ITEM METADATA RECORD
Title: AUTOMATIC MONITORING OF TURKEYS: A VISION-BASED APPROACH TO DETECT AND ANALYSE THE BEHAVIOUR OF TURKEYS IN TRANSPORT CAGES BASED ON ELLIPSE FITTING
Other Titles: Welfare monitoring of turkeys in a real-time image based system in transport
Authors: Poursaberi, Ahmad
Bahr, Claudia
Berckmans, Daniel #
Issue Date: 2009
Conference: SEAG2009 location:Queensland , AUS date:13-16 September 2009
Abstract: The aim in this project was to develop a tool which can reliably do automatic scoring of different behaviors performed by turkeys confided in cages of different heights. These behaviors may, after some further evaluation, be used as an assessment of welfare during transport. Eighteen weeks old male turkeys in two different cage heights 40 cm (low cage) and 90 cm (high cage) were followed. In the low cage the height was too low for the bird to assume a standing position whereas in the high cage bird could stand in a normal position and had more opportunities to perform different behaviors like standing and turning. A camera captured videos simultaneously of one turkey in a low and high cage respectively. The four behaviors turning, lying, standing and wing flapping were chosen to represent different behaviors for welfare assessment. An algorithm based on image analysis was developed to classify Behaviour in real time and automatically. A coarse estimation of bird was obtained through its colour filtering and shape properties. By using image enhancement and binarization techniques, a binary image is produced from each cage. Morphological operators are used to conclude if the cage is empty or not. Then according to the binary image the boundary of bird and then the parameters of the best fitted ellipse are extracted. To speed up procedure of finding turkey in next time with the previous ellipse parameters, we can limit search area to update the new position. According to ellipse parameters in each frame the four behaviors are categorized. Distinction between lying and standing postures from single top-view image is difficult and not accurate with ellipse fitting techniques. Further solutions are tested based on area and functional shape descriptor of bird. A. In comparison with the manually labelled reference frame by frame, the algorithm on 60 hours video resulted in 100% correct classification of turning, 94% wing flapping, 83% of lying and 71% of standing behaviors.
Publication status: accepted
KU Leuven publication type: IC
Appears in Collections:Division M3-BIORES: Measure, Model & Manage Bioresponses (-)
# (joint) last author

Files in This Item:

There are no files associated with this item.

Request a copy

 




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