A Viterbi tracker for local features
Citation:
Gary Baugh and Anil Kokaram, A Viterbi tracker for local features, Proceedings of SPIE, Visual Information Processing and Communication, San Jose, California, USA, 19 January, 2010, 7543, 75430L, SPIE, 2010Download Item:
A Viterbi tracker for local features.pdf (Published (publisher's copy) - Peer Reviewed) 4.575Mb
Abstract:
The long term tracking of sparse local features in an image is important for many applications including camera calibration for stereo applications, camera or global motion estimation and people surveillance. The majority of existing tracking frameworks are based on some kind of prediction/correction idea e.g. KLT and Particle Filters. However, given a careful selection of interest points throughout the sequence, the problem of tracking can be solved with the Viterbi algorithm. This work introduces a novel approach to interest point selection for tracking using the Mean Shift algorithm over short time windows. The resulting points are then articulated within a Viterbi algorithm for creating very long term tracking data. The tracks are shown to be more accurate than traditional KLT implementations and also do not suffer from accumulation of error with time.
Sponsor
Grant Number
Science Foundation Ireland (SFI)
Author's Homepage:
http://people.tcd.ie/akokaramDescription:
PUBLISHEDSan Jose, California, USA
Author: KOKARAM, ANIL
Other Titles:
Proceedings of SPIEVisual Information Processing and Communication
Publisher:
SPIEType of material:
Conference PaperSeries/Report no:
754375430L
Availability:
Full text availableKeywords:
Electronic & Electrical EngineeringDOI:
http://dx.doi.org/10.1117/12.839469Licences: