Image analysis – Applications – 3-d or stereo imaging analysis
Reexamination Certificate
2005-03-29
2005-03-29
Bali, Vikkram (Department: 2623)
Image analysis
Applications
3-d or stereo imaging analysis
C345S419000
Reexamination Certificate
active
06873724
ABSTRACT:
A method recovers a 3D model of non-rigid 3D shape and motion of an object directly from an input video of the object by first identifying a set of features on the object in a reference image of the input video. Correspondences are then determined between the set of features in the reference image and corresponding features in each other image of the input video, These correspondences are factored by cascaded singular value decompositions into a motion matrix and a shape matrix. The 3D model can then be extracted from the factored motion matrix and shape matrix. The 3D model includes a linear basis for deformable shape of the object in the input video, and for each image a 3D rotations matrix, deformation coefficients, and translation vectors. A novel video can now be generated from the input video by manipulating the 3D model.
REFERENCES:
patent: 6212510 (2001-04-01), Brand
patent: 6650335 (2003-11-01), Brand
patent: 20030072482 (2003-04-01), Brand
Factorization with uncertainty, by Irani et al., ECCV 2000, p. 539-553.*
Flexible flow for 3D nonrigid tracking and shape recovery, by Brand et al., IEEE 2001, pp. 1-315-1-322.*
Understanding manipulation in video, by Brand, IEEE 1996, pp. 94-99.*
Recovering non rigid 3D shape from image streams, by Bregler et al., IEEE 2000, p. 1-7.*
Digital image processing, by Baxes.
Bali Vikkram
Brinkman Dirk
Curtin Andrew J.
Mitsubishi Electric Research Laboratories Inc.
LandOfFree
Rendering deformable 3D models recovered from videos does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Rendering deformable 3D models recovered from videos, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Rendering deformable 3D models recovered from videos will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3401147