Accurate human detection by appearance and motion

Shaopeng Tang, Satoshi Goto

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, a human detection method is developed. An appearance based detector and a motion based detector are proposed respectively. A multi scale block histogram of template feature (MB-HOT) is used to detect human by the appearance. It integrates the gray value information and the gradient value information, and represents the relationship of three blocks. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). A motion based feature is also proposed to capture the relative motion of human body. This feature is calculated in optical flow domain and experimental result in our dataset shows that this feature outperforms other motion based features. The detection responses obtained by two features are combined to reduce the false detection. Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time applications.

Original languageEnglish
Pages (from-to)2728-2736
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE93-D
Issue number10
DOIs
Publication statusPublished - 2010 Oct

Fingerprint

Detectors
Optical flows
Chemical reactions
Experiments

Keywords

  • Graphics process unit
  • Human detection
  • Multi scale block histogram of template

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

Accurate human detection by appearance and motion. / Tang, Shaopeng; Goto, Satoshi.

In: IEICE Transactions on Information and Systems, Vol. E93-D, No. 10, 10.2010, p. 2728-2736.

Research output: Contribution to journalArticle

Tang, Shaopeng ; Goto, Satoshi. / Accurate human detection by appearance and motion. In: IEICE Transactions on Information and Systems. 2010 ; Vol. E93-D, No. 10. pp. 2728-2736.
@article{8726061dfbe847b288a15546ae8d4d8c,
title = "Accurate human detection by appearance and motion",
abstract = "In this paper, a human detection method is developed. An appearance based detector and a motion based detector are proposed respectively. A multi scale block histogram of template feature (MB-HOT) is used to detect human by the appearance. It integrates the gray value information and the gradient value information, and represents the relationship of three blocks. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). A motion based feature is also proposed to capture the relative motion of human body. This feature is calculated in optical flow domain and experimental result in our dataset shows that this feature outperforms other motion based features. The detection responses obtained by two features are combined to reduce the false detection. Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time applications.",
keywords = "Graphics process unit, Human detection, Multi scale block histogram of template",
author = "Shaopeng Tang and Satoshi Goto",
year = "2010",
month = "10",
doi = "10.1587/transinf.E93.D.2728",
language = "English",
volume = "E93-D",
pages = "2728--2736",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "10",

}

TY - JOUR

T1 - Accurate human detection by appearance and motion

AU - Tang, Shaopeng

AU - Goto, Satoshi

PY - 2010/10

Y1 - 2010/10

N2 - In this paper, a human detection method is developed. An appearance based detector and a motion based detector are proposed respectively. A multi scale block histogram of template feature (MB-HOT) is used to detect human by the appearance. It integrates the gray value information and the gradient value information, and represents the relationship of three blocks. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). A motion based feature is also proposed to capture the relative motion of human body. This feature is calculated in optical flow domain and experimental result in our dataset shows that this feature outperforms other motion based features. The detection responses obtained by two features are combined to reduce the false detection. Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time applications.

AB - In this paper, a human detection method is developed. An appearance based detector and a motion based detector are proposed respectively. A multi scale block histogram of template feature (MB-HOT) is used to detect human by the appearance. It integrates the gray value information and the gradient value information, and represents the relationship of three blocks. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). A motion based feature is also proposed to capture the relative motion of human body. This feature is calculated in optical flow domain and experimental result in our dataset shows that this feature outperforms other motion based features. The detection responses obtained by two features are combined to reduce the false detection. Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time applications.

KW - Graphics process unit

KW - Human detection

KW - Multi scale block histogram of template

UR - http://www.scopus.com/inward/record.url?scp=77957846997&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957846997&partnerID=8YFLogxK

U2 - 10.1587/transinf.E93.D.2728

DO - 10.1587/transinf.E93.D.2728

M3 - Article

VL - E93-D

SP - 2728

EP - 2736

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 10

ER -