Mean-shift Blob Tracking through Scale Space

Robert Collins
Computer Vision and Pattern Recognition (CVPR'03), June, 2003.


Download
  • Adobe portable document format (pdf) (288KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
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.

Keywords
tracking, mean-shift, scale space

Notes

Text Reference
Robert Collins, "Mean-shift Blob Tracking through Scale Space," Computer Vision and Pattern Recognition (CVPR'03), June, 2003.

BibTeX Reference
@inproceedings{Collins_2003_4369,
   author = "Robert Collins",
   title = "Mean-shift Blob Tracking through Scale Space",
   booktitle = "Computer Vision and Pattern Recognition (CVPR'03)",
   publisher = "IEEE",
   month = "June",
   year = "2003",
}