Real-time counting people in crowded areas by using local empirical templates and density ratios

Dao Huu Hung, Gee Sern Hsu, Sheng Luen Chung, Hideo Saito

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, a fast and automated method of counting pedestrians in crowded areas is proposed along with three contributions. We firstly propose Local Empirical Templates (LET), which are able to outline the foregrounds, typically made by single pedestrians in a scene. LET are extracted by clustering foregrounds of single pedestrians with similar features in silhouettes. This process is done automatically for unknown scenes. Secondly, comparing the size of group foreground made by a group of pedestrians to that of appropriate LET captured in the same image patch with the group foreground produces the density ratio. Because of the local scale normalization between sizes, the density ratio appears to have a bound closely related to the number of pedestrians who induce the group foreground. Finally, to extract the bounds of density ratios for groups of different number of pedestrians, we propose a 3D human models based simulation in which camera viewpoints and pedestrians' proximity are easily manipulated. We collect hundreds of typical occluded-people patterns with distinct degrees of human proximity and under a variety of camera viewpoints. Distributions of density ratios with respect to the number of pedestrians are built based on the computed density ratios of these patterns for extracting density ratio bounds. The simulation is performed in the offline learning phase to extract the bounds from the distributions, which are used to count pedestrians in online settings. We reveal that the bounds seem to be invariant to camera viewpoints and humans' proximity. The performance of our proposed method is evaluated with our collected videos and PETS 2009's datasets. For our collected videos with the resolution of 320×240, our method runs in real-time with good accuracy and frame rate of around 30 fps, and consumes a small amount of computing resources. For PETS 2009's datasets, our proposed method achieves competitive results with other methods tested on the same datasets [1], [2].

Original languageEnglish
Pages (from-to)1791-1803
Number of pages13
JournalIEICE Transactions on Information and Systems
VolumeE95-D
Issue number7
DOIs
Publication statusPublished - 2012 Jul

Fingerprint

Cameras

Keywords

  • Density ratio bounds
  • Local density ratios
  • Local empirical templates
  • People counting

ASJC Scopus subject areas

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

Cite this

Real-time counting people in crowded areas by using local empirical templates and density ratios. / Hung, Dao Huu; Hsu, Gee Sern; Chung, Sheng Luen; Saito, Hideo.

In: IEICE Transactions on Information and Systems, Vol. E95-D, No. 7, 07.2012, p. 1791-1803.

Research output: Contribution to journalArticle

@article{393a454cb1444dbe894047e86b5aeb3d,
title = "Real-time counting people in crowded areas by using local empirical templates and density ratios",
abstract = "In this paper, a fast and automated method of counting pedestrians in crowded areas is proposed along with three contributions. We firstly propose Local Empirical Templates (LET), which are able to outline the foregrounds, typically made by single pedestrians in a scene. LET are extracted by clustering foregrounds of single pedestrians with similar features in silhouettes. This process is done automatically for unknown scenes. Secondly, comparing the size of group foreground made by a group of pedestrians to that of appropriate LET captured in the same image patch with the group foreground produces the density ratio. Because of the local scale normalization between sizes, the density ratio appears to have a bound closely related to the number of pedestrians who induce the group foreground. Finally, to extract the bounds of density ratios for groups of different number of pedestrians, we propose a 3D human models based simulation in which camera viewpoints and pedestrians' proximity are easily manipulated. We collect hundreds of typical occluded-people patterns with distinct degrees of human proximity and under a variety of camera viewpoints. Distributions of density ratios with respect to the number of pedestrians are built based on the computed density ratios of these patterns for extracting density ratio bounds. The simulation is performed in the offline learning phase to extract the bounds from the distributions, which are used to count pedestrians in online settings. We reveal that the bounds seem to be invariant to camera viewpoints and humans' proximity. The performance of our proposed method is evaluated with our collected videos and PETS 2009's datasets. For our collected videos with the resolution of 320×240, our method runs in real-time with good accuracy and frame rate of around 30 fps, and consumes a small amount of computing resources. For PETS 2009's datasets, our proposed method achieves competitive results with other methods tested on the same datasets [1], [2].",
keywords = "Density ratio bounds, Local density ratios, Local empirical templates, People counting",
author = "Hung, {Dao Huu} and Hsu, {Gee Sern} and Chung, {Sheng Luen} and Hideo Saito",
year = "2012",
month = "7",
doi = "10.1587/transinf.E95.D.1791",
language = "English",
volume = "E95-D",
pages = "1791--1803",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "7",

}

TY - JOUR

T1 - Real-time counting people in crowded areas by using local empirical templates and density ratios

AU - Hung, Dao Huu

AU - Hsu, Gee Sern

AU - Chung, Sheng Luen

AU - Saito, Hideo

PY - 2012/7

Y1 - 2012/7

N2 - In this paper, a fast and automated method of counting pedestrians in crowded areas is proposed along with three contributions. We firstly propose Local Empirical Templates (LET), which are able to outline the foregrounds, typically made by single pedestrians in a scene. LET are extracted by clustering foregrounds of single pedestrians with similar features in silhouettes. This process is done automatically for unknown scenes. Secondly, comparing the size of group foreground made by a group of pedestrians to that of appropriate LET captured in the same image patch with the group foreground produces the density ratio. Because of the local scale normalization between sizes, the density ratio appears to have a bound closely related to the number of pedestrians who induce the group foreground. Finally, to extract the bounds of density ratios for groups of different number of pedestrians, we propose a 3D human models based simulation in which camera viewpoints and pedestrians' proximity are easily manipulated. We collect hundreds of typical occluded-people patterns with distinct degrees of human proximity and under a variety of camera viewpoints. Distributions of density ratios with respect to the number of pedestrians are built based on the computed density ratios of these patterns for extracting density ratio bounds. The simulation is performed in the offline learning phase to extract the bounds from the distributions, which are used to count pedestrians in online settings. We reveal that the bounds seem to be invariant to camera viewpoints and humans' proximity. The performance of our proposed method is evaluated with our collected videos and PETS 2009's datasets. For our collected videos with the resolution of 320×240, our method runs in real-time with good accuracy and frame rate of around 30 fps, and consumes a small amount of computing resources. For PETS 2009's datasets, our proposed method achieves competitive results with other methods tested on the same datasets [1], [2].

AB - In this paper, a fast and automated method of counting pedestrians in crowded areas is proposed along with three contributions. We firstly propose Local Empirical Templates (LET), which are able to outline the foregrounds, typically made by single pedestrians in a scene. LET are extracted by clustering foregrounds of single pedestrians with similar features in silhouettes. This process is done automatically for unknown scenes. Secondly, comparing the size of group foreground made by a group of pedestrians to that of appropriate LET captured in the same image patch with the group foreground produces the density ratio. Because of the local scale normalization between sizes, the density ratio appears to have a bound closely related to the number of pedestrians who induce the group foreground. Finally, to extract the bounds of density ratios for groups of different number of pedestrians, we propose a 3D human models based simulation in which camera viewpoints and pedestrians' proximity are easily manipulated. We collect hundreds of typical occluded-people patterns with distinct degrees of human proximity and under a variety of camera viewpoints. Distributions of density ratios with respect to the number of pedestrians are built based on the computed density ratios of these patterns for extracting density ratio bounds. The simulation is performed in the offline learning phase to extract the bounds from the distributions, which are used to count pedestrians in online settings. We reveal that the bounds seem to be invariant to camera viewpoints and humans' proximity. The performance of our proposed method is evaluated with our collected videos and PETS 2009's datasets. For our collected videos with the resolution of 320×240, our method runs in real-time with good accuracy and frame rate of around 30 fps, and consumes a small amount of computing resources. For PETS 2009's datasets, our proposed method achieves competitive results with other methods tested on the same datasets [1], [2].

KW - Density ratio bounds

KW - Local density ratios

KW - Local empirical templates

KW - People counting

UR - http://www.scopus.com/inward/record.url?scp=84863436267&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863436267&partnerID=8YFLogxK

U2 - 10.1587/transinf.E95.D.1791

DO - 10.1587/transinf.E95.D.1791

M3 - Article

AN - SCOPUS:84863436267

VL - E95-D

SP - 1791

EP - 1803

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 7

ER -