A method to identify black spot candidates in built-up areas

Abstract

ABSTRACTOne of the most important road safety interventions is the elimination of accident black spots (places with accident density higher than expected). The first step of this process is the identification of these locations. There are several methods for this purpose, but most of them are now outdated. The primary objective of our 5-year project was to adopt data collection and analysis methods according to the related developments of the last decades: (1) the spreading of global positioning system (GPS) technology, (2) the appearance of tablets and smartphones, and (3) the existence of critical amounts of accidental data (enough for data mining approaches). This article presents the final results of our examinations. The authors prepared several methods, regulations, and computer software to integrate these advancements into the daily routine. From the year 2011, Hungarian police officers have used smartphones to record all data about accidents while on the scene, including the GPS coordinates, which leads to more accurate and reliable location information. This allowed the authors to develop a novel black spot–searching algorithm (inspired by some data mining techniques), based on the GPS coordinates of accidents. The authors have implemented it as a web service, and the practical experience shows that it performs very well, especially in built-up areas. Compared to the sliding window method, the site consistency is significantly higher, whereas the method consistency and the rank consistency are quite similar.