Optical flow, behaviour and broiler chicken welfare in the UK and Switzerland
Introduction
‘Smart’ or ‘precision’ farming has revolutionized the cultivation of agricultural crops but its application to livestock farming has raised ethical concerns because of its possible adverse effects on animal welfare (Wathes et al., 2008; Banhazi et al., 2012; Fournel et al., 2017; Winckler, 2019). Some people see the efficiency gains offered by the new technology as a direct threat to the animals themselves, allowing producers to get “more for less” in the interests of efficiency and to further encourage the use of intensive systems which they see as damaging to welfare (Stevenson, 2017). Others see major welfare advantages through life-long health monitoring, the ability to deliver care to individual animals and to provide optimal environmental conditions (Wathes et al., 2008; Banhazi et al., 2012; Berckmans, 2017; Buscher, 2019; Veissier et al., 2019). They also point to other potential benefits of the technology such as reducing waste and cutting the need for medication through improved animal health and lowered environmental impact (Clark and Tilman, 2017; Lovarelli et al., 2020; Perakis et al., 2020).
The extent to which smart technology has been adopted by farmers varies greatly with the animals concerned. With dairy cows, for example, changes in the health status and behaviour of each individual cow can now be monitored through a variety of different devices attached to a cow’s body or in the environment (Beer et al., 2016; Alsaaod et al., 2019). As a result, many dairy farmers have found that investment in such technology benefits their entire business (Lovarelli et al., 2020). However, with animals kept in large groups such as laying hens and broiler chickens, there are technological issues arising from the need to monitor many thousands of animals simultaneously and although a number of systems have been developed (Dawkins et al., 2009, 2012; Aydin et al., 2010; Silvera et al., 2017; Fernandez et al., 2018; Li et al., 2020), automated assessment of poultry health and welfare is not currently in widespread commercial use (Rowe et al., 2019; Rios et al., 2020). One major reason for this may be that no system has yet been sufficiently validated in a commercial setting for producers to be confident that it is worth adopting (Wathes et al., 2008; Wurtz et al., 2019; Dawkins and Rowe, 2020). More attention therefore needs to be given to validation and to farmer adoption strategies (Rios et al., 2020).
We here report a study on the welfare of broiler chickens that uses cameras to analyse the optical flow patterns made by flocks of chickens as they move around a house (Dawkins et al., 2012; Roberts et al., 2012). Although some automated systems of welfare assessment focus on the behaviour of individual birds (e.g. Naas et al., 2018), the system tested here is one of an increasing number that focus on behaviour and welfare at group level (Dawkins et al., 2009; Aydin et al., 2010; Ben Sassi et al., 2016; Van Hertem et al., 2018). We analysed the movements of whole flocks by detecting the rate of change of image brightness (‘optical flow’) in different parts of the whole camera image both through time and space (Beauchemin and Barron, 1995; Fleet and Weiss, 2005). These changes were then combined to give an estimate of local velocity vectors.
This approach has already been successfully used on commercial farms in the UK and has demonstrated significant correlations between optical flow parameters and key welfare outcomes for poultry such as hockburn, pododermatitis (Dawkins et al., 2009, 2012; 2017) and infection with Campylobacter (Colles et al., 2016). We here tested the hypothesis that the optical flow patterns of flocks less than two weeks old are correlated with two key welfare outcomes – mortality and % hockburn – measured several weeks later and can therefore provide an early warning to farmers of potential health and welfare problems. By obtaining results from commercial farms in both the UK and Switzerland, we aimed to demonstrate that this approach was practical enough to be deployed on commercial farms even where there are differences in farm conditions and in times and methods of data collection.
Section snippets
Optical flow analysis
Each frame of a video was divided into 1200 (40 × 30) 8-by-8 pixel blocks and the optical flow estimated for each block every 0.25 s. These estimated flow velocities were then combined, on a frame-by-frame basis to give the total ‘flow’ over the entire image expressed as the mean, variance, skew and kurtosis of optical flow. Median values were used to eliminate spuriously large numbers that occasionally occurred in the raw optical flow records. Further details are given in Roberts et al. (2012)
Ethical statement
All the work described here was based on surveillance of commercially farmed chickens kept under standard agricultural practice. There was no interference with the birds above routine inspection and care by the farm managers. Cameras were installed in the houses when the houses were empty to avoid disturbance to the birds. The work was approved in the UK by the Local Ethical Review Panel of the Department of Zoology, University of Oxford. In Switzerland, it was approved by the Canton of Bern
Optical flow, hockburn and mortality
The basic mortality and hockburn data for the UK and Switzerland are shown in Table 1. There was a considerably greater range of mortalities in the UK flocks. To illustrate the way in which the 4 optical flow variables summarize the movement of a flock, Table 2 shows the daily summary statistics for all the flocks for one day (Day 7).
The optical flow results from both the Swiss and the UK flocks showed high positive kurtosis or leptokurtic distribution – that is, one in which there are more
Discussion
Our results confirm the hypothesis that optical flow patterns in flock movements convey information about two key welfare outcomes – hockburn and mortality. A cumulative model that took data from each successive day together with all previous days showed significant correlations between daily optical flow patterns and both hockburn and mortality in the UK and Switzerland (Fig. 2, Fig. 4). This result shows that the system we used can function in real farm environments and give similar results
Conclusions
The hypothesis that optical flow patterns made by the movements of broiler chicken flocks are correlated with two key welfare outcomes - mortality and hockburn - has been confirmed on commercial farms in both the UK and Switzerland. By combining average level of activity (measured by mean optical flow) with measures of variation in activity (variance, skew and kurtosis of optical flow) and cumulating information over time, differences between flocks become apparent within the first few days of
Declaration of Competing Interest
None.
Acknowledgements
This work was carried out as part of the Era-NET ANIHWA programme. It was supported in the UK by BBSRC grant BB/N023803/1 and in Switzerland by FSVO grant 2.16.03. We would like to thank Cargill (AVARA) and Bell AG for their help with facilitating this project. We would also like to thank the farmers and farm managers involved for letting us use their barns and their data from the abattoirs.
References (46)
- et al.
Automated lames detection in cattle
Vet. J.
(2019) Development of an early detection system for lameness in broilers using computer vision
Comput. Electron. Agric.
(2017)- et al.
Application of a fully automatic analysis tool to assess the activity of broiler chickens with different gait scores
Comput. Electron. Agric.
(2010) - et al.
Effects of increasing environmental complexity on the physical activity of broiler chickens
Appl. Anim. Behav. Sci.
(2002) - et al.
Effects of breeder feeding restriction programs and incubation temperatures on progeny footpad development
Poult. Sci.
(2014) - et al.
Optical flow patterns in broiler chickens as automated measures of behaviour and gait
Appl. Anim. Behav. Sci.
(2009) - et al.
Optical flow, flock behaviour and chicken welfare
Anim. Behav.
(2012) - et al.
Rethinking environnmental control strategy of confined animal housing systems through precision livestock farming
Biosyst. Eng.
(2017) - et al.
Lameness and its relationship with health and production measures in broiler chickens
Animal
(2019) - et al.
The effects of eggshell temperature fluctuations during incubation on welfare status and gait score of broilers
Poult. Sci.
(2016)
Review: automated techniques for monitoring the behavior and welfare of broilers and laying hens: towards the goal of precision livestock farming
Animal
A review of cattle farming: is precision livestock farming the compromise for an environmental, economic and social sustainable production
J. Clean. Prod.
Paraconsistent logic used for estimating the gait score of broiler chickens
Biosyst. Eng.
CYBELE- fostering precision agriculture & livestock farming through secure access to large-scale HPC-enabled virtual industrial experimentation enviornments fostering scaleable big data analytics
Comput. Netw.
Lameness assessment with automatic monitoring of activity in commercial broiler flocks
Poult. Sci.
Hatching egg characteristics, chick quality, and broiler performance at 2 breeder flock ages and from 3 egg weights
Poult. Sci.
Predicting broiler gaits scores from activity monitoring and flock data
Biosyst. Eng.
Is precision livestock farming an engineer’s daydream or nightmare, an animal’s friend or foe and a farmer’s panacea or pitfall?
Comp. Electron. Agric.
Field study on broilers’ first-week mortality
Poult. Sci.
Precision Livestock Farming: an international review of scientific and commercial aspects
Int. J. Agric. Biol Eng
The effects of relative humidity and turning in incubator machines on the incubation yield and chick performance
Worlds Poult. Sci. J.
The computation of optical flow
ACM Comp. Surv.
Use of extended characteristics of locomotion and feeding for automatic identification of lame dairy cows
PLoS One
Cited by (17)
Individuality of a group: detailed walking ability analysis of broiler flocks using optical flow approach
2023, Smart Agricultural TechnologyInternet of Things and Machine Learning techniques in poultry health and welfare management: A systematic literature review
2022, Computers and Electronics in AgricultureCitation Excerpt :Commonly used image analysis software for the studies reviewed includes MATLAB, (Mathworks, Inc. MA, USA) (Amraei et al., 2017a; Aydin, 2017; Bloch et al., 2020; Fernández et al., 2018; Guo et al., 2020; Hemalatha & Maheswaran, 2014; Kashiha et al., 2013, 2014; Li et al., 2020b; Ma et al., 2020; Mehdizadeh et al., 2015; Mortensen et al., 2016; Neves et al., 2015; Okinda et al., 2019), R Programming Language (R Development Core Team, Vienna, Austria) (Hwang et al., 2020; Mollah et al., 2010; Qiang & Kou, 2019; Zaninelli et al., 2018), Python (Dawkins et al., 2021; Fang et al., 2021; González et al., 2017; Li et al., 2020a; You et al., 2021), Minitab (Minitab Inc, PA, USA) (Mehdizadeh et al., 2015; Neves et al., 2015), Weka (University of Waikato, New Zealand) (Branco et al., 2020; Carroll et al., 2014; Pereira et al., 2013), SPSS (IBM, Armonk, New York, USA) (Okinda et al., 2019), and Rapidminer Studio (Rapidminer Inc, Boston, MA, USA) (de Alencar Nääs et al., 2020; Fernández et al., 2018). In addition, however, libraries, i.e., OpenCV (Intel Corporation) (Debauche et al., 2020; González et al., 2017; Pu et al., 2018; Wang et al., 2016; Zhuang et al., 2018; Zhuang & Zhang, 2019), TensorFlow (Google Brain Team) (Li et al., 2020a, 2021), Pytorch (Meta AI, New York, USA) (Cao et al., 2021), and Keras (You et al., 2021; Zhuang & Zhang, 2019) are recently gaining grounds.
Differences and variation in welfare performance of broiler flocks in three production systems
2022, Poultry ScienceCitation Excerpt :This could have resulted in a larger difference in welfare score between C, DRB, and BLS, as it is known that reduced stocking density and environmental enrichment can have positive effects on behavior, for example (Estevez, 2007; Riber et al., 2018), but the actual variation in behavior between flocks is yet not known and remains to be further studied. Likely, with the recent developments in smart farming technologies, these type of data can be collected on a large scale in commercial flocks in the future (Dawkins et al., 2021; Gebhardt-Henrich et al., 2021). This will lead to a more balanced welfare assessment including all dimensions and measured on the animal itself.
Highlights of published papers in applied Animal Behaviour Science in 2021
2022, Applied Animal Behaviour ScienceCCTV Camera With Intelligence Technology to Minimize Chicken Mortality Due to Hazardous Gas
2023, 2023 11th International Conference on Cyber and IT Service Management, CITSM 2023