Vision-based crowd pedestrian detection

Shih Shinh Huang, Feng Chia Chang, You Chen Liu, Pei Yung Hsiao, Hong Fa Ho

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

Abstract

This paper proposes a crowd pedestrian detection based on monocular vision. To handle with the challenges faced in crowded scenes, such as occlusion, this study combines multiple cues to detect individuals in the observed image. Based on the assumptions that the human head is generally visible and background scene is stationary, all circular regions in the segmented foreground mask are firstly extracted by an algorithm called circle Hough transform (CHT). Each circle is then considered as the head candidate and further verified whether it is exactly an individual or a false one by combining multiple cues. Matching a candidate to a several constructed pedestrian templates is firstly applied for verification. Then, two proposed cues called head foreground contrast (HFC) and block color relation (BCR) are incorporated for further verification. In the experiment, three videos are used to validate the proposed method and the results show that the proposed one lowers the false positives at the expense of little detection rate.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Digital Signal Processing, DSP 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages878-881
Number of pages4
ISBN (Electronic)9781479980581, 9781479980581
DOIs
Publication statusPublished - 2015 Sep 9
EventIEEE International Conference on Digital Signal Processing, DSP 2015 - Singapore, Singapore
Duration: 2015 Jul 212015 Jul 24

Publication series

NameInternational Conference on Digital Signal Processing, DSP
Volume2015-September

Other

OtherIEEE International Conference on Digital Signal Processing, DSP 2015
CountrySingapore
CitySingapore
Period15/7/2115/7/24

Fingerprint

Hough transforms
Masks
Color
Experiments

Keywords

  • block color relation
  • circular Hough transform
  • crowd pedestrian detection
  • head foreground contrast

ASJC Scopus subject areas

  • Signal Processing

Cite this

Huang, S. S., Chang, F. C., Liu, Y. C., Hsiao, P. Y., & Ho, H. F. (2015). Vision-based crowd pedestrian detection. In 2015 IEEE International Conference on Digital Signal Processing, DSP 2015 (pp. 878-881). [7252002] (International Conference on Digital Signal Processing, DSP; Vol. 2015-September). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDSP.2015.7252002

Vision-based crowd pedestrian detection. / Huang, Shih Shinh; Chang, Feng Chia; Liu, You Chen; Hsiao, Pei Yung; Ho, Hong Fa.

2015 IEEE International Conference on Digital Signal Processing, DSP 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 878-881 7252002 (International Conference on Digital Signal Processing, DSP; Vol. 2015-September).

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

Huang, SS, Chang, FC, Liu, YC, Hsiao, PY & Ho, HF 2015, Vision-based crowd pedestrian detection. in 2015 IEEE International Conference on Digital Signal Processing, DSP 2015., 7252002, International Conference on Digital Signal Processing, DSP, vol. 2015-September, Institute of Electrical and Electronics Engineers Inc., pp. 878-881, IEEE International Conference on Digital Signal Processing, DSP 2015, Singapore, Singapore, 15/7/21. https://doi.org/10.1109/ICDSP.2015.7252002
Huang SS, Chang FC, Liu YC, Hsiao PY, Ho HF. Vision-based crowd pedestrian detection. In 2015 IEEE International Conference on Digital Signal Processing, DSP 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 878-881. 7252002. (International Conference on Digital Signal Processing, DSP). https://doi.org/10.1109/ICDSP.2015.7252002
Huang, Shih Shinh ; Chang, Feng Chia ; Liu, You Chen ; Hsiao, Pei Yung ; Ho, Hong Fa. / Vision-based crowd pedestrian detection. 2015 IEEE International Conference on Digital Signal Processing, DSP 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 878-881 (International Conference on Digital Signal Processing, DSP).
@inproceedings{e5f06c5a3fe14ef6b3f716edf324ce0b,
title = "Vision-based crowd pedestrian detection",
abstract = "This paper proposes a crowd pedestrian detection based on monocular vision. To handle with the challenges faced in crowded scenes, such as occlusion, this study combines multiple cues to detect individuals in the observed image. Based on the assumptions that the human head is generally visible and background scene is stationary, all circular regions in the segmented foreground mask are firstly extracted by an algorithm called circle Hough transform (CHT). Each circle is then considered as the head candidate and further verified whether it is exactly an individual or a false one by combining multiple cues. Matching a candidate to a several constructed pedestrian templates is firstly applied for verification. Then, two proposed cues called head foreground contrast (HFC) and block color relation (BCR) are incorporated for further verification. In the experiment, three videos are used to validate the proposed method and the results show that the proposed one lowers the false positives at the expense of little detection rate.",
keywords = "block color relation, circular Hough transform, crowd pedestrian detection, head foreground contrast",
author = "Huang, {Shih Shinh} and Chang, {Feng Chia} and Liu, {You Chen} and Hsiao, {Pei Yung} and Ho, {Hong Fa}",
year = "2015",
month = "9",
day = "9",
doi = "10.1109/ICDSP.2015.7252002",
language = "English",
series = "International Conference on Digital Signal Processing, DSP",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "878--881",
booktitle = "2015 IEEE International Conference on Digital Signal Processing, DSP 2015",

}

TY - GEN

T1 - Vision-based crowd pedestrian detection

AU - Huang, Shih Shinh

AU - Chang, Feng Chia

AU - Liu, You Chen

AU - Hsiao, Pei Yung

AU - Ho, Hong Fa

PY - 2015/9/9

Y1 - 2015/9/9

N2 - This paper proposes a crowd pedestrian detection based on monocular vision. To handle with the challenges faced in crowded scenes, such as occlusion, this study combines multiple cues to detect individuals in the observed image. Based on the assumptions that the human head is generally visible and background scene is stationary, all circular regions in the segmented foreground mask are firstly extracted by an algorithm called circle Hough transform (CHT). Each circle is then considered as the head candidate and further verified whether it is exactly an individual or a false one by combining multiple cues. Matching a candidate to a several constructed pedestrian templates is firstly applied for verification. Then, two proposed cues called head foreground contrast (HFC) and block color relation (BCR) are incorporated for further verification. In the experiment, three videos are used to validate the proposed method and the results show that the proposed one lowers the false positives at the expense of little detection rate.

AB - This paper proposes a crowd pedestrian detection based on monocular vision. To handle with the challenges faced in crowded scenes, such as occlusion, this study combines multiple cues to detect individuals in the observed image. Based on the assumptions that the human head is generally visible and background scene is stationary, all circular regions in the segmented foreground mask are firstly extracted by an algorithm called circle Hough transform (CHT). Each circle is then considered as the head candidate and further verified whether it is exactly an individual or a false one by combining multiple cues. Matching a candidate to a several constructed pedestrian templates is firstly applied for verification. Then, two proposed cues called head foreground contrast (HFC) and block color relation (BCR) are incorporated for further verification. In the experiment, three videos are used to validate the proposed method and the results show that the proposed one lowers the false positives at the expense of little detection rate.

KW - block color relation

KW - circular Hough transform

KW - crowd pedestrian detection

KW - head foreground contrast

UR - http://www.scopus.com/inward/record.url?scp=84961384874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961384874&partnerID=8YFLogxK

U2 - 10.1109/ICDSP.2015.7252002

DO - 10.1109/ICDSP.2015.7252002

M3 - Conference contribution

AN - SCOPUS:84961384874

T3 - International Conference on Digital Signal Processing, DSP

SP - 878

EP - 881

BT - 2015 IEEE International Conference on Digital Signal Processing, DSP 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -