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.

References

  1. Amit, Y. and Geman, D. (1997). Shape quantization and recognition with randomized trees. Neural Computation, 9(7):1545-1588.
  2. Bergstra, J., Bardenet, R., Bengio, Y., Kégl, B., et al. (2011). Algorithms for hyper-parameter optimization. In Neural Information Processing Systems (NIPS).
  3. Breiman, L. (2001). Random forests. Machine Learning, 45(1):5-32.
  4. Couprie, C., Farabet, C., Najman, L., and LeCun, Y. (2013). Indoor semantic segmentation using depth information. The Computing Resource Repository (CoRR) abs/1301.3572.
  5. Hermans, A., Floros, G., and Leibe, B. (2014). Dense 3d semantic mapping of indoor scenes from rgb-d images. In Int. Conf. on Robotics and Automation (ICRA), Hong Kong. IEEE.
  6. Ho, T. (1995). Random decision forests. In Int. Conf. on Document Analysis and Recognition (ICDAR), volume 1, pages 278-282. IEEE.
  7. Lepetit, V. and Fua, P. (2006). Keypoint recognition using randomized trees. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 28(9):1465-1479.
  8. Lepetit, V., Lagger, P., and Fua, P. (2005). Randomized trees for real-time keypoint recognition. In Computer Vision and Pattern Recognition (CVPR), Conf. on, volume 2, pages 775-781.
  9. Liao, Y., Rubinsteyn, A., Power, R., and Li, J. (2013). Learning random forests on the gpu. In NIPS Workshop on Big Learning: Advances in Algorithms and Data Management.
  10. Müller, A. C. and Behnke, S. (2014). Learning depthsensitive conditional random fields for semantic segmentation of rgb-d images. In Int. Conf. on Robotics and Automation (ICRA), Hong Kong. IEEE.
  11. Rodrigues, J., Kim, J., Furukawa, M., Xavier, J., Aguiar, P., and Kanade, T. (2012). 6D pose estimation of textureless shiny objects using random ferns for binpicking. In Intelligent Robots and Systems (IROS), Int. Conf. on, pages 3334-3341. IEEE.
  12. Sharp, T. (2008). Implementing decision trees and forests on a GPU. In Europ. Conf. on Computer Vision (ECCV), pages 595-608.
  13. Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., and Blake, A. (2011). Realtime human pose recognition in parts from single depth images. In Computer Vision and Pattern Recognition (CVPR), Conf. on, pages 1297-1304.
  14. Shotton, J., Johnson, M., and Cipolla, R. (2008). Semantic texton forests for image categorization and segmentation. In Computer Vision and Pattern Recognition (CVPR), Conf. on.
  15. Silberman, N., Hoiem, D., Kohli, P., and Fergus, R. (2012). Indoor segmentation and support inference from RGBD images. In Europ. Conf. on Computer Vision (ECCV), pages 746-760.
  16. Slat, D. and Lapajne, M. (2010). Random Forests for CUDA GPUs. PhD thesis, Blekinge Institute of Technology.
  17. Stückler, J., Biresev, N., and Behnke, S. (2012). Semantic mapping using object-class segmentation of RGB-D images. In Intelligent Robots and Systems (IROS), Int. Conf. on, pages 3005-3010. IEEE.
  18. Stückler, J., Waldvogel, B., Schulz, H., and Behnke, S. (2013). Dense real-time mapping of object-class semantics from RGB-D video. Journal of Real-Time Image Processing.
  19. Van Essen, B., Macaraeg, C., Gokhale, M., and Prenger, R. (2012). Accelerating a random forest classifier: Multi-core, GP-GPU, or FPGA? In Int. Symp. on FieldProgrammable Custom Computing Machines (FCCM). IEEE.
  20. Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Computer Vision and Pattern Recognition (CVPR), Conf. on.
  21. Wehenkel, L. and Pavella, M. (1991). Decision trees and transient stability of electric power systems. Automatica, 27(1):115-134.
Download


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