Online multimodal video registration based on shape matching

The registration of video sequences captured using different types of sensors often relies on dense feature matching methods, which are very costly. In this paper, we study the problem of “almost planar” scene registration (i.e. where the planar ground assumption is almost respected) in multimodal imagery using target shape information. We introduce a new strategy for robustly aligning scene elements based on the random sampling of shape contour correspondences and on the continuous update of our transformation model's parameters. We evaluate our solution on a public dataset and show its superiority by comparing it to a recently published method that targets the same problem. To make comparisons between such methods easier in the future, we provide our evaluation tools along with a full implementation of our solution online.