Image analysis – Image compression or coding – Interframe coding
Reexamination Certificate
2007-01-16
2007-01-16
Do, Anh Hong (Department: 2624)
Image analysis
Image compression or coding
Interframe coding
C375S240000, C348S699000
Reexamination Certificate
active
10369967
ABSTRACT:
A method for determining motion vectors from one point in one image frame of a scene to corresponding points in at least two other image frames of the scene, wherein the frames are obtained in a capture process utilizing one or more cameras, wherein the method employs an iterative and hierarchical dense motion estimation that computes the geometry-consistent and appearance-consistent motion fields between three images simultaneously by enforcing both a trilinear constraint and a constant-brightness constraint. This method includes the steps of: providing first, second and third images of a scene under perspective projection with unconstrained motion of the camera, wherein points (x′,y′) and (x″,y″) in the second and third frames are projections of the same spatial points (x,y) in the first frame; specifying a system of trifocal tensors and optical flow equations that describe point correspondence across the three images; and applying both a geometric constraint of trilinearity and an appearance constraint of constant brightness, thereby utilizing a trilinear constraint and a constant brightness constraint to obtain the pointwise displacement between the three frames simultaneously.
REFERENCES:
patent: 5241608 (1993-08-01), Fogel
patent: 5471252 (1995-11-01), Iu
patent: 5581276 (1996-12-01), Cipolla et al.
patent: 5680487 (1997-10-01), Markandey
patent: 5821943 (1998-10-01), Shashua
patent: 5963664 (1999-10-01), Kumar et al.
patent: 6192145 (2001-02-01), Anandan et al.
patent: 6219462 (2001-04-01), Anandan et al.
patent: 6507661 (2003-01-01), Roy
Soatto et al., “Reducing “Structure From Motion”: A General Framework for Dynamic Vision Part 2: Implemetation and Experimental Assessment”, IEEE, vol. 20, No. 9, Sep. 1998, pp. 943-960.
“On the computation of motion from sequences of images—A review” by J.K. Aggarwal et al.,Proceedings of the IEEE, 76:917-935, 1988.
“Performance of Optical Flow Techniques” by J.L. Baron, et al.,International Journal of Computer Vision(IJCV), 2(1): 43-77, 1994.
“A taxonomy and evaluation of dense two-frame stereo correspondence algorithms” by D. Scharstein, et al.,IJCV, 47(Jan. 2, 2003); 7-42, 2002.
“An iterative image registration technique with an application to stereo vision” by B. Lucas, et al. inImage Understanding Workshop, pp. 121-130, 1981.
“A three-frame algorithm for estimating two-component image motion” by J. Bergen, et al.,IEEE Trans. On Pattern Analysis and Machine Intelligence(TPAMI), 14: 886-896, 1992.
“On the estimation of optical flow: relations between different approaches and some new results” by H. Nagel, et al.,Artificial Intelligence, 33: 299-324, 1987.
“A computational framework and an algorithm for the measurement of structure from motion” by P. Anandan,IJCV, 2:283-310, 1989.
“Algebraic functions for recognition” by A. Shashua.IEEE Transactions on Pattern Analysis and Machine Intelligence, 17:449-789, 1995.
“Structure from motion using line correspondences” by M.E. Spetsakis, et al., IJCV, 4: 171-183, 1990.
“Lines and points in three views and trifocal tensor” by R.I. Harley, In IJCV, 22:125-140, 1997.
“Trifocal motion modeling for object-based video compression and manipulation” by Z. sun and A.M. Tekalp.IEEE Trans. On Circuits and Systems for Video Technology, 8:667-685, 1998.
Do Anh Hong
Eastman Kodak Company
Woods David M.
LandOfFree
Method and system for constraint-consistent motion estimation does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and system for constraint-consistent motion estimation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for constraint-consistent motion estimation will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3778018