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.
[1]
David J. Fleet,et al.
Performance of optical flow techniques
,
1994,
International Journal of Computer Vision.
[2]
Allan D. Jepson,et al.
Subspace methods for recovering rigid motion I: Algorithm and implementation
,
2004,
International Journal of Computer Vision.
[3]
Yushin Kim,et al.
Flight test results of automatic tilt control for small scaled tilt rotor aircraft
,
2008,
2008 International Conference on Control, Automation and Systems.
[4]
Jae Weon Choi,et al.
Distributed Target Tracking Algorithm in Underwater Wireless Sensor Networks
,
2008
.
[5]
Kim Jong-Hun,et al.
Vision-Based Indoor Object Tracking Using Mean-Shift Algorithm
,
2006
.