Code covered by the BSD License

### Highlights from A Ball Tracking Application

3.83333

3.8 | 6 ratings Rate this file 65 Downloads (last 30 days) File Size: 1.17 MB File ID: #25435

# A Ball Tracking Application

The tracker implements the Covariance Tracking method to track the ball in a football match

File Information
Description

The application uses the approach introduced in paper "Covariance Tracking using Model Update Based on Means on Riemannian Manifolds", F.Porikli, O.Tuzel, P.Meer.

The tracking is based on:
1) initializing the target region
2) constructing the Feature Vectors for each pixel in the target region (first frame)
3) forming the Covariance Matrix using feature vectors generated in step 1
4) determining the candidate regions for the following frames and constructing the covariance matrices of these regions
5) finding the minimum covariance-distanced region from these candidate region
6) assign this region as the estimated region

MATLAB release MATLAB 7.6 (R2008a)
Tags for This File   Please login to tag files.
Comments and Ratings (16)
22 May 2012

1) Object appearance model is never updated, just a half-way implementation of the cited paper...
2) aviread() can be replaced by VideoReader() to make the code working, details can be found in MATLAB help.
3) The tracker drifts quite quickly after a few frames.
4) Fast computation of Covariance feature by integral image is not used...

26 Mar 2012

Hi
I am new to matlab, can anone explain me to understand the equation stand for.
f(i+(j-1)*size,:) = [positionX+i-1 positionY+j-1 dI(positionY+j-1, positionX+i-1) ...
Ix(positionY+j-1, positionX+i-1) Iy(positionY+j-1, positionX+i-1) ...
Ixx(positionY+j-1, positionX+i-1) Iyy(positionY+j-1,positionX+i-1)];

Thanks
Sanki

24 Mar 2012

Hi
can you explain me why the CR dimension is 7x7

Thanks
Ram

08 Aug 2011

For some reason, my comment was deleted! don't know why, sorry!

this was my comment which is apparently deleted!

Thanks Fuat for the code, very helpful! I just wanted to ask if you implemented the update mechanism which is based on Riemannian manifold. I guess it's not included in the code! Am i right?

08 Aug 2011

?

08 Aug 2011

Sorry, the last bit in my previous comment (I had only one question!) was added by mistake!

11 Jul 2011

I have a problem in understanding the initial position of the object, How is it calculated?
what does position offset mean?

01 Feb 2011

I have used findCovarianceMatrix.m,
and it works fine, although it is not efficiently implemented e.g. it is not using the integral image method. However I do not see any function to deal with the computation of a minimum covariance-distance.

17 Dec 2010

how to run this file i am finding diffcult please help me out

14 Sep 2010
14 Sep 2010

Guys It works for me, but the thing is it displays all frames as images.
What if we want to track the ball in real time ????

06 Sep 2010

i am also getting same problem

17 May 2010

i cannot understand CovarianceMatrix , eig and temp ...
can someone help me understanding ..

12 Mar 2010

Not working! Same errors.

@Ronak:

05 Jan 2010

With the above comment I meant that the error was coming in the trackball.m file, with line47:

mov = aviread(videoFile, 1:maxFrame);

And I solved it by replacing it with following lines:

for k = 1 : maxFrame
mov(k).cdata = vidFrames(:,:,:,k);
mov(k).colormap = [];
end

And the modified code works just fine.

05 Jan 2010

hey i tried your code. But it showed an error,
??? Error using ==> aviread at 76
Unable to locate decompressor to decompress video stream
for the command:
mov = aviread(videoFile, 1:maxFrame);
but i got a solution for it, using mmreader....