Learning Temporal Context in Active Object Recognition Using Bayesian Analysis

Authors:
Affiliations:
Venue:
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Year:
2000

Citing 0
Cited 9

Information Theoretic Sensor Data Selection for Active Object Recognition and State Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence
On Optimal Camera Parameter Selection in Kalman Filter Based Object Tracking

Proceedings of the 24th DAGM Symposium on Pattern Recognition
Optimal Camera Parameter Selection for State Estimation with Applications in Object Recognition

Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
On Fusion of Multiple Views for Active Object Recognition

Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
Efficient Discriminant Viewpoint Selection for Active Bayesian Recognition

International Journal of Computer Vision
Using visual context and region semantics for high-level concept detection

IEEE Transactions on Multimedia - Special issue on integration of context and content
Predictive visual context in object detection

CONTEXT'03 Proceedings of the 4th international and interdisciplinary conference on Modeling and using context
Information selection and probabilistic 2D - 3D integration in mobile mapping

ICVS'03 Proceedings of the 3rd international conference on Computer vision systems
Context based object detection from video

ICVS'03 Proceedings of the 3rd international conference on Computer vision systems

Quantified Score

Hi-index	0.06

Visualization

Abstract

Active object recognition is a successful strategy to reduce uncertainty of single view recognition, by planning sequences of views, actively obtaining these views, and integrating multiple recognition results. Understanding recognition as a sequential decision problem challenges the visual agent to select discriminative information sources. The presented system emphasizes the importance of temporal context in disambiguating initial object hypotheses, provides the corresponding theory for Bayesian fusion processes, and demonstrates its performance being superior to alternative view planning schemes. Instance based learning proposed to estimate the control function enables then real-time processing with improved performance characteristics.