Framework for Motorcycle Risk Assessment Using Onboard Panoramic Camera (Short Paper)

Medientyp: Sonstige Veröffentlichung; E-Artikel; Elektronischer Konferenzbericht

Titel: Framework for Motorcycle Risk Assessment Using Onboard Panoramic Camera (Short Paper)

Beteiligte: Jongwiriyanurak, Natchapon [Verfasser:in]; Zeng, Zichao [Verfasser:in]; Wang, Meihui [Verfasser:in]; Haworth, James [Verfasser:in]; Tanaksaranond, Garavig [Verfasser:in]; Boehm, Jan [Verfasser:in]

Erschienen: Schloss Dagstuhl – Leibniz-Zentrum für Informatik, 2023

Sprache: Englisch

DOI: https://doi.org/10.4230/LIPIcs.GIScience.2023.44

Schlagwörter: Vision-Language Model ; Large Language Model ; Traffic incident risk

Entstehung:

Anmerkungen: Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.

Beschreibung: Traditional safety analysis methods based on historical crash data and simulation models have limitations in capturing real-world driving scenarios. In this experiment, panoramic videos recorded from a motorcyclist’s helmet in Bangkok, Thailand, were narrated using an image-to-text model and then put into a Large Language Model (LLM) to identify potential hazards and assess crash risks. The framework can assess static and moving objects with the potential for early warning and incident analysis. However, the limitations of the existing image-to-text model cause its inability to handle panoramic images effectively.

Zugangsstatus: Freier Zugang

Nur in Feld suchen:

Zuletzt gesuchte Begriffe: