Abstract
RFID, a key enabling technology of Internet of Things (IoT), has a broad development prospect in the device-free localization (DFL). The RFID-based radio tomographic imaging (RTI) method has received great attention from scholars, owing to its properties of good real-time performance, low computational complexity, high localization accuracy. However, RTI suffers from the influence of multipath and noise, which results in the artifacts and false targets appearing in the imaging result and, in turn, decreases the positioning performance significantly, especially when there are multiple targets. Therefore, how to recognize the locations and number of true targets from the imaging result becomes an urgent problem in multi-target positioning. To solve this problem, we propose a novel scanning circle link analysis (SCLA-RTI) method to eliminate false targets and locate real targets in UHF RFID scenario. First, scanning circle method is introduced to detect the line-of-sight (LOS) links through the detecting region of the local maximum pixel in the imaging result. After feature analysis and selection of the RSS change of links, the random forest classifier is used to determine the location and number of real targets. Experiments demonstrate that SCLA-RTI method has superior performance in an indoor environment, which can accurately identify true and false targets and obtain high localization accuracy.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.