Understanding volume and correlations of automated walk count: Predictors for necessary, optional, and social activities in Dilworth Park

Abstract

In this paper, we explore the potential use of automated pedestrian walk count data in urban design research. The Center City District (CCD) research group used computer vision to collect automated pedestrian walk data from Dilworth Park, Philadelphia. By comparing the count data and participant observations of social activities in the park, we found that the frequencies of social activities in the park could be predicted by the pedestrian count when considering the outdoor thermal comfort index and the types of events taking place in Dilworth Park. By examining correlations among multiple sensors, we found that the entry?exit correlation is a useful indicator to assess how people use public space by estimating the ratio of necessary-tooptional activities.