RF-based Action Recognition
1 papers with code • 0 benchmarks • 0 datasets
Similar to many other activity recognition systems, WiFi signal is pervasive nowadays with densely deployed WiFi infrastructures in public places, which delivers the idea of ubiquitous device-free surveillance into a practical solution.
he key intuition is that Wi-Fi signals are easily distorted by human motions, and motion-induced signals could convey informative characteristics, such as intensity, regularity, and continuity.
Benchmarks
These leaderboards are used to track progress in RF-based Action Recognition
Latest papers
Joint Activity Recognition and Indoor Localization With WiFi Fingerprints
geekfeiw/apl
•
•
arXiv:1904.04964 Search... Help | Advanced Search 2019
In this paper, we propose a novel deep learning framework for joint activity recognition and indoor localization task using WiFi Channel State Information~(CSI) fingerprints.
