Identification and Characterization of Lanes in Pedestrian Flows Through a Clustering Approach

Pedestrian behavioral dynamics have been growingly investigated by means of (semi)automated computing techniques for almost two decades, exploiting advancements on computing power, sensor accuracy and availability, computer vision algorithms. This has led to a unique consensus on the existence of significant difference between uni-directional and bi-directional flows of pedestrians, where the phenomenon of lane formation seems to play a major role. This collective behavior emerges in condition of variable density and due to a self-organization dynamics, for which pedestrians are induced to walk following preceding persons to avoid and minimize conflictual situations. Although the formation of lanes is a well-known phenomenon in this field of study, there is still a lack of methods offering the possibility to provide an (even semi-)automatic identification and a quantitative characterization. In this context, the paper proposes an unsupervised learning approach for an automatic detection of lanes in multi-directional pedestrian flows, based on the DBSCAN clustering algorithm. The reliability of the approach is evaluated through a inter-agreement test between a human expert coder and the results of the automated analysis.