Seeing physics, or

physics is for prediction

Matthew Brand, Paul Cooper, Lawrence Birnbaum

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

We describe how knowledge of the physics of the scene itself is important to computer vision. High-level knowledge of scene physics can help programs see the world, and programs that see and understand this way are useful for planning plan scene interactions. We illustrate these points with two of our most recent knowledge-intensive vision systems. One uses knowledge of physics and function to understand noisy and ambiguous images of gear-train machines; i.e. to report what the machine does. The other uses physical knowledge to guide a robotic eye-hand system to pick up a mug of coffee by its handle.

Original languageEnglish (US)
Title of host publicationProc Workshop Phys Based Model Computer Vision
Editors Anon
PublisherIEEE
Pages144-150
Number of pages7
StatePublished - Jan 1 1995
EventProceedings of the Workshop on Physics-Based Modeling in Computer Vision - Cambridge, MA, USA
Duration: Jun 18 1995Jun 19 1995

Other

OtherProceedings of the Workshop on Physics-Based Modeling in Computer Vision
CityCambridge, MA, USA
Period6/18/956/19/95

Fingerprint

Physics
Coffee
End effectors
Computer vision
Gears
Robotics
Planning

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Brand, M., Cooper, P., & Birnbaum, L. (1995). Seeing physics, or: physics is for prediction. In Anon (Ed.), Proc Workshop Phys Based Model Computer Vision (pp. 144-150). IEEE.
Brand, Matthew ; Cooper, Paul ; Birnbaum, Lawrence. / Seeing physics, or : physics is for prediction. Proc Workshop Phys Based Model Computer Vision. editor / Anon. IEEE, 1995. pp. 144-150
@inproceedings{0ebb546f2b7f49f9a6cffc8d56dacf40,
title = "Seeing physics, or: physics is for prediction",
abstract = "We describe how knowledge of the physics of the scene itself is important to computer vision. High-level knowledge of scene physics can help programs see the world, and programs that see and understand this way are useful for planning plan scene interactions. We illustrate these points with two of our most recent knowledge-intensive vision systems. One uses knowledge of physics and function to understand noisy and ambiguous images of gear-train machines; i.e. to report what the machine does. The other uses physical knowledge to guide a robotic eye-hand system to pick up a mug of coffee by its handle.",
author = "Matthew Brand and Paul Cooper and Lawrence Birnbaum",
year = "1995",
month = "1",
day = "1",
language = "English (US)",
pages = "144--150",
editor = "Anon",
booktitle = "Proc Workshop Phys Based Model Computer Vision",
publisher = "IEEE",

}

Brand, M, Cooper, P & Birnbaum, L 1995, Seeing physics, or: physics is for prediction. in Anon (ed.), Proc Workshop Phys Based Model Computer Vision. IEEE, pp. 144-150, Proceedings of the Workshop on Physics-Based Modeling in Computer Vision, Cambridge, MA, USA, 6/18/95.

Seeing physics, or : physics is for prediction. / Brand, Matthew; Cooper, Paul; Birnbaum, Lawrence.

Proc Workshop Phys Based Model Computer Vision. ed. / Anon. IEEE, 1995. p. 144-150.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Seeing physics, or

T2 - physics is for prediction

AU - Brand, Matthew

AU - Cooper, Paul

AU - Birnbaum, Lawrence

PY - 1995/1/1

Y1 - 1995/1/1

N2 - We describe how knowledge of the physics of the scene itself is important to computer vision. High-level knowledge of scene physics can help programs see the world, and programs that see and understand this way are useful for planning plan scene interactions. We illustrate these points with two of our most recent knowledge-intensive vision systems. One uses knowledge of physics and function to understand noisy and ambiguous images of gear-train machines; i.e. to report what the machine does. The other uses physical knowledge to guide a robotic eye-hand system to pick up a mug of coffee by its handle.

AB - We describe how knowledge of the physics of the scene itself is important to computer vision. High-level knowledge of scene physics can help programs see the world, and programs that see and understand this way are useful for planning plan scene interactions. We illustrate these points with two of our most recent knowledge-intensive vision systems. One uses knowledge of physics and function to understand noisy and ambiguous images of gear-train machines; i.e. to report what the machine does. The other uses physical knowledge to guide a robotic eye-hand system to pick up a mug of coffee by its handle.

UR - http://www.scopus.com/inward/record.url?scp=0029238164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029238164&partnerID=8YFLogxK

M3 - Conference contribution

SP - 144

EP - 150

BT - Proc Workshop Phys Based Model Computer Vision

A2 - Anon, null

PB - IEEE

ER -

Brand M, Cooper P, Birnbaum L. Seeing physics, or: physics is for prediction. In Anon, editor, Proc Workshop Phys Based Model Computer Vision. IEEE. 1995. p. 144-150