Determining Object Attitude from Extended Gaussian Images
Proceedings of the Ninth International Joint Conference on Artificial Intelligence. Perception. Pages 960-962.
Abstract
The Extended Gaussian Image (EGI) of an object records the variation of surface area with surface orientation, uniquely representing convex objects. The inversion problern for polyhedra (from an EGI to a description in terms of vertices and faces) has been solved, by an iterative algorithm [Little, 1983[. The algorithm depends upon the mixed volume, a geometric construction linking the areas and positions of the faces of an object. A robust method for determining object attitude from the EGI is developed here, using this construction. Experiments show the method's insensitivity to small attitude differences.
@inproceedings{ijcai1985p192,
title = {Determining Object Attitude from Extended Gaussian Images},
author = {Little, James J.},
booktitle = {Proceedings of the Ninth International Joint Conference on
Artificial Intelligence, {IJCAI-85}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Aravind Joshi},
pages = {960--962},
year = {1985},
note = {Perception},
url = {https://ijcai.org/proceedings/1985/192},
}
TY - CPAPER TI - Determining Object Attitude from Extended Gaussian Images AU - Little, James J. T2 - Proceedings of the Ninth International Joint Conference on Artificial Intelligence, IJCAI-85 PB - International Joint Conferences on Artificial Intelligence PY - 1985 SP - 960 EP - 962 UR - https://ijcai.org/proceedings/1985/192 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
