Self-supervised learning unveils change in urban housing from street-level images

TL;DR

This paper introduces Street2Vec, a self-supervised learning method that analyzes 15 million street images over 13 years to detect urban housing changes in London, aiding urban planning without manual labels.

Contribution

The paper presents a novel self-supervised approach, Street2Vec, that effectively captures urban structural changes from street images over time, outperforming generic embeddings.

Findings

Successfully identified point-level housing changes in London.

Distinguished between major and minor urban changes.

Outperformed generic embedding methods in change detection.

Abstract

Cities around the world face a critical shortage of affordable and decent housing. Despite its critical importance for policy, our ability to effectively monitor and track progress in urban housing is limited. Deep learning-based computer vision methods applied to street-level images have been successful in the measurement of socioeconomic and environmental inequalities but did not fully utilize temporal images to track urban change as time-varying labels are often unavailable. We used self-supervised methods to measure change in London using 15 million street images taken between 2008 and 2021. Our novel adaptation of Barlow Twins, Street2Vec, embeds urban structure while being invariant to seasonal and daily changes without manual annotations. It outperformed generic embeddings, successfully identified point-level change in London's housing supply from street-level images, and distinguished between major and minor change. This capability can provide timely information for urban planning and policy decisions toward more liveable, equitable, and sustainable cities.