Publication detail

Low-Level Image Features for Real-Time Object Detection

HEROUT, A. ZEMČÍK, P. HRADIŠ, M. JURÁNEK, R. HAVEL, J. JOŠTH, R. ŽÁDNÍK, M.

Original Title

Low-Level Image Features for Real-Time Object Detection

English Title

Low-Level Image Features for Real-Time Object Detection

Type

book chapter

Language

en

Original Abstract

The main aim of the chapter is to provide information about the Local Rank Patterns image feature: Its background, mathematical definition, evaluation of its performance and notes on its implementation and use in object detectors. Implementations on the MMX, SSE, FPGA (programmable hardware), GPU (Cg) and CUDA platforms are described and experimentally evaluated. The performance of the image feature is evaluated within the WaldBoost classifier on the task of face detection, and it is compared to the commonly used Haar wavelets, local binary patterns and other low level features. The Local Rank Patterns feature seems suitable for hardware acceleration both directly by programmable or hard-wired hardware, but also by processors supporting different sets of the SIMD instructions. It is shown, that the LRP feature is an important alternative for construction of fast object detectors.

English abstract

The main aim of the chapter is to provide information about the Local Rank Patterns image feature: Its background, mathematical definition, evaluation of its performance and notes on its implementation and use in object detectors. Implementations on the MMX, SSE, FPGA (programmable hardware), GPU (Cg) and CUDA platforms are described and experimentally evaluated. The performance of the image feature is evaluated within the WaldBoost classifier on the task of face detection, and it is compared to the commonly used Haar wavelets, local binary patterns and other low level features. The Local Rank Patterns feature seems suitable for hardware acceleration both directly by programmable or hard-wired hardware, but also by processors supporting different sets of the SIMD instructions. It is shown, that the LRP feature is an important alternative for construction of fast object detectors.

Keywords

real-time object detection, image features, Local Rank Patterns

RIV year

2010

Released

17.02.2010

Publisher

IN-TECH Education and Publishing

Location

Vienna

ISBN

978-953-7619-90-9

Book

Pattern Recognition, Recent Advances

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

111

Pages to

136

Pages count

26

Documents

BibTex


@inbook{BUT55167,
  author="Adam {Herout} and Pavel {Zemčík} and Michal {Hradiš} and Roman {Juránek} and Jiří {Havel} and Radovan {Jošth} and Martin {Žádník}",
  title="Low-Level Image Features for Real-Time Object Detection",
  annote="The main aim of the chapter is to provide information about the Local Rank
Patterns image feature: Its background, mathematical definition, evaluation of
its performance and notes on its implementation and use in object detectors.
Implementations on the MMX, SSE, FPGA (programmable hardware), GPU (Cg) and CUDA
platforms are described and experimentally evaluated. The performance of the
image feature is evaluated within the WaldBoost classifier on the task of face
detection, and it is compared to the commonly used Haar wavelets, local binary
patterns and other low level features. The Local Rank Patterns feature seems
suitable for hardware acceleration both directly by programmable or hard-wired
hardware, but also by processors supporting different sets of the SIMD
instructions. It is shown, that the LRP feature is an important alternative for
construction of fast object detectors.",
  address="IN-TECH Education and Publishing",
  booktitle="Pattern Recognition, Recent Advances",
  chapter="55167",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IN-TECH Education and Publishing",
  year="2010",
  month="february",
  pages="111--136",
  publisher="IN-TECH Education and Publishing",
  type="book chapter"
}