I built a DIY plane spotting system at home

peanutbutter

Discoverer
I built this over the weekend using an old Nokia phone and a Raspberry PI 3B+, you can view the images here: https://pilane.obviy.us/

Some technical details:
- The Nokia 5.4 Android device is powered by the Pi via USB
- Pi connects to the phone via adb
- The Pi uses `scrcpy` to mirror the phone's back camera to /dev/video0 using v4l2loopback
- The video feed is then fed to a Python script that uses YOLOv11 to detect airplanes
- If the image contains an airplane, the flight data is fetched from Flightradar24
- The data is sent to a Telegram channel and updated on the website

It's working really well! I'm able to see pictures of Air Force planes flying overhead for Republic Day too (one of these is not like the others :) ):
1737876211488.png


Please feel free to suggest any improvements. Right now I'm not too happy with the image quality, would love to hear your ideas!
 
Last edited:
Helps to live in a place where the planes fly low enough for this thing to work.

Then again I don't envy you. The noise must be quite disturbing.
It helps being near an airport!

There’s hardly any noise inside the house unless I go to the balcony or terrace. I never noticed the planes until I was on the terrace with a few friends :D
 
Great project. Would it be able to identify and distinguish between multiple planes flying ahead?

Also, did you look at Visual LMs that can process images?
I think you can run them on raspberry pi now. Look at Ollama
 
Great project. Would it be able to identify and distinguish between multiple planes flying ahead?
No chance of that I'm afraid. Right now it assumes there's only a single plane in the image and in the area.

Also, did you look at Visual LMs that can process images?
I think you can run them on raspberry pi now. Look at Ollama
I did! I run the Llama3.2-11B models on my laptop occasionally but unfortunately this Pi only has 1GB of RAM. Inference would take ages on that
 
  • Like
Reactions: draglord