Evaluation of Multi-part Models for Mean-Shift Tracking
Citation:
Darren Caulfield & Kenneth Dawson-Howe, Evaluation of Multi-part Models for Mean-Shift Tracking, Proceedings, 2008 International Machine Vision and Image Processing Conference, (IMVIP 2008), 2008 International Machine Vision and Image Processing Conference, (IMVIP 2008), Portrush, Northern Ireland, 3-5 Sept., Bryan Scotney, Philip Morrow, IEEE, 2008, 77-82Download Item:
Evaluation of Multi-Part Models for Mean-Shift Tracking.pdf (Published (publisher's copy) - Peer Reviewed) 330.0Kb
Abstract:
Mean-shift tracking is a data-driven technique for tracking
objects through a video sequence. We propose an innovation
to mean-shift tracking that combines the background
exclusion constraint with multi-part appearance models.
The former constraint prevents the tracker from moving to
regions where no foreground objects are present, while the
multi-part nature of the models enforces a spatial structure
on the tracked object. We also use a simple formula to determine
the scale of the object in each video frame, and note
the importance of setting an appropriate convergence condition.
An evaluation of our proposed tracker and several
existing trackers is performed using a ground truth dataset.
We demonstrate that our innovation yields more accurate
tracking than existing mean-shift techniques.
Sponsor
Grant Number
Irish Research Council for Science and Engineering Technology (IRCSET)
Author's Homepage:
http://people.tcd.ie/kdawsonDescription:
PUBLISHEDPortrush, Northern Ireland
Author: DAWSON-HOWE, KENNETH
Other Titles:
Proceedings, 2008 International Machine Vision and Image Processing Conference, (IMVIP 2008)2008 International Machine Vision and Image Processing Conference, (IMVIP 2008)
Publisher:
IEEEType of material:
Conference PaperCollections:
Availability:
Full text availableKeywords:
Computer ScienceLicences: