Performance Comparison of Semantic Segmentation Models and Loss Functions for Seat Belt Detection

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: 2024/07/01

タイトル(英語): Performance Comparison of Semantic Segmentation Models and Loss Functions for Seat Belt Detection

著者名: Junya Sato (Faculty of Engineering, Gifu University), Takuya Akashi (Faculty of Science and Engineering, Iwate University)

著者名(英語): Junya Sato (Faculty of Engineering, Gifu University), Takuya Akashi (Faculty of Science and Engineering, Iwate University)

キーワード: seat belt detection，semantic segmentation，convolutional neural network，deep learning

要約(英語): In Japan, despite seat belts being mandatory for drivers, some choose not to comply. This non-compliance is typically identified through visual inspections by police officers. However, Japan's population decline has facilitated a growing need for automating this process using camera and vision technologies. This study explores the optimal combination of semantic segmentation models and loss functions for seat belt detection in images. We created a dataset using various car models in outdoor settings and evaluated the performance of all combinations of nine models and five loss functions. Our findings indicate that the UNet++ model paired with the Lovasz loss function delivers superior performance.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.144 No.7 （2024） 特集：2023年電子・情報・システム部門大会

本誌掲載ページ: 665-671 p

原稿種別: 論文／英語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/144/7/144_665/_article/-char/ja/