Image analysis – Image transformation or preprocessing – Image storage or retrieval
Reexamination Certificate
2006-10-24
2006-10-24
Alavi, Amir (Department: 2624)
Image analysis
Image transformation or preprocessing
Image storage or retrieval
C382S181000
Reexamination Certificate
active
07127127
ABSTRACT:
Computationally efficient searching, browsing and retrieval of one or more objects in a video sequence are accomplished using learned generative models. The generative model is trained on an automatically or manually selected query sequence from a sequence of image frames. The resulting generative model is then used in searching, browsing or retrieval of one or more similar or dissimilar image frames or sequences within the image sequence by determining the likelihood of each frame under the learned generative model. Further, this method allows for automatic separation and balancing of various causes of variability while analyzing the image sequence. The generative models are based on appearances of multiple, possibly occluding objects in an image sequence. Further, the search strategies used include clustering and intelligent fast forward through the image sequence. Additionally, in one embodiment, a fast forward speed is relative to the current frame likelihood under the learned generative model.
REFERENCES:
patent: 6928638 (2005-08-01), Parvathala et al.
patent: 2003/0058268 (2003-03-01), Loui et al.
patent: 2003/0234805 (2003-12-01), Toyama et al.
patent: 2004/0095374 (2004-05-01), Jojic et al.
patent: 2004/0175058 (2004-09-01), Jojic et al.
patent: 2004/0189691 (2004-09-01), Jojic et al.
patent: 2005/0047646 (2005-03-01), Jojic et al.
Burl, M. C., M. Weber, P. Perona, A probabilistic approach to object recognition using local photometry and global geometry,Proc. 6thEurope Conf. Comp. Vision, ECCV, 1998, pp. 628-641.
Chang, S.-F., W. Chen, H. J. Meng, H. Sundaram, and D. Zhong, A fully automated content-based video search engine supporting spatiotemporal queries,IEEE Trans. on Circuits and Systems for Video Tech., Sep. 1998, vol. 8, No. 4, pp. 602-615.
De Bonet, J., and P.Viola, Structure driven image database retrieval,Proc. of the 1997 Conf. on Advances in Neural Information Processing Systems 10, Jul. 1998, Denver, Colorado, pp. 866-872.
Hadjidemetriou, E., M. D. Grossberg and S. K. Nayar, Spatial information in multiresolution histograms,IEEE Comp. Society Conf. on Comp. Vision and Pattern Recognition, CVPR'01, 2001, vol. 1, pp. 702-709.
Irani, M., P. Anandan, Video indexing based on mosaic representations,IEEE Transactions on Pattern Analysis and Mach. Inteligence, vol. 86, No. 5, 1998, pp. 905-921.
Jojic, N., B. Frey, Learning flexible sprites in video layers,Proc. of IEEE Conf. on Comp. Vision and Pattern Recognition, (CVPR 01), 2001, pp. 199-206.
Jojic, N., N. Petrovic, B. Frey, and T. Huang, Transformed hidden Markov models: Estimating mixture models of images and inferring spatial transformations in video sequences,IEEE Conf. on Comp. Vision and Pattern Recognition, 2000, vol. 2, pp. 26-33.
Maron, O., A. L. Ratan, Multiple-instance learning for natural scene classification,Proc. 15thInt'l Conf. on Machine Learning, 1998, pp. 341-349.
Ngo, C.-W., T.-C. Pong, H.-J. Zhang, On clustering and retrieval of video shots,Proc. of 9thACM Multimedia Conf., 2001, pp. 51-60.
Pingali, G. S., A. Opalach, I. Carlbom, Multimedia retrieval through spatio-temporal activity maps,ACM Multimedia, 2001, pp. 129-136.
Rui, Y., A. Gupta, A. Acero, Automatically extracting highlights for TV baseball programs,Proc. of 8thACM Int'l Conf. on Multimedia, Los Angeles, CA, 2000, pp. 105-115.
C. Schmid, Constructing models for content-based image retrieval,Proc. IEEE Comp. Soc'y Conf. Comp. Vision and Pattern Recognition, 2001, Hawaii, vol. 2, pp. 39-45
Stauffer, C., E. G. Miller, and K. Tieu, Transform-invariant image decomposition with similarity templates,Advances in Neural Information Processing Systems 14, MIT Press, Cambridge, MA, 2002, pp. 1295-1302.
Swain, M. J., and D. H. Ballard, Color indexing,Int'l J. of Comp. Vision, 1991, vol. 7, No. 1, pp. 11-32.
Tieu, K., and P. Viola, Boosting image retrieval,Proc. of the IEEE Conf. on Comp. Vision and Patterns Recognition, 2000, pp. 228-235.
Weber, M., M. Welling, and P. Perona, Unsupervised learning of models for recognition,Proc. European Conf. on Comp. Vision, 2000, pp. 18-32.
Wren, C., A. Azarbayejani, T. Darrell and A. Pentland. Pfinder: Real-time tracking of the human body,IEEE Transactions on Pattern Analysis and Mach. Intelligence, Jul. 1997, vol. 19, No. 7, pp. 780-785.
Zelnik-Manor, L., and M. Irani, Event-based analysis of video,Proc. of the 2001 IEEE Comp. Soc'y Conf. on Comp. Vision and Pattern Recognition, 2001, vol. 2, pp. 123-130.
Jojic Nebojsa
Petrovic Nemanja
Alavi Amir
Lyon & Harr LLP
Microsoft Corporation
Watson Mark A.
LandOfFree
System and method for adaptive video fast forward using... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for adaptive video fast forward using..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for adaptive video fast forward using... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3641701