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

Authors:
Rodney A. Brooks
Affiliations:
Stanford Artificial Intelligence Laboratory, Stanford University, Stanford, CA 94305/ Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1983

Citing 0
Cited 7

Efficient search and verification for function based classification from real range images

Computer Vision and Image Understanding
Coordinating interactive vision behaviors for cognitive assistance

Computer Vision and Image Understanding
Learning function-based object classification from 3D imagery

Computer Vision and Image Understanding
Knowledge modeling for the image understanding task as a design task

Expert Systems with Applications: An International Journal
Learning hierarchical shape models from examples

EMMCVPR'05 Proceedings of the 5th international conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Discovering hierarchical object models from captioned images

Computer Vision and Image Understanding
SeTES: A self-teaching expert system for the analysis, design, and prediction of gas production from unconventional gas resources

Computers & Geosciences

Quantified Score

Hi-index	0.15

Visualization

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.