Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I built a system that takes pictures of all the airplanes that fly over my house

twitter.com

Post reply on HN
Print view View original

21–30 of 192 posts

Re: I built a system that takes pictures of all the airplanes that fly over my house

#22

Post by gnabgib »

Feels like the website-about page: http://skybot.cam/about is a much better link than a tweet.. loaded with details. For example:

  - Most planes are passing at over 30,000'
  - It's using a Costar RISE 4260 camera /w built in heater
  - It leverages SkyScan by IQT labs[0]
  - It leverages Azure custom vision API[1]
[0]: https://github.com/IQTLabs/SkyScan [1]: https://azure.microsoft.com/en-us/services/cognitive-service...

Re: I built a system that takes pictures of all the airplanes that fly over my house

#23

Post by busheezy »

robotastic wrote: post #19

Hi! I am the guy behind this, awesome to see it posted here. Happy to answer any questions. To answer a question I saw pop up, I am using the FAA aircraft registration data to pull up the extra information about the planes. It lists who actually owns the plane, vs who is operating it. That is why you see so many banks. Places like Flightaware have much better data, but a pricy to look up.

If you set up an ADB, Flight Aware will give you an Enterprise account. FlightRadar24 also will give you a Business account. There is a docker image out there that will let you pump data to both services.

Re: I built a system that takes pictures of all the airplanes that fly over my house

#24

Post by phkahler »

yeldarb wrote: post #20

Any interest in sharing the plane dataset you used to train Azure Custom Vision with others? Happy to host it on Roboflow Universe along with an API to a trained model others can hit to detect planes in images. We’ve got one detecting planes on the ground but not yet in the air! https://universe.roboflow.com/gdit/aerial-airport

Did they ever indicate using a model like that? Just plug in an ADS-B receiver and they'll broadcast their tail number and location to you. Everything else can be looked up.

Re: I built a system that takes pictures of all the airplanes that fly over my house

#25

Post by csours »

robotastic wrote: post #19

Hi! I am the guy behind this, awesome to see it posted here. Happy to answer any questions. To answer a question I saw pop up, I am using the FAA aircraft registration data to pull up the extra information about the planes. It lists who actually owns the plane, vs who is operating it. That is why you see so many banks. Places like Flightaware have much better data, but a pricy to look up.

Awesome! I live north of Austin-Bergstrom and I quite often see planes on final approach. I've thought about doing this, and also trying to find a physical site for a telescope or telescopes to watch take-offs and landings.

Re: I built a system that takes pictures of all the airplanes that fly over my house

#26

Post by ytjohn »

robotastic wrote: post #19

Hi! I am the guy behind this, awesome to see it posted here. Happy to answer any questions. To answer a question I saw pop up, I am using the FAA aircraft registration data to pull up the extra information about the planes. It lists who actually owns the plane, vs who is operating it. That is why you see so many banks. Places like Flightaware have much better data, but a pricy to look up.

This is absolutely incredible. I have been wanting to do this as well, but I was going to approach it from the computer vision approach (blueiris and deepstack ai). Or a dedicated camera and pythoncv. I never even thought of having cameras move to match flightaware data.

A number of planes fly low and when I check flightaware, they're not on it. Or there's a plane that could be it, but it's flight path is heading East to West 30 miles North of me, while this plane came from the South heading North. Also, pretty much once a month or so, a pair of A10 Warthogs fly over or near our house. Last month, we had a real treat with 4 of them directly over the house, better than an air show.

So I'd like to setup 4 cameras on my tower focused skyward and have them try to catch clips of planes. I'll be looking at your work to see if I can also match those with flightaware.

Re: I built a system that takes pictures of all the airplanes that fly over my house

#27

Post by metadat »

gnabgib wrote: post #22

Feels like the website-about page: http://skybot.cam/about is a much better link than a tweet.. loaded with details. For example: - Most planes are passing at over 30,000' - It's using a Costar RISE 4260 camera /w built in heater - It leverages SkyScan by IQT labs[0] - It leverages Azure custom vision API[1] [0]: https://github.com/IQTLabs/SkyScan [1]: https://azure.microsoft.com/en-us/services/cognitive-service...

I wonder what the monthly Azure bill is.

Also wondering what the stack would look like for a self-hosted version with equivalent or better functionality!

Re: I built a system that takes pictures of all the airplanes that fly over my house

#29

Post by chopsuei3 »

Very slick! Were you using PiAware or listening to ADSB prior to this project?

I remember starting a similar project years ago when I got my first RTL-SDR adapter - didn't get too far, but probably cheaper than this setup https://web.archive.org/web/20160228105159/http://simonaubur...

Re: I built a system that takes pictures of all the airplanes that fly over my house

#30

Post by robotastic »

ytjohn wrote: post #26
robotastic wrote: post #19

Hi! I am the guy behind this, awesome to see it posted here. Happy to answer any questions. To answer a question I saw pop up, I am using the FAA aircraft registration data to pull up the extra information about the planes. It lists who actually owns the plane, vs who is operating it. That is why you see so many banks. Places like Flightaware have much better data, but a pricy to look up.

This is absolutely incredible. I have been wanting to do this as well, but I was going to approach it from the computer vision approach (blueiris and deepstack ai). Or a dedicated camera and pythoncv. I never even thought of having cameras move to match flightaware data. A number of planes fly low and when I check flightaware, they're not on it. Or there's a plane that could be it, but it's flight path is heading Eas…

Doing a vision only approach would be really cool. A lot of the interesting planes do not have their ADS-B transponder on. The two systems could actually work well together. My system ends up generating a really nice, labeled dataset. I put some initial scripts / notebooks together for building ML models that can classify the different types of aircraft. https://github.com/IQTLabs/SkyScan/tree/main/ml-model/script...
Post reply on HN