Urban Space Perception

Urban space perception research investigates how people experience and understand their built environment, aiming to improve urban design and planning based on these insights. Current research utilizes deep learning models, including convolutional neural networks and transformers, often coupled with explainable AI techniques like GradCAM, to analyze visual appeal and perceived safety from images and other data. This work leverages large language models (LLMs) to enhance understanding of urban spaces and integrates human perception alongside AI assessments to create more holistic and accurate models of urban experience, ultimately informing decisions that improve resident well-being and urban livability.