Fast and robust motion computations using direct methods

Details Fast and robust motion computations using direct methods Fast and robust motion computations using direct methods

2011-02-22

2011-02-22

Senfi, Behrooz (Department: 2482)

Pulse or digital communications

Bandwidth reduction or expansion

Television or motion video signal

C382S103000

Reexamination Certificate

active

07894528

ABSTRACT:
A respective intensity gradient of a first spatially aligned pixel in each frame of a sequence of images is multiplied by a respective intensity or function thereof of a second pixel in the new frame, this being done for all pixels in the set and the resulting products being summed. This is repeated so that in one of the sums the first and second pixels have identical locations in the respective frames and where in each additional sum the second pixel is shifted by a non-zero shift relative to its location in other sums. The transformation is computed using intensity and gradient values of the image frames in the sequence and the sums. Weighted averages of at least two of the sums are stored and used together with the intensity and gradient values of the frames in the sequence to re-compute the transformation.

REFERENCES:
patent: 6219462 (2001-04-01), Anandan et al.
patent: 2004/0130552 (2004-07-01), Duluk et al.
Lucas, B. et al., “An interactive image registration technique with an application to stereo vision”; IJCAI; pp. 674-679, 1981.
Bergen, J. et al., “Hierarchical model-based motion estimation”; ECCV'92, pp. 237-252, Italy, 1992.
Irani, M. et al., “Computing occluding and transparent motions”; Int. J. Computer Vision, vol. 12, pp. 5-16, 1994.
Baker, S. et al., “Lucas-kanade 20 years on: A unifying framework”; International Journal of Computer Vision; vol. 56, pp. 221-255, 2004.
Shi, J. et al., “Good features to track”; CVPR; Seattle, 1994.
Burt, P. et al., “Mechanisms for isolating component patterns in the sequential analysis of multiple motion”; Visual Motion, Proceedings of the IEEE Workshop, pp. 187-193, 1991.
Triggs, B. et al., “Bundle adjustment- A modern synthesis”; Vision Algorithms: Theory and Practice.; LNCS, Springer Verlag, pp. 298-375, 2000.
Shum, H. et al., “Construction and refinement of panoramic mosaics with global and local alignment”; ICCV 98, Washington, DC, pp. 953-958, 1998.
Sawhney, S.H. et al., “Robust video mosaicing through topology inference and local to global alignment”; ECCV, pp. 103-119, 1998.
Sawhney, H. et al., “True multi-image alignment and its application to mosaicing and lens distortion correction”; PAMI, vol. 21, pp. 245-243, 1999.
Irani, M., “Multi-frame optical flow estimation using subspace constraints”; IEEE International Conference on Computer Vision; Corfu, 1999.
Torr, P. et al., “A new robust estimator with application to estimating image geometry”; CVIU, vol. 78, pp. 138-156, 2000.
Capel, D. et al., Automated mosaicing with super-resolution zoom; CVPR, Santa Barbara, 1998, pp. 885-891.
Yalcin, H. et al., A flow-based approach to vehicle detection and background mosaicking in airborne video; Video Proceedings in conjunction with CVPR'05, 2005.
Bergen, J. et al., A three frame algorithm for estimating two-component image; IEEE Trans. On PAMI 14, 1992, pp. 886-896.

Affiliated with

Also associated with

Rating

Fast and robust motion computations using direct methods does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Fast and robust motion computations using direct methods, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fast and robust motion computations using direct methods will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2643149