From images to bodies: modelling and exploiting spatial occlusion and motion parallax

Authors:
David Randell;Mark Witkowski;Murray Shanahan
Affiliations:
Dept. of Electrical and Electronic Engineering, Imperial College of Science, Technology and Medicine, London, United Kingdom;Dept. of Electrical and Electronic Engineering, Imperial College of Science, Technology and Medicine, London, United Kingdom;Dept. of Electrical and Electronic Engineering, Imperial College of Science, Technology and Medicine, London, United Kingdom
Venue:
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
Year:
2001

Citing 5
Cited 12

Qualitative navigation for mobile robots

Artificial Intelligence
Visibility, occlusion, and the aspect graph

International Journal of Computer Vision
Occlusions and binocular stereo

International Journal of Computer Vision
Visual space geometry derived from occlusion axioms

Journal of Mathematical Imaging and Vision - Special issue on topology and geometry in computer vision
Qualitative Spatial Representation and Reasoning Techniques

KI '97 Proceedings of the 21st Annual German Conference on Artificial Intelligence: Advances in Artificial Intelligence

Foundations for a Formalism of Nearness

AI '02 Proceedings of the 15th Australian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence
Relation Algebras and their Application in Temporal and Spatial Reasoning

Artificial Intelligence Review
Using Occlusion Calculi to Interpret Digital Images

Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy
Reasoning about Dynamic Depth Profiles

Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
Qualitative robot localisation using information from cast shadows

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Multi-dimensional observer-centred qualitative spatial-temporal reasoning

RSFDGrC'03 Proceedings of the 9th international conference on Rough sets, fuzzy sets, data mining, and granular computing
Towards an architecture for cognitive vision using qualitative spatio-temporal representations and abduction

Spatial cognition III
Knowledge-based adaptive thresholding from shadows

Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
Spatial proximity is more than just a distance measure

International Journal of Human-Computer Studies
OCS-14: you can get occluded in fourteen ways

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Reasoning about shadows in a mobile robot environment

Applied Intelligence
MOWL: An ontology representation language for web-based multimedia applications

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes the Region Occlusion Calculus (ROC-20), that can be used to model spatial occlusion and the effects of motion parallax of arbitrary shaped objects. ROC-20 assumes the region based ontology of RCC-8 and extends Galton's Lines of Sight Calculus by allowing concave shaped objects into the modelled domain. This extension is used to describe the effects of mutually occluding bodies. The inclusion of van Benthem's axiomatisation of comparative nearness facilitates reasoning about relative distances between occluding bodies. Further, an envisionment table is developed to model sequences of occlusion events enabling reasoning about objects and their images formed in a changing visual field.