2026-07-31T17:58:35Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:18939 2024-03-06T11:03:01Z ddc:004 open_access

Framework for Motorcycle Risk Assessment Using Onboard Panoramic Camera (Short Paper) Jongwiriyanurak, Natchapon Zeng, Zichao Wang, Meihui Haworth, James Tanaksaranond, Garavig Boehm, Jan Traffic incident risk Large Language Model Vision-Language Model 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. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Natchapon Jongwiriyanurak and Zichao Zeng and Meihui Wang and James Haworth and Garavig Tanaksaranond and Jan Boehm 2023 Is Part Of LIPIcs, Volume 277, 12th International Conference on Geographic Information Science (GIScience 2023) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.GIScience.2023.44 urn:nbn:de:0030-drops-189394 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.GIScience.2023.44 eng https://creativecommons.org/licenses/by/4.0/legalcode