Efficient human detection in crowded environment based on motion and appearance information

Chuan Shen Hu, Min-Chun Hu, Wen Huang Cheng, Ja Ling Wu

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

Abstract

Detecting human in crowded environment is profitable but challenging in video surveillance. We propose an efficient human detection method by combining both motion and appearance clues. Moving pixels are first extracted by background subtraction, and then a filtering step is used to narrow the range for human template matching. We utilize integral images to fast generate shape information from edge maps of each frame and define the matching probability to be capable of detecting both full-body and partial-body. Representative human templates are constructed by sparse contours on the basis of the point distribution model (PDM). Moreover, linear regression analysis is also applied to adaptively adjust the template sizes. With the aid of the proposed foreground ratio filtering and the multi-sized template matching techniques, our method not only can efficiently detect human in a crowded environment but also largely enhance the detection accuracy.

Original languageEnglish
Title of host publicationICIMCS 2013 - Proceedings of the 5th International Conference on Internet Multimedia Computing and Service
Pages97-100
Number of pages4
DOIs
Publication statusPublished - 2013 Sep 16
Event5th International Conference on Internet Multimedia Computing and Service, ICIMCS 2013 - Huangshan, China
Duration: 2013 Aug 172013 Aug 19

Publication series

NameACM International Conference Proceeding Series

Other

Other5th International Conference on Internet Multimedia Computing and Service, ICIMCS 2013
CountryChina
CityHuangshan
Period13-08-1713-08-19

Fingerprint

Template matching
Linear regression
Regression analysis
Pixels

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Cite this

Hu, C. S., Hu, M-C., Cheng, W. H., & Wu, J. L. (2013). Efficient human detection in crowded environment based on motion and appearance information. In ICIMCS 2013 - Proceedings of the 5th International Conference on Internet Multimedia Computing and Service (pp. 97-100). (ACM International Conference Proceeding Series). https://doi.org/10.1145/2499788.2499837
Hu, Chuan Shen ; Hu, Min-Chun ; Cheng, Wen Huang ; Wu, Ja Ling. / Efficient human detection in crowded environment based on motion and appearance information. ICIMCS 2013 - Proceedings of the 5th International Conference on Internet Multimedia Computing and Service. 2013. pp. 97-100 (ACM International Conference Proceeding Series).
@inproceedings{f5c0a3bccd204af1a5a793c3b7001367,
title = "Efficient human detection in crowded environment based on motion and appearance information",
abstract = "Detecting human in crowded environment is profitable but challenging in video surveillance. We propose an efficient human detection method by combining both motion and appearance clues. Moving pixels are first extracted by background subtraction, and then a filtering step is used to narrow the range for human template matching. We utilize integral images to fast generate shape information from edge maps of each frame and define the matching probability to be capable of detecting both full-body and partial-body. Representative human templates are constructed by sparse contours on the basis of the point distribution model (PDM). Moreover, linear regression analysis is also applied to adaptively adjust the template sizes. With the aid of the proposed foreground ratio filtering and the multi-sized template matching techniques, our method not only can efficiently detect human in a crowded environment but also largely enhance the detection accuracy.",
author = "Hu, {Chuan Shen} and Min-Chun Hu and Cheng, {Wen Huang} and Wu, {Ja Ling}",
year = "2013",
month = "9",
day = "16",
doi = "10.1145/2499788.2499837",
language = "English",
isbn = "9781450322522",
series = "ACM International Conference Proceeding Series",
pages = "97--100",
booktitle = "ICIMCS 2013 - Proceedings of the 5th International Conference on Internet Multimedia Computing and Service",

}

Hu, CS, Hu, M-C, Cheng, WH & Wu, JL 2013, Efficient human detection in crowded environment based on motion and appearance information. in ICIMCS 2013 - Proceedings of the 5th International Conference on Internet Multimedia Computing and Service. ACM International Conference Proceeding Series, pp. 97-100, 5th International Conference on Internet Multimedia Computing and Service, ICIMCS 2013, Huangshan, China, 13-08-17. https://doi.org/10.1145/2499788.2499837

Efficient human detection in crowded environment based on motion and appearance information. / Hu, Chuan Shen; Hu, Min-Chun; Cheng, Wen Huang; Wu, Ja Ling.

ICIMCS 2013 - Proceedings of the 5th International Conference on Internet Multimedia Computing and Service. 2013. p. 97-100 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Efficient human detection in crowded environment based on motion and appearance information

AU - Hu, Chuan Shen

AU - Hu, Min-Chun

AU - Cheng, Wen Huang

AU - Wu, Ja Ling

PY - 2013/9/16

Y1 - 2013/9/16

N2 - Detecting human in crowded environment is profitable but challenging in video surveillance. We propose an efficient human detection method by combining both motion and appearance clues. Moving pixels are first extracted by background subtraction, and then a filtering step is used to narrow the range for human template matching. We utilize integral images to fast generate shape information from edge maps of each frame and define the matching probability to be capable of detecting both full-body and partial-body. Representative human templates are constructed by sparse contours on the basis of the point distribution model (PDM). Moreover, linear regression analysis is also applied to adaptively adjust the template sizes. With the aid of the proposed foreground ratio filtering and the multi-sized template matching techniques, our method not only can efficiently detect human in a crowded environment but also largely enhance the detection accuracy.

AB - Detecting human in crowded environment is profitable but challenging in video surveillance. We propose an efficient human detection method by combining both motion and appearance clues. Moving pixels are first extracted by background subtraction, and then a filtering step is used to narrow the range for human template matching. We utilize integral images to fast generate shape information from edge maps of each frame and define the matching probability to be capable of detecting both full-body and partial-body. Representative human templates are constructed by sparse contours on the basis of the point distribution model (PDM). Moreover, linear regression analysis is also applied to adaptively adjust the template sizes. With the aid of the proposed foreground ratio filtering and the multi-sized template matching techniques, our method not only can efficiently detect human in a crowded environment but also largely enhance the detection accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84883716232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883716232&partnerID=8YFLogxK

U2 - 10.1145/2499788.2499837

DO - 10.1145/2499788.2499837

M3 - Conference contribution

SN - 9781450322522

T3 - ACM International Conference Proceeding Series

SP - 97

EP - 100

BT - ICIMCS 2013 - Proceedings of the 5th International Conference on Internet Multimedia Computing and Service

ER -

Hu CS, Hu M-C, Cheng WH, Wu JL. Efficient human detection in crowded environment based on motion and appearance information. In ICIMCS 2013 - Proceedings of the 5th International Conference on Internet Multimedia Computing and Service. 2013. p. 97-100. (ACM International Conference Proceeding Series). https://doi.org/10.1145/2499788.2499837