Liam Ellis, Jirí Matas, Nicholas Dowson, and Richard Bowden. Linear predictors for fast simultaneous modeling and tracking. In Dimitris Metaxas, Baba Vemuri, Amnon Shashua, and Harry Shum, editors, Workshop on Non-rigid Registration and Tracking through Learning - NRTL, at ICCV 2007: Proceedings of Eleventh IEEE International Conference on Computer Vision, page 8, Los Alamitos, USA, October 2007. IEEE Computer Society, IEEE Computer Society Press.
An approach for fast tracking of arbitrary image features with no prior model and no offline learning stage is presented. Fast tracking is achieved using banks of linear displacement predictors learnt online. A multi-modal appearance model is also learnt on-the-fly that facilitates the selection of subsets of predictors suitable for prediction in the next frame. The approach is demonstrated in real-time on a number of challenging video sequences and experimentally compared to other simultaneous modeling and tracking approaches with favourable results.