A direct interpretation of dynamic images and camera motion for vision guided robotics

Abstract

A general scheme t o represent the relation between dyn a m i c images and camera m o t i o n i s presented. T h e n , its application t o visual servoing i s proposed. For a specific object, the possible combination of the camera pose and the obtained image should be constrained o n a lower dimensional hyper surface within the product space of whole combination of image data and camera position. T h e visual servoing, f o r example, is interpreted as t o find a path o n this surface leading t o a gzven goal zmage. O u r approach zs t o analyze the properties of this surface, and utilize its diferential or tangential property f o r visual servoing. For this approach, the dimension of the image informatzon becomes key problem. We propose t o use the principal component analysis and t o represent images with a composition of small n u m b e r of "eigenimages " b y uszng K-L (Karhunen-Lohe) expansion. I n this paper, we describe, first, that a normal vect o r of this surface i s related t o the so-called Interaction Matrix, and confirm the feasibility of our basic idea f o r vzsual servozng with a prelzminary experiment. T h e n , we present a dynamical estimatzon of the normal vectors t o move robot a r m mounting a camera t o a goal position where a given goal image will be obtained. We also consider the construction of the eigen space (the eigenimage space) t o represent images eficiently and t o speedu p convergence in the control. Experimental results of visual servoing with proposed method show the feasibility and applicability of o u r newly proposed approach.

Point-based and region-based image moments for visual servoing of planar objects

“…Furthermore, the design of x n and y n allows us to completely partition the three selected features to the three translational dofs. This decoupling property was expected from (8). We also obtain the same dynamics for the three features (note the diagonal block equal to −I 3 in (20)).…”

“…Similarly, for the same configurations, we can check from (12) that the invariants to scale given by (8) are invariant to translational motion along the optical axis (I svz = 0 if A = B = 0). Finally, after quite tedious computations, we can also check that the invariants c i given in (9) are such that c iωz = 0, and, if A = B = 0, such that c ivx = c ivy = c ivz = 0.…”

“…They have also the basic requirement of feature matching between initial and desired images. More recent works have tried to surmount the problems mentioned above, by using for example an eigenspace representation [8], the polar signature of an object contour [5], or, as in this paper, image moments [4]. Image moments are particularly interesting.…”

Colorimetry-based visual servoing

“…The main issue of these works C. Collewet was to exhibit the analytical form of the interaction matrix related to the luminance. This was therefore a very different approach than previous works based on luminance [4]- [7] (see [1] for more details).…”

Application of moment invariants to visual servoing

“…These methods have also the basic requirement of feature matching between initial and desired images, which is generally not easy to obtain. Other methods try to surmount the problems mentioned above, by using for example the Eigen space method [7] or the polar signature of an object contour [5]. Recently, a new method was proposed using image moments [4].…”