Graphical object models for detection and tracking

Details Graphical object models for detection and tracking Graphical object models for detection and tracking

2005-05-23

2008-10-14

Lu, Tom Y (Department: 2624)

Image analysis

Applications

Target tracking or detecting

Reexamination Certificate

active

07436980

ABSTRACT:
A computer implemented method for object detection includes providing a spatio-temporal model for an object to be detected, providing a video including a plurality of images including the object, and measuring the object as a collection of components in each image. The method further includes determining a probability that the object is in each image, and detecting the object in any image upon comparing the probabilities for each image to a threshold for detecting the object.

REFERENCES:
patent: 6597801 (2003-07-01), Cham et al.
patent: 7200266 (2007-04-01), Ozer et al.
patent: 1 217 572 (2002-06-01), None
M. Isard. Pampas: Real-valued graphical models for computer vision, CVPR, vol. 1, pp. 613-620, 2003.
K. Okuma, A. Teleghani, N. de Freitas, J. Little and D. Lowe. A boosted particle filter: Multi-target detection and tracking, ECCV, 2004.
L. Sigal, S. Bhatia, S. Roth, M. Black and M. Isard. Tracking loose-limbed people, CVPR, 2004.
E. Sudderth, A. Ihler, W. Freeman and A. Willsky. Nonpararmetric belief propagation, MIT Laboratory for Information and Decision Systems Technical Report P-2551 (Oct. 15, 2002).
P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features, CVPR, 2001.
P. Viola, M. Jones and D. Snow. Detecting pedestrians using patterns of motion and appearance, ICCV, pp. 734-741, 2003.
Lan et al., “A unified spatio-temporal articulated model for tracking”, Computer Vision and Pattern Recognition, 2004, Proceedings of the 2004 IEEE Computer Society Conference on Washington, DC, Jun. 27-Jul. 2, 2004, Piscataway, NJ, vol. 1, pp. 722-729.
Donohoe, “Combining Segmentation and Tracking for the Classification of Moving Objects in video Scenes”, Conference Record, 22ndAsilomar Conference on Signals, Systems and Computers (Cat. No. 88CH2835-7), Maple Press San Jose, CA, USA, vol. 2, Oct. 31, 1988, pp. 533-538.

Affiliated with

Also associated with

Rating

Graphical object models for detection and tracking does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Graphical object models for detection and tracking, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Graphical object models for detection and tracking will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4019619