Problems with using ForegroundGaussian

Problems with using ForegroundGaussian

Hello,

I try to replace my 'home-brew' gaussian mixture model with the ipp version, but I run into two problems:

  • Setting the parameters of the model doesn't seem to have any influence on the results
  • The reference image buffer doesn't get filled at all.

This is what I do:

  • I allocate a IppFGGaussianModel and set it's parameters.
  • I call ippiForegroundGaussianInitAlloc
  • and for each incoming image I call ippiForegroundGaussian

As mentioned the reference image doesn't get filled at all. The foreground mask is incredibly noisy, it seems that a foreground probabilty > 0 is enough to mark the pixel as foreground. And again: changing the model parameters doesn't change anything at all.

Am I doing something wrong ? Or is this a bug ?

Rob Ottenhoff

15 posts / 0 new
Last post
For more complete information about compiler optimizations, see our Optimization Notice.

I have had exactly the same experience, and have spent quite a bit of time trying to get the ippForegroundGaussian functions to produce sane results without success.

I can see absolutely no change in the reference image no matter what parameters are set. The output image does produce output, but seems to behave very strange. Noisy, as Rob said would be a good (if gentle) discription.

Some guidance on proper usage of these functions would be appreciated.

Best,
Doug

Hello,

From the latest release notes:
'Corrected results from calling
Image Segmentation function ippiForegroundGaussian'

So I ran my test project using the new version:
I must admit the reference image does get filled now. The segmentation result however remains 'suboptimal', and changing the model parameters still doesn't affect the result at all. I suggest some more bug fixing.

Greetings,

Rob

Hi Rob,

the function use some default parameters and changing parameters is not supported yet. This might be improved in future versions of IPP.

Regards,
Vladimir

Hi Vladimir,

Thank you for your answer. It creates clarity.

Regards,

Rob

Thanks Vladmir,
I posed a similar question over a year ago 4-13-07 and never recieved an answer.
I've had to use my own code as well.
I'll look forward to improvement in the future.

PS. I love IPP but some of the functions in Chapt 14 "Computer Vision" are similar to ippiForegroundHistogram in their limitations.

Hello,

please submit your findings on Intel Premier Support, otherwise they might be overlooked.

Regards,
Vladmir

Quoting - vdudnik

Hello,

please submit your findings on Intel Premier Support, otherwise they might be overlooked.

Regards,
Vladmir

Hi Vladimir,

I submitted this issue on premier support. And after some intial checks ( did I really use the right version etc. ) they looked into the matter. After a month I received an answer: 'the issue was added to an engineering database as a feature request'. I fear this can also be quoted as 'the issue has been send into oblivion' but I might be wrong. I'll see. I have no idea if they reproduced the problem or if they even tried.

Regards,

Rob

Well, don't be so sceptic :)
The reason I'm asked you to submit it as an official feature request is to keep that in our product feature requests data base. Now it will be tracked within development team until we get a final decision (implement, postpone, decline, whatever else...).
Regards,
Vladimir

Quoting - Vladimir Dudnik (Intel)

Well, don't be so sceptic :)
The reason I'm asked you to submit it as an official feature request is to keep that in our product feature requests data base. Now it will be tracked within development team until we get a final decision (implement, postpone, decline, whatever else...).
Regards,
Vladimir

Hi Vladimir,

I told you : oblivion...

Regards,

Rob

Quoting - Rob Ottenhoff

Hi Vladimir,

I told you : oblivion...

Regards,

Rob

For what it's worth, I also filed a premier support issue about this last year. I was told that the input parameters dont work, and the case was closed.

This function is not simple though, and might be too high level for IPP. That said, it should be removed if it doesn't work.

Quoting - dvj

For what it's worth, I also filed a premier support issue about this last year. I was told that the input parameters dont work, and the case was closed.

This function is not simple though, and might be too high level for IPP. That said, it should be removed if it doesn't work.

i agree with you

Quoting - dvj

For what it's worth, I also filed a premier support issue about this last year. I was told that the input parameters dont work, and the case was closed.

This function is not simple though, and might be too high level for IPP. That said, it should be removed if it doesn't work.

i agree with you

Quoting - sss474948

i agree with you

Hi,

Well I don't agree. A decent backgroundsubtraction method, like a gaussian mixture, running on IPP speed would certainly be helpfull. I would leave more time for high-level algorithms. I would prefer the Zivkovic variant over the promised one. I do agree that the current version which doesn't work at all should be removed, this way intel wastes the time of people trying to use the function only to find that it doesn't work...

Regards,

Rob

p.s. Z.Zivkovic: Improved Adaptive Gaussian Mixture Model for Background Subtraction. ICPR, 2004

Hello,

thanks all for your feedback on this thread. We actually do consider computer vision IPP functionality (or might be better to call it image analysis functionality?) as an important part of product. Unfortunately we not always can provide new product features at a speed anyone want, especially in case of complex functions like one discussed here.

I would suggest to create a separate thread for discussing a new features requests in computer vision library (this should make it easier to solidify all inputs). Whatalso interesting for us is to know what functionality in computer vision is really in use and what might be designed not that well and might be deprecated in future?

Regards,
Vladimir

Leave a Comment

Please sign in to add a comment. Not a member? Join today