Wireless AI Perception: A New Sense for Machine Intelligence

Principal Investigator: Dr. Chenshu WU (Assistant Professor from Department of Computer Science)

This project is showcased in the second exhibition – Digitization in Innovation Wing Two

About the scholar

Dr. Chenshu WU

Research interests:
• Mobile and wireless AIoT systems
• Digital health
• Ubiquitous computing
• Internet of Things
Email: chenshu@cs.hku.hk
website: https://cswu.me

Project information

Can Machines Sense without Cameras/Sensors?

Computer vision enables machines to “see”. The capability of machine vision based on cameras, however, is fundamentally limited to a certain field-of-view with good lighting conditions – they cannot see through any occlusions or in the dark. 
Wireless sensing opens a new sense for machine perception to decipher the physical world, even in absolute darkness and through walls and obstacles. 
It can capture human activities invisibly in a contactless and sensorless way.

Still use Wi-Fi for the Internet only? You are missing a lot!

Wireless AI perception leverages ambient wireless signals (such as Wi-Fi / millimeter-wave / UWB signals) to enable ubiquitous sensing. 
Wireless sensing technology turns a Wi-Fi device into an all-in-one sensor and revolutionizes sensing from sensor-based to sensorless. 
Wireless sensing utilizes ambient Wi-Fi signals to analyze and interpret human motions and object movements, underpinning many sensing applications such as motion detection, sleep monitoring, fall detection, gait recognition, etc.

What’s Next?

The next big deal for wireless technologies is not about communication, but sensing.
With wireless AI perception, Wi-Fi sensing will enter billions of devices and millions of homes, creating a smarter space for a smarter life. Now is just the beginning of this revolution.

 
Project video
Project images
Wireless AI leverages omnipresent wireless signals to enable pervasive sensing for various applications in smart homes, digital health, smart buildings, smart cars, all in a wireless, contactless, and sensorless way without any cameras, wearables, or dedicated sensors.
Using Wi-Fi signals for sensing, we can (a) detect motion, (b) monitor respiration, (c) estimate speed, and enable applications such as motion detection, fall detection, gait monitoring, sleep monitoring, and many more to imagine.
Enquiry / Feedback

Please feel free to give your enquiry / feedbacks to the research team by filling the form (https://forms.gle/JV59N47nTj19ndYz6). Thank you!