Motion recovery from image sequences using only first order optical flow information

Abstract

The primary goal in motion vision is to extract information about the motion and shape of an object in a scene that is encoded in the optic flow. While many solutions to this problem, both iterative and in closed form, have been proposed, practitioners still view the problem as unsolved, since these methods, for the most part, cannot deal with some important aspects of realistic scenes. Among these are comlex unsegmented scenes, nonsmooth objects, and general motion of the camera. In addition, the performance of many methods degrades ungracefully as the quality of the data deteriorates.Here, we will derive a closed-form solution for motion estimation based on the first-order information from two image regions with distinct flow "structures." A unique solution is guaranteed when these corespond to two surface patches with different normal vectors. Given an image sequence, we will show how the image may be segmented into regions with the necessary properties, optical flow is computed for these regions, and motion parameters are calculated. The method can be applied to arbitrary scenes and any camera motion. We will show theoretically why the method is more robust than other proposed techniques that require the knowledge of the full flow or information up to the second-order terms of it. Experimental results are presented to support the theoretical derivations.

Visual Servoing on Non-Planar Objects From Active Vision

“…These parameters can be then computed by a 2D motion estimation method. Finally, an expression of the structure of the object can be extracted [17]. Such an approach has also been used in our previous work [1] to deal with planar objects.…”

“…This point is chosen so that its projection p described by x p = (x p , y p , 1) lies in the center of the ROI. The position of this point being used in a control scheme, we will not assume as usually that it lies near the principal point as it is in lots of papers (see [1], [13], [17] for example), since the goal of the task is precisely to move it to this particular point. Let us also consider a point M in a neighborhood of P .…”

“…Note that v * = 0 is also the best choice for the condition number since it leads to an optimal value ν = 1 (see (17)). In addition, since the other translations are not null, we are sure that the matrix C C will be never singular (see the remark at the end of Section III).…”

Model-free visual servoing on complex images based on 3D reconstruction

“…On the other hand, these parameters can be obtained by a method of computation of the 2D motion. Finally, an expression of the structure of the object can be extracted [11] (here too, by considering a second point, the case where T c is unknown is treated). These approaches are known as indirect approaches since they require an intermediate computation of the 2D motion.…”

Visual servoing based on dynamic vision

“…On the other hand, these parameters can be obtained by a method of computation of the 2D motion, like in [4] for example. Finally, an expression of the structure of the object can be extracted [11] (here too, by considering a second point, the case where T c is unknown is treated). These approaches are known as indirect approaches since they require an intermediate computation of the 2D motion.…”