UMS’s latest research, published in Cities (JCR Q1, IF 6.6), shows that how a city changes between scenes predicts how it feels, far better than single views.
The paper, “Beyond single snapshots: Quantifying multi-scale heterogeneity from street-view imagery and what it reveals about perception,” was authored by Guosheng Yang, Yunlei Su, Minwei Zhao, Chaosu Li, and Cai Wu. It appears in Cities and is available at https://doi.org/10.1016/j.cities.2026.107227.
We are excited to share the latest publication from the Urban Morphology Studio. Using nearly 69,000 street-view images and 2 million geotagged social media posts from Guangzhou, the study reframes how computational urban analytics should measure visual experience by moving from point-based assessment to trajectory-based assessment.
The study also provides the first large-scale empirical validation of a proposition urban designers have held for more than half a century: transitions between scenes matter as much as the scenes themselves.
This work was conducted by researchers affiliated with the Urban Governance and Design Thrust at The Hong Kong University of Science and Technology (Guangzhou).