Objects in an environment affect electromagnetic waves. While this effect varies across frequencies, there exists a correlation between them, and a model with enough capacity can capture this correlation between the measurements in different frequencies. In this paper, we propose the Wi2Vi model for associating variations in the WiFi channel state information with video frames. The proposed Wi2Vi system can generate video frames entirely using CSI measurements. The produced video frames by the Wi2Vi provide auxiliary information to the conventional surveillance system in critical circumstances. Our implementation of the Wi2Vi system confirms the feasibility of constructing a system capable of deriving the correlations between measurements in different frequency spectrums.
WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network
School of Information and Communication Engineering, University of Electronic Science and Technology of China（电子科技大学信息与通信工程学院）；College of Computer Science, Sichuan University（四川大学计算机学院）
Physics-Guided Attention in a Lightweight TCN for Efficient WiFi CSI-Based Human Activity Recognition
Signal Processing, Artificial Intelligence and Vision Technologies (SAIVT) Research Group, School of Electrical Engineering and Robotics, Queensland University of Technology (QUT)（信号处理、人工智能与视觉技术（SAIVT）研究组，电气工程与机器人学院，昆士兰科技大学（QUT））
WiFlow: A Lightweight WiFi-based Continuous Human Pose Estimation Network with Spatio-Temporal Feature Decoupling
Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology（昆明理工大学机电工程学院）；Shanghai ChingMu Vision Technology Co. Ltd（上海清目视觉科技有限公司）
