Histogram of template for human detection

Shaopeng Tang, Satoshi Goto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

28 Citations (Scopus)

Abstract

In this paper, we propose a novel feature named histogram of template (HOT) for human detection in still images. For every pixel of an image, various templates are defined, each of which contains the pixel itself and two of its neighboring pixels. If the intensity and gradient values of the three pixels satisfy a pre-defined function, the central pixel is regarded to meet the corresponding template for this function. Histograms of pixels meeting various templates are calculated for a set of functions, and combined to be the feature for detection. Compared to the other features, the proposed feature takes intensity as well as the gradient information into consideration. Besides, it reflects the relationship between 3 pixels, instead of focusing on only one. Experiments for human detection are performed on INRIA dataset, which shows the proposed HOT feature is more discriminative than histogram of orientated gradient (HOG) feature, under the same training method.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages2186-2189
Number of pages4
DOIs
Publication statusPublished - 2010
Event2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Dallas, TX
Duration: 2010 Mar 142010 Mar 19

Other

Other2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
CityDallas, TX
Period10/3/1410/3/19

Fingerprint

Pixels
Experiments

Keywords

  • Feature extraction
  • Histogram of template
  • Human detection

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Tang, S., & Goto, S. (2010). Histogram of template for human detection. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 2186-2189). [5495685] https://doi.org/10.1109/ICASSP.2010.5495685

Histogram of template for human detection. / Tang, Shaopeng; Goto, Satoshi.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2010. p. 2186-2189 5495685.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tang, S & Goto, S 2010, Histogram of template for human detection. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 5495685, pp. 2186-2189, 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010, Dallas, TX, 10/3/14. https://doi.org/10.1109/ICASSP.2010.5495685
Tang S, Goto S. Histogram of template for human detection. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2010. p. 2186-2189. 5495685 https://doi.org/10.1109/ICASSP.2010.5495685
Tang, Shaopeng ; Goto, Satoshi. / Histogram of template for human detection. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2010. pp. 2186-2189
@inproceedings{37c7a51e5a72423497a6036f01c17387,
title = "Histogram of template for human detection",
abstract = "In this paper, we propose a novel feature named histogram of template (HOT) for human detection in still images. For every pixel of an image, various templates are defined, each of which contains the pixel itself and two of its neighboring pixels. If the intensity and gradient values of the three pixels satisfy a pre-defined function, the central pixel is regarded to meet the corresponding template for this function. Histograms of pixels meeting various templates are calculated for a set of functions, and combined to be the feature for detection. Compared to the other features, the proposed feature takes intensity as well as the gradient information into consideration. Besides, it reflects the relationship between 3 pixels, instead of focusing on only one. Experiments for human detection are performed on INRIA dataset, which shows the proposed HOT feature is more discriminative than histogram of orientated gradient (HOG) feature, under the same training method.",
keywords = "Feature extraction, Histogram of template, Human detection",
author = "Shaopeng Tang and Satoshi Goto",
year = "2010",
doi = "10.1109/ICASSP.2010.5495685",
language = "English",
isbn = "9781424442966",
pages = "2186--2189",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Histogram of template for human detection

AU - Tang, Shaopeng

AU - Goto, Satoshi

PY - 2010

Y1 - 2010

N2 - In this paper, we propose a novel feature named histogram of template (HOT) for human detection in still images. For every pixel of an image, various templates are defined, each of which contains the pixel itself and two of its neighboring pixels. If the intensity and gradient values of the three pixels satisfy a pre-defined function, the central pixel is regarded to meet the corresponding template for this function. Histograms of pixels meeting various templates are calculated for a set of functions, and combined to be the feature for detection. Compared to the other features, the proposed feature takes intensity as well as the gradient information into consideration. Besides, it reflects the relationship between 3 pixels, instead of focusing on only one. Experiments for human detection are performed on INRIA dataset, which shows the proposed HOT feature is more discriminative than histogram of orientated gradient (HOG) feature, under the same training method.

AB - In this paper, we propose a novel feature named histogram of template (HOT) for human detection in still images. For every pixel of an image, various templates are defined, each of which contains the pixel itself and two of its neighboring pixels. If the intensity and gradient values of the three pixels satisfy a pre-defined function, the central pixel is regarded to meet the corresponding template for this function. Histograms of pixels meeting various templates are calculated for a set of functions, and combined to be the feature for detection. Compared to the other features, the proposed feature takes intensity as well as the gradient information into consideration. Besides, it reflects the relationship between 3 pixels, instead of focusing on only one. Experiments for human detection are performed on INRIA dataset, which shows the proposed HOT feature is more discriminative than histogram of orientated gradient (HOG) feature, under the same training method.

KW - Feature extraction

KW - Histogram of template

KW - Human detection

UR - http://www.scopus.com/inward/record.url?scp=78049387080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78049387080&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2010.5495685

DO - 10.1109/ICASSP.2010.5495685

M3 - Conference contribution

AN - SCOPUS:78049387080

SN - 9781424442966

SP - 2186

EP - 2189

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -