Multiple parametric motion model estimation and segmentation
Raúl Montoliu, Filiberto Pla · 2002
This paper presents a motion estimation and segmentation algorithm based on multiple parametric model estimation that determines the a priori unknown number of motion models present in the data. The algorithm applies a quasi-simultaneous parametric model fitting method based on a general least square fitting. Some experiments are showed in order to demonstrate the results obtained using the proposed algorithm.