GPU Accelerated Likelihoods for Stereo-Based Articulated Tracking
Abstract
For many years articulated tracking has been an active research topic in the computer vision community. While working solutions have been suggested, computational time is still problematic. We present a GPU implementation of a ray-casting based likelihood model that is orders of magnitude faster than a traditional CPU implementation. We explain the non-intuitive steps required to attain an optimized GPU implementation, where the dominant part is to hide the memory latency effectively. Benchmarks show that computations which previously required several minutes, are now performed in few seconds.
Cite
Text
Friborg et al. "GPU Accelerated Likelihoods for Stereo-Based Articulated Tracking." European Conference on Computer Vision Workshops, 2010. doi:10.1007/978-3-642-35740-4_28Markdown
[Friborg et al. "GPU Accelerated Likelihoods for Stereo-Based Articulated Tracking." European Conference on Computer Vision Workshops, 2010.](https://mlanthology.org/eccvw/2010/friborg2010eccvw-gpu/) doi:10.1007/978-3-642-35740-4_28BibTeX
@inproceedings{friborg2010eccvw-gpu,
title = {{GPU Accelerated Likelihoods for Stereo-Based Articulated Tracking}},
author = {Friborg, Rune Møllegaard and Hauberg, Søren and Erleben, Kenny},
booktitle = {European Conference on Computer Vision Workshops},
year = {2010},
pages = {359-371},
doi = {10.1007/978-3-642-35740-4_28},
url = {https://mlanthology.org/eccvw/2010/friborg2010eccvw-gpu/}
}