A Viewpoint Planning Strategy for Determining True Angles on Polyhedral Objects by Camera Alignment
IEEE Transactions on Pattern Analysis and Machine Intelligence
CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Information Theoretic Sensor Data Selection for Active Object Recognition and State Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Active Object Recognition: Looking for Differences
International Journal of Computer Vision - Special issue: Research at McGill University
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Neuro-Dynamic Programming
Handling Uncertainty in 3D Object Recognition Using Bayesian Networks
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
On Fusion of Multiple Views for Active Object Recognition
Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
Alignment by maximization of mutual information
Alignment by maximization of mutual information
Transinformation for Active Object Recognition
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Conditional Feature Sensitivity: A Unifying View on Active Recognition and Feature Selection
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Handling camera movement constraints in reinforcement learning based active object recognition
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Hi-index | 0.00 |
In the past decades, most object recognition systems were based on passive approaches. But in the last few years a lot of research was done in the field of active object recognition. In this context, there are several unique problems to be solved, such as the fusion of views and the selection of an optimal next viewpoint. In this paper we present an approach to solve the problem of choosing optimal views (viewpoint selection) and the fusion of these for an optimal 3D object recognition (viewpoint fusion). We formally define the selection of additional views as an optimization problem and we show how to use reinforcement learning for viewpoint training and selection in continuous state spaces without user interaction. In this context we focus on the modeling of the reinforcement learning reward. We also present an approach for the fusion of multiple views based on density propagation, and discuss the advantages and disadvantages of two approaches for the practical evaluation of these densities, namely Parzen estimation and density trees.