In this paper, we present an approach for motion estimate adopted by standards actual videos. The proposed method consists modeling the considered domain in form of a structure of mesh-size using the finite elements method. Basing on the object of interest via the finite elements. Then, the obtained mesh is used in order follow-up of objects deformation. It is a question of determining the deformation of an object nets, from one image to another. For that we used the algorithm allowing following a deformable plane object. On the one hand, we improve its performance, and then we study the optimization of the error function by mesh simplification of our model, among the different triangular meshes associated with images references. At the end of this work, we present the simulation results.