Kalman Filter in Matlab

http://www.mathworks.com/matlabcentral/fileexchange/33804-tracking-of-a-point-in-video-using-kalman-filter

 

http://www.mathworks.com/matlabcentral/fileexchange/14243-2d-target-tracking-using-kalman-filter

http://wn.com/Object_Tracking_in_MATLAB

http://www.mathworks.com/matlabcentral/fileexchange/5377-learning-the-kalman-filter

http://www.inf.ed.ac.uk/teaching/courses/av/LECTURE_NOTES/SMALL/avsys2s.pdf

http://www.mathworks.se/matlabcentral/newsreader/view_thread/301097

 

 

Share

A few more links on ball tracking…

Tennis annotation:

 

http://info.ee.surrey.ac.uk/Research/VSSP/Publications/papers/yan-bmvc2005.pdf

 

Unsupervised Video Segmentation Based
on Watersheds and Temporal Tracking
http://lagis-vi.univ-lille1.fr/bibtex/upload/1998/wang_csvt_1998.pdf
http://multimedialab.elis.ugent.be/users/chpoppe/Masterproef/sportsAnalysis/tennis/TrajectoryBased%20ball%20detection%20and%20tracking%20algorithm%20in%20broadcast%20tennis%20video.pdf
http://info.ee.surrey.ac.uk/Research/VSSP/Publications/papers/Yan-PAMI-2008.pdf

 

http://adi.ac.ir/uploads/06.pdf

 

Share

Basketball Tracking

http://www.google.co.uk/url?sa=t&rct=j&q=tracking%20of%20a%20basketball%20using%20multiple%20cameras&source=web&cd=4&ved=0CD4QFjAD&url=http%3A%2F%2Fupcommons.upc.edu%2Fpfc%2Fbitstream%2F2099.1%2F11457%2F1%2F62272.pdf&ei=JZfSTp22BMefOrGS1a8P&usg=AFQjCNHSxcR_TxeDAo3dL11GJT6sfGq-zw&sig2=TN-FX7t-KD4xt5OVGKd_pg

 

Hough Transformation

Share

PATENT APPLICATION

Relevance is dubious, but fact is this is a patent…surely not?

http://www.freepatentsonline.com/EP2372653.pdf

First, the data of a moving image that is captured
is read for each frame, and whether to start tracking is
determined based on the presence or absence of a target
object (S20, S22). An edge image of the image frame is
created after it is determined to start tracking (S24).
Meanwhile, a particle is distributed in a space of a coefficient
set for each control point sequence when the control
point sequence of a B-spline curve representing the
shape of the target object is represented in a linear combination
of control point sequence of a B-spline curve
representing a plurality of reference shapes that are
made available in advance (S26). A particle is also distributed
in the space of a shape-space vector (S28), the
likelihood of each particle is observed, and the probability
density distribution is acquired (S30). A curve obtained
by weighting parameters by the probability density distribution
and then averaging the weighted parameters is
created as a tracking result (S32).

Share