How Much Does Color Information Help Optical Flow Computation?

• OHTA Naoya

  Department of Computer Science, Gunma University

• NISHIZAWA Satoe

  NTT Data Corporation

Abstract

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.

Journal

• IEICE transactions on information and systems

  IEICE transactions on information and systems 89 (5), 1759-1762, 2006-05-01

  The Institute of Electronics, Information and Communication Engineers

Keywords

• color image
• RGB image
• optical flow
• image gradient

Details

• CRID: 1573668927372543744
• NII Article ID: 110007503089
• NII Book ID: AA10826272
• ISSN: 09168532
• Text Lang: en
• Data Source:
  • CiNii Articles