This study proposes a new approach to perform motion estimation on a set of feature points via elastic graph matching.
The approach starts by constructing a labeled graph on a set of feature points in the first image of a given sequence, and
then continues to sequentially match the graph with the remaining images in this sequence. The matching is based on a
similarity function that depends on image brightness and motion characteristics on one side, and on geometric distortion
on the other side. The main advantage of the proposed approach is that it preserves high-level image characteristics
outlined by the geometrical structure of moving objects and their relative positions in space and time, while it
simultaneously accounts for both low-level measurements (motion and intensity).
In this study, we propose a new multi-frame method to compute a smooth and boundary preserving optical flow estimate. The approach is based on the bilateral filtering, a fast edge preserving smoothing tool. Inspired by the variational origin of the bilateral filter, we construct an energy functional that takes into account the image brightness conservation constraint and the bilateral smoothness of the optical flow. Minimization of this energy functional is performed using the Gauss Seidel iterations. Experimental results on synthetic and real image sequences demonstrate that the proposed approach yields an optical flow that is smooth and yet motion boundary preserving.