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
- Wenyue Yang
Institutions
- South China Agricultural University (CN)
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