To search, Click below search items.


All Published Papers Search Service


A Genetic Algorithm for Motion Estimation


A. El ouaazizi, M. Zaim, R. Benslimane


Vol. 11  No. 4  pp. 165-172


We derive a robust algorithm for estimating motion parameters of rigid features resulted from a segmentation of dynamic scenes into several differently moving objects. Thus each objects is characterized by a transform h (x, T) with a parameter vector T which implicitly describes the surface shape and the three-dimensional motion of the objects in the scene. In this paper, a split and merge technique for the segmentation is used. Moreover, in order to estimates the vector parameter T we propose to use a genetic algorithm.


Moving object, Segmentation, Estimation, Genetic Algorithms