Memory Efficient 3D Integral Volumes
Abstract
Integral image data structures are very useful in computer vision applications that involve machine learning approaches based on ensembles of weak learners. The weak learners often are simply several regional sums of intensities subtracted from each other. In this work we present a memory efficient integral volume data structure, that allows reduction of required RAM storage size in such a supervised learning framework using 3D training data. We evaluate our proposed data structure in terms of the tradeoff between computational effort and storage, and show an application for 3D object detection of liver CT data.
Cite
Text
Urschler et al. "Memory Efficient 3D Integral Volumes." IEEE/CVF International Conference on Computer Vision Workshops, 2013. doi:10.1109/ICCVW.2013.99Markdown
[Urschler et al. "Memory Efficient 3D Integral Volumes." IEEE/CVF International Conference on Computer Vision Workshops, 2013.](https://mlanthology.org/iccvw/2013/urschler2013iccvw-memory/) doi:10.1109/ICCVW.2013.99BibTeX
@inproceedings{urschler2013iccvw-memory,
title = {{Memory Efficient 3D Integral Volumes}},
author = {Urschler, Martin and Bornik, Alexander and Donoser, Michael},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2013},
pages = {722-729},
doi = {10.1109/ICCVW.2013.99},
url = {https://mlanthology.org/iccvw/2013/urschler2013iccvw-memory/}
}