Sciweavers

CVPR
2003
IEEE
14 years 11 months ago
Methods and Geometry for Plane-Based Self-Calibration
Abstract. We consider the problem of camera selfcalibration, from images of a planar object with unknown Euclidean structure. The general case of possibly varying focal length is a...
Pierre Gurdjos, Peter Sturm
CVPR
2003
IEEE
14 years 11 months ago
Wide-baseline Multiple-view Correspondences
We present a novel approach for establishing multiple-view feature correspondences along an unordered set of images taken from substantially different viewpoints. While recently s...
Vittorio Ferrari, Tinne Tuytelaars, Luc J. Van Goo...
CVPR
2003
IEEE
14 years 11 months ago
Object Class Recognition by Unsupervised Scale-Invariant Learning
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constel...
Robert Fergus, Pietro Perona, Andrew Zisserman
CVPR
2003
IEEE
14 years 11 months ago
Representation and Detection of Deformable Shapes
We describe some techniques that can be used to represent and detect deformable shapes in images. The main difficulty with deformable template models is the very large or infinite...
Pedro F. Felzenszwalb
CVPR
2003
IEEE
14 years 11 months ago
Transforming Camera Geometry to A Virtual Downward-Looking Camera: Robust Ego-Motion Estimation and Ground-Layer Detection
This paper presents a robust method to solve the two coupled problems: ground layer detection and vehicle egomotion estimation, which appear in visual navigation. We virtually rot...
Qifa Ke, Takeo Kanade
CVPR
2003
IEEE
14 years 11 months ago
3D Shape from Anisotropic Diffusion
Paolo Favaro, Stanley Osher, Stefano Soatto, Lumin...
CVPR
2003
IEEE
14 years 11 months ago
A Road Sign Recognition System Based on Dynamic Visual Model
We propose a computational model motivated by human cognitive processes for detecting changes of driving environments. The model, call dynamic visual model, consists of three majo...
C. Y. Fang, C. S. Fuh, S. W. Chen, P. S. Yen
CVPR
2003
IEEE
14 years 11 months ago
Learning Appearance and Transparency Manifolds of Occluded Objects in Layers
By mapping a set of input images to points in a lowdimensional manifold or subspace, it is possible to efficiently account for a small number of degrees of freedom. For example, i...
Brendan J. Frey, Nebojsa Jojic, Anitha Kannan