CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
On Fusion of Multiple Views for Active Object Recognition
Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
A Resource Based Framework for Planning and Replanning
IAT '03 Proceedings of the IEEE/WIC International Conference on Intelligent Agent Technology
Risk-sensitive reinforcement learning applied to control under constraints
Journal of Artificial Intelligence Research
Planning executing sensing and replanning for information gathering
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Aspects of optimal viewpoint selection and viewpoint fusion
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking
IEEE Transactions on Signal Processing
Hi-index | 0.00 |
In real world scenes, objects to be classified are usually not visible from every direction, since they are almost always positioned on some kind of opaque plane. When moving a camera selectively around those objects for classifying them in an active manner, a hemisphere is fully sufficient for positioning meaningful camera viewpoints. Based on this constraint, this paper addresses the problem of handling planned camera actions which nevertheless lead to viewpoints beyond the plane of that hemisphere. Those actions arise from the uncertainty in the current vertical camera position combined with the view planning method's request of a relative action. The latter is based on an optimized and interpolating query of a knowledge base which is built up in a Reinforcement Learning training phase beforehand. This work discusses the influence of three different, intuitive and optimized, methods for handling invalid action suggestions generated by Reinforcement Learning. Influence is measured by the difference in classification results after each step of merging the image data information with active view planning.