Title: Development of an Early Warning System For a Broiler House Using Computer Vision
Authors: Kashiha, Mohammadamin ×
Pluk, Arno
Bahr, Claudia
Vranken, Erik
Berckmans, Daniel #
Issue Date: 2013
Publisher: Published for Silsoe Research Institute by Academic Press
Series Title: Biosystems Engineering vol:116 issue:1 pages:36-45
Abstract: Anomalous animal behaviour and reduced growth rate are just a few signs that can indicate an undesired situation in a broiler house. It is important that problems such as diseases, technical malfunctioning in feeding and drinking lines and suboptimal management procedures are detected in an early stage to avoid harming the welfare or the production results of broilers. This paper introduces an automated method to detect problems in a broiler house using cameras and an image analysis software. An automated tool for monitoring animal behaviour was employed which used camera technology in the broiler house with a dimension of 19.8 by 63.5 meters. Three top view cameras mounted in the ridge of the house at the height of 5 meters continuously monitored the floor space below. Analysis software translated these images into an index for animal distribution index in the house. The final objective was to develop a system that could report malfunctioning in a broiler house to the farmer in real-time. In an experiment with Ross 308 broilers, distribution index data were collected every 5 minutes in a commercial broiler house with 28000 animals. Based on the distribution index data, a linear real-time model was developed and tested to model the animal distribution index as a response to the light input. Using this model, an online prediction could be made on animal distribution index. By comparing the predicted values with the measurements in real-time, malfunctioning could be detected. Results showed that this method was able to report 95.24 per cent (20 out of 21) of events in real-time, demonstrating a high potential of using automatic monitor tools for the monitoring of broiler production over a complete growing period.
ISSN: 1537-5110
Publication status: published
KU Leuven publication type: IT
Appears in Collections:Division M3-BIORES: Measure, Model & Manage Bioresponses (-)
Division of Gene Technology (-)
× corresponding author
# (joint) last author

Files in This Item:
File Description Status SizeFormat
eYenamic data analysis- v5 - Submission ready.pdf Published 207KbAdobe PDFView/Open


All items in Lirias are protected by copyright, with all rights reserved.

© Web of science