Publication result detail

Real-time Algorithms of Object Detection using Classifiers

JURÁNEK, R.; HRADIŠ, M.; ZEMČÍK, P.

Original Title

Real-time Algorithms of Object Detection using Classifiers

English Title

Real-time Algorithms of Object Detection using Classifiers

Type

Chapter in a book

Original Abstract

Real-time objectdetection is currently expanding field of computer vision. One ofmost popular methods for the object detection is based onexploitation of statistical classifiers (namely those based onAdaBoost algorithm). This contribution presents methods foracceleration of object detection based on the AdaBoost. First itdescribes image pre-processing and the learning of classifiers.Finally, the contribution presents algorithmic accelerations of thedetection process and effective implementations of classification onvarious architectures - CPU/SSE, GPGPU and FPGA. Accelerateddetectors achieve high performance compared to state of the artsolutions and are suitable for real-time applications.

English abstract

Real-time objectdetection is currently expanding field of computer vision. One ofmost popular methods for the object detection is based onexploitation of statistical classifiers (namely those based onAdaBoost algorithm). This contribution presents methods foracceleration of object detection based on the AdaBoost. First itdescribes image pre-processing and the learning of classifiers.Finally, the contribution presents algorithmic accelerations of thedetection process and effective implementations of classification onvarious architectures - CPU/SSE, GPGPU and FPGA. Accelerateddetectors achieve high performance compared to state of the artsolutions and are suitable for real-time applications.

Keywords

WaldBoost, Object Detection, Classification Cost, EnMS, Neighborhood Suppression, Acceleration, GPU, SIMD, FPGA

Key words in English

WaldBoost, Object Detection, Classification Cost, EnMS, Neighborhood Suppression, Acceleration, GPU, SIMD, FPGA

Authors

JURÁNEK, R.; HRADIŠ, M.; ZEMČÍK, P.

RIV year

2013

Released

24.03.2012

Publisher

InTech - Open Access Publisher

Location

Rijeka

ISBN

9789535105107

Book

Real-Time System

Pages from

1

Pages to

22

Pages count

22

URL

http://www.intechopen.com/books/real-time-systems-architecture-scheduling-and-application

BibTex

@inbook{BUT91467,
  author="Roman {Juránek} and Michal {Hradiš} and Pavel {Zemčík}",
  title="Real-time Algorithms of Object Detection using Classifiers",
  booktitle="Real-Time System",
  year="2012",
  publisher="InTech - Open Access Publisher",
  address="Rijeka",
  pages="1--22",
  isbn="9789535105107",
  url="http://www.intechopen.com/books/real-time-systems-architecture-scheduling-and-application"
}