Jump to content
Sign in to follow this  
Lurker

Open Source UAV Post Processing Solution

Recommended Posts

Hello, UAV recently gain huge popularity, 

 

We could find low cost UAV too (we have a recent project using custom fix wing drone that only cost approx under 5000 dollar), but how bout low cost or even free post processing software ?

 

I find this interesting articles and tutorials :

http://flightriot.com/tutorials/post-processing/

using open source software like Meshlab, CMPMVS, VisualSFM, and such

 

but, anyone in here have the experience with above method?

 

share your thought

  • Like 1

Share this post


Link to post
Share on other sites

I have already conduct some test with Meshlab and VisualSFM based in this tutorial.

Never heard about CMPMVS and that looks interesting.

 

Thanks for this.

 

;)

 

darksabersan.

Share this post


Link to post
Share on other sites

so my friend how do you think about processing UAV data using Meshlab and VisualSFM?

 

stitching picture based on their motion when capturing is interesting concept, Microsoft also have interesting software bout it ;

http://research.microsoft.com/en-us/downloads/69699e5a-5c91-4b01-898c-ef012cbb07f7/default.aspx?tduid=(515a7ed2cb698cd5dd841e750cdb3839)(256380)(2459594)(TnL5HPStwNw-xqhAQtOyAXSrDl80u.wJsg)() 

I found another one :

 

OpenDroneMap

http://opendronemap.github.io/odm/ 
  • Like 1

Share this post


Link to post
Share on other sites

I recently developed an online cloud service structure-from-motion algorithm for many purposes called CloudSfM (do a Github search :D ). It combines these three libraries below:

I found that the three combination yields very good result, even comparable to that of Agisoft Photoscan. 

 

Another open source libraries with quite satisfactory result (as far as I have tried):

Happy opensourcing!  :)

  • Like 2

Share this post


Link to post
Share on other sites

interesting project shin_conan, with your project, have you achieve DSM and orthophoto already? 

using cloud based processing, I cant imagine how to manage resource with huge traffic  :o

Share this post


Link to post
Share on other sites

 

so my friend how do you think about processing UAV data using Meshlab and VisualSFM?

 

stitching picture based on their motion when capturing is interesting concept, Microsoft also have interesting software bout it ;

http://research.microsoft.com/en-us/downloads/69699e5a-5c91-4b01-898c-ef012cbb07f7/default.aspx?tduid=(515a7ed2cb698cd5dd841e750cdb3839)(256380)(2459594)(TnL5HPStwNw-xqhAQtOyAXSrDl80u.wJsg)() 

I found another one :

 

OpenDroneMap

http://opendronemap.github.io/odm/ 

I have tried the Image Composite Editor and it does pretty decent job until a certain limit.

Lens correction is really better managed in comparison with Photomerge (Photoshop) as example because this software can handle planar Imagery.

 

;)

 

darksabersan.

  • Like 1

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
Sign in to follow this  

×

Important Information

By using this site, you agree to our Terms of Use.