Model-Based Three-Dimensional Interpretations of Two-Dimensional Images

Author

Brooks, Rodney A.

Author_Institution

Stanford Artificial Intelligence Laboratory, Stanford University, Stanford, CA 94305; Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139.

Issue

2

fYear

1983

fDate

3/1/1983 12:00:00 AM

Firstpage

140

Lastpage

150

Abstract

ACRONYM is a comprehensive domain independent model-based system for vision and manipulation related tasks. Many of its submodules and representations have been described elsewhere. Here the derivation and use of invariants for image feature prediction is described. Predictions of image features and their relations are made from three-dimensional geometric models. Instructions are generated which teli the interpretation algorithms how to make use of image feature measurements to derive three-dimensional size, structural, and spatial constraints on the original three-dimensional models. Some preliminary examples of ACRONYM´s interpretations of aerial images are shown.

Keywords

Artificial intelligence; Cameras; Computer vision; Contracts; Image recognition; Labeling; Machine vision; Predictive models; Size measurement; Solid modeling; Algebraic vision; computer vision; constraint systems; geometric models; model-based vision; spatial reasoning;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/TPAMI.1983.4767366

Filename

4767366