マルチモーダル深層学習に基づく道路構造・出現物体・操作で構成される運転場面の検出

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2024/10/01

タイトル(英語): Detection of Driving Scenes Composed of Road Structures, Appearing Objects, and Operations Based on Multimodal Deep Learning

著者名: 橋本　幸二郎（公立諏訪東京理科大学 工学部情報応用工学科），柳原　大地（公立諏訪東京理科大学 工学部情報応用工学科）

著者名(英語): Kohjiro Hashimoto (Department of Applied Information Engineering, Suwa University of Science), Daichi Yanagihara (Department of Applied Information Engineering, Suwa University of Science)

キーワード: 運転シーン検出，時系列パターン認識，深層学習　　driving scene detection，recognition of time series pattern，deep learning

要約(英語): In this paper, we propose a method to detect driving scenes where cognitive function can be evaluated. This method defines assessable scenes as those composed of three elements: road structure, appearing objects, and operations. It detects scenes composed of these three elements, which are arbitrarily set. When detecting targets composed of multiple information sources, and for targets where the pre-description of useful feature vectors is difficult, multimodal deep learning is used. While there are cases where an intermediate fusion model structure is used in existing research, it has been suggested that such models face challenges with hyperparameter tuning and may fail to learn the inter-modality relationships when there are discrepancies in the amount of information each modality provides. Therefore, in this paper, a new model structure that incorporates an attention mechanism into a late fusion model is proposed. This model not only enables individual evaluation of each modality constituting the scenes and achieves the final detection result, but also provides a structure with high readability regarding how the detection results are produced. In experiments, this method is compared in terms of detection accuracy with the intermediate fusion model structure used in existing research, and improvements in both recall and precision were confirmed.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.144 No.10 （2024） 特集：2023電気・電子・情報関係学会四国支部連合大会

本誌掲載ページ: 985-996 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/144/10/144_985/_article/-char/ja/