Abstract
A currently popular trend in object detection and pattern recognition is usage of statistical classifiers, namely AdaBoost and its modifications. The speed performance of these classifiers largely depends on the low level image features they are using: both on the amount of information the feature provides and the processor time of its evaluation. Local Rank Differences is an image feature that is alternative to commonly used haar wavelets. It is suitable for implementation in programmable (FPGA) or specialized (ASIC) hardware, but -as this paper shows -it performs very well on graphics hardware (GPU) used in general purpose manner (GPGPU, namely CUDA in this case) as well. The paper discusses the LRD features and their properties, describes an experimental implementation of the LRD in graphics hardware using CUDA, presents its empirical performance measures compared to alter native approaches, suggests several notes on practical usage of LRD and proposes directions for future work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR (2001)
Sochman, J., Matas, J.: Learning A Fast Emulator of a Binary Decision Process. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds.) ACCV 2007, Part II. LNCS, vol. 4844, pp. 236–245. Springer, Heidelberg (2007)
Sochman, J., Matas, J.: WaldBoost -Learning for Time Constrained Sequential Detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 2 (2005)
General-Purpose Computation on GPUs (2008-07), http://www.gpgpu.org
Sinha, S.N., Frahm, J.M., Pollefeys, M., Genc, Y.: GPU-based Video Feature Tracking And Matching, Technical Report TR 06-012, Department of Computer Science, UNC Chapel Hill (May 2006)
Michel, P., et al.: GPU-accelerated Real-Time 3D Tracking for Humanoid Locomotion and Stair Climbing. In: Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems (2007)
Lienhart, R., Maydt, J.: An extended set of Haar-like features for rapid object detection. In: ICIP 2002, pp. I:900–I:903 (2002)
Ojala, T., Pietikäinen, M., Mäenpää, T.: Gray scale and rotation invariant texture classification with local binary patterns. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 404–420. Springer, Heidelberg (2000)
Zemcik, P., Hradis, M., Herout, A.: Local Rank Differences -Novel Features for Image Processing. In: Proceedings of SCCG, Budmerice, SK, pp. 1–12 (2007)
CUDA (2008-07), http://www.nvidia.com/cuda
Polok, L., Herout, A., Zemcik, P., Hradis, M., Juranek, R., Josth, R.: Local Rank Differences Image Feature Implemented on GPU. In: Blanc-Talon, J., Bourennane, S., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2008. LNCS, vol. 5259. Springer, Heidelberg (2008)
Schapire, R., Singer, Y.: Improved boosting algorithms using confidence-rated predictions. Machine Learning 37(3), 297–336 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Herout, A., Josth, R., Zemcik, P., Hradis, M. (2009). GP-GPU Implementation of the “Local Rank Differences” Image Feature. In: Bolc, L., Kulikowski, J.L., Wojciechowski, K. (eds) Computer Vision and Graphics. ICCVG 2008. Lecture Notes in Computer Science, vol 5337. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02345-3_37
Download citation
DOI: https://doi.org/10.1007/978-3-642-02345-3_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02344-6
Online ISBN: 978-3-642-02345-3
eBook Packages: Computer ScienceComputer Science (R0)