Fusing RFID and computer vision for fine-grained object tracking

Chunhui Duan, Xing Rao, Lei Yang, Yunhao Liu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

58 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationINFOCOM 2017 - IEEE Conference on Computer Communications
PublisherIEEE
ISBN (Electronic)9781509053360
DOIs
Publication statusPublished - 2 Oct 2017
Event2017 IEEE Conference on Computer Communications, INFOCOM 2017 - Atlanta, United States
Duration: 1 May 20174 May 2017

Conference

Conference2017 IEEE Conference on Computer Communications, INFOCOM 2017
Country/TerritoryUnited States
CityAtlanta
Period1/05/174/05/17

Keywords

  • Computer vision
  • RFID
  • TagVision
  • Tracking

ASJC Scopus subject areas

  • General Computer Science
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Fusing RFID and computer vision for fine-grained object tracking'. Together they form a unique fingerprint.

Cite this