Using automated image analysis in pig groups behavioural research: Assessment of the influence of enrichment substrate provision on the lying behaviour

10 Visual monitoring of pig behaviours over long periods is very time consuming and has 11 possibility for observer bias. Automated image processing techniques now give the potential 12 to carry out behavioural research in a more effective way. To illustrate this, an image 13 processing technique was applied to identify whether any changes in pig lying behaviour 14 which might be detrimental to welfare resulted from an enrichment provision treatment. The 15 lying patterns of pigs in 6 enriched pens were compared with those of 6 control pens, which 16 had only a suspended enrichment toy, to determine whether daily provision of a rooting 17 material (maize silage) onto a solid plate in the lying area of a fully slatted pen resulted in 18 changed lying time and location. Pigs were monitored by top view CCTV cameras and 19 animals were extracted from their background using image processing algorithms. An ellipse 20 fitting technique was applied to localize each pig and the centre of each fitted ellipse was 21 used in x–y coordinates to find the lying positions after use of an algorithm to remove images 22 in motion preceding the scan. Each pen was virtually subdivided into four zones and the 23 position of each lying pig obtained at 10 minute intervals over a series of 24 h periods. 24 Results of a validation study showed that the image processing technique had an accuracy of 25 1 Corresponding author: abozar.nasirahmadi@ncl.ac.uk, a.nasirahmadi@gmail.com 2 93-95% when compared to visual scoring. Results from image processing indicated that once 26 daily provision of rooting material significantly changed the diurnal activity pattern 27 (p<0.001) and resulted in a modified diurnal pattern of resting location. The study 28 demonstrates that machine vision can be used as a precise and rapid method for quantifying 29 pig lying behaviour for research or practical applications. 30