Journal
IEEE INTERNET OF THINGS JOURNAL
Volume 5, Issue 6, Pages 4632-4641Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2018.2795893
Keywords
Indoor localization; particle swarm optimization (PSO); radio frequency identification (RFID); trajectory tracking
Categories
Funding
- National Science Foundation of China [U1713212, 61572330, 61273354, 61602319]
- Natural Science Foundation of Guangdong Province [S2011040004700, 2014A030313554, 2017A030313357]
- Technology Planning Project from Guangdong Province [2014B010118005]
- Technology Planning Project of Shenzhen City [JCYJ20170302143118519]
- Scientific Research Program through Shaanxi Provincial Education Department [2013JK1139]
Ask authors/readers for more resources
Radio frequency identification (RFID) technology, with its advantages such as battery-free tags, low cost, and scalability, has been playing an important role in many application domains, such as large-scale storage systems, supermarkets, construction sites, etc. Many of those application scenarios also require indoor positioning technologies, for example, warehouse goods positioning, item positioning in production assembly lines, and worker positioning in construction sites. However, indoor positioning using RFID faces accuracy degradation in dynamic environments, especially when tracking randomly moving targets. In this paper, we propose PSOTrack, a continuous RFID-based tracking system for random moving targets in unconstrained indoor environments. In PSOTrack, a data preprocessed, and an optimized particle swarm optimization algorithm is applied to determine the initial position, after that a dynamic correction method for trajectory prediction is proposed for continuous tracking. Results show that the proposed algorithm effectively improves the positioning accuracy and is able to achieve 1 m localization accuracy in dynamic indoor environments, which makes it a promising technology to support future pervasive RFID-based tracking applications.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available