Representation, Modeling and Recognition of Outdoor Scenes
Abstract
The primary goal of this project was to advance the state-of-the-art in scene interpretation for autonomous systems that operate in natural terrain. In particular, techniques are being developed for representing knowledge about complex cultural and natural environments so that a computer vision system can successfully plan, navigate, recognize and manipulate objects and answer questions or make decisions relevant to this knowledge. The initial results are centered on the development of representations and associated methods for rapidly modeling natural terrain (from image sequences) at a level of organization higher than that of the conventional dense array of depths. This work will provide the essential advance need to turn raw geometric measurements into timely information usable by robotic navigation and planning systems. Work is also progressing on two additional problems: modeling compact 3-D objects from their projected 2-D contours, and the problem of recognizing important classes of natural and man-made objects - especially roads, trees and rocks. Machine vision, Automated scene analysis, Interactive scene analysis, Object recognition, Terrain modeling, Automated cartography, Feature extraction delineation partitioning, Geometric modeling.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 01, 1993
- Accession Number
- ADA283257
Entities
People
- Martin A. Fischler
- Robert C. Bolles
Organizations
- SRI International