How Visual Attention and Suppression Facilitate Object Recognition?

doi:10.1007/978-3-319-11179-7_58

Paper

How Visual Attention and Suppression Facilitate Object Recognition?

Published Sep 15, 2014 · Frederik Beuth, Amir H. Jamalian, F. Hamker

UNKNOWN SJR score

2

Citations

0

Influential Citations

Full text Semantic Scholar

Abstract

Visual attention can support object recognition by selecting the relevant target information in the huge amount of sensory data, espe- cially important in scenes composed of multiple objects. Here we demon- strate how attention in a biologically plausible and neuro-computational model of visual perception facilitates object recognition in a robotic real world scenario. We will point out that it is not only important to select the target information, but rather to explicitly suppress the distracting sensory data. We found that suppressing the features of each distractor is not sufficient to achieve robust recognition. Instead, we also have to suppress the location of each distractor. To demonstrate the effect of this spatial suppression, we disable this property and show that the recogni- tion accuracy drops. By this, we show the interplay between attention and suppression in a real world object recognition task.

Study Snapshot

Key takeawayVisual attention and spatial suppression play a crucial role in object recognition, with attention selecting relevant target information and suppressing distracting sensory data for robust recognition.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Sign up to use Study Snapshot

Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.

Create an account

Paper

How Visual Attention and Suppression Facilitate Object Recognition?

Sign up to use Study Snapshot

References

A Hierarchical System for a Distributed Representation of the Peripersonal Space of a Humanoid Robot

This research demonstrates a humanoid robot with an integrated working representation of its peripersonal space, enabling complex tasks like recognizing, gazing, and reaching target objects in an unknown environment.

Learning Invariance from Natural Images Inspired by Observations in the Primary Visual Cortex

Hebbian learning rules based on calcium dynamics and homeostatic regulations of single neurons can effectively learn complex cells invariant to phase and position in a simple model of the primary visual cortex.

Where to Look Next? Combining Static and Dynamic Proto-objects in a TVA-based Model of Visual Attention

This novel computational model combines static and dynamic features, motion features, and task-dependent priority control to effectively determine where to look next in complex visual tasks.

An Active Vision System for Detecting, Fixating and Manipulating Objects in the Real World

This paper presents a stereo-based vision system framework for robotic object grasping in domestic environments, focusing on top-down, bottom-up, and foveated attention.

The Normalization Model of Attention

The Normalization Model of Attention explains the variety of effects on visual cortex neurons, highlighting the importance of stimulus conditions and the subject's attentional strategy in experimental results.

Modeling attention to salient proto-objects

Selective visual attention can access and validate proto-objects in complex scenes, enabling a model of object recognition in the brain to expand from recognizing individual objects to sequentially recognizing all objects in a complex scene.

The emergence of attention by population-based inference and its role in distributed processing and cognitive control of vision

High-level cognitive processes guide vision by modulating stimulus signals, enabling flexible vision systems for various tasks, such as object detection in natural scenes.

Robust Object Detection at Regions of Interest with an Application in Ball Recognition

VOCUS and robust object detection methods create a reliable system for ball recognition in the RoboCup context, eliminating false detections and adapting to different scenarios.

The reentry hypothesis: the putative interaction of the frontal eye field, ventrolateral prefrontal cortex, and areas V4, IT for attention and eye movement.

Attention is an emergent phenomenon involving multiple brain areas, with reentry and competitive interactions playing a key role in perception and eye movement guidance.

Citations

Extended Design Science Research Methodology for parallel vision system

The Design Science Research Methodology (DSRM) can effectively design efficient parallel vision systems for autonomous robots.

Biologically-Inspired Models for Attentive Robot Vision: A Review

Biologically-inspired models of visual attention can improve robot vision by focusing on specific aspects, potentially speeding up processing and providing additional guidance for future research.