WIFI Antena Lets Scientists
See Through Walls to
Map Your Body Pose
Your home and cell phone WIFI can be used to create a computer generated model of you behind walls and without your permission.
Three research scientists at Carnegie Mellon University “developed a deep neural network that maps the phase and amplitude of WiFi signals to UV coordinates within 24 human regions.”
Don’t worry, apparently they’re gonna smooth over your crotch.
Similar technology has been used in computer vision which uses “deep learning architectures.”
Geng, Huan, and De la Torre’s research expands use of a WiFi combo with deep learning architectures “to estimate dense human pose correspondence.”
Their “model can estimate the dense pose of multiple subjects (with comparable performance to image-based approaches)” using WiFi signals as the only input.
This is the beginning of “low-cost, broadly accessible, and privacy-preserving algorithms for human sensing.”
JK Editor presumes it preserves privacy using “deep learning architectures” to help smooth over detailed anatomical accuracy, making everyone look more like a naked Ken or Barbie.
Privacy was absent in prior technology of human pose estimation that used:
a) RGB cameras,
b) LiDAR, and
c) radar.
Variations of prior technology made it into airport terminals in the aftermath of 911. Public outcry was so widespread that the FAA pulled the machines from use because it revealed private sexual parts of men and women.
Apparently, the new ‘naked gun’ is going to be kinder to us. But, we’ll see, er uh, they will too.
Reference Kernel:
Dense Pose From WiFi, by Jiaqi Geng, Dong Huang, Fernando De la Torre, 12/31/2022
https://arxiv.org/abs/2301.00250
