Detecting the city-scale spatial pattern of the urban informal sector by using the street view images: A street vendor massive investigation case

Abstract

Automatically obtaining information on informal practitioners, especially their spatial distribution, has proven challenging when using traditional methods. This study addresses this issue by presenting a street view deep learning method, called the Street Informal Practitioners Spatial Investigation (SIPSI) methodology. This paper's application of this technology focuses on the study case of the street vendor, which is one of the most visible occupations in the informal economy. There were 3907 street vendors that were detected using this method; as well, the kernel density estimation indicated that they agglomerated in a multi-core cluster pattern in the city. Further analysis of the factors that influence agglomeration shows that the street vendors prefer premises that are near the lower level of the road and the higher density population sites, whereas the NIMBY (Not In My Back Yard) syndrome keeps these vendors away from the central City Business Districts and high-rent regions. The presented methodology and the study results contribute to high-efficiency investigations of informal economy employment, and it further assists in advising for the spatial governance policies improvement and implementation in any cities whose street view images are abundant and open-access.