Preventing Drowning Accidents Using Thermal Cameras

Søren Bonderup, Jonas Lundgaard Olsson, Morten Bojesen Bonderup, Thomas B. Moeslund

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

Every year approximately 372 000 people die from unintentional drowning, causing it to be a top-3 cause to unintentional injury [1]. In Denmark 25% of drownings happen at harbor areas [2]. To address this problem thermal cameras have been placed strategically at a harbor. Using computer vision techniques an automatic surveillance system for predicting and detecting drowning accidents has been implemented. First a person detector has been implemented using simple human characteristics. The person is tracked using a Kalman Filter. Using the tracker as a prior, a fall prediction is determined. A fall detector is implemented using a virtual trip-wire in combination with an optical flow algorithm making the system able to detect 100% of all falls and only yielding a 0.08 false positive rate hourly. The entire system has been developed using 155 h of real life thermal video, hereof 56 h are manually annotated.
Original languageEnglish
Title of host publicationAdvances in Visual Computing
EditorsGeorge Bebis, Richard Boyle, Bahram Parvin, Darco Koracin, Faith Porikili, Sandra Skaff, Alireza Entezari, Jianjuan Min, Daisuke Iwai, Amela Sadagic, Carlos Scheidegger, Tobias Isenberg
Number of pages12
PublisherSpringer
Publication date2016
Pages111-122
ISBN (Print)978-3-319-50831-3
ISBN (Electronic)978-3-319-50832-0
DOIs
Publication statusPublished - 2016
EventISVC16: 12th International Symposium on Visual Computing - Monte Carlo Resort & Casino, Las Vegas, United States
Duration: 12 Dec 201614 Dec 2016
http://www.isvc.net

Conference

ConferenceISVC16: 12th International Symposium on Visual Computing
LocationMonte Carlo Resort & Casino
CountryUnited States
CityLas Vegas
Period12/12/201614/12/2016
Internet address
SeriesLecture Notes in Computer Science
Volume10073
ISSN0302-9743

Fingerprint

Ports and harbors
Accidents
Cameras
Detectors
Heat problems
Optical flows
Kalman filters
Computer vision
Wire
Hot Temperature

Cite this

Bonderup, S., Olsson, J. L., Bonderup, M. B., & Moeslund, T. B. (2016). Preventing Drowning Accidents Using Thermal Cameras. In G. Bebis, R. Boyle, B. Parvin, D. Koracin, F. Porikili, S. Skaff, A. Entezari, J. Min, D. Iwai, A. Sadagic, C. Scheidegger, ... T. Isenberg (Eds.), Advances in Visual Computing (pp. 111-122). Springer. Lecture Notes in Computer Science, Vol.. 10073 https://doi.org/10.1007/978-3-319-50832-0_12
Bonderup, Søren ; Olsson, Jonas Lundgaard ; Bonderup, Morten Bojesen ; Moeslund, Thomas B. / Preventing Drowning Accidents Using Thermal Cameras. Advances in Visual Computing. editor / George Bebis ; Richard Boyle ; Bahram Parvin ; Darco Koracin ; Faith Porikili ; Sandra Skaff ; Alireza Entezari ; Jianjuan Min ; Daisuke Iwai ; Amela Sadagic ; Carlos Scheidegger ; Tobias Isenberg. Springer, 2016. pp. 111-122 (Lecture Notes in Computer Science, Vol. 10073).
@inproceedings{c21b09e44e934cef8f3b3b6d0e75d680,
title = "Preventing Drowning Accidents Using Thermal Cameras",
abstract = "Every year approximately 372 000 people die from unintentional drowning, causing it to be a top-3 cause to unintentional injury [1]. In Denmark 25{\%} of drownings happen at harbor areas [2]. To address this problem thermal cameras have been placed strategically at a harbor. Using computer vision techniques an automatic surveillance system for predicting and detecting drowning accidents has been implemented. First a person detector has been implemented using simple human characteristics. The person is tracked using a Kalman Filter. Using the tracker as a prior, a fall prediction is determined. A fall detector is implemented using a virtual trip-wire in combination with an optical flow algorithm making the system able to detect 100{\%} of all falls and only yielding a 0.08 false positive rate hourly. The entire system has been developed using 155 h of real life thermal video, hereof 56 h are manually annotated.",
author = "S{\o}ren Bonderup and Olsson, {Jonas Lundgaard} and Bonderup, {Morten Bojesen} and Moeslund, {Thomas B.}",
year = "2016",
doi = "10.1007/978-3-319-50832-0_12",
language = "English",
isbn = "978-3-319-50831-3",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "111--122",
editor = "George Bebis and Richard Boyle and Bahram Parvin and Darco Koracin and Faith Porikili and Sandra Skaff and Alireza Entezari and Jianjuan Min and Daisuke Iwai and Amela Sadagic and Carlos Scheidegger and Tobias Isenberg",
booktitle = "Advances in Visual Computing",
address = "Germany",

}

Bonderup, S, Olsson, JL, Bonderup, MB & Moeslund, TB 2016, Preventing Drowning Accidents Using Thermal Cameras. in G Bebis, R Boyle, B Parvin, D Koracin, F Porikili, S Skaff, A Entezari, J Min, D Iwai, A Sadagic, C Scheidegger & T Isenberg (eds), Advances in Visual Computing. Springer, Lecture Notes in Computer Science, vol. 10073, pp. 111-122, Las Vegas, United States, 12/12/2016. https://doi.org/10.1007/978-3-319-50832-0_12

Preventing Drowning Accidents Using Thermal Cameras. / Bonderup, Søren; Olsson, Jonas Lundgaard; Bonderup, Morten Bojesen; Moeslund, Thomas B.

Advances in Visual Computing. ed. / George Bebis; Richard Boyle; Bahram Parvin; Darco Koracin; Faith Porikili; Sandra Skaff; Alireza Entezari; Jianjuan Min; Daisuke Iwai; Amela Sadagic; Carlos Scheidegger; Tobias Isenberg. Springer, 2016. p. 111-122 (Lecture Notes in Computer Science, Vol. 10073).

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Preventing Drowning Accidents Using Thermal Cameras

AU - Bonderup, Søren

AU - Olsson, Jonas Lundgaard

AU - Bonderup, Morten Bojesen

AU - Moeslund, Thomas B.

PY - 2016

Y1 - 2016

N2 - Every year approximately 372 000 people die from unintentional drowning, causing it to be a top-3 cause to unintentional injury [1]. In Denmark 25% of drownings happen at harbor areas [2]. To address this problem thermal cameras have been placed strategically at a harbor. Using computer vision techniques an automatic surveillance system for predicting and detecting drowning accidents has been implemented. First a person detector has been implemented using simple human characteristics. The person is tracked using a Kalman Filter. Using the tracker as a prior, a fall prediction is determined. A fall detector is implemented using a virtual trip-wire in combination with an optical flow algorithm making the system able to detect 100% of all falls and only yielding a 0.08 false positive rate hourly. The entire system has been developed using 155 h of real life thermal video, hereof 56 h are manually annotated.

AB - Every year approximately 372 000 people die from unintentional drowning, causing it to be a top-3 cause to unintentional injury [1]. In Denmark 25% of drownings happen at harbor areas [2]. To address this problem thermal cameras have been placed strategically at a harbor. Using computer vision techniques an automatic surveillance system for predicting and detecting drowning accidents has been implemented. First a person detector has been implemented using simple human characteristics. The person is tracked using a Kalman Filter. Using the tracker as a prior, a fall prediction is determined. A fall detector is implemented using a virtual trip-wire in combination with an optical flow algorithm making the system able to detect 100% of all falls and only yielding a 0.08 false positive rate hourly. The entire system has been developed using 155 h of real life thermal video, hereof 56 h are manually annotated.

U2 - 10.1007/978-3-319-50832-0_12

DO - 10.1007/978-3-319-50832-0_12

M3 - Article in proceeding

SN - 978-3-319-50831-3

T3 - Lecture Notes in Computer Science

SP - 111

EP - 122

BT - Advances in Visual Computing

A2 - Bebis, George

A2 - Boyle, Richard

A2 - Parvin, Bahram

A2 - Koracin, Darco

A2 - Porikili, Faith

A2 - Skaff, Sandra

A2 - Entezari, Alireza

A2 - Min, Jianjuan

A2 - Iwai, Daisuke

A2 - Sadagic, Amela

A2 - Scheidegger, Carlos

A2 - Isenberg, Tobias

PB - Springer

ER -

Bonderup S, Olsson JL, Bonderup MB, Moeslund TB. Preventing Drowning Accidents Using Thermal Cameras. In Bebis G, Boyle R, Parvin B, Koracin D, Porikili F, Skaff S, Entezari A, Min J, Iwai D, Sadagic A, Scheidegger C, Isenberg T, editors, Advances in Visual Computing. Springer. 2016. p. 111-122. (Lecture Notes in Computer Science, Vol. 10073). https://doi.org/10.1007/978-3-319-50832-0_12