Image analysis – Applications – Target tracking or detecting
Reexamination Certificate
2011-03-22
2011-03-22
Carter, Aaron W (Department: 2624)
Image analysis
Applications
Target tracking or detecting
C382S100000, C382S181000, C382S190000, C382S240000, C382S276000
Reexamination Certificate
active
07912248
ABSTRACT:
An image processing apparatus enables efficient feature point tracking. A displacement calculating unit reads a hierarchical tier image with the smallest image size from each of a reference pyramid and a tracking pyramid in an image memory, and performs repetitive detection of a tracking point using a hierarchical gradient method. The displacement calculating unit repeatedly calculates a displacement amount between the feature points, and outputs a value of a repetition count of tracking point detection until convergence of the displacement amount and the value of the displacement amount at a time of convergence. A repetition criterion setting unit changes the criterion for determination of displacement amount convergence based on the repetition count and displacement amount. The displacement calculating unit reads upper hierarchical tier images and detects a tracking point according to the changed criterion. The repetitive tracking point detection and convergence determination criterion setting change are repeated.
REFERENCES:
patent: 5627905 (1997-05-01), Sebok et al.
patent: 5748761 (1998-05-01), Chang et al.
patent: 6456731 (2002-09-01), Chiba et al.
patent: 6788802 (2004-09-01), Chiba et al.
patent: 7522749 (2009-04-01), Zitnick et al.
patent: 2005/0226462 (2005-10-01), Wittebrood et al.
patent: 2006/0023786 (2006-02-01), Li et al.
patent: 3435084 (2003-05-01), None
patent: 2007-49545 (2007-02-01), None
Carter Aaron W
FUJIFILM Corporation
Koziol Stephen R
McGinn IP Law Group PLLC
LandOfFree
Hierarchical feature tracking using optical flow does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Hierarchical feature tracking using optical flow, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Hierarchical feature tracking using optical flow will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2685377