geometric AIC." />


Moving Object Detection from Optical Flow without Empirical Thresholds

Naoya OHTA  Kenichi KANATANI  Kazuhiro KIMURA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E81-D   No.2   pp.243-245
Publication Date: 1998/02/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Processing,Computer Graphics and Pattern Recognition
Keyword: 
geometric AIC,  model selection,  optical flow,  moving object detection,  statistical inference,  

Full Text: PDF(279KB)>>
Buy this Article




Summary: 
We show that moving objects can be detected from optical flow without using any knowledge about the magnitude of the noise in the flow or any thresholds to be adjusted empirically. The underlying principle is viewing a particular interpretation about the flow as a geometric model and comparing the relative "goodness" of candidate models measured by the geometric AIC.