Preliminary Investigation of Employing Smartphone Active Sound Sensing to Predict Distance and Relative Velocity of the Roadside Obstacles to Aid Distracted Pedestrians

• Item type: SIG Technical Reports(1)
• 公開日: 2022-11-01
• タイトル: Preliminary Investigation of Employing Smartphone Active Sound Sensing to Predict Distance and Relative Velocity of the Roadside Obstacles to Aid Distracted Pedestrians
• タイトル / 言語: en
• タイトル: Preliminary Investigation of Employing Smartphone Active Sound Sensing to Predict Distance and Relative Velocity of the Roadside Obstacles to Aid Distracted Pedestrians
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 計測・インタフェース
• 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: Graduate School of Information Science and Technology, Osaka University
• 著者所属: Graduate School of Information Science and Technology, Osaka University
• 著者所属: Graduate School of Information Science and Technology, Osaka University
• 著者所属(英): en
• 著者所属(英): Graduate School of Information Science and Technology, Osaka University
• 著者所属(英): en
• 著者所属(英): Graduate School of Information Science and Technology, Osaka University
• 著者所属(英): en
• 著者所属(英): Graduate School of Information Science and Technology, Osaka University
• 著者名: Thilina, Dissanayake; 前川, 卓也; 原, 隆浩
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Pedestrians that view their smartphones while walking on the sidewalk are prone to collisions with numerous roadside obstacles. Estimating obstacle attributes related to the presumed collision time, i.e., the distance between the pedestrian and the obstacle, and the relative velocity of the obstacle, is an important task to assure the safety of the pedestrians. However, most of the prior studies focus on estimating either the distance to the obstacle or its relative velocity. Furthermore, the majority of these studies focus on predicting obstacle attributes of either static or mobile obstacles. This study proposes a method to estimate both the distance and the relative velocity of oncoming static and mobile roadside obstacles. We propose a novel probing signal that facilitates distance and relative velocity estimation and propose a neural network architecture that considers the mobility of the obstacle to select the most appropriate method to estimate those attributes.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Pedestrians that view their smartphones while walking on the sidewalk are prone to collisions with numerous roadside obstacles. Estimating obstacle attributes related to the presumed collision time, i.e., the distance between the pedestrian and the obstacle, and the relative velocity of the obstacle, is an important task to assure the safety of the pedestrians. However, most of the prior studies focus on estimating either the distance to the obstacle or its relative velocity. Furthermore, the majority of these studies focus on predicting obstacle attributes of either static or mobile obstacles. This study proposes a method to estimate both the distance and the relative velocity of oncoming static and mobile roadside obstacles. We propose a novel probing signal that facilitates distance and relative velocity estimation and propose a neural network architecture that considers the mobility of the obstacle to select the most appropriate method to estimate those attributes.
• 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: AA1221543X
• 書誌情報: 研究報告ヒューマンコンピュータインタラクション（HCI）; 巻 2022-HCI-200, 号 25, p. 1-8, 発行日 2022-11-01
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8760
• 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