Comparison of Different Road Segmentation Methods

  • Maen Qaseem Ghadi Budapest University of Technology and Economics
  • Árpád Török Budapest University of Technology and Economics
Keywords: K-means clustering, road segmentation, safety performance function, road accidents, homogeneous segment


In road safety, the process of organizing road infrastructure
network data into homogenous entities is called segmentation.
Segmenting a road network is considered the
first and most important step in developing a safety performance
function (SPF). This article aims to study the benefit
of a newly developed network segmentation method which is based on the generation of accident groups applying K-means clustering approach. K-means algorithm has been used to identify the structure of homogeneous accident groups. According to the main assumption of the proposed clustering method, the risk of accidents is strongly influenced by the spatial interdependence and traffic attributes of the accidents. The performance of K-means clustering was compared with four other segmentation methods applying constant average annual daily traffic segments, constant length segments, related curvature characteristics and a multivariable method suggested by the Highway Safety Manual (HSM). The SPF was used to evaluate the performance of the five segmentation methods in predicting accident frequency. K-means clustering-based segmentation method has been proved to be more flexible and accurate than the other models in identifying homogeneous infrastructure segments with similar safety characteristics.

Author Biographies

Maen Qaseem Ghadi, Budapest University of Technology and Economics
Engineering-Department of Transport Technology and EconomicsPhD student
Árpád Török, Budapest University of Technology and Economics

Engineering-Department of Transport Technology and Economics



[1] Federal Highway Administration. Federal Highway Administration. Safety Analyst Overview. 2009a [Internet]. 2010 [cited 2010 Feb 16]. Available from:
[2] Gupta M, Solanki VK, Singh VK. Analysis of Datamining Technique for Traffic Accident Severity Problem: A Review. In: Proceedings of the Second International Conference on Research in Intelligent and Computing in Engineering [Internet]. ACSIS; 2017. p. 197-9. Available from:
[3] Black WR, Thomas I. Accidents on belgium’s motorways: a network autocorrelation analysis. J Transp Geogr. 1998 Mar;6(1): 23-31. Available from:
[4] Sadeghi A, Ayati E, Neghab MP. Identification and prioritization of hazardous road locations by segmentation and data envelopment analysis approach. Promet - Traffic - Traffico. 2013;25(2): 127-36. Available from:
[5] Kwon OH, Park MJ, Yeo H, Chung K. Evaluating the performance of network screening methods for detecting high collision concentration locations on highways. Accid Anal Prev. 2013;51: 141-9.
[6] Thomas I. Spatial data aggregation: exploratory analysis of road accidents. Accid Anal Prev. 1996;28(2): 251-64.
[7] Koorey G. Road Data Aggregation and Sectioning Considerations for Crash Analysis. Transp Res Rec J Transp Res Board. 2009;2103(1):61–8. Available from: doi:10.3141/2103-08
[8] Cafiso S, D’Agostino C, Persaud B. Investigating the influence of segmentation in estimating safety performance functions for roadway sections. TRB 92nd Annu Meet. 2013;15.
[9] P. Resende RB. Effect of roadway section length on accident modeling traffic congestion and traffic safety. In: The 21st Century Conference, II. Chicago. ASCE; 1997.
[10] Fayyad U, Piatetsky-Shapiro G, Smyth P. From data mining to knowledge discovery in databases. AI Mag. 1996; 37-54. Available from:
[11] Depaire B, Wets G, Vanhoof K. Traffic accident segmentation by means of latent class clustering. Accid Anal Prev. 2008;40(4): 1257-66.
[12] De Luca M, Mauro R, Lamberti R, Dell’Acqua G. Road Safety Management Using Bayesian and Cluster analysis. Procedia - Soc Behav Sci. 2012;54: 1260-9. Available from:
[13] Ghadi M, Török Á, Tánczos K. Integration of Probability and Clustering Based Approaches in the Field of Black Spot Identification. Period Polytech Civ Eng. 2018 Oct 19; Available from:
[14] Kumar S, Toshniwal D. A data mining framework to analyse road accident data. J Big Data. 2015;2(1).
[15] Ghadi M, Török Á. Comparison Different Black Spot Identification Methods. In: Transportation Research Procedia. 2017;27: 1105-12.
[16] Everitt BS, Landau S, Leese M, Stahl D. Cluster Analysis. 5th Edition [Internet]. Wiley Series in Probability and Statistics; 2011. Available from:
[17] Flahaut B, Mouchart M, San Martin E, Thomas I. The local spatial autocorrelation and the kernel method for identifying black zones: A comparative approach. Accid Anal Prev. 2003;35(6): 991-1004.
[18] Calinski T, Harabasz J. A dendrite method for cluster analysis. Commun Stat - Theory Methods. 1974;3(1): 1-27. Available from: doi:abs/10.1080/03610927408827101
[19] American Association of State Highway and Transportation Officials. Highway Safety Manual. 1st Edition; 2010.
[20] Pan W. Akaike’s information criterion in generalized estimating equations. Biometrics. 2001;57(1): 120-5.
[21] Smyth GK. Pearson’s Goodness of Fit Statistic as a Score Test Statistic. Sci Stat A Festschrift Terry Speed. 2003;40(March): 1-12. Available from:
How to Cite
Ghadi M, Török Árpád. Comparison of Different Road Segmentation Methods. Promet - Traffic & Transportation [Internet]. 18Apr.2019 [cited 25May2019];31(2):163-72. Available from: