Thumbnail
Access Restriction
Open

Author Gribble, William S.
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Moving-object Recognition ♦ Realtime Vision Task ♦ Lower-level Representation ♦ High-level Perceptual Processing ♦ Direct Observation ♦ Live Video Stream ♦ Human Vision ♦ Limited Computational Power ♦ Higherlevel Processing ♦ Task-dependent Description ♦ Closed-loop Task ♦ Model-based Object Recognition Operate ♦ Frame Rate ♦ Visual Subsystem ♦ Visual Routine Theory ♦ Relevant Image Feature ♦ Plentiful Workstation ♦ Slow Visual Search ♦ Reactive Feature ♦ Real-time Feedback ♦ Distributed Real-time Vision ♦ Fast-changing World ♦ Domaininformed Selection
Description Attention focusing mechanisms and domaininformed selection of representations can make realtime vision tasks work with limited computational power. This paper describes ongoing work in distributed real-time vision which aims to use cheap and plentiful workstations and PCs rather than specialpurpose hardware. I discuss a system called Argus which is inspired by the visual routines theory of human vision. In Argus, reactive feature tracking agents maintain minimal, task-dependent descriptions of relevant image features by direct observation of the live video stream. Routines for model-based object recognition operate on these descriptions. Higherlevel processing is independent of the maintenance of lower-level representations. This allows the visual subsystem to provide real-time feedback for closed-loop tasks even when high-level perceptual processing is slow compared to video frame rates. Experiments in moving-object recognition are described which demonstrate the strength of this app...
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 1995-01-01
Publisher Institution In Proceedings of the 1995 IEEE Symposium on Computer Vision (ISCV-95