Measurement method for objective cyclist behaviour parameters

Although, in The Netherlands the infrastructure has been made cyclist friendly, 78.400 cyclist were treated at the first aid because of an accident in 2014. Especially with the upcoming of various types of powered bikes, more detailed analyses on the safety critical situations for cy-clists is needed in order to adequately adapt and further optimise the infrastructure for cyclists. The objective of this research is to study the feasibility of developing a measurement method from which objective behaviour parameters can be defined. An experiment was performed us-ing 6 cameras above a separated cycle lane next to a road which included a crossing with both cyclists and cars. A learning method based on Single Shot MultiBox Detector was applied to au-tomatically detect the cyclists, and cyclist tracks were defined. Next, kinematic parameters were calculated from the cyclists’ tracks. Amongst others, the cyclists’ intensity, speed, position on the cycle lane, and the distance to each other were analysed for a busy period as well as for a quiet period of the day. It can be concluded that the developed measurement method provides insight of the cyclists’ behaviour in such a way that it can already be used for obtaining infor-mation to make changes to the infrastructure that will improve the comfort and safety of cy-clists. The method could be further developed for making qualitative comfort and safety anal-yses, and for making analyses of the interaction between various types of road participants.