Attention control for robot vision

Focus of attention mechanisms for robot vision are discussed. A new method for neglecting low level filter responses from already modelled structures is presented. The method is based on a filtering technique termed normalized convolution. In one experiment, the robot is continuously moving its arm...

Full description

Saved in:
Bibliographic Details
Main Authors: Westin, C.-F., Westelius, C.-J., Knutsson, H., Granlund, G.
Format: Conference Proceeding
Language:English
Subjects:
Computational modeling
Context modeling
Feature extraction
Filtering
Focusing
Laboratories
Layout
Robot control
Robot sensing systems
Robot vision systems
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Focus of attention mechanisms for robot vision are discussed. A new method for neglecting low level filter responses from already modelled structures is presented. The method is based on a filtering technique termed normalized convolution. In one experiment, the robot is continuously moving its arm in the scene while tracking other objects. It is shown how the arm can be made "invisible" so that only the moving object of interest is detected. This makes tracking of objects much simpler. In another experiment, the attention of the system is shifted between objects by simply cancelling the mask of the object to be attended to. With this strategy the low level processes do not need to know the difference between a new object entering the scene and a mask being cancelled, and thus a complex communication structure between high and low levels is avoided.
ISSN:1063-6919
DOI:10.1109/CVPR.1996.517153