SIM: a framework for geometric measurement of built environment features using street view imagery

Built environment auditing refers to the systematic documentation and assessment of the physical, social, and environmental characteristics of urban and rural spaces, including walkability, road conditions, and traffic lights. Traditionally, built environment audits were conducted using field surveys and manual observations, which are time-consuming and costly. The emerging street view imagery, e.g. Google Street View, has become a widely used data source for conducting built environment audits remotely. Deep learning and computer vision techniques can extract and classify objects from street images to enhance auditing productivity. However, mapping methods and tools based on street images are underexplored, and no universal frameworks or solutions exist yet, which poses difficulties for auditing street objects. In this study, we introduced an open-source street view mapping framework, providing three pipelines to map and measure: (1) width measurement for ground objects, such as roads; (2) 3D localization for objects with a known dimension (e.g. doors and stop signs); and (3) diameter measurements (e.g. street trees). Three case studies, including road width measurement, stop sign localization, and street tree diameter measurement, are provided in this paper to showcase pipeline usage.