An Effective Personnel Detection System Based on Radio Frequency Identification

In privacy scenarios, the camera based personnel detection is usually not feasible. To this end, we present a radio frequency identification (RFID) based personnel detection approach in this paper, which can not only avoid the privacy violation problem, but also have the advantage of low cost, strong practicability and easy implementation. Specifically, the passive RFID tags are placed on the walls with a fixed distance, which can return the received signal strength indication (RSSI). Signals are received through the RFID antenna, and data are processed preliminarily by the RFID reader. With the collected data, a machine learning model is trained, and then used to detect the existence of people in a stable and reliable approach. Our experiments show that the detection accuracy of the proposed approach is approximately 99%.