Paper Info
Title
A novel robotic visual perception method using object-based attention
Abstract
The object-based attention theory has shown that perception processes only select relevant objects of the world which are then represented for action. Thus this paper proposes a novel computational method of robotic visual perception based on the object-based attention mechanism. It involves three modules: pre-attentive processing, attentional selection and perception learning. Visual scene is firstly segmented into discrete proto-objects pre-attentively and the gist of scene is identified as well. The attentional selection module simulates two types of modulation: bottom-up competition and top-down biasing. Bottom-up competition is evaluated by center-surround contrast; Given the task or scene category, the task-relevant object and a task-relevant feature of it is determined based on perception control rules and then used to evaluate top-down biasing. Following attentional selection, the attended object is put into perception learning module to update the existing object representations and perception control rules in long-term memory. An object representation consisting of between-object and within-object codings is built using probabilistic neural networks. An association memory using Bayesian network is also built to model perception control rules. Two types of robotic tasks are used to test this proposed model: task-specific object detection and landmark detection.
Year
DOI
Venue
2009
10.1109/ROBIO.2009.5420944
ROBIO
Keywords
Field
DocType
belief networks,model perception control rule,image representation,center-surround contrast,visual scene,relevant object,robotic visual perception,pre-attentive processing,learning (artificial intelligence),perception control rules,image segmentation,attentional selection,existing object representation,top-down biasing,bottom-up competition,landmark detection,perception control rule,perception learning,object detection,task-relevant object,probabilistic neural networks,visual perception,novel robotic visual perception,content-addressable storage,object-based attention,object representation,bayesian network,task-specific object detection,association memory,neural nets,robot vision,robotic visual perception method,bottom up,navigation,long term memory,feature extraction,associative memory,encoding,top down,learning artificial intelligence,probabilistic neural network,indexes,computational modeling
Object detection,Computer vision,Object-based attention,Computer science,Feature extraction,Bayesian network,Artificial intelligence,Artificial neural network,Perception,Visual perception,Encoding (memory)
Conference
ISBN
Citations 
PageRank 
978-1-4244-4775-6
2
0.35
References 
Authors
14
3
Name
Order
Citations
PageRank
Yuanlong Yu112412.65
George K. I. Mann242539.50
Raymond G. Gosine325224.37