Walkable to Whom? Capturing Subjective Variability in Walkability Perception Using Multimodal Deep Learning

2026-08-07

AI Summary

This study addresses the limitations of existing walkability assessments, which predominantly rely on street-view imagery captured from non-pedestrian perspectives and fail to account for individual perceptual differences, thereby inadequately reflecting real-world walking experiences. To overcome this, the authors construct a large-scale dataset comprising nearly 30,000 individual walkability ratings, integrating sidewalk-level imagery with user demographic attributes. They propose the first user-conditioned multimodal deep learning framework that explicitly models how evaluator identity influences walkability perception. Experimental results demonstrate a 65% improvement in ranking consistency over image-only baselines, with weighted Kappa increasing from 0.29 to 0.47, underscoring the superiority of sidewalk-perspective imagery. This work establishes a new paradigm for developing more inclusive and perceptually grounded walkability evaluation systems.

Abstract

Visual perception of walkability varies substantially across individuals, reflecting differences in personal characteristics, experiences, and preferences. Existing studies, however, often reduce these diverse judgements to aggregated scores, implicitly assuming uniform perception, and commonly rely on vehicle-mounted street-view imagery that does not reflect the pedestrian's visual experience. This paper introduces a dataset of 29,870 walkability ratings from 1,196 respondents, linking sidewalk-view imagery across urban, suburban, and regional Australian environments with individual rater attributes, and proposes the first user-conditioned multimodal deep learning framework for walkability perception, fusing visual features with respondent-level representations. A viewpoint-comparison study shows that sidewalk-view images receive significantly higher walkability ratings than matched street-view images, indicating that imagery source is a substantive design decision in perception surveys. The user-conditioned model improves rank agreement with observed ratings by 65% over an image-only baseline (quadratic weighted kappa 0.47 vs. 0.29), demonstrating that who is evaluating an environment carries predictive indication beyond image content alone. These findings support moving from aggregated, observer-independent walkability scores toward models that represent diverse users, enabling more inclusive assessment of pedestrian environments.

Problem

• walkability perception
• subjective variability
• pedestrian viewpoint
• inclusive assessment
• urban environment

Innovation

• user-conditioned modeling
• multimodal deep learning
• sidewalk-view imagery
• subjective walkability perception
• inclusive urban assessment