Anomaly Detection of Pedestrian Flow: A Machine Learning Method for Monitoring-Data of Visitors to a Building


  • Kentaro Kumagai Graduate School of Management, Kyoto University Maskawa Bld. for Res. and Ed., Kitashirakawa-Oiwake, Sakyo, Kyoto, Japan and Disaster Prevention Research Institute, Kyoto University, Kitashirakawa-Oiwake, Sakyo, Kyoto, Japan



anomaly detection, pedestrian flow, integrated system, iot sensor, machine learning


Many public facilities such as community halls and gymnasiums are supposed to be evacuation sites when disasters occur. From the viewpoint of managing such facilities, it is necessary to monitor the usage and to respond immediately when an anomaly occurs. In this study, an integrated system of IoT sensors and machine learning for anomaly detection of pedestrian flow was proposed for buildings that are expected to be used as emergency evacuation sites in the event of a disaster. For trial practice of the system, infrared sensors were installed in a research building of a university, and data of visitors to the fourth floor of the building was collected as a time series data of pedestrian flow. As a result, it was shown that anomalies of pedestrian flow at an arbitrary time of a day with an occurrence probability of 5 % or less can be detected properly using the data collected.


T. Ide, Introduction of Anomaly Detection by Machine Learning - Practical Guide by R, Corona

Publishing Co.,Ltd., ISBN 9784339024913, 2015.

T. Ide and M. Sugiyama, Anomary Detection and Change Detection, Machine Learning Professional

Series, Kodansha Ltd., ISBN 9784061529083, 2015.

M. Jin, Data Science by R - from the Foundation of Data Analysis to the Latest Method, Morikita

Publishing Co., Ltd., ISBN 9784627096028, 2017.




How to Cite

Kumagai, K. (2020). Anomaly Detection of Pedestrian Flow: A Machine Learning Method for Monitoring-Data of Visitors to a Building. Collective Dynamics, 5, 41–45.



Proceedings of Pedestrian and Evacuation Dynamics 2018