Robert T. Collins,
"Mean-shift Blob Tracking through Scale Space,"
IEEE Computer Vision and Pattern Recognition,
Madison, WI, June 2003.
The mean-shift algorithm is an efficient technique
for tracking 2D blobs through an image.
Although the scale of the mean-shift kernel is a
crucial parameter, there is presently no clean mechanism
for choosing or updating scale while tracking
blobs that are changing in size.
We adapt Lindeberg's theory of feature
scale selection based on local maxima of differential
scale-space filters to the problem of selecting
kernel scale for mean-shift blob tracking. We show
that a difference of Gaussian (DOG) mean-shift
kernel enables efficient tracking of blobs through
scale space. Using this kernel requires generalizing the
mean-shift algorithm to handle images that contain
negative sample weights.
Click here for
full paper (287924 bytes, pdf file).