Object Recognition in Multisensory Scene Analysis
by Nitzan, David
Technical Note 83
Institution: AI Center, SRI International
Address: 333 Ravenswood Ave, Menlo Park, CA 94025
Note: SRI Project 1530. The research reported herein was supported at SRI by the Advanced Research Projects Agency of the Department of Defense, monitored by the U.S. Army Research Office, Durham, North Carolina, under Contract DAHC04-72-C-0008.
A perception strategy for recognizing an object on the basis of color and range data is illustrated by finding a desk in an office scene. Geometrical models of objects (such as a desk, a chair, and a glass) are described by transformation (using scaling, rotation, and translation matrices) of primitive surfaces (unit cube, sphere, and cylinder). An image-bounding window for the acquisition element of an object is based on range data. Image bounding windows are derived for four cases in which single and multiple acquisition elements are oriented vertically and horizontally.
|Nitzan, David||Senior Principal Scientist|