Optical flow cannot be computed locally, since only one independent measurement is available from the image sequence at a point, while the flow velocity has two components. A second constraint is needed. A method for finding the optical flow pattern is presented which assumes that the apparent velocity of the brightness pattern varies smoothly almost everywhere in the image. An iterative implementation is shown which successfully computes the optical flow for a number of synthetic image sequences. The algorithm is robust in that it can handle image sequences that are quantized rather coarsely in space and time. It is also insensitive to quantization of brightness levels and additive noise. Examples are included where the assumption of smoothness is violated at singular points or along lines in the image.

Abstract — Interactive perception augments the process of perception with physical interactions. By adding interactions into the perceptual process, manipulating the environment becomes part of the effort to learn task-relevant information, leading to more reliable task execution. Interactions include obstruction removal, object repositioning, and object manipulation. In this paper, we show how to extract kinematic properties from novel objects. Many objects in human environments, such as doors, drawers, and hand tools, contain inherent kinematic degrees of freedom. Knowledge of these degrees of freedom is required to use the objects in their intended manner. We demonstrate how a simple algorithm enables the construction of kinematic models for such objects, resulting in knowledge necessary for the correct operation of those objects. The simplicity of the framework and its effectiveness, demonstrated in our experimental results, indicate that interactive perception is a promising perceptual paradigm for autonomous mobile manipulation. I.