Identifying the Indoor Space Characteristics for Spatial Status Monitoring of Railway Station based on Pedestrian Trajectory Data

초록

Stations are being transformed into complex living spaces that have various functionalities, including being spaces of work, commerce, and leisure, rather than simply being a space for the public transportation. To support the various needs and expectations of this expansion, it is necessary to investigate and understand various types of spatial utilization patterns generated by users. This study proposes a method for clustering of the pedestrian space of a railway station using the pedestrian trajectory data collected from the actual operating station, and for defining the spatial usability of the movement and stay through the results of the clustering. The clustering procedure proposed in this study comprises four steps: data collection, feature vector extraction, K-means clustering, and cluster characteristics analysis. As a result of the analysis through spatial clustering proposed in this study, it was demonstrated that there are various space types, according to the space occupation characteristics of pedestrians. In particular, the importance of the spatial analysis reflecting the pedestrian’ travel behavior was emphasized. The proposed methodology can be applied to space management and monitoring through spatial diagnosis for the utilization patterns of actual pedestrians. In addition, it can support flexible responses for unexpected events by proactively monitoring the occupation pattern of indoor space according to whether the flow is normal or in the event of an emergency.