Presentation 1999/7/15
Target Tracking by Matching Shapes Represented by Compact Trees of Sigmoid Functions : A Cellular Computation Framework
Itsuo Kumazawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This report describes a shape matching method which transforms a template shape represented by a tree of sigmoid functions so that it fits target shapes included in a sequence of image frames. The tree-based shape representation is automatically constructed by a training procedure in advance to the shape matching process. Through the matching process, the position and the posture of the target are computed by a gradient-descent-based searching procedure. The amount of computation is reduced by using a compact tree which represents a shape roughly but with sufficient details for determining the object postures. The search are a is also limited assuming small changes of the object positions and postures in consecutive frames. The number of iterations in gradient-descent-based search is reduced using the previous position and posture as initial conditions for the next search. Some experiments were conducted and the method's sensitivity to noises and initial parameter values were examined. The results suggest the method's feasibility as a target tracking method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Shape modeling / shape matching / gradient descent / neural network / target tracking / back propagation / learning
Paper # PRMU99-37
Date of Issue

Conference Information
Committee PRMU
Conference Date 1999/7/15(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Vice Chair

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Target Tracking by Matching Shapes Represented by Compact Trees of Sigmoid Functions : A Cellular Computation Framework
Sub Title (in English)
Keyword(1) Shape modeling
Keyword(2) shape matching
Keyword(3) gradient descent
Keyword(4) neural network
Keyword(5) target tracking
Keyword(6) back propagation
Keyword(7) learning
1st Author's Name Itsuo Kumazawa
1st Author's Affiliation Department of Computer Science Tokyo Institute of Technology()
Date 1999/7/15
Paper # PRMU99-37
Volume (vol) vol.99
Number (no) 181
Page pp.pp.-
#Pages 8
Date of Issue