Identification of Hazardous Situations using Kernel Density Estimation Method Based on Time to Collision, Case study: Left-turn on Unsignalized Intersection

Document Type : Research Paper


1 Assistant professor, Department of Civil and Environmental Engineering, Tarbiat Modares University, Tehran, Iran

2 MSc Student, Department of Civil and Environmental Engineering, Tarbiat Modares University, Tehran, Iran


The first step in improving traffic safety is identifying hazardous situations. Based on traffic accidents’ data, identifying hazardous situations in roads and the network is possible. However, in small areas such as intersections, especially in maneuvers resolution, identifying hazardous situations is impossible using accident’s data. In this paper, time-to-collision (TTC) as a traffic conflict indicator and kernel density estimation (KDE) method have been used to identify hazardous situations. KDE applies smooth function on critical TTC value events, this surface indicates risk changes. The maximum quantity of this function represents the hazardous situations. To assess and implement the presented method, left-turn on unsignalized intersection has been chosen. TTC data are determined by automated video analysis and coordinating TTC smaller than threshold value was used as input data in KDE method. Hazardous situations have been identified and the factors that caused them have been recognized using these results and performing safety audit. Two countermeasures are proposed to improve safety of left-turn in study location.


- Allen, B. L., Shin, B. T. and Cooper, D. J. (1978) "Analysis of traffic conflicts and collision" Transportation Research Record: Journal of the Transportation Research Board, 667, pp. 67-74.
- Almquist, S., Hyden, C. and Risser, R. (1991) "Use of speed limiters in cars for increased safety and a better environment" Transportation Research Record: Journal of the Transportation Research Board, 1318, pp. 34–39.
-Autey, J., Sayed, T. and Zaki, M. H. (2012) "Safety evaluation of right-turn smart channels using automated traffic conflict analysis" Accid Anal Prev, 45, pp. 120-30.
- Bil, M., Andrasik, R. and Janoska, Z. (2013) "Identification of hazardous road locations of traffic accidents by means of kernel density estimation and cluster significance evaluation" Accid Anal Prev, 55, pp. 265-73.
- Caltec. (2013) "Camera Calibration Toolbox for MATLAB" [Online]. Available: [Accessed 3/18/2013 2013].
- Cunto, F. and Saccomanno, F. F. (2007) "Microlevel traffic simulation method for assessing crash potential at intersections"  Proceedings of the 86th Annual Meeting of the Transportation Research Board, 2007 Washington, D.C.
- Duong, T. and Hazelton, M. (2003) "Plug-in bandwidth matrices for bivariate kernel density estimation" Journal of Nonparametric Statistics, 15(1), pp. 17-30.
- Duong, T. and Hazelton, M. L. (2005) "Cross-validation Bandwidth Matrices for Multivariate Kernel Density Estimation" Scandinavian Journal of Statistics, 32(3), pp. 485-506.
- El-Basyouny, K. and Sayed, T. (2013) "Safety performance functions using traffic conflicts" Safety Science, 51(1), pp. 160-164.
- Erdogan, S., Yilmaz, I., Baybura, T. and Gullu, M. (2008) "Geographical information systems aided traffic accident analysis system case study: city of Afyonkarahisar" Accid Anal Prev, 40(1), pp. 174-81.
- Guido, G., Saccomanno, F., Vitale, A., Astarita, V. and Festa, D. (2011) "Comparing Safety Performance Measures Obtained from Video Capture Data" Journal of Transportation Engineering, 137(7), pp. 481-491.
- Hayward, J. C. (1971) "Near misses as ameasure of safety at urban intersections" Doctoral Thesis, The Pensilvania State University.
- Horová, I., Koláček, J. and Zelinka, J. (2012) "Kernel smoothing in matlab" London, World Scientific.
- Ismail, K., Sayed, T. and Saunier, N. (2009b) "Automated pedestrian safety analysis using video data in the context of scramble phase intersections"  Annual Conference of the Transportation Association of Canada,  Vancouver, BC.
- Ismail, K., Sayed, T., Saunier, N. and Lim, C. (2009a) "Automated analysis of pedestrian-vehicle conflicts using video data" Transportation Research Record: Journal of the Transportation Research Board, 2140(-1), pp. 44-54.
- Ismail,  Karim, Sayed, Tarek  and Saunier, Nicolas (2012) "Camera calibration for urban traffic scenes: practical issues and a robust approach". Transportation Research Board 89th Annual Meeting. Washington DC
- Jin, S., Qu, X. and Wang, D. (2011) "Assessment of expressway traffic safety using Gaussian mixture model based on time to collision" International Journal of Computational Intelligence Systems, 4(6), pp. 1122-1130.
- Jin, S., Wang, D.-H., Xu, C. and Ma, D.-F. (2013) "Short-term traffic safety forecasting using Gaussian mixture model and Kalman filter" Journal of Zhejiang University SCIENCE A, 14(4), pp. 231-243.
-Laureshyn, A., Ardö, H., Svensson, A. and Jonsson, T. (2009a) "Application of automated video analysis for behavioural studies: concept and experience" IET Intelligent Transport Systems, 3(3), pp. 345.
- Laureshyn, A., Åström, K. and Brundell-Freij, K. (2009b) "From speed profile data to analysis of behaviour" IATSS research, 33(2), pp. 89.
- Laureshyn, A., Svensson, A. and Hyden, C. (2010) "Evaluation of traffic safety, based on micro-level behavioural data: theoretical framework and first implementation" Accid Anal. Prev, 42(6), pp. 1637-46.
- Mehmood, A., Saccomanno, F. and Hellinga, B. (2001) "Simulation of road accidents by use of systems dynamics" Transportation Research Record: Journal of the Transportation Research Board, 1746, pp. 37–46.
- Minderhoud, M. M. and Bovy, P. H. L. (2001) "Extended time-to-collision measures for road traffic safety assessment" Accid Anal Prev, 33(1), pp. 89-97.
- Oh, C. and Kim, T. (2010) "Estimation of rear-end crash potential using vehicle trajectory data" Accid Anal Prev, 42(6), pp. 1888-93. 
- Perkins, S. R. and Harris, J. L. (1967) "Criteria for traffic conflicts characteristics". Report GMR 632. General Motors Corporation.
- Sayed, T., Brown, G. and Navin, F. (1994) "Simulation of traffic conflicts at unsignalized intersections with TSC-Sim" Accident Analysis & Prevention, 26(5), pp. 593-607.
- Sayed, T., Ismail, K., Zaki, M. and Autey, J. (2012) "Feasibility of computer vision-based safety evaluations" Transportation Research Record: Journal of the Transportation Research Board, 2280(-1), pp. 18-27.
- Sayed, T. and Saunier, N. (2008) "Probabilistic framework for automated analysis of exposure to road Collisions" Transportation Research Record: Journal of the Transportation Research Board, 2083(-1), pp. 96-104.
- Sayed, T., Zaki, M. H. and Autey, J. (2013) "Automated safety diagnosis of vehicle–bicycle interactions using computer vision analysis" Safety Science, 59, pp. 163–172.
- Sayed, T. and Zein, S. (1999) "Traffic conflict standards for intersections" Transportation Planning and Technology, 22(4), pp. 309-323.
- Silverman, B. W. (1986) "Density estimation for statistics and data analysis" London, Chapman and Hall.
- Vogel, K. (2003) "A comparison of headway and time to collision as safety indicators" Accid Anal Prev, 35(3), pp. 427-433.
- Weiming, H., Xuejuan, X., Xie, D., Tieniu, T. and Maybank, S. (2004) "Traffic accident prediction using 3-D model-based vehicle tracking" Vehicular Technology, IEEE Transactions on, 53(3), pp. 677-694.
- World Health Organisation (2013) "Global status report on road safety : supporting a decade of action". Switzerland: WHO
- Xie, Z. and Yan, J. (2008) "Kernel density estimation of traffic accidents in a network space" Computers, Environment and Urban Systems, 32(5), pp. 396-406.
- Yu, H., Liu, P., Wang, H. and Liang, Q. (2012) "Kernel density estimation based method for hazardous road segments identification" CICTP 2012, pp. 2095-2106.