Blog

One of the things that we love at Inlet Technologies is using tech in innovative ways to solve problems. We also love to see other's innovations, so that we can learn from and maybe learn from.

Here the team at Massachusetts Institute of Technology, have trained machines equipped with AI to detect how Wi-Fi signals reflect off of people to track human movement - even through barriers or in the dark.

Here's an excerpt from the Massachusetts Institute of Technology paper, "Through-Wall Human Pose Estimation Using Radio Signals":

This paper demonstrates accurate human pose estimation through walls and occlusions. We leverage the fact that wireless signals in the WiFi frequencies traverse walls and reflect off the human body. We introduce a deep neural network approach that parses such radio signals to estimate 2D poses. Since humans cannot annotate radio signals, we use state-of-the-art vision model to provide cross-modal supervision. Specifically, during training the system uses synchronized wireless and visual inputs, extracts pose information from the visual stream and uses it to guide the training process. Once trained, the network uses only the wireless signal for pose estimation. We show that, when tested on visible scenes, the radio-based system is almost as accurate as the vision-based system used to train it.

According to the MIT News website, this new technology would be useful in healthcare to monitor patients or to help the elderly live more independently by allowing them to "age in place." However, it doesn't take a huge leap of imagination to see how technologies like these could be used to invade peoples' privacy. A recently released video from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) illustrates how the RF-pose system works.