Measuring Perceptions of Walkable Streetscapes in Cultural Heritage Contexts

This study examines pedestrian perceptions of streetscapes in Isfahan’s cultural heritage site by integrating deep learning–based image segmentation with urban morphological analysis. It addresses the opportunity to develop a scalable and context-sensitive method for assessing pedestrian-oriented heritage streetscapes, particularly where conventional street-view datasets are unavailable. Using a U-Net model applied to First-Person Pedestrian View (FPPV) images, five perceptual indices, imageability, enclosure, human scale, greenness, and walking index, were quantified to examine their associations with pedestrian experience. Street width was incorporated as a morphological variable to explore its relationship with perceptual qualities using Spearman correlation and visual trend analysis. The results indicate exploratory associations between visual composition and perceptual outcomes within the analysed heritage streetscape context, particularly between imageability, enclosure, and vegetation structure. In contrast, variables such as human scale and walking index showed weak or negligible associations with street width, indicating that pedestrian activity patterns within the analysed heritage streetscape may be influenced by additional spatial, landscape, and socio-functional factors beyond dimensional characteristics alone. Segmentation-based analysis achieved an accuracy of 83% in classifying dominant streetscape elements, offering a reproducible alternative to traditional survey-based methods. This study contributes a data-driven framework for assessing pedestrian streetscapes, emphasising morphological continuity, human-scale design, and green infrastructure as important dimensions of walkability assessment. It also identifies key challenges, including fragmented spatial morphology and inconsistent urban furniture placement, which may affect pedestrian comfort and use of space. These findings offer evidence-informed design considerations for historic streetscape assessment, with implications for balancing heritage conservation and contemporary pedestrian needs. Future research may refine perceptual metrics, incorporate behavioural or longitudinal validation, and extend the approach across diverse urban contexts.