A parallel mapping of optical flow to Compute Unified Device Architecture for motion-based image segmentation
Department of Electrical and Computer Engineering, McMaster University, 1280 Main St. W., Hamilton, ON, Canada, L8S 4L8
16th IEEE International Conference on Image Processing (ICIP), 2009
@inproceedings{kuchnio2009parallel,
title={A parallel mapping of optical flowto Compute Unified Device Architecture for motion-based image segmentation},
author={Kuchnio, P. and Capson, D.W.},
booktitle={Image Processing (ICIP), 2009 16th IEEE International Conference on},
pages={2325–2328},
year={2009},
organization={IEEE}
}
A correlation-based optical flow algorithm using compute unified device architecture (CUDA) technology to achieve fast motion-based image segmentation is described. Using CUDA, a 240 processor GPU implementation of an optimized correlation-based optical flow algorithm allows segmentation to be achieved at high frame rates on high-resolution video sequences. Details of the mapping of the optical flow segmentation algorithm onto the CUDA architecture as well as performance results are given. The performance of the algorithm is further characterized as a function of the search and correlation window radii.
August 10, 2011 by hgpu
