August 25, 2025SustainabilityOpen Access

Assessing Urban Safety Perception Through Street View Imagery and Transfer Learning: A Case Study of Wuhan, China

View Full Paper

Ask AI

Bookmark

Safety perception displays a distinctly clustered spatial distribution, primarily along arterial roads and transit corridors.
Achieving a classification accuracy of 78.3%, a convolutional neural network model was applied to assess street scenes.
Spatial clustering and correlation analysis revealed moderate associations with road characteristics and weak ties to housing prices.
This approach offers practical insights and framework for urban planners to enhance safety in urban environments.

Authors

Discussion

No takes yet. Share an insight, caveat, or question.

Analysis reveals urban safety perception clusters near major roads in Wuhan, indicating transfer learning's potential for urban planning.

Chen et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark