Sciweavers

5 search results - page 1 / 1
» Multi-step Entropy Based Sensor Control for Visual Object Tr...
Sort
View
DAGM
2004
Springer
13 years 10 months ago
Multi-step Entropy Based Sensor Control for Visual Object Tracking
We describe a method for selecting optimal actions affecting the sensors in a probabilistic state estimation framework, with an application in selecting optimal zoom levels for a ...
Benjamin Deutsch, Matthias Zobel, Joachim Denzler,...
ICIP
2005
IEEE
14 years 6 months ago
Multi-step active object tracking with entropy based optimal actions using the sequential Kalman filter
We describe an enhanced method for the selection of optimal sensor actions in a probabilistic state estimation framework. We apply this to the selection of optimal focal lengths f...
Benjamin Deutsch, Heinrich Niemann, Joachim Denzle...
IVC
2007
301views more  IVC 2007»
13 years 5 months ago
Kinematic sets for real-time robust articulated object tracking
In this article a new approach is given for real-time visual tracking of a class of articulated non-rigid objects in 3D. The main contribution of this paper consists in symmetrica...
Andrew I. Comport, Éric Marchand, Fran&cced...
ICRA
2002
IEEE
148views Robotics» more  ICRA 2002»
13 years 10 months ago
A Neural Approach to Adaptive Behavior and Multi-Sensor Action Selection in a Mobile Device
Sampling multisensory information and taking the appropriate motor action is critical for a biological organism’s survival, but a difficult task for robots. We present a Neurally...
Jeffrey L. Krichmar, James A. Snook
CVPR
2007
IEEE
14 years 7 months ago
Large scale vision-based navigation without an accurate global reconstruction
Autonomous cars will likely play an important role in the future. A vision system designed to support outdoor navigation for such vehicles has to deal with large dynamic environme...
Albert Diosi, Anthony Remazeilles, François...