Robust, on-line, view-based appearance models for visual...

Details Robust, on-line, view-based appearance models for visual... Robust, on-line, view-based appearance models for visual...

2006-06-06

2006-06-06

Wu, Jingge (Department: 2621)

Image analysis

Applications

Target tracking or detecting

Reexamination Certificate

active

07058205

ABSTRACT:
A robust, adaptive, appearance model is disclosed that includes both a stable model component, learned over a long time course, and a transient component, learned over a relatively short time course (e.g., a 2-frame motion component and/or an outlier processing component). An on-line EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. The appearance model is used in a motion-based tracking algorithm to provide robustness in the face of image outliers, such as those caused by occlusions. It is also provides the ability to adapt to natural changes in appearance, such as those due to facial expressions, or variations in 3D pose.

REFERENCES:
patent: 5625715 (1997-04-01), Trew et al.
patent: 6724915 (2004-04-01), Toklu et al.
patent: 6731799 (2004-05-01), Sun et al.
patent: 6741756 (2004-05-01), Toyama et al.
patent: 6798897 (2004-09-01), Rosenberg
Fleet et al, “A Framework for Modeling Appearance Change in Image Sequences”, Computer Vision, 1998. Sixth International Conference on, Jan. 4-7, 1998.
Meier et al.: “Automatic Video Sequence Segmentation Using Object Tracking”, Tencon '97 Brisbane-Australia, Proceedings of IEEE Tencon 1997, pp. 283-286.
Jojic et al.: “Learning Mixtures of Smooth, Nonuniform Deformation Models for Probabilistic Image Matching”, Eight International Workshop on Artifical Intelligence and Statistics, Jan. 2001, XP-002248199.
Black et al.: “Robustly Estimating Changes in Image Appearance”, Computer Vision And Image Understanding, Apr. 2000, Academic Press, USA, vol. 78, No. 1, pp. 8-31, XP-002248200.

Affiliated with

Also associated with

Rating

Robust, on-line, view-based appearance models for visual... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Robust, on-line, view-based appearance models for visual..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Robust, on-line, view-based appearance models for visual... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3660223