Image-based positioning system using LED Beacon based on IoT central management
- PDF / 2,406,637 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 37 Downloads / 175 Views
Image-based positioning system using LED Beacon based on IoT central management Hyeonwoo An 1
& Nammee Moon
1
Received: 11 April 2020 / Revised: 12 August 2020 / Accepted: 10 November 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
The benefits of technologies related to the Internet of Things (IoT), virtual and augmented reality (VR/AR), digital twins, and so on, can be fully realized when associated devices are positioned intuitively. However, AR systems hosted within smartphones pose challenges where auxiliary hardware and computational configurations associated with precise positioning are concerned. To this effect, we propose a deep learning-based indoor measurement system that can determine positions using images collected via beacons designed as IoT terminals. The proposed system is broadly divided into a detection unit, an extraction unit, a positioning unit, and a management server. The beacons were detected using deep learning algorithms, from which the postures were extracted using a homography matrix, and position of the imaging device was determined in reference to the beacon’s position. With the unique design of our system, in that it simultaneously performs posture and positioning estimations, high immersive AR can be achieved. Moreover, scalability of the positioning space is also guaranteed as multiple beacons can be monitored at once. For the experiment, we simulated a virtual indoor space comprising pyramid beacons and the results were promising. Keywords Positioning . IoT . Object detection . Deep learning
1 Introduction Estimating the position of an object is crucial for technologies that coalesce reality and the virtual world, such as Internet of Things (IoT), virtual and augmented reality (VR/AR) applications, and digital twins. Positioning is an important determinant in mapping the real world onto AR systems i.e., projecting the information of real-world objects as is or based on a map of real space [6].
* Nammee Moon [email protected]
1
Department of Computer Engineering, Hoseo University, Asan, Republic of Korea
Multimedia Tools and Applications
Recently, positioning methods using various technologies such as image-based, sensorbased, fingerprinting, and visible light communication (VLC)-based have been studied [9, 14, 20]. However, mobile devices that are commonly used to host AR applications are neither suited to accommodate the auxiliary hardware required to implement them (like sensors) nor do they harbor appropriate navigation systems that can utilize dead reckoning, for instance, unless the design is customized for positioning. Moreover, even with the in-built positioning options available, such as the global positioning system (GPS) and Wi-Fi fingerprinting, implementing immersive AR is inherently difficult, owing to projection errors i.e., erroneous mapping of real-world objects to the virtual space, thereby rendering a heterogenous AR experience. Researchers have previously explored several approaches to improving positioning in A
Data Loading...
