Computer Vision and Sensor-Based Robots. Immediate eBook download after purchase; Hardcover $99.00.

• • • Part of the book series (LNCS, volume 3852) Abstract In this paper we consider some questions related to the orientation of shapes. We introduce as a new shape feature shape orientability, i.e. The degree to which a shape has distinct (but not necessarily unique) orientation. A new method is described for measuring shape orientability, and has several desirable properties.

In particular, unlike the standard moment based measure of elongation, it is able to differentiate between the varying levels of orientability of n-fold rotationally symmetric shapes.

• • Abstract At the National Bureau of Standards, a method is being developed for transferring sufficient information directly from the solid modeling system to the robot vision system to enable the robot to recognize a part. The information is encoded in the form of a graph, called an aspect graph, together with functions associated to each vertex of the graph.

Aspect graphs were developed by J. Koenderink of the State University of Utrecht in the Netherlands, as part of an attempt to understand how shape information is represented by the human vision system. Currently the method is being developed for parts designed on the PADL-2 system. In particular, it does not yet handle contoured surfaces.

Logitrace Serial Number. Extensions to deal with contoured surfaces appear to be feasible and are mentioned briefly.

Download preview PDF. Horn, B.K.P.: Robot Vision. MIT Press, Cambridge (1986) Google Scholar. EBook Packages Computer Science; About this book. Horn: Robot Vision. (1999) Control of Robot Arm Approach by Fuzzy Pattern Comparison Technique. In: Reusch B. EBook Packages Springer Book.