Format

Send to

Choose Destination
Neural Netw. 2014 Dec;60:182-93. doi: 10.1016/j.neunet.2014.08.010. Epub 2014 Sep 4.

A computer vision system for rapid search inspired by surface-based attention mechanisms from human perception.

Author information

1
Department for Electrical Engineering and Computer Science, Technische Universität Berlin, Germany; MAR 5-6, Marchstr. 23, D-10587 Berlin, Germany. Electronic address: johannes.mohr@tu-berlin.de.
2
Department for Electrical Engineering and Computer Science, Technische Universität Berlin, Germany; MAR 5-6, Marchstr. 23, D-10587 Berlin, Germany.

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.

KEYWORDS:

Attention; Biological vision; Computer vision; Object recognition; Search

PMID:
25241349
DOI:
10.1016/j.neunet.2014.08.010
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center