‌ Beyond the shortest path: Identifying optimal walkable routes using a street walkability index derived from deep learning and micro-scale pedestrian environment features

Urban streets are fundamental public spaces that underpin residents’ daily non-motorized travel, and their on-street pedestrian environment and walkability directly shape people’s walking mode decisions and walking experiences. However, few existing studies have systematically examined street-level walkability from the perspective of micro-scale pedestrian environment features—particularly its critical role in identifying the truly optimal walkable routes. This study develops a Street Walkability Index (SWI) based on street view image data, deep learning and seven specific street micro-environmental indicators. Leveraging this index, we propose an innovative method for optimal walkable route identification, and conduct empirical validation and performance testing in a historic urban district of Guangzhou. The results show that the average SWI in this district is 35.0638, with 56.25% of the streets scoring below this mean value. Overall, arterial roads exhibit the poorest walkability, while branch roads and internal roads show relatively better walkability. The seven street micro-environmental indicators display distinct spatial distribution characteristics. Branch roads and internal roads perform outstandingly in terms of space vitality, enclosure, pedestrian conditions, and visual permeability. Secondary arterial roads generally have the best street greenery coverage, while arterial roads perform best in openness. For the vast majority of origin-destination pairs, the optimal walkable route is not equivalent to the path with the shortest walking distance. Although the total travel distance of the optimal walkable route increases only marginally, its overall walkability can be improved by a substantially larger margin. This study advances our in-depth understanding of street walkability and optimal walkable route planning, and facilitates their practical implementation in pedestrian navigation systems.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-18
DOI
https://doi.org/10.21203/rs.3.rs-11639030/v1
Primary Topic
Urban Transport and Accessibility
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

‌ Beyond the shortest path: Identifying optimal walkable routes using a street walkability index derived from deep learning and micro-scale pedestrian environment features

Wenyue Yang
5 links
Research Square
Urban Transport and Accessibility
preprint

‌ Beyond the shortest path: Identifying optimal walkable routes using a street walkability index derived from deep learning and micro-scale pedestrian environment features

Wenyue Yang
preprint en

Abstract

Urban streets are fundamental public spaces that underpin residents’ daily non-motorized travel, and their on-street pedestrian environment and walkability directly shape people’s walking mode decisions and walking experiences. However, few existing studies have systematically examined street-level walkability from the perspective of micro-scale pedestrian environment features—particularly its critical role in identifying the truly optimal walkable routes. This study develops a Street Walkability Index (SWI) based on street view image data, deep learning and seven specific street micro-environmental indicators. Leveraging this index, we propose an innovative method for optimal walkable route identification, and conduct empirical validation and performance testing in a historic urban district of Guangzhou. The results show that the average SWI in this district is 35.0638, with 56.25% of the streets scoring below this mean value. Overall, arterial roads exhibit the poorest walkability, while branch roads and internal roads show relatively better walkability. The seven street micro-environmental indicators display distinct spatial distribution characteristics. Branch roads and internal roads perform outstandingly in terms of space vitality, enclosure, pedestrian conditions, and visual permeability. Secondary arterial roads generally have the best street greenery coverage, while arterial roads perform best in openness. For the vast majority of origin-destination pairs, the optimal walkable route is not equivalent to the path with the shortest walking distance. Although the total travel distance of the optimal walkable route increases only marginally, its overall walkability can be improved by a substantially larger margin. This study advances our in-depth understanding of street walkability and optimal walkable route planning, and facilitates their practical implementation in pedestrian navigation systems.

Research Square
South China Agricultural University (CN)
Sustainable cities and communities, Industry, innovation and infrastructure
Urban Transport and Accessibility
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon