29 January 2007 Feature point tracking combining the Interacting Multiple Model filter and an efficient assignment algorithm
Author Affiliations +
Abstract
An algorithm for feature point tracking is proposed. The Interacting Multiple Model (IMM) filter is used to estimate the state of a feature point. The problem of data association, i.e. establishing which feature point to use in the state estimator, is solved by an assignment algorithm. A track management method is also developed. In particular a track continuation method and a track quality indicator are presented. The evaluation of the tracking system on real sequences shows that the IMM filter combined with the assignment algorithm outperforms the Kalman filter, used with the Nearest Neighbour (NN) filter, in terms of data association performance and robustness to sudden feature point manoeuvre.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
David Marimon, Yousri Abdeljaoued, Bruno Palacios, and Touradj Ebrahimi "Feature point tracking combining the Interacting Multiple Model filter and an efficient assignment algorithm", Proc. SPIE 6508, Visual Communications and Image Processing 2007, 650808 (29 January 2007); doi: 10.1117/12.702800; https://doi.org/10.1117/12.702800
PROCEEDINGS
8 PAGES


SHARE
Advertisement
Advertisement
Back to Top