Trail and wildlife cameras are commonly available nowadays, but the Wild Eye project aims to go beyond simply taking digital snapshots of critters. [Brenda Armour] uses a Raspberry Pi to not only take photos of wildlife who wander into the camera’s field of view, but to also automatically identify and categorize the animals seen using a visual recognition API from IBM via the Node-RED infrastructure. The result is a system that captures an image when motion is detected, sends the image to the visual recognition API, and attempts to identify any wildlife based on the returned data.
The visual recognition isn’t flawless, but a recent proof of concept shows promising results with crows, a cat, and a dog having been successfully identified. Perhaps when the project is ready to move deeper into the woods, elements from these solar-powered networked birdhouses (which also use the Raspberry Pi) could help cut some cords.
What I really want is something to identify squirrels and gives me coordinates so I can spray water in that direction. Squirrels love to tease my dogs…
Then I have the PyCon talk for you:
https://www.youtube.com/watch?v=QPgqfnKG_T4
Mandatory XKCD
https://xkcd.com/382/
Other mandatory XKCD
https://xkcd.com/1425/
Starling identified… fire laser. Dead. Yeah!
Next, stinkbugs!
Don’t forget to program in Asimov’s Three Laws!
Actually I prefer a single feeding station feeder that discriminates around who perches on each electric wired perch and feeding hole. A camera is positioned to get a good profile as to the feeding position. Like the silhouette camera and software to allow cat without mouse treat only to open the cat door featured here. No squirrels, skunk, or birds allowed!
I could use this if it can reliably differentiate between crows and other birds :P
System is going to have fits when Bigfoot shows up.
“Yo mama detected!”
“Not hotdog”