Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/74913
Title: Fusing RFID and computer vision for fine-grained object tracking
Authors: Duan, C
Rao, X
Yang, L 
Liu, Y
Keywords: Computer vision
RFID
TagVision
Tracking
Issue Date: 2017
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Proceedings - IEEE INFOCOM, 2017, 8057161 How to cite?
Abstract: In recent years, both the RFID and computer vision technologies have been widely employed in indoor scenarios aimed at different goals while faced with respective limitations. For example, the RFID-based EAS system is useful in quickly identifying tagged objects but the accompanying false alarm problem is troublesome and hard to tackle with except that the accurate trajectory of the target tag can be easily acquired. On the other side, the CV system performs fairly well in tracking multiple moving objects precisely while finding it difficult to screen out the specific target among them. To overcome the above limitations, we present TagVision, a hybrid RFID and computer vision system for fine-grained localization and tracking of tagged objects. A fusion algorithm is proposed to organically combine the position information given by the CV subsystem, and phase data output by the RFID subsystem. In addition, we employ the probabilistic model to eliminate the measurement error caused by thermal noise and device diversity. We have implemented TagVision with COTS camera and RFID devices and evaluated it extensively in our lab environment. Experimental results show that TagVision can achieve 98% blob matching accuracy and 10.33mm location tracking precision.
Description: 2017 IEEE Conference on Computer Communications, INFOCOM 2017, Atlanta, GA, USA, 1-4 May, 2017
URI: http://hdl.handle.net/10397/74913
ISBN: 9781509053360
ISSN: 0743166X
DOI: 10.1109/INFOCOM.2017.8057161
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

2
Last Week
0
Last month
Citations as of Oct 6, 2018

Page view(s)

11
Citations as of Oct 15, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.