Man defends himself from package thieves who use machine learning AI, flour and very strong sirens

Man defends himself from package thieves who use machine learning ai, flour and very strong sirens

(embed) https://www.youtube.com/watch?v=nPnOtm1Uadw (/ embed)

There’s no worse feeling than watching the packages rise with nothing you can do to stop the porch pirates. After recently stealing a package, Youtuber Ryder is calm built its own anti-pillar package alarm system with AI, flour and a truck horn. It looks like something coming out of Evil Genius 2, minus the fatal trap.

The setup is simple enough: a camera observes the porch in real time with a custom model TensorFlow (a machine learning platform) to recognize when a package is there. Then he arms himself. If the package is removed by an unauthorized person, such as a cash bandit, an alarm will sound, the sprinkler system will be activated, and flour will be fired in the general direction of the culprit.

This month-long project involved teaching the AI ​​to identify a bunch of packets of different sizes, so as not to confuse any box with, say, a stray cat. Ryder also trained AI to identify his face as a "known person" and basically uses a whitelist to disarm the alert system. When an "unknown person" takes out the package, all hell breaks loose.

Ryder is no stranger to Raspberry Pi creative projects, which are a good reminder of all the interesting things you can do with a Pi that only run emulators. He has previously done one dog detector which goes off whenever a dog walks in front of the house and secret door which opens with a piano like in the Batman movies.

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *