On-barn pig weight estimation based on body measurements by a Kinect v1 depth camera

Abstract Information on the daily growth rate of pigs enables the stockman to monitor their performance and health and to predict and control their market weight and date. Manual measurements are among the most common ways to get an indication of animal growth. However, this approach is laborious and difficult, and it may be stressful for both the pigs and the stockman. As a consequence, manual measurements can be very time-consuming, induce costs and sometimes cause injuries to the animals and the stockman. The present work proposes the implementation of a Microsoft Kinect v1 depth camera for the fast, non-contact measurement of pig body dimensions such as heart girth, length and height. In the present work, these dimension values were related to animal weight, and two models (linear and non-linear) were developed and applied to the Kinect and manual measurement data. Both models were highly correlated with the direct weight measurements considered as references, as demonstrated by high coefficients of determination (R 2  > 0.95). Specifically, in the case of the non-linear model based on non-contact depth camera measurements, the mean absolute error exhibited a reduction of over 40% compared to the same non-linear model based on manual measurements (from 0.82 to 0.48 kg).

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

[2]  Claudia Arcidiacono,et al.  A threshold-based algorithm for the development of inertial sensor-based systems to perform real-time cow step counting in free-stall barns , 2017 .

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

[4]  Anders Krogh Mortensen,et al.  Weight prediction of broiler chickens using 3D computer vision , 2016, Comput. Electron. Agric..

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

[6]  Chen Shi,et al.  An approach of pig weight estimation using binocular stereo system based on LabVIEW , 2016, Comput. Electron. Agric..

[7]  Daniel Berckmans,et al.  The use of image analysis as a new approach to assess behaviour classification in a pig barn , 2013 .

[8]  I Halachmi,et al.  Editorial: Precision livestock farming: a 'per animal' approach using advanced monitoring technologies. , 2016, Animal : an international journal of animal bioscience.

[9]  David J. Parsons,et al.  Real-time Control of Pig Growth through an Integrated Management System , 2007 .

[10]  Enrico Savio,et al.  Geometrical modelling of scanning probe microscopes and characterization of errors , 2009 .

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

[12]  Jiahua Wu,et al.  Extracting the three-dimensional shape of live pigs using stereo photogrammetry , 2004 .

[13]  Xiande Zhao,et al.  Compensation method for the influence of angle of view on animal temperature measurement using thermal imaging camera combined with depth image. , 2016, Journal of thermal biology.

[14]  Daniel Berckmans,et al.  Automatic estimation of number of piglets in a pen during farrowing, using image analysis , 2016 .

[15]  M B M Bracke,et al.  Decision support system for overall welfare assessment in pregnant sows A: model structure and weighting procedure. , 2002, Journal of animal science.

[16]  B. Sturm,et al.  Implementation of machine vision for detecting behaviour of cattle and pigs , 2017 .

[17]  Y. Wang,et al.  Walk-through weighing of pigs using machine vision and an artificial neural network , 2008 .

[18]  Marvelous Sungirai,et al.  Validity of Weight Estimation Models in Pigs Reared under Different Management Conditions , 2014, Veterinary medicine international.

[19]  Uwe Richter,et al.  Using machine vision for investigation of changes in pig group lying patterns , 2015, Comput. Electron. Agric..

[20]  Francesco Marinello,et al.  Last generation instrument for agriculture multispectral data collection , 2017 .

[21]  Torben Gregersen,et al.  Original papers: Development of a real-time computer vision system for tracking loose-housed pigs , 2011 .

[22]  M Nilsson,et al.  Development of automatic surveillance of animal behaviour and welfare using image analysis and machine learned segmentation technique. , 2015, Animal : an international journal of animal bioscience.

[23]  Erik Jørgensen,et al.  Determination of live weight of pigs from dimensions measured using image analysis , 1996 .

[24]  Federico Pallottino,et al.  Comparison between manual and stereovision body traits measurements of Lipizzan horses , 2015, Comput. Electron. Agric..

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

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

[27]  J. R. Rosell-Polo,et al.  Advances in Structured Light Sensors Applications in Precision Agriculture and Livestock Farming , 2015 .

[28]  Daniel Berckmans,et al.  Image-processing technique to measure pig activity in response to climatic variation in a pig barn , 2014 .

[29]  J. A. Marchant,et al.  Monitoring pig growth using a prototype imaging system , 1999 .

[30]  Wei Li,et al.  Validity of the Microsoft Kinect sensor for assessment of normal walking patterns in pigs , 2015, Comput. Electron. Agric..

[31]  Victor A. Kulikov,et al.  Application of 3-D imaging sensor for tracking minipigs in the open field test , 2014, Journal of Neuroscience Methods.

[32]  Dries Berckmans,et al.  Precision livestock farming for pigs , 2017 .

[33]  Yael Edan,et al.  Development of automatic body condition scoring using a low-cost 3-dimensional Kinect camera. , 2016, Journal of dairy science.

[34]  Andrea Pezzuolo,et al.  A Feasibility Study on the Use of a Structured Light Depth-Camera for Three-Dimensional Body Measurements of Dairy Cows in Free-Stall Barns , 2018, Sensors.

[35]  Enrico Savio,et al.  Traceable volume measurements using coordinate measuring systems , 2011 .

[36]  Ling Shao,et al.  Enhanced Computer Vision With Microsoft Kinect Sensor: A Review , 2013, IEEE Transactions on Cybernetics.

[37]  Jørgen Kongsro,et al.  Estimation of pig weight using a Microsoft Kinect prototype imaging system , 2014 .

[38]  Claudia Arcidiacono,et al.  The automatic detection of dairy cow feeding and standing behaviours in free-stall barns by a computer vision-based system , 2015 .

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

[40]  Daniel Berckmans,et al.  Automatic weight estimation of individual pigs using image analysis , 2014 .