Online Learning and Partitioning of Linear Displacement Predictors for Tracking
Ellis, L, Matas, J and Bowden, R (2008) Online Learning and Partitioning of Linear Displacement Predictors for Tracking In: BMVC 2008, 2008-09-01 - 2008-09-04, Leeds, UK.
Available under License : See the attached licence file.
A novel approach to learning and tracking arbitrary image features is presented. Tracking is tackled by learning the mapping from image intensity differences to displacements. Linear regression is used, resulting in low computational cost. An appearance model of the target is built on-the-fly by clustering sub-sampled image templates. The medoidshift algorithm is used to cluster the templates thus identifying various modes or aspects of the target appearance, each mode is associated to the most suitable set of linear predictors allowing piecewise linear regression from image intensity differences to warp updates. Despite no hard-coding or offline learning, excellent results are shown on three publicly available video sequences and comparisons with related approaches made.
|Item Type:||Conference or Workshop Item (Conference Paper)|
|Divisions :||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Identification Number :||10.5244/C.22.4|
|Additional Information :||© The authors. Published by The British Machine Vision Association (BMVA).|
|Depositing User :||Symplectic Elements|
|Date Deposited :||22 May 2012 15:31|
|Last Modified :||09 Jun 2014 13:18|
Actions (login required)
Downloads per month over past year