Detail výsledku

Implementing the Local Binary Patterns with SIMD Instructions of CPU

HEROUT, A.; JURÁNEK, R.; ZEMČÍK, P. Implementing the Local Binary Patterns with SIMD Instructions of CPU. Proceedings of WSCG 2010. Plzeň: University of West Bohemia in Pilsen, 2010. p. 39-42. ISBN: 978-80-86943-86-2.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Herout Adam, prof. Ing., Ph.D., UPGM (FIT)
Juránek Roman, Ing., Ph.D., UPGM (FIT)
Zemčík Pavel, prof. Dr. Ing., dr. h. c., UAMT (FEKT), UPGM (FIT)
Abstrakt

Usage of statistical classifiers, namely AdaBoost and its modifications, is very common in object detection and pattern recognition. Performance of such classifiers strongly depends on low level features they use. This paper presents an experimental implementation of the Local Binary Patterns (LBP) that uses SIMD instructions for acceleration. The experiments shows that the proposed implementation is about six times faster than the plain C implementation (i.e. with no special optimizations) and superior to optimized implementations of features with similar descriptive power.

Klíčová slova

LBP, AdaBoost, Object Detection, Feature Extraction, SIMD, SSE, CUDA

Rok
2010
Strany
39–42
Sborník
Proceedings of WSCG 2010
Konference
Winter School of Computer Graphics 2010
ISBN
978-80-86943-86-2
Vydavatel
University of West Bohemia in Pilsen
Místo
Plzeň
BibTeX 
@inproceedings{BUT34653,
  author="Adam {Herout} and Roman {Juránek} and Pavel {Zemčík}",
  title="Implementing the Local Binary Patterns with SIMD Instructions of CPU",
  booktitle="Proceedings of WSCG 2010",
  year="2010",
  pages="39--42",
  publisher="University of West Bohemia in Pilsen",
  address="Plzeň",
  isbn="978-80-86943-86-2",
  url="https://www.fit.vut.cz/research/publication/9205/"
}
Soubory
Projekty
Centrum počítačové grafiky, MŠMT, Centra základního výzkumu, LC06008, zahájení: 2006-03-01, ukončení: 2011-12-31, ukončen
Výzkumné skupiny
Výzkumná skupina zpracování obrazu a videa (VZ VIDEO)
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Nahoru