Seeing physics, or: physics is for prediction

Matthew Brand*, Paul Cooper, Lawrence Birnbaum

*Corresponding author for this work

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

5 Scopus citations


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
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


OtherProceedings of the Workshop on Physics-Based Modeling in Computer Vision
CityCambridge, MA, USA

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Seeing physics, or: physics is for prediction'. Together they form a unique fingerprint.

Cite this