URBAN-SPIN: A street-level bikeability index to inform design implementations in historical city centres

TL;DR

This study addresses the gap in street-level bikeability research within historic city centres by combining first-person video data, perception surveys, and built-environment indicators in a typology-sensitive framework. It introduces a typology-aware Bikeability Index that fuses machine-vision streetscape features, subjective cycling experience, and structural urban form, and demonstrates how micro-scale perceptual improvements can yield meaningful gains without major infrastructural changes. Through elastic-net, random forest with SHAP, and Kruskal-Wallis analyses across Cambridge’s 116 street segments and six typologies, greenness emerges as a robust predictor while typology moderates several effects, underscoring the need for context-aware design. The resulting design implementations show how targeted visual and perceptual adjustments can enhance bikeability in heritage settings, offering a transferable tool for planning and policy in historic cities. The work also outlines a roadmap for future research involving embodied measures, longitudinal pilots, and dynamic simulations to strengthen empirical grounding and practical impact.

Abstract

Cycling is reported by an average of 35\% of adults at least once per week across 28 countries, and as vulnerable road users directly exposed to their surroundings, cyclists experience the street at an intensity unmatched by other modes. Yet the street-level features that shape this experience remain under-analysed, particularly in historical urban contexts where spatial constraints rule out large-scale infrastructural change and where typological context is often overlooked. This study develops a perception-led, typology-based, and data-integrated framework that explicitly models street typologies and their sub-classifications to evaluate how visual and spatial configurations shape cycling experience. Drawing on the Cambridge Cycling Experience Video Dataset (CCEVD), a first-person and handlebar-mounted corpus developed in this study, we extract fine-grained streetscape indicators with computer vision and pair them with built-environment variables and subjective ratings from a Balanced Incomplete Block Design (BIBD) survey, thereby constructing a typology-sensitive Bikeability Index that integrates subjective and perceived dimensions with physical metrics for segment-level comparison. Statistical analysis shows that perceived bikeability arises from cumulative, context-specific interactions among features. While greenness and openness consistently enhance comfort and pleasure, enclosure, imageability, and building continuity display threshold or divergent effects contingent on street type and subtype. AI-assisted visual redesigns further demonstrate that subtle, targeted changes can yield meaningful perceptual gains without large-scale structural interventions. The framework offers a transferable model for evaluating and improving cycling conditions in heritage cities through perceptually attuned, typology-aware design strategies.

Figures (10)

• Figure 1: An overview of the research design. The study includes seven stages: (1) A first person cycling video dataset processed with computer vision to derive streetscape indicators, (2) A BIBD perception survey capturing segment level cycling experience, (3) Built environment indicators derived from OSM and DEM, (4) Correlational modelling linking environmental indicators to perceived outcomes, (5) Typology based comparative analysis across street contexts, (6) Construction and mapping of a street level Bikeability Index, and (7) Design implementations informed by the index and statistical results.
• Figure 2: Research methodological framework. The methodological workflow integrates three core components across 116 street segments: (1) the Cambridge Cycling Experience Video Dataset (CCEVD), a handlebar-mounted dataset capturing real-world cycling conditions in Cambridge; (2) a Balanced Incomplete Block Design (BIBD) perception survey assessing five experiential dimensions; and (3) spatial indicators derived from OpenStreetMap (OSM) and digital elevation models (DEM).
• Figure 3: Study area and street typologies. To account for spatial heterogeneity, all segments are classified into six typologies adapted from established classifications houde_ride_2018nazemi_studying_2021noland_understanding_2023teschke_proximity_2017zhang_measuring_2022: (1) off-street bicycle lanes, (2) residential street bicycle lanes, (3) commercial street mixed-traffic lanes, (4) pedestrian-bicycle shared lanes, (5) vehicle-bicycle shared lanes, and (6) protected bicycle lanes. Each typology represents a distinct configuration of spatial form, supporting comparative analysis of how identical features, such as greenness or enclosure, may operate differently across street types. This typological structure informs all subsequent modelling and design implementation stages.
• Figure 4: Cambridge Cycling Experience Video Dataset: quantifying machine-vision streetscape features using OpenCV and semantic segmentation models.
• Figure 5: Correlational analysis.