by Michael J. Black, Yaser Yacoob, Allan D. Jepson, David J. Fleet
http://www.cs.brown.edu/people/black/Papers/cvpr97-motion.ps.gz
Add To MetaCart
Abstract:
A framework for learning parameterized models of optical flow from image sequences is presented. A class of motions is represented by a set of orthogonal basis flow fields that are computed from a training set using principal component analysis. Many complex image motions can be represented by a linear combination of a small number of these basis flows. The learned motion models may be used for opticalflow estimationand for model-based recognition. For optical flow estimation we describe a robust, multi-resolution scheme for directly computing the parameters of the learned flow models from image derivatives. As examples we consider learning motion discontinuities, non-rigid motion of human mouths, and articulated human motion. 1
Citations
|
686
|
Performance of optical flow techniques
– Barron, Fleet, et al.
- 1994
|
|
337
|
EigenTracking: Robust matching and tracking of articulated objects using a view-based representation
– Black, Jepson
- 1998
|
|
328
|
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields
– Black, Anandan
- 1996
|
|
200
|
Tracking and recognizing rigid and non-rigid facial motions using local parametric models of image motion
– Black, Yacoob
- 1995
|
|
135
|
Cardboard people: A parameterized model of articulated image motion
– Ju, Black, et al.
- 1996
|
|
131
|
Learning flexible models from image sequences
– Baumberg, Hogg
- 1994
|
|
89
|
Real-Time Tracking of Image Regions with Changes
– Hager, Belhumeur
- 1996
|
|
51
|
Generalized image matching: Statistical learning of physically-based deformations
– Nastar, Moghaddam, et al.
- 1996
|
|
37
|
Facial analysis and synthesis using image-based models
– Ezzat, Poggio
- 1996
|
|
26
|
Physically-based combinations of views: Representing rigid and nonrigid motion
– Sclaroff, Pentland
- 1994
|
|
21
|
Learning novel views to a single face image
– Vetter
- 1996
|
|
20
|
A framework for modeling appearance change in image sequences
– Black, Fleet, et al.
- 1998
|
|
19
|
Constraints for the early detection of discontinuity from motion
– Black, Anandan
- 1990
|
|
18
|
A deformable model for the recognition of human faces under arbitrary illumination
– Hallinan
- 1995
|
|
12
|
Feature correspondence by interleaving shape and texture computations
– Beymer
- 1996
|
|
3
|
Parametric feature detection. CVPR'96
– Nayar, Baker, et al.
|
|
3
|
Detecting kinetic occlusion. ICCV'95
– Niyogi
|
|
3
|
The early detection of motion boundaries. ICCV'87
– Spoerri, Ullman
|
