Development of a Machine Vision Method for the Monitoring of Laying Hens and Detection of Multiple Nest Occupations

Abstract

Free range systems can improve the welfare of laying hens. However, the access to environmental resources can be partially limited by social interactions, feeding of hens, and productivity, can be not stable and damaging behaviors, or negative events, can be observed more frequently than in conventional housing systems. In order to reach a real improvement of the hens’ welfare the study of their laying performances and behaviors is necessary. With this purpose, many systems have been developed. However, most of them do not detect a multiple occupation of the nest negatively affecting the accuracy of data collected. To overcome this issue, a new “nest-usage-sensor” was developed and tested. It was based on the evaluation of thermografic images, as acquired by a thermo-camera, and the performing of patter recognitions on images acquired from the nest interior. The sensor was setup with a “Multiple Nest Occupation Threshold” of 796 colored pixels and a template of triangular shape and sizes of 43 × 33 pixels (high per base). It was tested through an experimental nesting system where 10 hens were reared for a month. Results showed that the evaluation of thermografic images could increase the detection performance of a multiple occupation of the nest and to apply an image pattern recognition technique could allow for counting the number of hens in the nest in case of a multiple occupation. As a consequence, the accuracy of data collected in studies on laying performances and behaviors of hens, reared in a free-range housing system, could result to be improved.

A Systematic Review of Precision Livestock Farming in the Poultry Sector: Is Technology Focussed on Improving Bird Welfare?

“…The presence of birds was used by Zaninelli and colleagues [67,68] to detect whether hens in a free-range system were present in the housing area, with the aim of removing all hens to the outside area so the housing can be treated to reduce atmospheric ammonia and bacterial load. Monitoring of the presence of hens was also used to detect multiple occupations of a nest area to improve monitoring of laying behaviour [69]. Li and colleagues [70,71] used presence of hens at specific areas (feeding trough and nest boxes) for automated monitoring and quantification of feeding, drinking and nesting behaviour.…”

Review: Automated techniques for monitoring the behaviour and welfare of broilers and laying hens: towards the goal of precision livestock farming

“…Photographs taken in a nest that was painted black, with the number of colour pixels counted and compared with the threshold double nest occupation, could detect whether there were two or more hens in a nest (Zaninelli et al, 2015). Later, with a thermographic camera to identify laying hens in a closed room (Zaninelli et al, 2016 and, this team developed a better 'nest usage sensor', which could count the number of hens in the nest (Zaninelli et al, 2018). The thermographic images were processed by binarisation and coloured, and the number of colour pixels was counted to detect whether there were more than one hen in the nest.…”

Review of Sensor Technologies in Animal Breeding: Phenotyping Behaviors of Laying Hens to Select Against Feather Pecking

“…Zaninelli et al [24,90,91] made several attempts to develop and improve a monitoring system for laying hens based on IR technology and image pattern recognition. Their approaches required a top-mounted thermal camera and were capable of processing acquired images in real-time while the proposed algorithm detected objects within an image based on gradient changes in pixel temperature values.…”