2011 TRB PapersPosted: December 12, 2010
The three papers I co-authored for the 2011 TRB Annual Meeting are now online on my website. Watch out in particular for our paper applying data mining techniques to study the similarities of traffic conflicts and collisions: N. Saunier, N. Mourji, and B. Agard. Investigating collision factors by mining microscopic data of vehicle conflicts and collisions. In Transportation Research Board Annual Meeting Compendium of Papers, Washington, D.C., January 2011. 11-0117.
Road collisions represent deplorable human and financial costs to society. Although some progress has been made, a renewed effort is necessary to tackle this growing worldwide issue. This paper advocates the development of proactive methods for road safety analysis that do not depend on the occurrence of collisions. In particular, collecting and analyzing microscopic data (road users’ trajectories) about all traffic events with and without a collision is the only way to gain insight into collision factors and processes, i.e. the chains of events that lead to collisions. This paper reports on the first phase of a project relying on microscopic data extracted from video sensors and data mining techniques to identify patterns in the traffic event database. Decision trees, the k-means algorithm and a hierarchical agglomerative clustering method are used to analyze the relationship between interaction attributes and outcome (collision or not) and identify groups of interactions with similar attributes. This approach is demonstrated on a dataset collected in Kentucky of 295 traffic events, constituted of 213 conflicts and 82 collisions. The decision tree confirms the importance of the evasive action in the interaction outcome. Three clusters are found based on speed indicators extracted from the road users’ trajectories: one cluster contains few collisions, with the lowest speeds among the three clusters. This result hints at the existence of conflicts that are dissimilar from most collisions and may therefore not be suitable for surrogate safety analysis.