Sciweavers

772 search results - page 12 / 155
» Novel Observation Model for Probabilistic Object Tracking
Sort
View
AAAI
2012
11 years 10 months ago
Model Learning and Real-Time Tracking Using Multi-Resolution Surfel Maps
For interaction with its environment, a robot is required to learn models of objects and to perceive these models in the livestreams from its sensors. In this paper, we propose a ...
Jörg Stückler, Sven Behnke
FSS
2008
108views more  FSS 2008»
13 years 7 months ago
A collaborative recommender system based on probabilistic inference from fuzzy observations
The problem of building recommender systems has attracted considerable attention in recent years. The objective of this paper is to automatically suggest and rank a list of new it...
Luis M. de Campos, Juan M. Fernández-Luna, ...
CVPR
2010
IEEE
1208views Computer Vision» more  CVPR 2010»
14 years 4 months ago
Visual Tracking Decomposition
We propose a novel tracking algorithm that can work robustly in a challenging scenario such that several kinds of appearance and motion changes of an object occur at the same time....
Junseok Kwon (Seoul National University), Kyoung M...
PAMI
2008
275views more  PAMI 2008»
13 years 7 months ago
Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles
Abstract-- We present a novel approach for multi-object tracking which considers object detection and spacetime trajectory estimation as a coupled optimization problem. Our approac...
Bastian Leibe, Konrad Schindler, Nico Cornelis, Lu...
ICIP
2005
IEEE
14 years 9 months ago
Novel likelihood estimation technique based on boosting detector
This paper presents novel likelihood estimation to be used for particle filter based object tracking. The likelihood estimation is built upon cascade object detector trained with ...
Haijing Wang, Peihua Li, Tianwen Zhang