Active object recognition integrating attention and viewpoint control
Computer Vision and Image Understanding
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Distortion Invariant Object Recognition in the Dynamic Link Architecture
IEEE Transactions on Computers
Occlusions as a Guide for Planning the Next View
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Selection of Reference Views for Image-Based Scene Representations
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
Autonomous recognition: driven by ambiguity
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Tracking and Learning Graphs and Pose on Image Sequences of Faces
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
Gaze Selection for Visual Search
Gaze Selection for Visual Search
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Multimedia Tools and Applications
Hi-index | 0.00 |
We propose an active vision system for the acquisition of internal object representations. The core of the approach is an agent which learns goal-directed action patterns depending on the perceived environment via reinforcement learning. The user supervision is restricted to the definition of this goal in the form of a reward function. We demonstrate this approach by means of learning a strategy to scan an object. The agent moves a virtual camera around an object and is able to adapt her scan path dynamically to different conditions of the environment such as different objects and different goals of the data acquisition. The purpose of the acquisition which we consider here is the view-based reconstruction of non-acquired views. The scan pattern obtained after the learned path has stabilised allows a better reconstruction of unfamiliar views than random scan paths.