Man defends against package thieves using machine learning AI, flour, and very loud sirens

There’s no feeling worse than watching your packages getting lifted with nothing you can do to stop the porch pirates. After recently having a package stolen, Youtuber Ryder Calm Down built himself his own anti-package pilfer alarm system using AI, flour, and a truck horn. It looks like something out of Evil Genius 2, minus the fatal spike trap. 

The setup is simple enough: a camera watches the front porch in real-time, using a custom model TensorFlow (a machine learning platform) to recognize when a package is there. Then it arms itself. If the package is removed by an unauthorized person, like a box bandit, an alarm starts blaring, the sprinkling system is activated, and a blast of flour is fired in the general direction of the culprit.

This month-long project involved teaching the AI to identify loads of differently sized packages so it wouldn’t confuse any boxes with, say, a stray cat. Ryder also trained the AI to identify his face as a ‘known person’ and basically uses a whitelist to disarm the alert system. When an ‘unknown person’ removes the package, all hell breaks loose. 

Ryder is no stranger to creative Raspberry Pi projects which is a good reminder of all the cool things you can do with a Pi than just run emulators. He’s previously made a dog detector that goes off whenever a dog walks in front of your house and a secret door that opens using a piano like in the Batman movies.