Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Learning Based Image Segmentation of Pigs in a Pen

Nilsson, Mikael LU ; Ardö, Håkan LU ; Åström, Karl LU orcid ; Herlin, Anders ; Bergsten, Christer and Guzhva, Oleksiy (2014) Visual observation and analysis of Vertebrate And Insect Behavior 2014 p.1-4
Abstract
As farms are getting bigger with more animals,

less manual supervision and attention can be given the animals

on both group and individual level. In order not to jeopardize

animal welfare, automated supervision is in some way already

in use. Function and control of ventilation is already in use in

modern pig stables, e.g. by the use of sensors for temperature,

relative humidity and malfunction connected to alarm. However,

by measuring continuously directly on the pigs, more information

and more possibilities to adjust production inputs would be

possible. In this work, the focus is on a key image processing

algorithm aiding such a continuous system -... (More)
As farms are getting bigger with more animals,

less manual supervision and attention can be given the animals

on both group and individual level. In order not to jeopardize

animal welfare, automated supervision is in some way already

in use. Function and control of ventilation is already in use in

modern pig stables, e.g. by the use of sensors for temperature,

relative humidity and malfunction connected to alarm. However,

by measuring continuously directly on the pigs, more information

and more possibilities to adjust production inputs would be

possible. In this work, the focus is on a key image processing

algorithm aiding such a continuous system - segmentation of pigs

in images from video. The proposed solution utilizes extended

state-of-the-art features in combination with a structured prediction

framework based on a logistic regression solver using elastic

net regularization. Objective results on manually segmented

images indicate that the proposed solution, based on learning,

performs better than approaches suggested in recent publications

addressing pig segmentation in video. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to conference
publication status
published
subject
keywords
Precision Livestock Farming, Machine Learning, Computer Vision
pages
4 pages
conference name
Visual observation and analysis of Vertebrate And Insect Behavior 2014
conference location
Stockholm, Sweden
conference dates
2014-08-24
language
English
LU publication?
yes
additional info
The paper was presented at a workshop in conjunction with the International Conference on Pattern Recognition (ICPR 2014): http://homepages.inf.ed.ac.uk/rbf/vaib14.html
id
c1a453fa-30f4-488f-9461-e87758c689b5 (old id 5142540)
alternative location
http://homepages.inf.ed.ac.uk/rbf/VAIB14PAPERS/nilsson.pdf
date added to LUP
2016-04-04 13:58:19
date last changed
2020-12-22 02:15:58
@misc{c1a453fa-30f4-488f-9461-e87758c689b5,
  abstract     = {As farms are getting bigger with more animals,<br/><br>
less manual supervision and attention can be given the animals<br/><br>
on both group and individual level. In order not to jeopardize<br/><br>
animal welfare, automated supervision is in some way already<br/><br>
in use. Function and control of ventilation is already in use in<br/><br>
modern pig stables, e.g. by the use of sensors for temperature,<br/><br>
relative humidity and malfunction connected to alarm. However,<br/><br>
by measuring continuously directly on the pigs, more information<br/><br>
and more possibilities to adjust production inputs would be<br/><br>
possible. In this work, the focus is on a key image processing<br/><br>
algorithm aiding such a continuous system - segmentation of pigs<br/><br>
in images from video. The proposed solution utilizes extended<br/><br>
state-of-the-art features in combination with a structured prediction<br/><br>
framework based on a logistic regression solver using elastic<br/><br>
net regularization. Objective results on manually segmented<br/><br>
images indicate that the proposed solution, based on learning,<br/><br>
performs better than approaches suggested in recent publications<br/><br>
addressing pig segmentation in video.},
  author       = {Nilsson, Mikael and Ardö, Håkan and Åström, Karl and Herlin, Anders and Bergsten, Christer and Guzhva, Oleksiy},
  language     = {eng},
  pages        = {1--4},
  title        = {Learning Based Image Segmentation of Pigs in a Pen},
  url          = {https://lup.lub.lu.se/search/files/6249431/5142541.pdf},
  year         = {2014},
}