Image Object Tracking System Using Parallel Mean Shift Algorithm
Department of Computer Engineering, Hannam University, Daejon, Korea
The 2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV’12), 2012
@article{lee2012image,
title={Image Object Tracking System Using Parallel Mean Shift Algorithm},
author={Lee, S.G.},
year={2012}
}
We implement a real-time image object tracking system with PTZ cameras. In general, mean shift algorithm is efficient for real-time tracking because of its fast and stable performance. However, in the image tracking system for PTZ cameras, the speed is not satisfied. So in this paper, we use parallel mean shift algorithm based on the color image distribution of detected object. In this system, MATLAB v.2012a and Parallel Computing Toolbox are used for CUDA computing in GPUs. This system can be applied to a faster image surveillance system for continuous object tracking in a wider area.
August 31, 2012 by hgpu
