A smart chemistry experimental environment for affirmative safety training and safe experiment

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K00265
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Human interface and interaction
• Research Institution: Tokyo University of Agriculture and Technology
• Principal Investigator: Fujinami Kaori 東京農工大学, 工学(系)研究科(研究院), 准教授 (10409633)
• Co-Investigator(Renkei-kenkyūsha): LENGGORO Wuled 東京農工大学, 大学院工学研究院, 准教授 (10304403)
• Research Collaborator: KINOSHITA Keiko ; ICHIHASHI Keita ; TANIDA Yuki ; MURAKOSHI Shuntaro ; TOKIWA Mai ; SATO Koji
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 安全学習 / 空間投影型拡張現実感 / 機械学習 / ウェアラブルデバイス

Outline of Final Research Achievements

Four core technologies were investigated that aimed to facilitate on-site safety training of university chemistry experiments; (1) a pose-aware whole-wrist circumference display was investigated, where the most visible position on the wrist is determined by a machine learning (ML)-based algorithm regardless of forearm posture; (2) a view management method for projection-based display was investigated, where the visibility of a particular tabletop condition is estimated by a ML-based estimator; (3) a still image extraction method was developed to make contents for learning, where situations of "having interests" and "grooving" were identified by image processing of first person view camera movies; (4) a notification device selection method was investigated, where the most appropriate device, e.g., a smart-watch, is chosen based on the features from positional relationship between candidate devices and the user, i.e., the distance, touching, gazing, angle of face.

Free Research Field

拡張現実感，行動認識，ヒューマン・コンピュータインタラクション