This Woman created an AI system to monitor her cat’s poop
The system logs the cat’s litter time so the owner can be informed of its bowel movement.
A software engineer spent two years designing a machine learning system to log her cat’s pooping habits, and it involved sensors, an infrared camera, a Raspberry Pi, and about 50,000 pictures of cat poop. The engineer, a YouTuber who goes by Estefanni, posted a video to her channel this week detailing the process of creating the AI system after learning that her cat Teddy had been eating plastic. The cat owner wanted a way to monitor her cat’s pooping schedule to more easily know whether or not he’s constipated.
The woman posted a video of the work of her invention on the Youtube channel Estefannie on the Youtube channel.
In the video, Estefanni describes in detail the process of creating an artificial intelligence system. She started off her project by writing a python script and setting up sensors above the litter box to see when Teddy went to bathroom. Except it isn’t just Teddy using the box— Teddy has his own cat named Luna who uses the same litter box.
In order to differentiate between the two cats, Estefanni used a picture taking script, as well as a camera setup with infrared lights pointed at the litter box. She then took 50,000 of pictures of her cats pooping, and fed the pictures to a machine learning system so that it could differentiate between Teddy and Luna.
The final step was to know whether the cats were going number one or two. Estefanni turned to a website that sends pictures to a server, which makes predictions based on the data, like how long Teddy spent in the kitty litter. The server then sends the cat owner its prediction of which cat was using the bathroom, and whether it was for pee or poop. That way, Estefanni can know if Teddy’s bowel movements are healthy, or if he’s constipated due to his self-destructive habit of consuming plastic.
The process of creating AI with detailed instructions Estefanni posted in the public domain.