There’s MIT’s wireless underwater camera, and then Carnegie Mellon University’s DensePose from WiFi technology, which lets you track the outlines of humans using wireless signals. Simply put, it’s based on a neural network architecture that uses only WiFi signals for human dense pose estimation in scenarios with occlusion and multiple people, making it ideal in elderly care homes or for identifying potential burglars.
How does it work? DensePose from WiFi essentially generates UV coordinates of the human body surface using raw CSI signals. Amplitude and phase sanitization, a two-branch encoder-decoder network, then clean these signals and that translates them into 2D feature maps that resemble images. A modified DensePose-RCNN architecture utilizes the 2D features from the previous step to estimate a UV map representing the dense correspondence between 2D and 3D humans.
- Next-gen WiFi standard – World's first Wi-Fi6E tri-band router boosts speeds up to 11000 Mbps..Power Supply : 12 V with max.3 A current / 19.5 V...
- 6GHz spectrum available – Wider channels and higher capacity to deliver higher performance, lower latency, and less interference.
- 2.5G LAN/WAN Port – All traffic through 2.5G port is given the top priority, and 2.5G port unlocks the full potential of WiFi 6.
People might be a little freaked out now, in the sense that internet service providers might locate what people are doing at home but, no, we are still not there. The only thing that this paper shows is that, in a very constrained setting… [with] three receivers of Wi-Fi signal, there is enough signal there for the fine-grained detection of human body parts,” said Fernando De la Torre, Carnegie Mellon University Researcher.
