Not logged in.
Quick Search - Contribution
Contribution Details
| Type | Master's Thesis |
| Scope | Discipline-based scholarship |
| Title | Ultra-high Frequency Passive RFID Identification and Visualization |
| Organization Unit | |
| Authors |
|
| Supervisors |
|
| Language |
|
| Institution | University of Zurich |
| Faculty | Faculty of Business, Economics and Informatics |
| Date | 2021 |
| Abstract Text | As people spend most of their time indoors, Indoor Positioning Systems (IPS) have extended their use from object tracking to human motion detection. Among a variety of IPS technologies, Radio Frequency Identification (RFID), a non-contact electromagnetic signal for automatic object identification, is often chosen due to its inexpensive nature and ability to promptly identify a number of distinct tags. However, unlike objects under traditional tracking setups, people typically move and act arbitrarily, which leads to difficulties in localization, especially as traditional measures, such as Received Signal Strength (RSS), are noisy. In this thesis, a novel data collection method, which integrates a 3-D camera and a static RFID reader to refine reading accuracy and obtain RFID tag measurements, is introduced. In addition, Kalman Filtering is proposed to smooth a tag's location estimation. Moreover, this thesis elevates current declarative visualization of RFID-marked objects with defined metrics and key performance indicators (KPIs) and integrates them in a prototype dashboard for enhanced understanding in a practical context. The upgraded data collection, simple localization algorithm and additional visualizations aim to bridge semantic gaps for a RFID indoor application and o r campaign marketers and health measure administrators an analytical tool to effectively leverage collected measurements. |
| PDF File |
Download
|
| Export |
BibTeX
|