How Much Does Color Information Help Optical Flow Computation?

Naoya OHTA  Satoe NISHIZAWA 

Publication
IEICE TRANSACTIONS on Information and Systems  Vol.E89-D  No.5  pp.1759-1762
Publication Date: 2006/05/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
Keyword: 
color image,  RGB image,  optical flow,  image gradient, 

Full Text: PDF(406KB)

Summary: 
Optical flow is usually computed only on the basis of intensity information of images. Therefore, if we use color information in addition to the intensity, it is expected that more accurate optical flow can be computed. However, this intuition will be correct only when the following conditions are satisfied. First, the images should contain rich color variations. Moreover, it is also required that the image gradient of each color band differs in its direction. In this report, we empirically examined the difference of gradient directions on each band using 500 images, and evaluated quantitatively the advantage of using color information for optical flow computation.