Citation

Torii K, Mizuno Y, Toyama K, Shimizu S, Kogo S. Trans. Soc. Automot. Eng. Jpn. 2022; 53(2): 404-409.

Vernacular Title

構造化データと衛星画像のマルチモーダルAI モデルによる交通事故発生確率の予測手法の開発

Copyright

(Copyright © 2022, Society of Automotive Engineers of Japan)

DOI

10.11351/jsaeronbun.53.404

PMID

unavailable

Abstract

Predicting traffic accidents is an important issue for improving public safety. In this study, we developed an AI model which predicts the probability of traffic accidents in Fukuoka City with spatial and temporal resolutions of ~130m and 1 month, respectively. A multimodal machine-learning model was developed by combining various structured data (roads, demographics and economic statistics, weather, events, etc.) and satellite imagery, and was trained using personal injury accident data between 2016 and 2017 in Fukuoka City. As a result, the model succeeded in predicting the outcome for Fukuoka City in 2018 at an AUC of the ROC curve of 77%.

===

本研究では，都市のあるエリア(約130m四方)における交通事故の有無を，年・月ごとに予測する手法を開発した．道路，天候，イベントなど様々な構造化データと衛星画像を融合したマルチモーダルAIを開発し，福岡市の人身事故データを用いて学習した結果，ROC曲線のAUC=77%を持つモデルの開発に成功した．

Language: ja

Keywords

accident analysis/statistical accident analysis; accident prediction; machine learning; road environment; safety