Autonomous recognition: driven by ambiguity

Recognition ambiguity, due to noisy measurements and uncertain object models, can be quantified and actively used by an autonomous agent to efficiently gather new data and improve its information about the environment. In this work an information-based utility measure is used to derive from a learne...

Full description

Saved in:
Bibliographic Details
Published inProceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 701 - 707
Main Authors Callari, F.G., Ferrie, F.P.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1996
Subjects
Active shape model
Autonomous agents
Measurement uncertainty
Noise shaping
Object recognition
Predictive models
Shape measurement
Surface fitting
Working environment noise
Online AccessGet full text

Cover

More Information
Summary:Recognition ambiguity, due to noisy measurements and uncertain object models, can be quantified and actively used by an autonomous agent to efficiently gather new data and improve its information about the environment. In this work an information-based utility measure is used to derive from a learned classification of shape models an efficient data collection strategy, specifically aimed at increasing classification confidence when recognizing uncertain shapes. Promising simulation results are presented and discussed.
ISBN:9780818672590
0818672595
ISSN:1063-6919
DOI:10.1109/CVPR.1996.517149