accident.
KeywordsUrban expressway Traffic accident detection Lengthways time series Catastrophe theory
This work was supported by National Natural Science Foundation of China (No. 71501061, 51408190 and 51608171), Natural Science Foundation of Jiangsu province (No. BK20150821), and Science and Technology Plan of Hubei Provincial Transport Department (No.2016-13-1-3).
- 2.Mahmassani, HS, Haas C, Zhou S, Peterman J (1998) “Evaluation of incident detection methodologies.” Research Report 1795-1. Center for Transportation Research, University of Texas at Austin, Austin, TXGoogle Scholar
- 3.Ouyang P, Zhang X, Sun L (2008) Traffic incident duration prediction grounded on bayesian decision method based tree algorithm. J Tongji Univ (Natural Science) 36(3):319–324Google Scholar
- 5.Payne HJ, Helfenbein ED, Knobel HC (1976) Development and testing of incident detection algorithms, vol 2: research methodology and results. Report No. FHWA-RD-76–20, Federal Highway AdministrationGoogle Scholar
- 7.Ahmed MS, Cook AR (1977) Analysis of freeway traffic time-series data using Box-Jenkins techniques. Transp Res Rec 722:1–9Google Scholar
- 8.Jenkins techniques.” Transportation Research Record, No. 722, TRB, National Research Council, 1–9Google Scholar