Automated video analysis of pig activity at pen level highly correlates to human observations of behavioural activities

Automated collection of continuous activity data of pigs can be performed easily using video analysis. In welfare and health research, this technique can be economically advantageous over manual observations. However, the relationship between activity measures by automated video analysis and manually scored behavioural activity has never been established. We correlated automated activity measures through video analysis to ethological scores of pig activity, using off-line video recordings of four pens with grower pigs. Human observations (HO) of different behavioural activities were carried out by 2-min scan sampling during four 30-min sessions on 6 observation days. HO of pig activity was expressed as a mean proportion per session. Automated observations (AO) of pig activity were calculated by the relative number of moving pixels between two consecutive image frames (1 frame/s) and expressed as a mean image activity index per session. The overall correlation between pig activity data from AO and HO was strong and positive (Rs=0.92, P<0.0001). When comparing AO and HO data at session level, the correlation coefficients for the two afternoon sessions were lower. Both static activities and activities involving locomotion had a significant effect on the activity index of AO (P<0.05), but activities that included locomotion had a three times higher effect than static activities. Further validation research is necessary, but it can be concluded that automated video analysis is a promising technique to continuously monitor behavioural activity level of pigs at pen level.

[1]  M. Kruk.  Measuring behaviour into the twenty-first century , 1997, Trends in Neurosciences.

[2]  Daniel Berckmans,et al.  A COMPUTER VISION METHOD FOR ON-LINE BEHAVIORAL QUANTIFICATION OF INDIVIDUALLY CAGED POULTRY , 2006 .

[3]  Jean-Marie Aerts,et al.  Real-Time Measurement of Pig Activity in Practical Conditions , 2008 .

[4]  Michael T Mendl,et al.  Predicting tail-biting from behaviour of pigs prior to outbreaks , 2009 .

[5]  Michael Vinther,et al.  Validation of a digital video tracking system for recording pig locomotor behaviour , 2005, Journal of Neuroscience Methods.

[6]  A. J Spink,et al.  The EthoVision video tracking system—A tool for behavioral phenotyping of transgenic mice , 2001, Physiology & Behavior.

[7]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[8]  X. Manteca,et al.  Assessment of animal welfare through behavioural parameters in Iberian pigs in intensive and extensive conditions , 2011 .

[9]  David H. Baker,et al.  Behaviour of pigs with viral and bacterial pneumonia , 2007 .

[10]  Katrin Hübner,et al.  Suffering in diseased pigs as expressed by behavioural, clinical and clinical–chemical traits, in a well defined parasite model , 2009 .

[11]  Willem G.P. Schouten,et al.  Behavioural development of pigs with different coping characteristics in barren and substrate-enriched housing conditions , 2005 .

[12]  Philip N. Lehner,et al.  Handbook of ethological methods , 1979 .

[13]  Michael Ellis,et al.  Behaviour of two genotypes of growing–finishing pig in three different housing systems , 2002 .

[14]  C. Bench,et al.  Effect of environmental enrichment and breed line on the incidence of belly nosing in piglets weaned at 7 and 14 days-of-age , 2007 .

[15]  Daniel Berckmans,et al.  The automatic monitoring of pigs water use by cameras , 2013 .

[16]  Dries Berckmans,et al.  Dust concentration variation in relation to animal activity in a pig barn , 2009 .

[17]  H. Gonyou,et al.  Productivity, time budgets and social aspects of eating in pigs penned in groups of five or individually , 1992 .

[18]  H. Andersson,et al.  Different roughages to organic growing/finishing pigs — Influence on activity behaviour and social interactions , 2009 .

[19]  J. McGlone,et al.  Differential dose effects of central CRF and effects of CRF astressin on pig behavior , 2004, Physiology & Behavior.

[20]  S. Wilson,et al.  Behavioral sampling techniques for feedlot cattle. , 2001, Journal of animal science.

[21]  G. Johnson,et al.  Regionally Adaptive Histogram Equalization of the Chest , 1987, IEEE Transactions on Medical Imaging.

[22]  J. A. Lines,et al.  A review of livestock monitoring and the need for integrated systems , 1997 .

[23]  C. Arnould,et al.  Pig's responses to repeated social regrouping and relocation during the growing-finishing period , 2007 .

[24]  S. Robert,et al.  Some observations on the role of environment and genetics in behaviour of wild and domestic forms of Sus scrofa (European wild boars and domestic pigs) , 1987 .

[25]  Cécile Cornou,et al.  Classifying sows' activity types from acceleration patterns An application of the Multi-Process Kalman Filter , 2008 .

[26]  Daniel Berckmans,et al.  Automatic Identification of Marked Pigs in a Pen Using Image Pattern Recognition , 2013, MDA.

[27]  Hongwei Xin,et al.  A real-time computer vision assessment and control of thermal comfort for group-housed pigs , 2008 .