Standard
Comparison of architectures and training strategies for convolutional neural networks intended for location-specific counting of slaughter pigs. / Jensen, D. B.; Vestbjerg Larsen, M. L.; Pedersen, L. J.
Precision Livestock Farming 2019 : Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019. red. / Bernadette O'Brien; Deirdre Hennessy; Laurence Shalloo. 2019. s. 476-483 (Precision Livestock Farming 2019 - Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019).
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
Jensen, DB, Vestbjerg Larsen, ML & Pedersen, LJ 2019, Comparison of architectures and training strategies for convolutional neural networks intended for location-specific counting of slaughter pigs. i B O'Brien, D Hennessy & L Shalloo (red), Precision Livestock Farming 2019 : Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019. Precision Livestock Farming 2019 - Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019, s. 476-483, 9th European Conference on Precision Livestock Farming, ECPLF 2019, Cork, Irland, 26/08/2019.
APA
Jensen, D. B., Vestbjerg Larsen, M. L., & Pedersen, L. J. (2019). Comparison of architectures and training strategies for convolutional neural networks intended for location-specific counting of slaughter pigs. I B. O'Brien, D. Hennessy, & L. Shalloo (red.), Precision Livestock Farming 2019 : Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019 (s. 476-483). Precision Livestock Farming 2019 - Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019
Vancouver
Jensen DB, Vestbjerg Larsen ML, Pedersen LJ. Comparison of architectures and training strategies for convolutional neural networks intended for location-specific counting of slaughter pigs. I O'Brien B, Hennessy D, Shalloo L, red., Precision Livestock Farming 2019 : Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019. 2019. s. 476-483. (Precision Livestock Farming 2019 - Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019).
Author
Jensen, D. B. ; Vestbjerg Larsen, M. L. ; Pedersen, L. J. / Comparison of architectures and training strategies for convolutional neural networks intended for location-specific counting of slaughter pigs. Precision Livestock Farming 2019 : Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019. red. / Bernadette O'Brien ; Deirdre Hennessy ; Laurence Shalloo. 2019. s. 476-483 (Precision Livestock Farming 2019 - Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019).
Bibtex
@inproceedings{a840d35beed44791bd25a3b49990daad,
title = "Comparison of architectures and training strategies for convolutional neural networks intended for location-specific counting of slaughter pigs",
abstract = "Pen fouling is an undesired behaviour seen in growing pigs, where they start resting in the excretion area and excrete in the designated resting area. It is reasonable to assume that automatic monitoring of the location of the pigs within the pen could be used for early warnings of imminent pen fouling events. We intend to provide such automatic monitoring using convolutional neural networks (CNN) applied to images captured above the pens. In this preliminary study, we compared 12 different combinations of CNN architectures and training strategies for this purpose. The best performing strategy yielded an overall mean absolute error of 0.35 pigs and a coefficient of determination of 96% between the predicted and observed number of pigs in a given area of the pen.",
keywords = "Convolutional neural network, Fouling, Monitoring, Slaughter pig",
author = "Jensen, {D. B.} and {Vestbjerg Larsen}, {M. L.} and Pedersen, {L. J.}",
note = "Publisher Copyright: {\textcopyright} Precision Livestock Farming 2019 - Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019. All rights reserved.; 9th European Conference on Precision Livestock Farming, ECPLF 2019 ; Conference date: 26-08-2019 Through 29-08-2019",
year = "2019",
language = "English",
series = "Precision Livestock Farming 2019 - Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019",
pages = "476--483",
editor = "Bernadette O'Brien and Deirdre Hennessy and Laurence Shalloo",
booktitle = "Precision Livestock Farming 2019",
}
RIS
TY - GEN
T1 - Comparison of architectures and training strategies for convolutional neural networks intended for location-specific counting of slaughter pigs
AU - Jensen, D. B.
AU - Vestbjerg Larsen, M. L.
AU - Pedersen, L. J.
N1 - Publisher Copyright:
© Precision Livestock Farming 2019 - Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019. All rights reserved.
PY - 2019
Y1 - 2019
N2 - Pen fouling is an undesired behaviour seen in growing pigs, where they start resting in the excretion area and excrete in the designated resting area. It is reasonable to assume that automatic monitoring of the location of the pigs within the pen could be used for early warnings of imminent pen fouling events. We intend to provide such automatic monitoring using convolutional neural networks (CNN) applied to images captured above the pens. In this preliminary study, we compared 12 different combinations of CNN architectures and training strategies for this purpose. The best performing strategy yielded an overall mean absolute error of 0.35 pigs and a coefficient of determination of 96% between the predicted and observed number of pigs in a given area of the pen.
AB - Pen fouling is an undesired behaviour seen in growing pigs, where they start resting in the excretion area and excrete in the designated resting area. It is reasonable to assume that automatic monitoring of the location of the pigs within the pen could be used for early warnings of imminent pen fouling events. We intend to provide such automatic monitoring using convolutional neural networks (CNN) applied to images captured above the pens. In this preliminary study, we compared 12 different combinations of CNN architectures and training strategies for this purpose. The best performing strategy yielded an overall mean absolute error of 0.35 pigs and a coefficient of determination of 96% between the predicted and observed number of pigs in a given area of the pen.
KW - Convolutional neural network
KW - Fouling
KW - Monitoring
KW - Slaughter pig
UR - http://www.scopus.com/inward/record.url?scp=85073734974&partnerID=8YFLogxK
M3 - Article in proceedings
AN - SCOPUS:85073734974
T3 - Precision Livestock Farming 2019 - Papers Presented at the 9th European Conference on Precision Livestock Farming, ECPLF 2019
SP - 476
EP - 483
BT - Precision Livestock Farming 2019
A2 - O'Brien, Bernadette
A2 - Hennessy, Deirdre
A2 - Shalloo, Laurence
T2 - 9th European Conference on Precision Livestock Farming, ECPLF 2019
Y2 - 26 August 2019 through 29 August 2019
ER -
