Combining Sources of Information in Vision I. Computing Shape from Shading and Motion
Proceedings of the Tenth International Joint Conference on Artificial Intelligence. Perception. Pages 738-740.
Abstract
Most of the basic prol;>lems in computer vision, as formulated, admit infinitely many solutions. But vision is full of redundancy and there are several sources of information that if combined can provide unique solutions for a problem. Furthermore, even if a problem as formulated has a unique solution, in most cases it is unstable. Combining information sources in this case leads to robust solutions. In this paper, we combine shading and motion to uniquely recover the light source direction and the shape of the object in view, and we describe how one could combine information sources present in the image in order to achieve uniqueness and robustness of low level visual computations.
@inproceedings{ijcai1987p148,
title = {Combining Sources of Information in Vision I. Computing Shape from Shading and Motion},
author = {Aloimonos, Yiannis},
booktitle = {Proceedings of the Tenth International Joint Conference on
Artificial Intelligence, {IJCAI-87}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {John McDermott},
pages = {738--740},
year = {1987},
note = {Perception},
url = {https://ijcai.org/proceedings/1987/148},
}
TY - CPAPER TI - Combining Sources of Information in Vision I. Computing Shape from Shading and Motion AU - Aloimonos, Yiannis T2 - Proceedings of the Tenth International Joint Conference on Artificial Intelligence, IJCAI-87 PB - International Joint Conferences on Artificial Intelligence PY - 1987 SP - 738 EP - 740 UR - https://ijcai.org/proceedings/1987/148 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
