Gesture recognition using RFID technology

Abstract

We propose a gesture recognition technique based on RFID: cheap and unintrusive passive RFID tags can be easily attached to or interweaved into user clothes, which are then read by RFID antennas. These readings can be used to recognize hand gestures, which enable interaction with applications in an RFID-enabled environment. For instance, it allows people to interact with large displays in public collaboration spaces without the need to carry a dedicated device. We propose the use of multiple hypothesis tracking and the use of subtag count information to track the motion patterns of passive RFID tags. To the best of our knowledge, this work is the first on motion pattern tracking using passive RFID tags. Despite the reading uncertainties inherent in passive RFID technology, our experiments show that the proposed gesture recognition technique has an accuracy of up to 93%.

Gesture recognition in smart home using passive RFID technology

“…We use class 3 tags and we put 2 to 4 on each object to improve localization (bad angle of arrival is the worse issue to tracking in real time). The gestures to be recognized by our algorithm are the same twelve of Asadzadeh et al [20] plus the idle gesture that we added to represent the fact that most of the time the objects do not move. The Fig.…”

“…As a first step toward recognition of gesture with passive RFID technology, we decided to directly reproduce the methodology of Asadzadeh et al [20] but in an appropriate setting. While they implemented their system on a small table with three antennas and 91 special references tags, we performed experiments in a full-size apartment comprising a large number of sensors.…”

“…The team of Asadzadeh & al. [20] investigated the problem with a partitioning localization technique combined to reference tags. With three antennas on a desk, they monitored an 80cm by 80cm area, which was divided into 64 equally sized square cells (10cm by 10 cm).…”

“…Amongst them there are the readings cycle in ms, the average positioning error, the duration of the gesture (with a random variable or not) and the speed of the object in meter per second. We used the parameters of the Asadzadeh et al [20] experiments (gestures average 4.5s at 0.2m/sec). The generator first randomly selects the gesture to generate (or idle).…”

RFID shakables

“…Di↵erent types of gestures (e.g., hand movement or preparing co↵ee) can be detected using a hierarchical model combining measurements of two RFID devices with the readings of three accelerometers and one location sensor, as reported in [9]. In [15], motion pattern tracking using passive RFID tags is proposed and analyzed. The focus of that contribution is on a complex scenario with multiple readers located at known positions and multiple tags.…”