Sciweavers

325 search results - page 14 / 65
» Novel iteration schemes for the Cluster Variation Method
Sort
View
ECCV
2004
Springer
16 years 4 hour ago
High Accuracy Optical Flow Estimation Based on a Theory for Warping
Abstract. We study an energy functional for computing optical flow that combines three assumptions: a brightness constancy assumption, a gradient constancy assumption, and a discon...
Thomas Brox, Andrés Bruhn, Nils Papenberg, ...
JISE
2010
144views more  JISE 2010»
14 years 4 months ago
Variant Methods of Reduced Set Selection for Reduced Support Vector Machines
In dealing with large datasets the reduced support vector machine (RSVM) was proposed for the practical objective to overcome the computational difficulties as well as to reduce t...
Li-Jen Chien, Chien-Chung Chang, Yuh-Jye Lee
DAGM
2005
Springer
15 years 3 months ago
3D Surface Reconstruction by Combination of Photopolarimetry and Depth from Defocus
Abstract. In this paper we present a novel image-based 3D surface reconstruction technique that incorporates reflectance, polarisation, and defocus information into a variational ...
Pablo d'Angelo, Christian Wöhler
ICCV
2007
IEEE
16 years 2 days ago
Variational Segmentation using Fuzzy Region Competition and Local Non-Parametric Probability Density Functions
We describe a novel variational segmentation algorithm designed to split an image in two regions based on their intensity distributions. A functional is proposed to integrate the ...
Benoit Mory, Roberto Ardon, Jean-Philippe Thiran
AVSS
2007
IEEE
15 years 4 months ago
Vehicular traffic density estimation via statistical methods with automated state learning
This paper proposes a novel approach of combining an unsupervised clustering scheme called AutoClass with Hidden Markov Models (HMMs) to determine the traffic density state in a R...
Evan Tan, Jing Chen