“streetscape” package in R: A reproducible method for analyzing open-source street view datasets and facilitating research for urban analytics

Abstract

Street view imagery (SVI) is an increasingly important data source for urban analytics and environmental researchers studying the visual quality of the built environment. Compared to remote sensing imagery, SVI can provide a different plane of perspective at ground level and better determine the interplay between urban physical settings and socio-ecological factors that enhance well-being and sustainability. Mapillary, a platform for volunteered street view imagery, has emerged as a promising alternative to Google Street View, offering greater accessibility. Nonetheless, the utility of this open-source database can be limited by the current Mapillary Application Programming Interface (API), which only partially meets the needs of urban analytics research. To address this, we introduce ''streetscape,'' an R package designed to provide user-friendly functions for collecting and analyzing street view imagery data from Mapillary. In addition, the package supports the generation of surveys for the qualitative study of urban landscapes.

Keywords

• Urban analytics
• Street-level imagery
• Urban greenery
• Urban landscape
• Urban perception
• R package