Lecture Notes in Computer Science 1205

Verifica disponibilità: Testo completo (sito dell'editore)

Abstract

Multiscale feature extraction from the visual environment in an active vision system Y.Machrouh 1, J.-S.Liénard 1, P.Tarroux 1, 2 Abstract. This paper presents a visual architecture able to identify salient regions in a visual scene and to use them to focus on interesting locations. It is inspired by the ability of natural vision systems to perform a differential processing of spatial frequencies both in time and space and to focus their attention on a very local part of the visual scene. The present paper analyzes how this differential processing of spatial frequencies is able to provide an artificial system with the information required to perform an exploration of its visual world based on a center-surround distinction of the external scene. It shows how the salient locations can be gathered on the basis of their similarities to form a high level representation of the visual scene.

Salvato in:
Pubblicato in: Industrial Robot the international journal of robotics research and application, vol. 26, n. 6
Data di pubblicazione:01/08/1999
Editore:Emerald Publishing Limited
Tipo di documento:Articolo
Lingua:inglese
DOI: 10.1108/ir.1999.04926fae.001
ISSN:0143-991X, 1758-5791
Accesso aperto: Nessuna copia ad accesso aperto nota: per le risorse in abbonamento usare Verifica disponibilità.
Citazioni ricevute:38.662
Soggetti:
Visual Attention and Saliency Detection (Physical Sciences > Computer Science > Computer Vision and Pattern Recognition)
Advanced Vision and Imaging (Physical Sciences > Computer Science > Computer Vision and Pattern Recognition)
Visual perception and processing mechanisms (Life Sciences > Neuroscience > Cognitive Neuroscience)
active vision, multi-scale feature extraction, salient region detection, spatial frequency processing, visual attention, visual scene representation
Identificativi: OpenAlex W2561675875

Dati dell'indice centrale: OpenAlex (licenza CC0).

Riassunto:Multiscale feature extraction from the visual environment in an active vision system Y.Machrouh 1, J.-S.Liénard 1, P.Tarroux 1, 2 Abstract. This paper presents a visual architecture able to identify salient regions in a visual scene and to use them to focus on interesting locations. It is inspired by the ability of natural vision systems to perform a differential processing of spatial frequencies both in time and space and to focus their attention on a very local part of the visual scene. The present paper analyzes how this differential processing of spatial frequencies is able to provide an artificial system with the information required to perform an exploration of its visual world based on a center-surround distinction of the external scene. It shows how the salient locations can be gathered on the basis of their similarities to form a high level representation of the visual scene.
ISSN:0143-991X
1758-5791
DOI:10.1108/ir.1999.04926fae.001