Sciweavers

244 search results - page 18 / 49
» Incremental Learning for Visual Tracking
Sort
View
ICRA
2010
IEEE
220views Robotics» more  ICRA 2010»
13 years 7 months ago
General object tracking with a component-based target descriptor
In this paper, we present a component-based visual object tracker for mobile platforms. The core of the technique is a component-based descriptor that captures the structure and ap...
Simone Frintrop

Publication
485views
12 years 10 months ago
Incremental Activity Modelling in Multiple Disjoint Cameras
Activity modelling and unusual event detection in a network of cameras is challenging particularly when the camera views are not overlapped. We show that it is possible to detect u...
Chen Change Loy, Tao Xiang, Shaogang Gong
JAIR
2007
124views more  JAIR 2007»
13 years 10 months ago
Closed-Loop Learning of Visual Control Policies
In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-...
Sébastien Jodogne, Justus H. Piater
ECML
2006
Springer
14 years 1 months ago
Task-Driven Discretization of the Joint Space of Visual Percepts and Continuous Actions
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Sébastien Jodogne, Justus H. Piater
IJCV
1998
163views more  IJCV 1998»
13 years 9 months ago
CONDENSATION - Conditional Density Propagation for Visual Tracking
The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimodal, cannot repre...
Michael Isard, Andrew Blake