An automatic drowning detection surveillance system for challenging outdoor pool environments

How Lung Eng, Kar Ann Toh, Alvin H. Kam, Junxian Wang, Wei Yun Yau

Research output: Contribution to conferencePaper

41 Citations (Scopus)

Abstract

Automatically understanding events happening at a site is the ultimate goal of visual surveillance system. This paper investigates the challenges faced by automated surveillance systems operating in hostile conditions and demonstrates the developed algorithms via a system that detects water crises within highly dynamic aquatic environments. An efficient segmentation algorithm based on robust block-based background modeling and thresholding-with-hysteresis methodology enables swimmers to be reliably detected amid reflections, ripples, splashes and rapid lighting changes. Partial occlusions are resolved using a Markov Random Field framework that enhances the tracking capability of the system. Visual indicators of water crises are identified based on professional knowledge of water crises detection, based on which a set of swimmer descriptors has been defined. Through seamlessly fusing the extracted swimmer descriptors based on a novel functional link network, the system achieves promising results for water crises detection. The developed algorithms have been incorporated into a live system with robust performance for different hostile environments faced by an outdoor swimming pool.

Original languageEnglish
Pages532-539
Number of pages8
Publication statusPublished - 2003 Dec 2
EventProceedings: Ninth IEEE International Conference on Computer Vision - Nice, France
Duration: 2003 Oct 132003 Oct 16

Other

OtherProceedings: Ninth IEEE International Conference on Computer Vision
CountryFrance
CityNice
Period03/10/1303/10/16

Fingerprint

Water
Swimming pools
Hysteresis
Lighting

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Eng, H. L., Toh, K. A., Kam, A. H., Wang, J., & Yau, W. Y. (2003). An automatic drowning detection surveillance system for challenging outdoor pool environments. 532-539. Paper presented at Proceedings: Ninth IEEE International Conference on Computer Vision, Nice, France.
Eng, How Lung ; Toh, Kar Ann ; Kam, Alvin H. ; Wang, Junxian ; Yau, Wei Yun. / An automatic drowning detection surveillance system for challenging outdoor pool environments. Paper presented at Proceedings: Ninth IEEE International Conference on Computer Vision, Nice, France.8 p.
@conference{2046c203a41547e0be22892504db5b55,
title = "An automatic drowning detection surveillance system for challenging outdoor pool environments",
abstract = "Automatically understanding events happening at a site is the ultimate goal of visual surveillance system. This paper investigates the challenges faced by automated surveillance systems operating in hostile conditions and demonstrates the developed algorithms via a system that detects water crises within highly dynamic aquatic environments. An efficient segmentation algorithm based on robust block-based background modeling and thresholding-with-hysteresis methodology enables swimmers to be reliably detected amid reflections, ripples, splashes and rapid lighting changes. Partial occlusions are resolved using a Markov Random Field framework that enhances the tracking capability of the system. Visual indicators of water crises are identified based on professional knowledge of water crises detection, based on which a set of swimmer descriptors has been defined. Through seamlessly fusing the extracted swimmer descriptors based on a novel functional link network, the system achieves promising results for water crises detection. The developed algorithms have been incorporated into a live system with robust performance for different hostile environments faced by an outdoor swimming pool.",
author = "Eng, {How Lung} and Toh, {Kar Ann} and Kam, {Alvin H.} and Junxian Wang and Yau, {Wei Yun}",
year = "2003",
month = "12",
day = "2",
language = "English",
pages = "532--539",
note = "Proceedings: Ninth IEEE International Conference on Computer Vision ; Conference date: 13-10-2003 Through 16-10-2003",

}

Eng, HL, Toh, KA, Kam, AH, Wang, J & Yau, WY 2003, 'An automatic drowning detection surveillance system for challenging outdoor pool environments' Paper presented at Proceedings: Ninth IEEE International Conference on Computer Vision, Nice, France, 03/10/13 - 03/10/16, pp. 532-539.

An automatic drowning detection surveillance system for challenging outdoor pool environments. / Eng, How Lung; Toh, Kar Ann; Kam, Alvin H.; Wang, Junxian; Yau, Wei Yun.

2003. 532-539 Paper presented at Proceedings: Ninth IEEE International Conference on Computer Vision, Nice, France.

Research output: Contribution to conferencePaper

TY - CONF

T1 - An automatic drowning detection surveillance system for challenging outdoor pool environments

AU - Eng, How Lung

AU - Toh, Kar Ann

AU - Kam, Alvin H.

AU - Wang, Junxian

AU - Yau, Wei Yun

PY - 2003/12/2

Y1 - 2003/12/2

N2 - Automatically understanding events happening at a site is the ultimate goal of visual surveillance system. This paper investigates the challenges faced by automated surveillance systems operating in hostile conditions and demonstrates the developed algorithms via a system that detects water crises within highly dynamic aquatic environments. An efficient segmentation algorithm based on robust block-based background modeling and thresholding-with-hysteresis methodology enables swimmers to be reliably detected amid reflections, ripples, splashes and rapid lighting changes. Partial occlusions are resolved using a Markov Random Field framework that enhances the tracking capability of the system. Visual indicators of water crises are identified based on professional knowledge of water crises detection, based on which a set of swimmer descriptors has been defined. Through seamlessly fusing the extracted swimmer descriptors based on a novel functional link network, the system achieves promising results for water crises detection. The developed algorithms have been incorporated into a live system with robust performance for different hostile environments faced by an outdoor swimming pool.

AB - Automatically understanding events happening at a site is the ultimate goal of visual surveillance system. This paper investigates the challenges faced by automated surveillance systems operating in hostile conditions and demonstrates the developed algorithms via a system that detects water crises within highly dynamic aquatic environments. An efficient segmentation algorithm based on robust block-based background modeling and thresholding-with-hysteresis methodology enables swimmers to be reliably detected amid reflections, ripples, splashes and rapid lighting changes. Partial occlusions are resolved using a Markov Random Field framework that enhances the tracking capability of the system. Visual indicators of water crises are identified based on professional knowledge of water crises detection, based on which a set of swimmer descriptors has been defined. Through seamlessly fusing the extracted swimmer descriptors based on a novel functional link network, the system achieves promising results for water crises detection. The developed algorithms have been incorporated into a live system with robust performance for different hostile environments faced by an outdoor swimming pool.

UR - http://www.scopus.com/inward/record.url?scp=0344551860&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0344551860&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0344551860

SP - 532

EP - 539

ER -

Eng HL, Toh KA, Kam AH, Wang J, Yau WY. An automatic drowning detection surveillance system for challenging outdoor pool environments. 2003. Paper presented at Proceedings: Ninth IEEE International Conference on Computer Vision, Nice, France.