[ptx] autopano #2, using SIFT

[Pablo d'Angelo]

Hallo Sebastian,

Sebastian Nowozin schrieb am Samstag, den 17. Januar 2004:

> On Fri, Jan 16, 2004 at 06:55:59PM +0100, Pablo d'Angelo wrote:
> 
> > On the practical side: so far we have many different languages, and no nice
> > codebase. Is .NET really so much better than C++? Is is it hard to port your
> > code to C/C++? People complain about the wxWindows dependency of hugin, so I
> > don't want to add yet another big dependency if its not really needed.
> > Actually all the project/reading writing is already implemented in C++, as
> > is an interface for the remapping functions and other stuff, so I would
> > prefer if we could use the same codebase.
>  
> I agree about that it would be unwise to split/port any solid established
> codebase, such as Hugin is. My C# implementation is just meant as prototype
> again, and it actually was a pleasure to program in C#, compared to C and C++.
> I hope Alexandre and me can come up with a C++ implementation and can do lots
> of performance tuning along the way. I added a small feature yesterday that
> allows for convenient downscaling of an image, and now I can get around 75
> precise keypoints with atound 5-10% false positives in two 5 Megapixel images
> in 30 seconds using 640x480 images.

I've been "keypoints" with 600x400 images, depending on the images, I get
appoximately 70 - 700 consistent matches. just taking the ones with the
lowest distance leads to very good results.

> On the long term, I think it may be better to leave wxWindows and turn to
> something like GTK+ or even GTK# for the GUI while using a very portable C++
> library and utilities as backend without any non-trivial dependancies. I have
> done some work with GTK# now and it is really maturing and such a pleasure to
> program with. But this is just a suggestion.

Hmm, that would mean rewriting a lot of boring gui code. Not likely to
happen, If I'm the only one involved. But I agree that wxWindows not a nice
environment. However, cross platform and stability also need to be taken
into account (Is gtk# available for win and mac?)

> > I'd really like to add feature detection stuff to hugin and a standalone
> > program. But I understand if you want to stick to C#.
> 
> As long as I have not completely nailed the algorithm I would prefer modding
> the C# stuff, but once that is complete, I am all for porting (although it will
> be boring, maybe some other people familar with the hugin code can help to
> avoid reinventing the wheel).

I'd like to provide all the stuff in a format that fits the vigra library.

> > Something I'd like to see in any case is a clone of the "keypoints" program,
> > available on Dr. Lowe's site :)
>  
> Thats exactly what my programs do right now. Plus using BBF matching instead of
> the vanilla O(N^2) euclid. And some small extra filtering on the match results
> (removing repeating features).

I've just used the "keypoints" program, call it externally from hugin, and
read in the created points. Reimplemented the simple O(N^2) matching. 

So any program that has the same interface and descriptors that can be
compared in a similar way can be used.

just select a bunch of images images in the first panel, and click "run" ;)

Do you think I can release the hugin code that expects the keypoint program?
The code is quite crude, and only works on linux. Maybe its better to
wait until we have our own SIFT implementation, so that people do not start
using Dr. Lowes Keypoint program for commercial purposes?

ciao
  Pablo
-- 
http://wurm.wohnheim.uni-ulm.de/~redman/
Please use PGP