Use Sound and Machine Learning to Identify Birds with a Raspberry Pi - BirdNET-Pi

Over 6000 Unique Bird Calls can be Recognised and it only takes 1 Terminal Command to set up 😍 Ah AI, you’ve done it again. Full Article (with Install Command) - https://core-electronics.com.au/proje... curl -sL https://coreelec.io/birdnet | bash Related Information How to Set-up a Raspberry Pi Single Board Computer - https://core-electronics.com.au/guide... Raspberry Pi Imager Download Location - https://www.raspberrypi.com/software/ BirdNet-Pi Website - https://birdnetpi.com/ BirdNet-Pi Github - https://github.com/mcguirepr89/BirdNE... How to Share Your BirdNet-Pi System Online - https://github.com/mcguirepr89/BirdNE... Original BirdNET System Github - https://github.com/kahst/BirdNET-Anal... BirdWeather - https://app.birdweather.com/ Face Recognition With a Raspberry Pi and OpenCV - https://core-electronics.com.au/guide... Hand Recognition and Finger Identification with Raspberry Pi - https://core-electronics.com.au/guide... Use Your Phone to Control Your Raspberry Pi - https://core-electronics.com.au/tutor... Garden Rooster STL - https://cults3d.com/en/3d-model/vario... BirdNET-Lite is the Tensor Flow lite version of the original BirdNET system. These are machine learned software that can recognise more than 6,000 species worldwide from audio. Theres No Cloud Analysis happening here, every identification is figured out by the Raspberry Pi. The system we are building here can run 24/7 non-stop. It records, tracks, and displays each recognised bird call. It provides confidence values. You can also access the data and the audio live stream through any locally connected computer/device. It even saves the best recordings so you can listen to them later. If you want to exclude species from being identified or focus on just a single species you can do so using the UI easily. As you read this around the world there are many Raspberry Pis around the globe running BirdNet Pi right now. Some have even been specially set up you can tune into them from anywhere in the world, from Nijmegen Netherlands, to Tyresö Sweden and Louisiana the Land of the Free (Links to them in Full Article). There are other great community projects that have sprung about recently that tap into this technology, like Birdweather. The Birdweather Website feeds all the data from BirdNET-Pi systems into a single place. It has a budding worldwide coverage and lets you easily see and analyse the collected data. With enough of Pi’s set up in a city or country, the potential to figure out the flight paths and migrations of bird species in real-time would be right at our fingertips. I also 3D printed a Case that disguises the setup in the form of a Garden Rooster. The Raspberry Pi and an Omnidirectional USB Microphone tuck into it nice and safely inside. This also provides some much-needed semi-waterproofing for outdoor placement. You could power the Rooster with a battery (and even solar panels!) but for today I will give those birdies a small chance of detecting my detection device and utilised wall power. If you have any questions about this content or want to share a project you're working on head over to our maker forum, we are full time makers and here to help - http://coreelec.io/forum Core Electronics is located in the heart of Newcastle, Australia. We're powered by makers, for makers. Drop by if you are looking for: Raspberry Pi 4 Model B (4GB) Ultimate Kit Bundle (AVALIABLE!) - https://core-electronics.com.au/raspb... Raspberry Pi Model B 2GB (used here): https://core-electronics.com.au/catal... Raspberry Pi 4 Model B 8GB: https://core-electronics.com.au/catal... Mini USB Microphone (used here): https://core-electronics.com.au/catal... Raspberry Pi Heatsinks (shown here): https://core-electronics.com.au/catal... Raspberry Pi 4 Power Supply: https://core-electronics.com.au/catal... 0:00 Intro 0:21 System Overview 0:50 What You Need 1:28 Flashing the SD Card 2:02 Assembly of Hardware 2:34 Single Terminal Command 3:36 http://birdnetpi.local 3:51 Pay-Off Time! Magpie Identified 4:29 Kookaburra Identified (~97% Confident) 4:40 Exploring the User Interface 5:27 Username - birdnet & Password - |leave empty| 5:35 How to Exclude Certain Species 5:58 Where to Now 6:26 BirdWeather 6:44 Acknowledgements 7:22 3D Printed Case 7:44 Outro