The Earth Speaks: Advanced Vehicle Classification with Seismic Data

• Item type: SIG Technical Reports(1)
• 公開日: 2024-05-08
• タイトル: The Earth Speaks: Advanced Vehicle Classification with Seismic Data
• タイトル / 言語: en
• タイトル: The Earth Speaks: Advanced Vehicle Classification with Seismic Data
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [MBL/ITS]自動運転と測位
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Computational Learning Theory Team, RIKEN-AIP
• 著者所属: Graduate School of Information Science and Technology, Osaka University
• 著者所属(英): en
• 著者所属(英): Computational Learning Theory Team, RIKEN-AIP
• 著者所属(英): en
• 著者所属(英): Graduate School of Information Science and Technology, Osaka University
• 著者名: Sherief, Hashima; Hamada, Rizk
• 著者名(英): Sherief, Hashima; Hamada, Rizk
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Recently, privacy-preserving vehicle classification (VC) methods have gained great focus, especially with the growing intelligent sensor technologies. Amongst these, seismic-aided VC is a promising intelligent solution but a challenging issue due to the interference of signals sourced from various noises. Seismic-aided VC overcomes the challenges of image/video classification as it can easily/low cost detect the traffic volume without private user information and in different weather conditions. Therefore, this paper proposes an efficient deep learning-based vehicle classification approach within the fractional wavelet domain to identify vehicle categories. The system achieves a high classification accuracy of 98% with real-time processing of 0.05 seconds.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Recently, privacy-preserving vehicle classification (VC) methods have gained great focus, especially with the growing intelligent sensor technologies. Amongst these, seismic-aided VC is a promising intelligent solution but a challenging issue due to the interference of signals sourced from various noises. Seismic-aided VC overcomes the challenges of image/video classification as it can easily/low cost detect the traffic volume without private user information and in different weather conditions. Therefore, this paper proposes an efficient deep learning-based vehicle classification approach within the fractional wavelet domain to identify vehicle categories. The system achieves a high classification accuracy of 98% with real-time processing of 0.05 seconds.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11515904
• 書誌情報: 研究報告高度交通システムとスマートコミュニティ（ITS）; 巻 2024-ITS-97, 号 24, p. 1-7, 発行日 2024-05-08
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8965
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会