Caption-Mediated Perceived-Safety Estimation for Pedestrian Routing
Quick summary
arXiv:2609.38479v1 Announce Type: cross Abstract: This paper presents an explainable approach to pedestrian routing, in which perceived safety is estimated from street-level imagery through an explicit natural-language intermediate representation. A vision--language model caption is generated and stored before any scoring is undertaken, and the perceived-risk class is derived entirely from structured features of that stored text, so that every segment score remains inspectable by the user. Nine captioning conditions across five model families are benchmarked against a direct Contrastive Langua
Key takeaways
- arXiv:2609.38479v1 Announce Type: cross Abstract: This paper presents an explainable approach to pedestrian routing, in which perceived safety is estimated from street-level imagery through an explicit natural-language intermediate representation.
- A vision--language model caption is generated and stored before any scoring is undertaken, and the perceived-risk class is derived entirely from structured features of that stored text, so that every segment score remains inspectable by the user.
- Nine captioning conditions across five model families are benchmarked against a direct Contrastive Langua
Why it matters
This development is a reminder to test misuse and data-leak scenarios alongside speed and quality. Trust should come from testable controls and clear failure reporting, not protection claims alone.
Member comments