Filtering and Smoothing for Motion Trajectory of Feature Point Using Non-Gaussian State Space Model

Naoyuki ICHIMURA  Norikazu IKOMA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E84-D   No.6   pp.755-759
Publication Date: 2001/06/01
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Processing, Image Pattern Recognition
Keyword: 
feature point tracking,  image sequence,  non-Gaussian state space model,  sequential Monte Carlo method,  

Full Text: PDF(943.8KB)>>
Buy this Article




Summary: 
Filtering and smoothing using a non-Gaussian state space model are proposed for motion trajectory of feature point in image sequence. A heavy-tailed non-Gaussian distribution is used for measurement noise to reduce the effect of outliers in motion trajectory. Experimental results are presented to show the usefulness of the proposed method.