Sciweavers

156 search results - page 9 / 32
» Learning Relational Kalman Filtering
Sort
View
NIPS
1998
13 years 11 months ago
Global Optimisation of Neural Network Models via Sequential Sampling
We propose a novel strategy for training neural networks using sequential Monte Carlo algorithms. This global optimisation strategy allows us to learn the probability distribution...
João F. G. de Freitas, Mahesan Niranjan, Ar...
MVA
1996
167views Computer Vision» more  MVA 1996»
13 years 11 months ago
Applying a Dynamic Recognition Scheme for Vehicle Recognition in Many Object Traffic Scenes
An adaptive object recognition scheme for image sequences of many object scenes is described. The scheme is applied for t r d c object recognition under ego-motion. The recursive ...
Wlodzimierz Kasprzak, Heinrich Niemann
ICASSP
2011
IEEE
13 years 2 months ago
Single target tracking using vector magnetometers
With the electromagnetic theory as basis, we present a sensor model for three-axis magnetometers suitable for localization and tracking applications. The model depends on a physic...
Niklas Wahlstrom, Jonas Callmer, Fredrik Gustafsso...
CVPR
2009
IEEE
1385views Computer Vision» more  CVPR 2009»
15 years 5 months ago
Distributed Multi-Target Tracking In A Self-Configuring Camera Network
This paper deals with the problem of tracking multiple targets in a distributed network of self-configuring pan-tilt-zoom cameras. We focus on applications where events unfold over...
Amit K. Roy Chowdhury, Bi Song, Cristian Soto
ECCV
2006
Springer
14 years 2 months ago
Using a Connected Filter for Structure Estimation in Perspective Systems
Three-dimensional structure information can be estimated from two-dimensional images using recursive estimation methods. This paper investigates possibilities to improve structure...
Fredrik Nyberg, Ola Dahl, Jan Holst, Anders Heyden