Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

For the time-consuming and stressful body measuring task of Qinchuan cattle and farmers, the demand for the automatic measurement of body dimensions has become more and more urgent. It is necessary to explore automatic measurements with deep learning to improve breeding efficiency and promote the development of industry. In this paper, a novel approach to measuring the body dimensions of live Qinchuan cattle with on transfer learning is proposed. Deep learning of the Kd-network was trained with classical three-dimensional (3D) point cloud datasets (PCD) of the ShapeNet datasets. After a series of processes of PCD sensed by the light detection and ranging (LiDAR) sensor, the cattle silhouettes could be extracted, which after augmentation could be applied as an input layer to the Kd-network. With the output of a convolutional layer of the trained deep model, the output layer of the deep model could be applied to pre-train the full connection network. The TrAdaBoost algorithm was employed to transfer the pre-trained convolutional layer and full connection of the deep model. To classify and recognize the PCD of the cattle silhouette, the average accuracy rate after training with transfer learning could reach up to 93.6%. On the basis of silhouette extraction, the candidate region of the feature surface shape could be extracted with mean curvature and Gaussian curvature. After the computation of the FPFH (fast point feature histogram) of the surface shape, the center of the feature surface could be recognized and the body dimensions of the cattle could finally be calculated. The experimental results showed that the comprehensive error of body dimensions was close to 2%, which could provide a feasible approach to the non-contact observations of the bodies of large physique livestock without any human intervention.

[1]  Chao Liu,et al.  Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning , 2017, Journal of Mountain Science.

[2]  G. Rosa,et al.  A novel automated system to acquire biometric and morphological measurements and predict body weight of pigs via 3D computer vision. , 2018, Journal of animal science.

[3]  Federico Pallottino,et al.  A low-cost stereovision system to estimate size and weight of live sheep , 2014 .

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

[5]  Shuqin Li,et al.  Non-Contact Body Measurement for Qinchuan Cattle with LiDAR Sensor , 2018, Sensors.

[6]  Liang Zheng,et al.  Image Classification base on PCA of Multi-view Deep Representation , 2019, J. Vis. Commun. Image Represent..

[7]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Samsung Lim,et al.  A voxel-based multiscale morphological airborne lidar filtering algorithm for digital elevation models for forest regions , 2018, Measurement.

[9]  Leonidas J. Guibas,et al.  PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space , 2017, NIPS.

[10]  Ke Wang,et al.  A portable and automatic Xtion-based measurement system for pig body size , 2018, Comput. Electron. Agric..

[11]  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.

[12]  Satoshi Oyama,et al.  Effective neural network training with adaptive learning rate based on training loss , 2018, Neural Networks.

[13]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[14]  Simone Scardapane,et al.  Kafnets: kernel-based non-parametric activation functions for neural networks , 2017, Neural Networks.

[15]  Jianxiong Xiao,et al.  3D ShapeNets: A deep representation for volumetric shapes , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[17]  L. L. Wilson,et al.  Body measurements and body weights of special-fed Holstein veal calves. , 1997, Journal of dairy science.

[18]  Boris Murmann,et al.  Toward Always-On Mobile Object Detection: Energy Versus Performance Tradeoffs for Embedded HOG Feature Extraction , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[19]  Victor S. Lempitsky,et al.  Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[20]  Nikolaos Doulamis,et al.  Building Extraction From LiDAR Data Applying Deep Convolutional Neural Networks , 2019, IEEE Geoscience and Remote Sensing Letters.

[21]  Michael G. Wing,et al.  Airborne Light Detection and Ranging (LiDAR) for Individual Tree Stem Location, Height, and Biomass Measurements , 2011, Remote. Sens..

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

[23]  Biswajeet Pradhan,et al.  Deep Learning Approach for Building Detection Using LiDAR-Orthophoto Fusion , 2018, J. Sensors.

[24]  Dereck S. Meek,et al.  On surface normal and Gaussian curvature approximations given data sampled from a smooth surface , 2000, Comput. Aided Geom. Des..

[25]  Richard I. Hartley,et al.  Optimised KD-trees for fast image descriptor matching , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Andrea Pezzuolo,et al.  On-barn pig weight estimation based on body measurements by a Kinect v1 depth camera , 2018, Comput. Electron. Agric..

[27]  Pedram Ghamisi,et al.  LiDAR Data Classification Using Spatial Transformation and CNN , 2019, IEEE Geoscience and Remote Sensing Letters.

[28]  Chao Yang,et al.  A Survey on Deep Transfer Learning , 2018, ICANN.

[29]  Harold J. Kushner,et al.  A nonlinear filtering algorithm based on an approximation of the conditional distribution , 2000, IEEE Trans. Autom. Control..

[30]  Herbert K. H. Lee,et al.  The Statistical Filter Approach to Constrained Optimization , 2019, Technometrics.

[31]  Sijung Kim,et al.  Estimating pig weights from images without constraint on posture and illumination , 2018, Comput. Electron. Agric..

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

[33]  Xingming Sun,et al.  Effective and Efficient Global Context Verification for Image Copy Detection , 2017, IEEE Transactions on Information Forensics and Security.

[34]  A. Gruen,et al.  Least squares 3D surface and curve matching , 2005 .

[35]  D. Vigo,et al.  Body Measures and Milk Production, Milk Fat Globules Granulometry and Milk Fatty Acid Content in Cabannina Cattle Breed , 2013 .

[36]  Qingwu Li,et al.  Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features , 2017, Comput. Intell. Neurosci..

[37]  G. C. Guarnera,et al.  Objective estimation of body condition score by modeling cow body shape from digital images. , 2011, Journal of dairy science.

[38]  Alexandre Escolà,et al.  Discriminating Crop, Weeds and Soil Surface with a Terrestrial LIDAR Sensor , 2013, Sensors.

[39]  Ming Li,et al.  Instance Transfer Learning with Multisource Dynamic TrAdaBoost , 2014, TheScientificWorldJournal.

[40]  Wei Zeng,et al.  3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues , 2017, ECCV Workshops.

[41]  N. Kamprasert,et al.  Estimation of genetic parameters for BW and body measurements in Brahman cattle. , 2019, Animal : an international journal of animal bioscience.

[42]  Fernando Martin,et al.  Detecting homogeneous groups in clustering using the Euclidean distance , 2001, Fuzzy Sets Syst..

[43]  S. Foix,et al.  Lock-in Time-of-Flight (ToF) Cameras: A Survey , 2011, IEEE Sensors Journal.

[44]  Qi Zhang,et al.  Deep learning-based tree classification using mobile LiDAR data , 2015 .

[45]  Hiroyuki Kitagawa,et al.  Efficient distance-based outlier detection on uncertain datasets of Gaussian distribution , 2014, World Wide Web.

[46]  Hui Fan,et al.  Curvature-direction measures for 3D feature detection , 2013, Science China Information Sciences.

[47]  Konstantin Eckle,et al.  A comparison of deep networks with ReLU activation function and linear spline-type methods , 2018, Neural Networks.

[48]  Liang Zhang,et al.  A Deep Neural Network With Spatial Pooling (DNNSP) for 3-D Point Cloud Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[49]  C. Qi.  Deep Learning on Point Sets for 3 D Classification and Segmentation , 2016 .

[50]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[51]  Yu Liu,et al.  A Density-Based Clustering Method for Urban Scene Mobile Laser Scanning Data Segmentation , 2017, Remote. Sens..

[52]  Shang Gao,et al.  Deep Learning: Individual Maize Segmentation From Terrestrial Lidar Data Using Faster R-CNN and Regional Growth Algorithms , 2018, Front. Plant Sci..

[53]  Qiang Yang,et al.  Ridesharing car detection by transfer learning , 2019, Artif. Intell..

[54]  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..

[55]  Liming Chen,et al.  Principal Curvature Measures Estimation and Application to 3D Face Recognition , 2017, Journal of Mathematical Imaging and Vision.

[56]  Yuanhao Gong,et al.  Mean Curvature Is a Good Regularization for Image Processing , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[57]  C Enevoldsen,et al.  Estimation of body weight from body size measurements and body condition scores in dairy cows. , 1997, Journal of dairy science.

[58]  Mustafa Zeybek,et al.  Point cloud filtering on UAV based point cloud , 2019, Measurement.

[59]  R. R. Rhinehart,et al.  A method to determine the required number of neural-network training repetitions , 1999, IEEE Trans. Neural Networks.

[60]  A Alempijevic,et al.  Live animal assessments of rump fat and muscle score in Angus cows and steers using 3-dimensional imaging. , 2017, Journal of animal science.

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

[62]  Wolfgang Junge,et al.  Feasibility of automated body trait determination using the SR4K time-of-flight camera in cow barns , 2014, SpringerPlus.

[63]  George Vosselman,et al.  Multi-Resolution Feature Fusion for Image Classification of Building Damages with Convolutional Neural Networks , 2018, Remote. Sens..

[64]  George Vosselman,et al.  Ground and Multi-Class Classification of Airborne Laser Scanner Point Clouds Using Fully Convolutional Networks , 2018, Remote. Sens..

[65]  Yoshihiro Okada,et al.  3D Model Generation of Cattle Using Multiple Depth-Maps for ICT Agriculture , 2017, CISIS.

[66]  Daniel Welfer,et al.  Cattle Brand Recognition using Convolutional Neural Network and Support Vector Machines , 2017, IEEE Latin America Transactions.

[67]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.