Sciweavers

206 search results - page 9 / 42
» Learning Parameterized Models of Image Motion
Sort
View
102
Voted
ECCV
2002
Springer
16 years 1 months ago
Tracking and Rendering Using Dynamic Textures on Geometric Structure from Motion
Estimating geometric structure from uncalibrated images accurately enough for high quality rendering is difficult. We present a method where only coarse geometric structure is trac...
Dana Cobzas, Martin Jägersand
WACV
2005
IEEE
15 years 5 months ago
Robust Salient Motion Detection with Complex Background for Real-Time Video Surveillance
Moving object detection is very important for video surveillance. In many environments, motion maybe either interesting (salient) motion (e.g., a person) or uninteresting motion (...
Ying-li Tian, Arun Hampapur
89
Voted
SCVMA
2004
Springer
15 years 5 months ago
2D Motion Description and Contextual Motion Analysis: Issues and New Models
Abstract. In this paper, several important issues related to visual motion analysis are addressed with a focus on the type of motion information to be estimated and the way context...
Patrick Bouthemy
128
Voted
IJCV
2010
158views more  IJCV 2010»
14 years 10 months ago
Metric Learning for Image Alignment
Abstract Image alignment has been a long standing problem in computer vision. Parameterized Appearance Models (PAMs) such as the Lucas-Kanade method, Eigentracking, and Active Appe...
Minh Hoai Nguyen, Fernando De la Torre
FGR
2008
IEEE
176views Biometrics» more  FGR 2008»
15 years 6 months ago
Learning image alignment without local minima for face detection and tracking
Active Appearance Models (AAMs) have been extensively used for face alignment during the last 20 years. While AAMs have numerous advantages relative to alternate approaches, they ...
Minh Hoai Nguyen, Fernando De la Torre