Detail publikace

GP-GPU Implementation of the "Local Rank Differences" Image Feature

HEROUT, A. JOŠTH, R. ZEMČÍK, P. HRADIŠ, M.

Originální název

GP-GPU Implementation of the "Local Rank Differences" Image Feature

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

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 Di erences 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 alternative approaches, suggests several notes on practical usage of LRD and proposes directions for future work.

Klíčová slova

pattern recognition, adaptive boosting, AdaBoost, WaldBoost, image features, LRD, Local Rank Differences, hardware acceleration

Autoři

HEROUT, A.; JOŠTH, R.; ZEMČÍK, P.; HRADIŠ, M.

Rok RIV

2008

Vydáno

12. 11. 2008

Nakladatel

Springer Verlag

Místo

Heidelberg

ISBN

978-3-642-02344-6

Kniha

Proceedings of International Conference on Computer Vision and Graphics 2008

Edice

Lecture Notes in Computer Science

Strany od

1

Strany do

11

Strany počet

11

URL

BibTex

@inproceedings{BUT29556,
  author="Adam {Herout} and Radovan {Jošth} and Pavel {Zemčík} and Michal {Hradiš}",
  title="GP-GPU Implementation of the {"}Local Rank Differences{"} Image Feature",
  booktitle="Proceedings of International Conference on Computer Vision and Graphics 2008",
  year="2008",
  series="Lecture Notes in Computer Science",
  pages="1--11",
  publisher="Springer Verlag",
  address="Heidelberg",
  isbn="978-3-642-02344-6",
  url="http://www.fit.vutbr.cz/research/groups/graph/publi/2008/2008-Herout-ICCVG-LRDonCUDA.pdf"
}