Enhancing real-time human detection based on histograms of oriented gradients

Marco Pedersoli; Jordi Gonzàlez; Bhaskar Chakraborty; Juan J. Villanueva

doi:10.1007/978-3-540-75175-5_91

Enhancing real-time human detection based on histograms of oriented gradients

Marco Pedersoli, Jordi Gonzàlez, Bhaskar Chakraborty, Juan J. Villanueva

Department of Computer Science

Research output: Contribution to journal › Article › Research › peer-review

3 Citations (Scopus)

Abstract

In this paper we propose a human detection framework based on an enhanced version of Histogram of Oriented Gradients (HOG) features. These feature descriptors are computed with the help of a precalculated histogram of square-blocks. This novel method outperforms the integral of oriented histograms allowing the calculation of a single feature four times faster. Using Adaboost for HOG feature selection and Support Vector Machine as weak classifier, we build up a real-time human classifier with an excellent detection rate. © 2007 Springer-Verlag Berlin Heidelberg.

Original language	English
Pages (from-to)	739-746
Journal	Advances in Soft Computing
Volume	45
DOIs	https://doi.org/10.1007/978-3-540-75175-5_91
Publication status	Published - 1 Dec 2007

Access to Document

10.1007/978-3-540-75175-5_91

Fingerprint Dive into the research topics of 'Enhancing real-time human detection based on histograms of oriented gradients'. Together they form a unique fingerprint.

Cite this

@article{e81132abb6a54a8f89ff78fa6181f96c,

title = "Enhancing real-time human detection based on histograms of oriented gradients",

abstract = "In this paper we propose a human detection framework based on an enhanced version of Histogram of Oriented Gradients (HOG) features. These feature descriptors are computed with the help of a precalculated histogram of square-blocks. This novel method outperforms the integral of oriented histograms allowing the calculation of a single feature four times faster. Using Adaboost for HOG feature selection and Support Vector Machine as weak classifier, we build up a real-time human classifier with an excellent detection rate. {\textcopyright} 2007 Springer-Verlag Berlin Heidelberg.",

author = "Marco Pedersoli and Jordi Gonz{\`a}lez and Bhaskar Chakraborty and Villanueva, {Juan J.}",

year = "2007",

month = dec,

day = "1",

doi = "10.1007/978-3-540-75175-5_91",

language = "English",

volume = "45",

pages = "739--746",

}

TY - JOUR

T1 - Enhancing real-time human detection based on histograms of oriented gradients

AU - Pedersoli, Marco

AU - Gonzàlez, Jordi

AU - Chakraborty, Bhaskar

AU - Villanueva, Juan J.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper we propose a human detection framework based on an enhanced version of Histogram of Oriented Gradients (HOG) features. These feature descriptors are computed with the help of a precalculated histogram of square-blocks. This novel method outperforms the integral of oriented histograms allowing the calculation of a single feature four times faster. Using Adaboost for HOG feature selection and Support Vector Machine as weak classifier, we build up a real-time human classifier with an excellent detection rate. © 2007 Springer-Verlag Berlin Heidelberg.

AB - In this paper we propose a human detection framework based on an enhanced version of Histogram of Oriented Gradients (HOG) features. These feature descriptors are computed with the help of a precalculated histogram of square-blocks. This novel method outperforms the integral of oriented histograms allowing the calculation of a single feature four times faster. Using Adaboost for HOG feature selection and Support Vector Machine as weak classifier, we build up a real-time human classifier with an excellent detection rate. © 2007 Springer-Verlag Berlin Heidelberg.

U2 - 10.1007/978-3-540-75175-5_91

DO - 10.1007/978-3-540-75175-5_91

M3 - Article

VL - 45

SP - 739

EP - 746

ER -