Spatial Augmented Reality Assistance System with Accelerometer and Projection Mapping at Cleaning Activities

Abstract

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s). SIGGRAPH ’22 Posters, August 07-11, 2022, Vancouver, BC, Canada © 2022 Copyright held by the owner/author(s). ACM ISBN 978-1-4503-9361-4/22/08. https://doi.org/10.1145/3532719.3543245 2015] and hardware-related appropriation [Ludwig et al. 2019]. On-desktop projection have been proposed for learning support systems for math development [Beşevli et al. 2019] and typing on a physical keyboard [Sono and Hasegawa 2019]. On-body projection systems were developed for education [Hoang et al. 2017][Ferdous et al. 2019]. Although projection-based human-machine interfaces have attracted attention, there have been very few works on integration with sensor-based activity recognition. Therefore, in this paper we propose an SAR assistance system with accelerometer and projection mapping. We considered cleaning activities [Yaegashi et al. 2022] for recognition to achieve wellbeing during and after the pandemic. The contribution of the proposed idea is to integrate SAR and real-time activity recognition technologies. The sensor-based activity recognition is advantageous in terms of privacy compared with well-known gesture recognition systems using a camera. The fixed floor-projection also contributes for disuse of a camera by avoiding dynamic calibration. A small and light-weight sensor device mounted on a cleaning tool does not affect the action. Low-latency feedback is achieved by an edge computing based architecture.