Sciweavers

959 search results - page 177 / 192
» Tracking objects in video using motion and appearance models
Sort
View
CVPR
2004
IEEE
14 years 9 months ago
View Independent Human Body Pose Estimation from a Single Perspective Image
Recovering the 3D coordinates of various joints of the human body from an image is a critical first step for several model-based human tracking and optical motion capture systems....
Vasu Parameswaran, Rama Chellappa
MVA
2007
211views Computer Vision» more  MVA 2007»
13 years 9 months ago
Shadow Elimination in Traffic Video Segmentation
Shadow detection is critical for robust and reliable vision-based systems for traffic vision analysis. Shadow points are often misclassified as object points causing errors in loc...
Hong Liu, Jintao Li, Qun Liu, Yueliang Qian
ICASSP
2010
IEEE
13 years 8 months ago
High order motion interpolation for side information improvement in DVC
A key step in distributed video coding is the generation of the side information (SI) i.e. the estimation of the Wyner-Ziv frame (WZF). This step is also frequently called image i...
Giovanni Petrazzuoli, Marco Cagnazzo, Béatr...
PAMI
2011
12 years 10 months ago
Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin
—We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden condi...
Yang Wang 0003, Greg Mori
ISMAR
2009
IEEE
14 years 2 months ago
Mobile augmented reality based 3D snapshots
: In this paper, we present a mobile augmented reality application that is based on the acquisition of user-generated content obtained by 3D snapshotting. To take a 3D snapshot of ...
Peter Keitler, Frieder Pankratz, Björn Schwer...