CURFIL: Random Forests for Image Labeling on GPU

Hannes Schulz, Benedikt Waldvogel, Rasha Sheikh, Sven Behnke

2015

Abstract

Random forests are popular classifiers for computer vision tasks such as image labeling or object detection. Learning random forests on large datasets, however, is computationally demanding. Slow learning impedes model selection and scientific research on image features. We present an open-source implementation that significantly accelerates both random forest learning and prediction for image labeling of RGB-D and RGB images on GPU when compared to an optimized multi-core CPU implementation. We use the fast training to conduct hyper-parameter searches, which significantly improves on previous results on the NYU depth v2 dataset. Our prediction runs in real time at VGA resolution on a mobile GPU and has been used as data term in multiple applications.

Paper Citation

in Harvard Style

Schulz H., Waldvogel B., Sheikh R. and Behnke S. (2015). CURFIL: Random Forests for Image Labeling on GPU . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 156-164. DOI: 10.5220/0005316201560164

in Bibtex Style

@conference{visapp15,
author={Hannes Schulz and Benedikt Waldvogel and Rasha Sheikh and Sven Behnke},
title={CURFIL: Random Forests for Image Labeling on GPU},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={156-164},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005316201560164},
isbn={978-989-758-090-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - CURFIL: Random Forests for Image Labeling on GPU
SN - 978-989-758-090-1
AU - Schulz H.
AU - Waldvogel B.
AU - Sheikh R.
AU - Behnke S.
PY - 2015
SP - 156
EP - 164
DO - 10.5220/0005316201560164