Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Maximum Likelihood Estimation of the Template of a Rigid Moving Object

Summary: Maximum Likelihood Estimation of the
Template of a Rigid Moving Object
Pedro M. Q. Aguiar1
and Jos´e M. F. Moura2
Instituto de Sistemas e Rob´otica, Instituto Superior T´ecnico, Lisboa, Portugal
E-mail: aguiar@isr.ist.utl.pt, Home-page: www.isr.ist.utl.pt/~aguiar
Electrical and Computer Eng., Carnegie Mellon University, Pittsburgh PA, USA
E-mail: moura@ece.cmu.edu, Home-page: www.ece.cmu.edu/~moura
Abstract. Motion segmentation methods often fail to detect the mo-
tions of low textured regions. We develop an algorithm for segmentation
of low textured moving objects. While usually current motion segmenta-
tion methods use only two or three consecutive images our method refines
the shape of the moving object by processing successively the new frames
as they become available. We formulate the segmentation as a parame-
ter estimation problem. The images in the sequence are modeled taking
into account the rigidity of the moving object and the occlusion of the
background by the moving object. The segmentation algorithm is derived
as a computationally simple approximation to the Maximum Likelihood


Source: Aguiar, Pedro M. Q. - Institute for Systems and Robotics (Lisbon)


Collections: Engineering