Accurate body measurement of live cattle using three depth cameras and non-rigid 3-D shape recovery

Abstract Body condition scoring of livestock is widely used as a subjective method for assessing energy reserves and making management decisions for livestock. Since animal dimensions are often measured manually, the procedure is time-consuming, expensive and stressful for both the farmer and animal. Recent advances in three-dimensional sensor technology provide innovative tools for the design of automated contactless systems for assessing the animal body condition. The objective of this paper is to design an automated computer vision system capable to generate an accurate three-dimensional model of live cattle. The system is based on a non-rigid 3-D shape reconstruction utilizing data from depth cameras. The design methodology includes three Microsoft Kinect v2 cameras, computer vision, signal filtering of point clouds, pattern recognition using 3-D feature extraction techniques, and statistical analysis using point and interval estimations. The quality of generated three-dimensional body models is validated against manually measured nine references, such as withers height, hip height, chest depth, oblique body length, heart girth, etc. With a 90% confidence level, measurement errors in the proposed system among all measured estimates are less than 3%. Experimental results show that the proposed approach can serve as a new accurate method for non-contact body measurement of livestock.

[1]  Arman Savran,et al.  Computer Vision and Image Understanding , 2022, SSRN Electronic Journal.

[2]  Wei Su,et al.  A bilateral symmetry based pose normalization framework applied to livestock body measurement in point clouds , 2019, Comput. Electron. Agric..

[3]  Toru Tamaki,et al.  A preliminarily study for predicting body weight and milk properties in lactating Holstein cows using a three-dimensional camera system , 2015, Comput. Electron. Agric..

[4]  Wolfgang Junge,et al.  Automated calculation of udder depth and rear leg angle in Holstein-Friesian cows using a multi-Kinect cow scanning system , 2017 .

[5]  X Song,et al.  Automated body condition scoring of dairy cows using 3-dimensional feature extraction from multiple body regions. , 2019, Journal of dairy science.

[6]  Lucia Maddalena,et al.  Background Subtraction for Moving Object Detection in RGBD Data: A Survey , 2018, J. Imaging.

[7]  Wolfgang Junge,et al.  A multi-Kinect cow scanning system: Calculating linear traits from manually marked recordings of Holstein-Friesian dairy cows , 2017 .

[8]  Dehai Zhu,et al.  On-Barn Pig Weight Estimation Based on Body Measurements by Structure-from-Motion (SfM) , 2018, Sensors.

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

[10]  Yasushi Makihara,et al.  RGB-D video-based individual identification of dairy cows using gait and texture analyses , 2019, Comput. Electron. Agric..

[11]  Hongchuan Yu,et al.  Geodesics on Point Clouds , 2014 .

[12]  Yu Zhong,et al.  Intrinsic shape signatures: A shape descriptor for 3D object recognition , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[13]  K. Weigel,et al.  Relationships between body condition score change, prior mid-lactation phenotypic residual feed intake, and hyperketonemia onset in transition dairy cows. , 2017, Journal of dairy science.

[14]  David Reiser,et al.  3-D Imaging Systems for Agricultural Applications—A Review , 2016, Sensors.

[15]  Daniel Berckmans,et al.  Implementation of an automatic 3D vision monitor for dairy cow locomotion in a commercial farm , 2017, Biosystems Engineering.

[16]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[17]  Kikuhito Kawasue,et al.  Black cattle body shape and temperature measurement using thermography and KINECT sensor , 2017, Artificial Life and Robotics.

[18]  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.

[19]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Amit Kumar Singh,et al.  Real-time recognition of cattle using animal biometrics , 2017, Journal of Real-Time Image Processing.

[21]  A. N. Ruchay,et al.  A novel switching bilateral filtering algorithm for depth map , 2019 .

[22]  Vitaly Kober,et al.  Accuracy of location measurement of a noisy target in a nonoverlapping background , 1996 .

[23]  Ke Wang,et al.  LSSA_CAU: An interactive 3d point clouds analysis software for body measurement of livestock with similar forms of cows or pigs , 2017, Comput. Electron. Agric..

[24]  Reinhard Klein,et al.  Efficient RANSAC for Point‐Cloud Shape Detection , 2007, Comput. Graph. Forum.

[25]  Vitaly Kober,et al.  Reconstruction of 3D deformable objects using a single Kinect sensor , 2019, Optical Engineering + Applications.

[26]  D. Hill,et al.  Non-rigid image registration: theory and practice. , 2004, The British journal of radiology.

[27]  Sakir Tasdemir,et al.  Original papers: Determination of body measurements on the Holstein cows using digital image analysis and estimation of live weight with regression analysis , 2011 .

[28]  Marie J. Haskell,et al.  Establishing the extent of behavioural reactions in dairy cattle to a leg mounted activity monitor , 2012 .

[29]  Y. Le Cozler,et al.  High-precision scanning system for complete 3D cow body shape imaging and analysis of morphological traits , 2019, Comput. Electron. Agric..

[30]  Daniel Berckmans,et al.  Comparison of a three-dimensional and two-dimensional camera system for automated measurement of back posture in dairy cows , 2014 .

[31]  Xunmu Zhu,et al.  Automatic recognition of lactating sow postures from depth images by deep learning detector , 2018, Comput. Electron. Agric..