Sciweavers

138 search results - page 5 / 28
» Object Segmentation Using Background Modelling and Cascaded ...
Sort
View
IJCV
2006
125views more  IJCV 2006»
14 years 9 months ago
Robust Tracking Using Foreground-Background Texture Discrimination
This paper conceives of tracking as the developing distinction of a foreground against the background. In this manner, fast changes in the object or background appearance can be de...
Hieu Tat Nguyen, Arnold W. M. Smeulders
ICCV
2001
IEEE
15 years 11 months ago
Plan-View Trajectory Estimation with Dense Stereo Background Models
In a known environment, objects may be tracked in multiple views using a set of background models. Stereo-based models can be illumination-invariant, but often have undefined valu...
Trevor Darrell, David Demirdjian, Neal Checka, Ped...
84
Voted
FGR
1998
IEEE
131views Biometrics» more  FGR 1998»
15 years 1 months ago
Tracking and Segmenting People in Varying Lighting Conditions Using Colour
Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models were used to estimate probability densi...
Yogesh Raja, Stephen J. McKenna, Shaogang Gong
CVPR
2005
IEEE
14 years 11 months ago
Fast Illumination-Invariant Background Subtraction Using Two Views: Error Analysis, Sensor Placement and Applications
Background modeling and subtraction to detect new or moving objects in a scene is an important component of many intelligent video applications. Compared to a single camera, the u...
Ser-Nam Lim, Anurag Mittal, Larry S. Davis, Nikos ...
ECCV
2000
Springer
15 years 11 months ago
Non-parametric Model for Background Subtraction
Abstract. Background subtraction is a method typically used to segment moving regions in image sequences taken from a static camera by comparing each new frame to a model of the sc...
Ahmed M. Elgammal, David Harwood, Larry S. Davis