Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Incremental focus of attention for robust vision-based tracking
Autore:
Toyama, K; Hager, GD;
Indirizzi:
Microsoft Corp, Res, Redmond, WA 98052 USA Microsoft Corp Redmond WA USA 98052 soft Corp, Res, Redmond, WA 98052 USA Johns Hopkins Univ, Dept Comp Sci, Baltimore, MD 21218 USA Johns Hopkins Univ Baltimore MD USA 21218 mp Sci, Baltimore, MD 21218 USA
Titolo Testata:
INTERNATIONAL JOURNAL OF COMPUTER VISION
fascicolo: 1, volume: 35, anno: 1999,
pagine: 45 - 63
SICI:
0920-5691(199911)35:1<45:IFOAFR>2.0.ZU;2-6
Fonte:
ISI
Lingua:
ENG
Soggetto:
MOTION TRACKING; OBJECTS; PURSUIT; MODELS; SEARCH; SYSTEM;
Keywords:
visual tracking; real-time tracking; robust tracking; face tracking;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
51
Recensione:
Indirizzi per estratti:
Indirizzo: Toyama, K Microsoft Corp, Res, 1 Microsoft Way, Redmond, WA 98052 USA Microsoft Corp 1 Microsoft Way Redmond WA USA 98052 WA 98052 USA
Citazione:
K. Toyama e G.D. Hager, "Incremental focus of attention for robust vision-based tracking", INT J COM V, 35(1), 1999, pp. 45-63

Abstract

We present the Incremental Focus of Attention (IFA) architecture for robust, adaptive, real-time motion tracking. IFA systems combine several visual search and vision-based tracking algorithms into a layered hierarchy. The architecture controls the transitions between layers and executes algorithmsappropriate to the visual environment at hand: When conditions are good, tracking is accurate and precise; as conditions deteriorate, more robust, yet less accurate algorithms take over; when tracking is lost altogether, layers cooperate to perform a rapid search for the target and continue tracking. Implemented IFA systems are extremely robust to most common types of temporary visual disturbances. They resist minor visual perturbances and recoverquickly after full occlusions, illumination changes, major distractions, and target disappearances. Analysis of the algorithm's recovery times are supported by simulation results and experiments on real data. In particular, examples show that recovery times after lost tracking depend primarily on the number of objects visually similar to the target in the field of view.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 05/04/20 alle ore 06:45:16