Image motion feature extraction for recognition of aggressive behaviors among group-housed pigs

Abstract The aim of this study is to develop a computer vision-based method to automatically detect aggressive behaviors among pigs. Ten repetitions of the same experiment were performed. In each of the experiment, 7 piglets were mixed from three litters in two pigpens and captured on video for a total of 6 h. From these videos, the first 3 h of video after mixing were recorded as a training set, and the 3 h of video after 24 h were recorded as a validation set. Connected area and adhesion index were used to locate aggressive pigs and to extract key frame sequences. The two pigs in aggression were regarded as a whole rectangle according to their characteristics of continuous and large-proportion adhesion. The acceleration feature was extracted by analyzing the displacement change of four sides of this rectangle between adjacent frames, and hierarchical clustering was used to calculate its threshold. Based on this feature, the recognition rules of medium and high aggression were designed. Testing 10 groups of pigs, the accuracy of recognizing medium aggression was 95.82% with a sensitivity of 90.57% and with a specificity of 96.95%, and the accuracy of recognizing high aggression was 97.04% with a sensitivity of 92.54% and with a specificity of 97.38%. These results indicate that the acceleration can be used to recognize pigs’ aggressive behaviors.

[1]  P. Jensen,et al.  Aggression between unacquainted pigs—sequential assessment and effects of familiarity and weight , 1998 .

[2]  H. W. Gonyou,et al.  The social behaviour of pigs. , 2001 .

[3]  Serdar Çakır,et al.  Image Feature Extraction Using 2 D , 2010 .

[4]  Yongxiong Wang,et al.  A self-adaptive weighted affinity propagation clustering for key frames extraction on human action recognition , 2015, J. Vis. Commun. Image Represent..

[5]  Weixing Zhu,et al.  Foreground detection of group-housed pigs based on the combination of Mixture of Gaussians using prediction mechanism and threshold segmentation , 2014 .

[6]  Stefano Viazzi,et al.  Image feature extraction for classification of aggressive interactions among pigs , 2014 .

[7]  R Roehe,et al.  Genetic validation of postmixing skin injuries in pigs as an indicator of aggressiveness and the relationship with injuries under more stable social conditions. , 2009, Journal of animal science.

[8]  Richard B. D’Eath,et al.  The Natural Behaviour of the Pig , 2009 .

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

[10]  Alistair Lawrence,et al.  The accumulation of skin lesions and their use as a predictor of individual aggressiveness in pigs , 2006 .

[11]  H W Gonyou,et al.  The effects of regrouping on behavioral and production parameters in finishing swine. , 1994, Journal of Animal Science.

[12]  Guoyin Wang,et al.  DenPEHC: Density peak based efficient hierarchical clustering , 2016, Inf. Sci..

[13]  Luigi Faucitano,et al.  Causes of skin damage to pig carcasses , 2001 .

[14]  Anne Grete Kongsted,et al.  Stress and fear as possible mediators of reproduction problems in group housed sows: a review , 2004 .

[15]  Joachim Krieter,et al.  Agonistic behaviour after mixing in pigs under commercial farm conditions , 2011 .

[16]  L. Keeling,et al.  Social Behaviour in Farm Animals , 2001 .

[17]  Daniel Berckmans,et al.  Classification of aggressive behaviour in pigs by activity index and multilayer feed forward neural network , 2014 .

[18]  Weixing Zhu,et al.  Multi-object extraction from topview group-housed pig images based on adaptive partitioning and multilevel thresholding segmentation , 2015 .

[19]  W G P Schouten,et al.  Decision support system for overall welfare assessment in pregnant sows B: validation by expert opinion. , 2002, Journal of animal science.

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

[21]  Murat Kulahci,et al.  Pig herd monitoring and undesirable tripping and stepping prevention , 2015, Comput. Electron. Agric..

[22]  Sandra A. Edwards,et al.  Automatic detection of mounting behaviours among pigs using image analysis , 2016, Comput. Electron. Agric..

[23]  Du-Ming Tsai,et al.  A motion and image analysis method for automatic detection of estrus and mating behavior in cattle , 2014 .

[24]  Michael T Mendl,et al.  Individual aggressiveness of pigs can be measured and used to reduce aggression after mixing , 1997 .

[25]  Sandra A. Edwards,et al.  Aggression among finishing pigs following mixing in kennelled and unkennelled accommodation. , 2000 .

[26]  Kai Liu,et al.  Automatic recognition of lactating sow behaviors through depth image processing , 2016, Comput. Electron. Agric..

[27]  V. E. Beattie,et al.  Influence of regrouping strategy on performance, behaviour and carcass parameters in pigs , 2005 .

[28]  J J McGlone,et al.  A quantitative ethogram of aggressive and submissive behaviors in recently regrouped pigs. , 1985, Journal of animal science.