Uncovering Dominant Social Class in Neighborhoods through Building Footprints: A Case Study of Residential Zones in Massachusetts using Computer Vision

TL;DR

This study uses deep learning and visual features of urban form to predict and analyze social class distribution in neighborhoods, demonstrating the potential of computer vision in urban socioeconomic research.

Contribution

It introduces a novel approach combining deep learning and handcrafted features to uncover social class from urban form at a large scale.

Findings

Deep learning effectively predicts social class from urban form.

Handcrafted features reveal specific morphological properties linked to social class.

The method demonstrates high accuracy in classifying neighborhoods by income level.

Abstract

In urban theory, urban form is related to social and economic status. This paper explores to uncover zip-code level income through urban form by analyzing figure-ground map, a simple, prevailing and precise representation of urban form in the field of urban study. Deep learning in computer vision enables such representation maps to be studied at a large scale. We propose to train a DCNN model to identify and uncover the internal bridge between social class and urban form. Further, using hand-crafted informative visual features related with urban form properties (building size, building density, etc.), we apply a random forest classifier to interpret how morphological properties are related with social class.