Sciweavers

515 search results - page 63 / 103
» Multiple parametric motion model estimation and segmentation
Sort
View
ICCV
2011
IEEE
13 years 9 months ago
Modeling Temporal Coherence for Optical Flow
Despite the fact that temporal coherence is undeniably one of the key aspects when processing video data, this concept has hardly been exploited in recent optical flow methods. I...
Sebastian Volz, Andres Bruhn, Levi Valgaerts, Henn...
CVPR
1996
IEEE
15 years 11 months ago
Skin and Bones: Multi-layer, Locally Affine, Optical Flow and Regularization with Transparency
This paper describes a new method for estimating optical flow that strikes a balance between the flexibility of local dense computations and the robustness and accuracy of global ...
Shanon X. Ju, Michael J. Black, Allan D. Jepson
LOCA
2009
Springer
15 years 2 months ago
Multi Activity Recognition Based on Bodymodel-Derived Primitives
Abstract. We propose a novel model-based approach to activity recognition using high-level primitives that are derived from a human body model estimated from sensor data. Using sho...
Andreas Zinnen, Christian Wojek, Bernt Schiele
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
AMDO
2010
Springer
14 years 7 months ago
Multiple-Activity Human Body Tracking in Unconstrained Environments
We propose a method for human full-body pose tracking from measurements of wearable inertial sensors. Since the data provided by such sensors is sparse, noisy and often ambiguous, ...
Loren Arthur Schwarz, Diana Mateus, Nassir Navab