Online Learning and Partitioning of Linear Displacement Predictors for Tracking | Zendy

Liam Ellis | Zendy; Jǐŕı Matas | Zendy; Richard Bowden | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Online Learning and Partitioning of Linear Displacement Predictors for Tracking

Author(s) -

Liam Ellis,

Jǐŕı Matas,

Richard Bowden

Publication year - 2008

Publication title -

citeseer x (the pennsylvania state university)

Language(s) - English

Resource type - Conference proceedings

DOI - 10.5244/c.22.4

Subject(s) - computer science , artificial intelligence , cluster analysis , tracking (education) , image (mathematics) , pattern recognition (psychology) , piecewise linear function , set (abstract data type) , linear regression , computer vision , regression , machine learning , mathematics , statistics , psychology , pedagogy , geometry , programming language

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

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research