Raspberry Pi unlocks computer by detecting push-ups with ML


If you’re tired of typing a password to log into your computer and you’re not using a fingerprint reader or infrared camera, you can at least practice. Manufacturer Victor Sonck has created a Raspberry pie– motorized pushes authentication project so that you sweat when you connect. Instead of connecting with something typical like a string, Sonck connects with a rep string using a little help from machine learning (ML) on our favorite single board computer.

Sonck shared the creative process behind this project through his ML Creator channel on YouTube which, for the moment, only presents this project. However, a quick look at its recent activity on GitHub shows a history of ML-based projects leading up to this Pi-powered, exercise-inducing creation.

The Raspberry Pi push-up detection system works independently of its PC and is positioned in a far corner of the room. Using a camera, it detects when Sonck has successfully completed the number of push-ups needed to log into his machine before sending a command to allow access.

The project is built around a Raspberry Pi 4 which is capable of handling machine learning applications on its own but to avoid increasing its workload, Sonck chose to use an Oak 1 AI module. This device includes a 4K camera as well as an Intel Myriad X chip that can handle the additional AI processing needs for the project. According to Sonck, it easily connects and interfaces with the Pi, making it an ideal component for his project needs. The setup also includes a display, microphone, and speaker for audio output.

The ML push-up detection system is based on an open-source application called Blazepose that can recognize human body poses from images and builds a skeleton with dots marking joint locations to duplicate said poses in real time. These skeletons are easier to interpret than raw images, which lightens the load on the push-up detection program. The source code is available on GitHub for anyone interested in learning more about how it works.

If you want to recreate this Raspberry Pi project and feel the burn for yourself, check out the original video shared on YouTube by Victor Sonck and be sure to follow him for more interesting ML projects.


Comments are closed.