Prediction of welfare outcomes for broiler chickens using Bayesian regression on continuous optical flow data

Currently, assessment of broiler (meat) chicken welfare relies largely on labour-intensive or post-mortem measures of welfare. We here describe a method for continuously and robustly monitoring the welfare of living birds while husbandry changes are still possible. We detail the application of Bayesian modelling to motion data derived from the output of cameras placed in commercial broiler houses. We show that the forecasts produced by the model can be used to accurately assess certain key aspects of the future health and welfare of a flock. The difference between healthy flocks and less-healthy ones becomes predictable days or even weeks before clinical symptoms become apparent. Hockburn (damaged leg skin, usually only seen in birds of two weeks or older) can be well predicted in flocks of only 1–2 days of age, using this approach. Our model combines optical flow descriptors of bird motion with robust multivariate forecasting and provides a sparse, efficient model with sparsity-inducing priors to achieve maximum predictive power with the minimum number of key variables.

[1]  Stephen J. Roberts,et al.  A tutorial on variational Bayesian inference , 2012, Artificial Intelligence Review.

[2]  Marian Stamp Dawkins,et al.  Prediction of feather damage in laying hens using optical flows and Markov models , 2011, Journal of The Royal Society Interface.

[3]  C. Nicol,et al.  Sub-clinical infection with Salmonella in chickens differentially affects behaviour and welfare in three inbred strains , 2010, British poultry science.

[4]  I. Muchnik,et al.  Early warning indicators for hock burn in broiler flocks , 2010, Avian pathology : journal of the W.V.P.A.

[5]  M. Dawkins,et al.  Optical flow patterns in broiler chicken flocks as automated measures of behaviour and gait , 2009 .

[6]  M. Mendl,et al.  Towards humane end points: behavioural changes precede clinical signs of disease in a Huntington's disease model , 2008, Proceedings of the Royal Society B: Biological Sciences.

[7]  J. Koolhaas Coping style and immunity in animals: Making sense of individual variation , 2008, Brain, Behavior, and Immunity.

[8]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[9]  J. B. Kjaer,et al.  Foot pad dermatitis and hock burn in broiler chickens and degree of inheritance. , 2006, Poultry science.

[10]  P. Warriss,et al.  Preliminary study to examine the utility of using foot burn or hock burn to assess aspects of housing conditions for broiler chicken , 2006, British poultry science.

[11]  David J. Fleet,et al.  Optical Flow Estimation , 2006, Handbook of Mathematical Models in Computer Vision.

[12]  D. Weary,et al.  Feeding behavior identifies dairy cows at risk for metritis. , 2005, Journal of dairy science.

[13]  V. E. Beattie,et al.  Factors identifying pigs predisposed to tail biting , 2005 .

[14]  S. Roberts,et al.  Bayesian multivariate autoregressive models with structured priors , 2002 .

[15]  Radford M. Neal Assessing Relevance determination methods using DELVE , 1998 .

[16]  Steven S. Beauchemin,et al.  The computation of optical flow , 1995, CSUR.

[17]  S. Kestin,et al.  Prevalence of leg weakness in broiler chickens and its relationship with genotype , 1992, Veterinary Record.