direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments


All Publications

A computer vision system for rapid search inspired by surface-based attention mechanisms from human perception
Citation key Mohr2014b
Author Mohr, J. and Park, J.-H. and Obermayer, K.
Pages 182 - 193
Year 2014
ISSN 0893-6080
DOI doi:10.1016/j.neunet.2014.08.010
Journal Neural Networks
Volume 60
Abstract Humans are highly efficient at visual search tasks by focusing selective attention on a small but relevant region of a visual scene. Recent results from biological vision suggest that surfaces of distinct physical objects form the basic units of this attentional process. The aim of this paper is to demonstrate how such surface-based attention mechanisms can speed up a computer vision system for visual search. The system uses fast perceptual grouping of depth cues to represent the visual world at the level of surfaces. This representation is stored in short-term memory and updated over time. A top-down guided attention mechanism sequentially selects one of the surfaces for detailed inspection by a recognition module. We show that the proposed attention framework requires little computational overhead (about 11 ms), but enables the system to operate in real-time and leads to a substantial increase in search efficiency.
Bibtex Type of Publication Selected:publications selected:main
Link to publication Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions