Technical Note: \cal Q-Learning
Machine Learning
Asynchronous Stochastic Approximation and Q-Learning
Machine Learning
Driving saccade to pursuit using image motion
International Journal of Computer Vision
Incremental multi-step Q-learning
Machine Learning - Special issue on reinforcement learning
A Scalable Image-Based Multi-Camera Visual Surveillance System
AVSS '03 Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance
A master-slave system to acquire biometric imagery of humans at distance
IWVS '03 First ACM SIGMM international workshop on Video surveillance
Scheduling an active camera to observe people
Proceedings of the ACM 2nd international workshop on Video surveillance & sensor networks
Acquiring Multi-Scale Images by Pan-Tilt-Zoom Control and Automatic Multi-Camera Calibration
WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
Acquisition of high-resolution images through on-line saccade sequence planning
Proceedings of the third ACM international workshop on Video surveillance & sensor networks
Improving evidential quality of surveillance imagery through active face tracking
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Hi-index | 0.00 |
In this paper we report on techniques for automatically learning foveal sensing strategies for an active pan-tilt-zoom camera. The approach uses reinforcement learning to discover foveal actions maximizing the performance of visual detectors, that are in turn assumed to be highly correlated with the task at hand. In our case,the main goal is to recognize people, hence a frontal face detection module is employed. The system uses reinforcement learning to learn if when and how to foveate on a subject, basedonits previous experience in terms or successful actions in similar situations. An action is successful if it leads to a correct face detection in the high resolution images obtained when the subject is zoomed in. In contrast with existing methods,the proposed approach obviates the need for camera calibration and camera performance modeling. Also, the method does not rely on active tracking of targets. Experimental results show how the system can be deployed in unconstrained surveillance environments, and is capable of learning foveation strategies without requiring extensive a priori information or environmental models. Results also illustrate how the system effectively learns a strategy that allows the camera to foveate only in situations where successful detection is highly likely.