Ask Your Question

UFO project - please advice

asked 2013-07-17 04:19:22 -0600

manases gravatar image

updated 2013-07-17 07:07:53 -0600

Hello guys,

Me and some friends are in the process of starting a foundation for UFO research enthusiasts and I am currently gathering data for this initiative. I am investigating different options to put together a UFO surveillance system. Most of the ppl I talked to

  • they use this OpenCV so I thought to ask here for advice
  • this seem to be the key to our project.

I found some already done systems but they are either pretty expensive either not doing what we need. We need a software solution that is modular and can grow in time with more features. The rough steps would be something like:

  • detect movement on the sky and only save when we have movement. This is to be able to leave a camera filming for days or even weeks and then see short films containing movement - not to need to watch the whole filmed week.
  • then we might need get more details on the filmed object - like size direction and speed. For that we need 2 cameras to do some triangulation
  • then knowing more about the obj - we should do some identification. We want to exclude planes, meteorites, birds, balloons, etc so we endup only with UFOs.

The good thing here is that to exclude those we need to identify each one. That means we could use the software to select to film them so it could be useful for astronomers, bird lovers and maybe even airports if it will be robust enough.

  • independent of the identification module - we need then to have a secondary more powerful camera or even telescope - that locks the moving object in the sky and zoom and track it.
  • remote analysis and sharing of the live data and other features...

So we need for the beginning a software that detects movement on the sky (night and day and then it can grow with a lot of other features) so it needs to be done with growth and scalability in mind.

I am a web programmer - PHP so unfortunately I wont attempt to play with this OpenCV myself so I am asking you guys what will be a good approach to have this software done.

Is here anyone interested to help us? Individual or company or where can I find such? We might have some money and once we got a proof of concept (a system that works we will start to build a community) website etc so we might get even more help (thought this is not always happening)

Many thanks, Alex

edit retag flag offensive close merge delete



first of all you need sample video file for test and than get some motion detection system\algorithm, there are some opensource solutions. you can try this

mrgloom gravatar imagemrgloom ( 2013-07-17 07:17:24 -0600 )edit

3 answers

Sort by » oldest newest most voted

answered 2013-07-17 06:19:43 -0600

updated 2013-07-17 06:20:31 -0600

This project sounds interesting and challenging. The beginning of the project is still difficult.

Some considerations:

You want to exclude planes, meteorites, birds, balloons, etc. But don't forget (in my opinion):

  • Clouds. Clouds are moving across the sky.
  • Weather conditions: Rain, snow, hail.

I was working on a cloud tracking algorithm and it is far from trivial.

So, as first step: Are you planning to deploy this system in a desert? It would be interesting in order to make tracking recognition easier.

edit flag offensive delete link more


I think that alberto probably hitted the largest problem of your system. Don't forget that you are trying to detect objects in the most varying possible situation. Clouds move, weather type changes, lightning changes. To get a system robust to all this variation will take probably years of fundamental research first. Look for example how many people are in active research for variation invariant detectors nowadays. However, keep up the work if you want to manage this! Just know it will take a long time to get a decent concept of proof :)

StevenPuttemans gravatar imageStevenPuttemans ( 2013-07-17 07:13:48 -0600 )edit

Ta guys for your replies. The identification algorithm does not have to be very complicated in the beginning. We can live without it. We will have to look at more videos and say - ah it was a bird. If we have a basic movement detection without identification at the beginning that is good enough to call it proof of concept. From what I saw in mrgloom s reply there a re a few approaches to this.

We can easily exclude planes using

About where do I want to deliver this? I want to make this open and as cheaper as possible so ppl all over the world will buy one. I want to give the software free and advice on how to setup the cameras so we can endup with a planetary surveillance system :)

manases gravatar imagemanases ( 2013-07-17 07:55:57 -0600 )edit

Basically all you need to start your idea is shitloads of cash :) You will need to pay a fulltime developer for writing your code and producing your sets for acquisition.

StevenPuttemans gravatar imageStevenPuttemans ( 2013-07-17 08:34:09 -0600 )edit

That does not sound very encouraging. Anyway - this is why I am here basically - to get a quote and a road-map for this project and a time estimate. I would enormously appreciate somebody to look at it as a project not as a job. Somebody who knows how this should be done should be able to say that

  • step 1 - create the basic software that detects movement and saves and is build in a modular way with scalability and modularity in mind for future development will take approximately x amount of time and y money.
  • step 2 - add a module to do triangulation and get more details about the target will take x1 time and will cost approximately y1 money.
  • step 3...
manases gravatar imagemanases ( 2013-07-17 10:23:47 -0600 )edit

Another option would be to exchange programming work - if somebody is willing to do this kind of work for this UFO project I could make him a website or features to existing websites. Please contact me here or PM if interested in anyway

manases gravatar imagemanases ( 2013-07-19 01:58:50 -0600 )edit

Well I don't know in the rest of the world, but here in Belgium compagnies ask for a 'feasability study', which is basically a year of cofunded research by innovation centres, which looks if a subject is actually plausible to get. This is a rather cheap way of setting up your small compagny project.

StevenPuttemans gravatar imageStevenPuttemans ( 2013-07-19 02:55:14 -0600 )edit

answered 2015-01-21 21:11:27 -0600

André Cortes gravatar image

This project is an excelent idea! It is more rational to search extraterrestrial life here in the earth than in the space , like have been done by the SETI PROJECT. We dont know how to reach they far in the space, but many ETs could be visiting us , just now. We know how to photograph , here. Let's make an International Network of Tracking Trap Cams for Extraterrestrial UFO Search, free of hoax , free of fakes and idiots.

edit flag offensive delete link more



I think that the biggest setback in this project is the fact that there are no UFO's visiting earth

Pedro Batista gravatar imagePedro Batista ( 2015-01-22 04:52:57 -0600 )edit

Ahaha - yeah was thinking in the same direction - there are just not enough positive examples XD

But you could the other way - train for known sky object(rockets, planes, birds, meteroids) - and if you have a motion and the prob of that object is below some tresh - then review it. But it could be that an ufo will be be classified as rocket and you still miss it - difficult.

holger gravatar imageholger ( 2019-10-10 19:36:56 -0600 )edit

answered 2013-07-17 06:04:22 -0600

Ben gravatar image

updated 2013-07-17 06:07:00 -0600

It might be hard to collect a significant amount of positive samples for that purpose, but as we all know, UFOs generally look like saucers, so you could try to train a Haar cascade with sample images like this.

Make sure not to test close to a trap shooting range, as this might lead to many false positives

edit flag offensive delete link more


first things .... detect motion ..

absdiff(previousframe, nextframe, n);
absdiff(currentframe, nextframe, l);
bitwise_and(n, l, result);

then you can use "result" as a mask to locate the area on the screen .... then take a deep zoom Area mask and see if the moving object was really a UFO ..... very fun project.

gfx gravatar imagegfx ( 2015-01-22 08:25:45 -0600 )edit

Question Tools


Asked: 2013-07-17 04:19:22 -0600

Seen: 2,968 times

Last updated: Jan 21 '15