How Much Does Color Information Help Optical Flow Computation?*This work was in part supported by the Ministry of Education, Culture, Sports, Science and Technology, Japan under a Grant in Aid for Scientific Research C (2) (No.16500099).

Authors:
Naoya Ohta;Satoe Nishizawa
Affiliations:
The author is with the Department of Computer Science, Gunma University, Kiryu-shi, 376--8515 Japan. E-mail: ohta@cs.gunma-u.ac.jp,;The author is with NTT Data Corporation, Tokyo, 135--6033 Japan.
Venue:
IEICE - Transactions on Information and Systems
Year:
2006

Citing 0
Cited 3

Optical flow using color information: preliminary results

Proceedings of the 2008 ACM symposium on Applied computing
SETh system spatio-temporal object tracking using combined color and motion features

ROCOM'09 Proceedings of the 9th WSEAS international conference on Robotics, control and manufacturing technology
A color neuromorphic approach for motion estimation

WMVC'09 Proceedings of the 2009 international conference on Motion and video computing

Quantified Score

Hi-index	0.00

Visualization

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.