By Topic

3D depth estimation for target region using optical flow and mean-shift algorithm

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Seon-Yeong ; Dept. of Aerosp. Eng., Pusan Nat. Univ., Busan ; Jong-Hun Kim ; Jeong-Ho Kim ; Dae-Woo Lee
more authors

Tracking in the image is important to get information in many difference sides. Also, we can get more useful information using only image. However, 2D image isnpsilat enough for getting more information. The purpose of this study is realization the 3D virtual target and surround environment models using 3D locate information. In the image, itpsilas hard to distinguish between target and surround. Mean-shift algorithm for target tracking sets ROI and indicates the target from surround. Subspace method and another method which uses optical flow and camera motion give 3D information. The same thing of both methods is that optical flow used for depth estimation. Subspace method uses residual function from least square method. In the other side, another method using region optical flow has formulas so easier to apply. This paper presents the first step of getting 3D locate information and also, paper includes comparing algorithms.

Published in:

Control, Automation and Systems, 2008. ICCAS 2008. International Conference on

Date of Conference:

14-17 Oct. 2008