Sciweavers

297 search results - page 20 / 60
» Monte Carlo Localization Using SIFT Features
Sort
View
ICCV
2011
IEEE
13 years 9 months ago
Perturb-and-MAP Random Fields: Using Discrete Optimization\\to Learn and Sample from Energy Models
We propose a novel way to induce a random field from an energy function on discrete labels. It amounts to locally injecting noise to the energy potentials, followed by finding t...
George Papandreou, Alan L. Yuille
ICPR
2006
IEEE
15 years 10 months ago
Rotation-Invariant Neoperceptron
Approaches based on local features and descriptors are increasingly used for the task of object recognition due to their robustness with regard to occlusions and geometrical defor...
Beat Fasel, Daniel Gatica-Perez
IJRR
2010
185views more  IJRR 2010»
14 years 8 months ago
FISST-SLAM: Finite Set Statistical Approach to Simultaneous Localization and Mapping
The solution to the problem of mapping an environment and at the same time using this map to localize (the simultaneous localization and mapping, SLAM, problem) is a key prerequis...
Bharath Kalyan, K. W. Lee, W. Sardha Wijesoma
IROS
2006
IEEE
128views Robotics» more  IROS 2006»
15 years 3 months ago
Improving Data Association in Vision-based SLAM
— This paper presents an approach to vision-based simultaneous localization and mapping (SLAM). Our approach uses the scale invariant feature transform (SIFT) as features and app...
Arturo Gil, Óscar Reinoso, Óscar Mar...
ICMCS
2007
IEEE
191views Multimedia» more  ICMCS 2007»
15 years 3 months ago
Variable Number of "Informative" Particles for Object Tracking
Particle filter is a sequential Monte Carlo method for object tracking in a recursive Bayesian filtering framework. The efficiency and accuracy of the particle filter depends on t...
Yu Huang, Joan Llach