Automatic Monitoring of Pig Activity Using Image Analysis

Mohammad Amin Kashiha; Claudia Bahr; Sanne Ott; Christel Moons; Theo Niewold; Frank Tuyttens; Daniel Berckmans

Automatic Monitoring of Pig Activity Using Image Analysis

Mohammad Amin Kashiha
, Claudia Bahr
, Sanne Ott
, Christel Moons
, Theo Niewold
, Frank Tuyttens
, Daniel Berckmans

Research output: Chapter in Book/Report/Conference proceeding › C1: Articles in proceedings › peer-review

Abstract

The purpose of this study is to investigate the feasibility and validity
of an automated image processing method to detect the activity status of pigs.
Top-view video images were captured for forty piglets, housed ten per pen.
Each pen was monitored by a top-view CCD camera. The image analysis
protocol to automatically quantify activity consisted of several steps. First, in
order to localise the pigs, ellipse fitting algorithms were employed.
Subsequently, activity was calculated by subtracting image background and
comparing binarised images. To validate the results, they were compared to
labelled behavioural data ('active' versus 'inactive'). This is the first study to
show that activity status of pigs in a group can be determined using image
analysis with an accuracy of 89.8 %. Since activity status is known to be
associated with issues such as lameness, careful monitoring can give an
accurate indication of the health and welfare of pigs.

Original language	English
Title of host publication	Advanced Concepts for Intelligent Vision Systems : Proceedings of the 15th International Conference
Editors	Jacques Blanc-Talon, Andrzej Kasinski, Wilfried Philips, Dan Popescu, Paul Scheunders
Number of pages	9
Publisher	Springer
Publication date	2013
Pages	555-563
ISBN (Print)	978-3-319-02894-1
ISBN (Electronic)	978-3-319-02895-8
Publication status	Published - 2013
Event	Advanced Concepts for Intelligent Vision Systems - Poznan, Poland Duration: 28-Oct-2013 → 31-Oct-2013

Cite this

Kashiha, M. A., Bahr, C., Ott, S., Moons, C., Niewold, T., Tuyttens, F., & Berckmans, D. (2013). Automatic Monitoring of Pig Activity Using Image Analysis. In J. Blanc-Talon, A. Kasinski, W. Philips, D. Popescu, & P. Scheunders (Eds.), Advanced Concepts for Intelligent Vision Systems: Proceedings of the 15th International Conference (pp. 555-563). (Lecture Notes in Computer Science; Vol. 8192). Springer.

Kashiha, Mohammad Amin ; Bahr, Claudia ; Ott, Sanne et al. / Automatic Monitoring of Pig Activity Using Image Analysis. Advanced Concepts for Intelligent Vision Systems: Proceedings of the 15th International Conference. editor / Jacques Blanc-Talon ; Andrzej Kasinski ; Wilfried Philips ; Dan Popescu ; Paul Scheunders. Springer, 2013. pp. 555-563 (Lecture Notes in Computer Science).

@inbook{83cd277002c9474fbbb3bf1b08fbe62b,

title = "Automatic Monitoring of Pig Activity Using Image Analysis",

abstract = "The purpose of this study is to investigate the feasibility and validity of an automated image processing method to detect the activity status of pigs. Top-view video images were captured for forty piglets, housed ten per pen. Each pen was monitored by a top-view CCD camera. The image analysis protocol to automatically quantify activity consisted of several steps. First, in order to localise the pigs, ellipse fitting algorithms were employed. Subsequently, activity was calculated by subtracting image background and comparing binarised images. To validate the results, they were compared to labelled behavioural data ('active' versus 'inactive'). This is the first study to show that activity status of pigs in a group can be determined using image analysis with an accuracy of 89.8 \%. Since activity status is known to be associated with issues such as lameness, careful monitoring can give an accurate indication of the health and welfare of pigs.",

author = "Kashiha, \{Mohammad Amin\} and Claudia Bahr and Sanne Ott and Christel Moons and Theo Niewold and Frank Tuyttens and Daniel Berckmans",

year = "2013",

language = "English",

isbn = "978-3-319-02894-1",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "555--563",

editor = "Jacques Blanc-Talon and Andrzej Kasinski and Wilfried Philips and Dan Popescu and \{ Scheunders\}, \{Paul \}",

booktitle = "Advanced Concepts for Intelligent Vision Systems",

address = "Netherlands",

note = "Advanced Concepts for Intelligent Vision Systems ; Conference date: 28-10-2013 Through 31-10-2013",

}

Kashiha, MA, Bahr, C, Ott, S, Moons, C, Niewold, T, Tuyttens, F & Berckmans, D 2013, Automatic Monitoring of Pig Activity Using Image Analysis. in J Blanc-Talon, A Kasinski, W Philips, D Popescu & P Scheunders (eds), Advanced Concepts for Intelligent Vision Systems: Proceedings of the 15th International Conference. Lecture Notes in Computer Science, vol. 8192, Springer, pp. 555-563, Advanced Concepts for Intelligent Vision Systems, Poznan, Poland, 28/10/13.

Automatic Monitoring of Pig Activity Using Image Analysis. / Kashiha, Mohammad Amin; Bahr, Claudia; Ott, Sanne et al.
Advanced Concepts for Intelligent Vision Systems: Proceedings of the 15th International Conference. ed. / Jacques Blanc-Talon; Andrzej Kasinski; Wilfried Philips; Dan Popescu; Paul Scheunders. Springer, 2013. p. 555-563 (Lecture Notes in Computer Science; Vol. 8192).

Research output: Chapter in Book/Report/Conference proceeding › C1: Articles in proceedings › peer-review

TY - CHAP

T1 - Automatic Monitoring of Pig Activity Using Image Analysis

AU - Kashiha, Mohammad Amin

AU - Bahr, Claudia

AU - Ott, Sanne

AU - Moons, Christel

AU - Niewold, Theo

AU - Tuyttens, Frank

AU - Berckmans, Daniel

PY - 2013

Y1 - 2013

N2 - The purpose of this study is to investigate the feasibility and validity of an automated image processing method to detect the activity status of pigs. Top-view video images were captured for forty piglets, housed ten per pen. Each pen was monitored by a top-view CCD camera. The image analysis protocol to automatically quantify activity consisted of several steps. First, in order to localise the pigs, ellipse fitting algorithms were employed. Subsequently, activity was calculated by subtracting image background and comparing binarised images. To validate the results, they were compared to labelled behavioural data ('active' versus 'inactive'). This is the first study to show that activity status of pigs in a group can be determined using image analysis with an accuracy of 89.8 %. Since activity status is known to be associated with issues such as lameness, careful monitoring can give an accurate indication of the health and welfare of pigs.

AB - The purpose of this study is to investigate the feasibility and validity of an automated image processing method to detect the activity status of pigs. Top-view video images were captured for forty piglets, housed ten per pen. Each pen was monitored by a top-view CCD camera. The image analysis protocol to automatically quantify activity consisted of several steps. First, in order to localise the pigs, ellipse fitting algorithms were employed. Subsequently, activity was calculated by subtracting image background and comparing binarised images. To validate the results, they were compared to labelled behavioural data ('active' versus 'inactive'). This is the first study to show that activity status of pigs in a group can be determined using image analysis with an accuracy of 89.8 %. Since activity status is known to be associated with issues such as lameness, careful monitoring can give an accurate indication of the health and welfare of pigs.

M3 - C1: Articles in proceedings

SN - 978-3-319-02894-1

T3 - Lecture Notes in Computer Science

SP - 555

EP - 563

BT - Advanced Concepts for Intelligent Vision Systems

A2 - Blanc-Talon, Jacques

A2 - Kasinski, Andrzej

A2 - Philips, Wilfried

A2 - Popescu, Dan

A2 - Scheunders, Paul

PB - Springer

T2 - Advanced Concepts for Intelligent Vision Systems

Y2 - 28 October 2013 through 31 October 2013

ER -

Automatic Monitoring of Pig Activity Using Image Analysis

Abstract

Fingerprint

Cite this