Use AI on a RASPBERRY PI to IDENTIFY BIRDS (Part 1)

In this video I take the first steps in developing object detection running on a Raspberry PI to identify different species of bird on my bird feeder. The purpose of this first part is to take some static images from a webcam pointing at my bird feeder and then run those through a pre-existing data model. I can then see how well it performs in identifying the birds. Future videos will carry this project forward to the point where I have a real-time feed from my webcam with the birds being located and identified (hopefully) at something approximating 30fps. Links to things you see in the video (shop around!! These are just what I used!!): Raspberry PI 5 - https://shop.pimoroni.com/products/ra... Webcam (This is the one I used but any weatherproof camera that captures full HD would be fine) - https://www.amazon.co.uk/gp/product/B... SecretBatCave Bird Classifier project - https://github.com/secretbatcave/Uk-B... My fork of the above (upgrade to Python 3 etc) - https://github.com/jeffspiinthesky/Uk... ISpyConnect website (figure out URI to access streams from your webcam) - https://www.ispyconnect.com/cameras Chapters: 00:00 - Intro 00:49 - Titles 00:56 - Like / Subscribe / Notify / Comment 02:15 - Project Intro 03:56 - Kit list 06:18 - Static image capture using FFMPEG 09:54 - Checking images and code walkthrough 14:06 - Build Docker container 14:36 - Run software against stock images 15:53 - Run software against my captured images 17:22 - Conclusions 19:56 - Outro 20:34 - Closing titles Equipment used: Canon M100 camera with 13-55mm kit lens Shure MV7 mic Elgato collapsable green screen Neewer GL1 Pro keylight Nanlite Pavotube 30C lights Original video capture using OBS All video editing using Kdenlive All image editing using GIMP