Tsarray: An Intelligent Access Control System Using Backscatter Communication

With the help of computer vision-based technology, current face recognition access control systems can effectively reduce the hassle of swiping cards. However, it is not suitable for special industry areas where privacy is concerned, and it cannot be used in environments where light conditions are not satisfied. In this paper, we propose Tsarray, an RFID-based method that intelligent senses access control events by vertically deploying large-scale passive tags to the attachment plane. By fully studying the correlation between access control events, and the received RF signals, we choose a tag array deployment strategy of 4 rows, and 15 columns to eliminate environmental interference, and extract distinctive time slot tag array maps for direction tracking. Besides, by setting the same direction conversion module, the signal feature differences caused by the direction are eliminated. Moreover, we built a model to extract the spatiotemporal characteristics, and explore the model structure that is most suitable for the access control event. We evaluate the performance of Tsarray in a real environment, and used a reserved unseen test sample as a system test. Results show that our system can achieve the optimal performance in direction tracking, the accuracy of the 10 volunteers' recognition is 97.5%, the accuracy of the height recognition is 95%, and the accuracy of the weight recognition is 92.5%.