[2J1-GS-10] AI application:

[2J1-GS-10-03] Building height estimation using vehicle-mounted images with the large language models, and evacuation simulation

〇Itaru Morita¹, Wong Man Boon², Tirtom Huseyin¹, Kunihiro Uzawa², Kazuya Nojima¹ (1. Nippon Koei Co.,Ltd., 2. Nippon Koei Business Partners Co., Ltd.)

Keywords:LLM, 360° camera images, Number of floors, Road obstruction, Evacuation simulation

In recent years, various big data have been acquired, and their use has begun in many fields. However, because the amount of data is large, the number of people who can handle it is limited, and it requires a lot of effort, so it is sometimes difficult to extract enough information. There are various methods to extract information from big data, but generative AI, which has recently made remarkable progress, can also extract information from big data, and it is thought that many users will be able to extract information from big data by combining it with large-scale language models.
We are conducting research on obtaining information on roads and roadside facilities from images taken with in-vehicle cameras etc., and this time, we used ChatGPT-4o to determine the number of floors of a building from images taken with a 360° camera, and used the latest LLM technology to improve the accuracy of readings. In addition, in order to understand the impact that differences in the read information have on road obstruction due to building collapses in an earthquake, evacuation simulations were conducted to understand the impact on evacuation times, etc.