An intelligent and modular sensing system for Augmented Reality application

Abstract

The scientific objective of this paper is to describe an innovative architecture of modular form in sensing and supervision system. In our study, a maintenance work at ATLAS detector in Large Hadron Collider at European Organization for Nuclear Research (CERN), Geneva, Switzerland has been considered. The research challenges lie in the development of real-time data-transmission, instantaneous analysis of data coming from different inputs, local intelligences in low power embedded system, interaction with augmented reality in multiple on-site users, complex interfaces, and portability. The proposed architecture is allocated with modular form. The prototype of this modular device is named a PSS (Personnel Supervision System) module. The hardware of the modular system includes with many sensor modules, cameras, IMU (Inertial Measurement Unit) sensors, processors, Wi-Fi module, laser, LED light plus its associated software. The mobile PSS module is responsible for local data processing for various sensors, image processing, 3D pose estimation, audio data acquisition, visualization and wireless interfaced devices. The advantage of modular concept is that it can work independently or together. The Head Mounted Display (HMD) includes HW and SW to communicate the augmented reality content to the user and to display visual information on a worker's field of view (FOV). The module serves as a supervision post, providing sensor data, video and audio stream to the supervisor. It stores data and provide the means for the supervisor to easily communicate and instruct the worker. It decides, selects and serves the AR (Augmented) content on multiple PTUs, automatically or with minor supervisor intervention. The development of this system to be compatible with a wearable use in a highly challenging environment presents an excellent opportunity to integrate today's leading technical knowledge in a product which can become accessible to industry and general public. This study is a part of the EDUSAFE project, a Marie Curie ITN project focusing on research into the use of Virtual and Augmented Reality (VR/AR) during planned and emergency maintenance in extreme environments.