Being interested in bird watching, I attached a bird feeder to a window of my flat and within a few days various species of bird started visiting the feeder. I decided it would be fun to rig up a motion triggered camera to capture images of the birds, and I used Home-Assistant and a £10 USB webcam to capture images via motion trigger, and setup Home-Assistant to send an image notification to my phone when an image was captured.
However I quickly discovered that all kinds of motion could trigger an image capture. The result was hundreds of images of all kinds of motion, such as planes flying in the distance or even funky light effects. Approximately less than half the images actually contained a bird, so I decided it was necessary to filter out the non-bird images. I have been interested in image classification for a while, and whilst searching online I came across this article on Classificationbox, which looked ideal for this project. This write-up will first present the image classification work using Classificationbox, then describe the practical implementation within an automated system
Each Friday is PiDay here at Adafruit! Be sure to check out our posts, tutorials and new Raspberry Pi related products. Adafruit has the largest and best selection of Raspberry Pi accessories and all the code & tutorials to get you up and running in no time!
8-6-2021 (August 6, 2021) is the Snakiest day of the year and it’s also this year’s CircuitPython Day! The day highlights all things CircuitPython and Python on Hardware. See you there!
Stop breadboarding and soldering – start making immediately! Adafruit’s Circuit Playground is jam-packed with LEDs, sensors, buttons, alligator clip pads and more. Build projects with Circuit Playground in a few minutes with the drag-and-drop MakeCode programming site, learn computer science using the CS Discoveries class on code.org, jump into CircuitPython to learn Python and hardware together, TinyGO, or even use the Arduino IDE. Circuit Playground Express is the newest and best Circuit Playground board, with support for CircuitPython, MakeCode, and Arduino. It has a powerful processor, 10 NeoPixels, mini speaker, InfraRed receive and transmit, two buttons, a switch, 14 alligator clip pads, and lots of sensors: capacitive touch, IR proximity, temperature, light, motion and sound. A whole wide world of electronics and coding is waiting for you, and it fits in the palm of your hand.