Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

An AI-based framework for studying visual diversity of urban neighborhoods and its relationship with socio-demographic variables.

In Journal of computational social science

This study presents a framework to study quantitatively geographical visual diversities of urban neighborhood from a large collection of street-view images using an Artificial Intelligence (AI)-based image segmentation technique. A variety of diversity indices are computed from the extracted visual semantics. They are utilized to discover the relationships between urban visual appearance and socio-demographic variables. This study also validates the reliability of the method with human evaluators. The methodology and results obtained from this study can potentially be used to study urban features, locate houses, establish services, and better operate municipalities.

Amiruzzaman Md, Zhao Ye, Amiruzzaman Stefanie, Karpinski Aryn C, Wu Tsung Heng

2022-Dec-28

Google street-view, Interrater reliability, Semantic segmentation, Social phenomena, Urban neighborhood, Visual diversity