Analysis of Real-Time Stereo Vision Algorithms On GPU
Department of Computer Science, University of Auckland, New Zealand
International Conference on Image and Vision Computing New Zealand (IVCNZ), 2011
@article{kalarot2011analysis,
title={Analysis of Real-Time Stereo Vision Algorithms On GPU},
author={Kalarot, Ratheesh and Morris, John and Berry, David and Dunning, James},
booktitle={International Conference on Image and Vision Computing New Zealand (IVCNZ)},
year={2011}
}
Dozens of stereo correspondence algorithms whose matching performance has been measured are available, but the trade-off between speed and matching performance of viable realtime stereo has received much less attention. Here, we evaluate five correspondence algorithms(Symmetric Dynamic Programming Stereo, SemiGlobal Matching, simple block matching, Belief Propagation, and its constant space variant) on a GPU using CUDA and report running time and matching performance. Analysis of these results leads to several insights into the advantages and limitations of the five algorithms – all on a GPU – and SemiGlobal block matching on a conventional CPU.
January 4, 2012 by hgpu
