Passenger Boarding and Alighting Tracking via Person Re-Identification for Smart Transit Systems

カテゴリ：部門大会

論文No：SS1-9

グループ名：【C】2025年電気学会電子・情報・システム部門大会

発行日：2025/8/20

タイトル(英語)：Passenger Boarding and Alighting Tracking via Person Re-Identification for Smart Transit Systems

著者名：Panyaso Thanandorn（）,Teawchim Sanit（KOSEN-KMITL, King Mongkut's Institute of Technology Ladkrabang, Thailand）,Srithanasarn Krittanik（KOSEN-KMITL, King Mongkut's Institute of Technology Ladkrabang, Thailand）,Doi Shigeo（苫小牧工業高等専門学校）

著者名(英語)： Thanandorn Panyaso (),Sanit Teawchim (King Mongkut's Institute of Technology Ladkrabang),Krittanik Srithanasarn (King Mongkut's Institute of Technology Ladkrabang),Shigeo Doi (National Institute of Technology, Tomakomai College)

キーワード：Person Re-Identification,Passenger Tracking,Deep Learning,Smart Transportation,Multi-Object TrackingVideo Surveillance

要約(日本語)：Recent advances in the Internet of Things (IoT) and smart city technologies have positioned video surveillance as a key enabler of intelligent transportation systems. This paper presents the development of a camera-based Person Re-Identification (Re-ID) system for tracking passengers boarding and alighting at designated observation points, simulating real-world public transit scenarios. The Re-ID system matches individuals across non-overlapping cameras using deep learning and multi-object tracking techniques. A prototype was deployed at a classroom entrance with entry and exit cameras to validate system performance. Results demonstrate the feasibility of accurate passenger counting and identity association in constrained environments, contributing to smarter transit monitoring solutions.

本誌掲載ページ：1781-1783p

原稿種別：英語

PDFファイルサイズ：383Kバイト