Three dimensional object pose estimation which employs dense...

Image analysis – Applications – Target tracking or detecting

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C382S106000, C382S107000

Reexamination Certificate

active

07003134

ABSTRACT:
Dense range data obtained at real-time rates is employed to estimate the pose of an articulated figure. In one approach, the range data is used in combination with a model of connected patches. Each patch is the planar convex hull of two circles, and a recursive procedure is carried out to determine an estimate of pose which most closely correlates to the range data. In another aspect of the invention, the dense range data is used in conjunction with image intensity information to improve pose tracking performance. The range information is used to determine the shape of an object, rather than assume a generic model or estimate structure from motion. In this aspect of the invention, a depth constraint equation, which is a counterpart to the classic brightness change constraint equation, is employed. Both constraints are used to jointly solve for motion estimates.

REFERENCES:
patent: 5036474 (1991-07-01), Bhanu et al.
patent: 5128874 (1992-07-01), Bhanu et al.
patent: 5307170 (1994-04-01), Itsumi et al.
patent: 5521633 (1996-05-01), Nakajima et al.
patent: 5675377 (1997-10-01), Gibas
patent: 5692061 (1997-11-01), Sasada et al.
patent: 6084979 (2000-07-01), Kanade et al.
patent: 6195445 (2001-02-01), Dubuisson-Jolly et al.
patent: 6445810 (2002-09-01), Darrell et al.
patent: 6492986 (2002-12-01), Metaxas et al.
Aggarwal, J.K.; Cai, Q.; Human Motion Analysis: A Review. Nonrigid and Articulated Motion Workshop, 1997. Proceedings., IEEE , Jun. 16, 1997 Pages(s): 90-102.
B. Sabata and J. Aggarwal. Estimation of motion from a pair of range images: A review. CVGIP, 54(3): 309-324, Nov. 1991.
Sharma et al. “Dynamic control of motion detection by an active, mobile observer” Intelligent Control, 1991. Proceedings of IEEE International Symposium on Aug. 13-15, 1991 pp. 43-48.
Bregler, Christoph, et al,“Tracking People with Twists and Exponential Maps”, Computer Science Division, U.C. Berkeley, 8 pages.
Murray, R. et al,“Chapter 2, Rigid Body Motion”, A Mathematical Introduction to Robotic Manipulation,CRC Press, Boca Raton, 1994, pps 19-30, 34-61, 85-87, 115-117.
Pentland, Alex et al,“Recovery of Nonrigid Motion and Structure”, IEEE Transactions of Pattern Analysis and Machine Intelligence,vol. 13, No. 7, Jul. 1991, pps 730-742.
Yamamoto, Masanobu et al,“Incremental Tracking of Human Actions from Multiple Views”, 1998 IEEE,Department of Information Engineering, Niigata University, pps 2-7.
Michael J. Black & Yaser Yacoob;Tracking and Recognizing Rigid and Non-Rigid Facial Motions Using Local Parametric Models of Image Motion; Xerox Palo Alto Research Center & Computer Vision Laboratory.
Michael H. Lin;Tracking Articulated Objects in Real-Time Range Image Sequences; Interval Research Corporation.
Sumit Basu, Irfan Essa, & Alex Pentland;Motion Regularization for Model-Based Head Tracking; Massachusetts Institute of Technology, Perceptual Computing Section.
D.M. Gavrila & L.S. Davis;3-D Model-Based Tracking of Humans in Action: A Multi-View Approach; University of Maryland, Computer Vision Laboratory, CfAR.
John Woodfill & Brian Von Herzen;Real-Time Stereo Vision on the PARTS Reconfigurable Computer;Interval Research Corporation & Rapid Prototypes, Inc.
James R. Bergen, P. Anandan, Keith J. Hanna, & Rajesh Hingorani;Hierarchical Model-Based Motion Estimation; May 19-22, 1992; Computer Vision ECCV '92; Second European Conference on Computer Vision.
Berthold K.P. Horn & E.J. Weldon Jr.;Direct Methods for Recovering Motion; 1998; International Journal of Computer Vision 2, p. 51-76.
Ramin Zabih & John Woodfill;Non-Parametric Local Transforms for Computing Visual Correspondence; May 2-6, 1994; Computer Vision ECCV '94; Third European Conference on Computer Vision.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Three dimensional object pose estimation which employs dense... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Three dimensional object pose estimation which employs dense..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Three dimensional object pose estimation which employs dense... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-3662771

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.