Study on Body Size Measurement Method of Goat and Cattle under Different Background Based on Deep Learning

Keqiang Li; Guifa Teng

doi:10.3390/electronics11070993

journal article Open Access Mar 23, 2022

Study on Body Size Measurement Method of Goat and Cattle under Different Background Based on Deep Learning

Keqiang Li

Guifa Teng

Electronics Vol. 11 No. 7 pp. 993 · MDPI AG

View at Publisher Save 10.3390/electronics11070993

Abstract

The feasibility of using depth sensors to measure the body size of livestock has been extensively tested. Most existing methods are only capable of measuring the body size of specific livestock in a specific background. In this study, we proposed a unique method of livestock body size measurement using deep learning. By training the data of cattle and goat with same feature points, different animal sizes can be measured under different backgrounds. First, a novel penalty function and an autoregressive model were introduced to reconstruct the depth image with super-resolution, and the effect of distance and illumination on the depth image was reduced. Second, under the U-Net neural network, the characteristics exhibited by the attention module and the DropBlock were adopted to improve the robustness of the background and trunk segmentation. Lastly, this study initially exploited the idea of human joint point location to accurately locate the livestock body feature points, and the livestock was accurately measured. According to the results, the average accuracy of this method was 93.59%. The correct key points for detecting the points of withers, shoulder points, shallowest part of the chest, highest point of the hip bones and ischia tuberosity had the percentages of 96.7%, 89.3%, 95.6%, 90.5% and 94.5%, respectively. In addition, the mean relative errors of withers height, hip height, body length and chest depth were only 1.86%, 2.07%, 2.42% and 2.72%, respectively.

Topics

No keywords indexed for this article. Browse by subject →

References

53

[1]

Thorup "On-farm estimation of energy balance in dairy cows using only frequent body weight measurements and body condition score" J. Dairy Sci. (2012) 10.3168/jds.2011-4631

[2]

Pezzuolo "On-barn pig weight estimation based on body measurements by a Kinect v1 depth camera" Comput. Electron. Agric. (2018) 10.1016/j.compag.2018.03.003

[3]

Kuzuhara "A preliminarily study for predicting body weight and milk properties in lactating Holstein cows using a three-dimensional camera system" Comput. Electron. Agric. (2015) 10.1016/j.compag.2014.12.020

[4]

Menesatti "A low-cost stereovision system to estimate size and weight of live sheep" Comput. Electron. Agric. (2014) 10.1016/j.compag.2014.01.018

[5]

Leonard "Development and application of an image acquisition system for characterizing sow behaviors in farrowing stalls" Comput. Electron. Agric. (2019) 10.1016/j.compag.2019.104866

[6]

Brandl "Determination of live weight of pigs from dimensions measured using image analysis" Comput. Electron. Agric. (1996) 10.1016/0168-1699(96)00003-8

[7]

Marchant "Pig growth and conformation monitoring using image analysis" Anim. Sci. (1999) 10.1017/s1357729800050165

[8]

Tasdemir "Determination of body measurements on the Holstein cows using digital image analysis and estimation of live weight with regression analysis" Comput. Electron. Agric. (2011) 10.1016/j.compag.2011.02.001

[9]

Ozkaya "Accuracy of body measurements using digital image analysis in female Holstein calves" Anim. Prod. Sci. (2012) 10.1071/an12006

[10]

Federico "Comparison between manual and stereovision body traits measurements of Lipizzan horses" Comput. Electron. Agric. (2015) 10.1016/j.compag.2015.09.019

[11]

Shi "An approach of pig weight estimation using binocular stereo system based on LabVIEW" Comput. Electron. Agric. (2016) 10.1016/j.compag.2016.08.012

[12]

Salau "A multi-Kinect cow scanning system: Calculating linear traits from manually marked recordings of Holstein-Friesian dairy cows" Biosyst. Eng. (2017) 10.1016/j.biosystemseng.2017.03.001

[13]

Wang "A portable and automatic Xtion-based measurement system for pig body size" Comput. Electron. Agric. (2018) 10.1016/j.compag.2018.03.018

[14]

Shi "Research on 3D surface reconstruction and body size measurement of pigs based on multi-view RGB-D cameras" Comput. Electron. Agric. (2020) 10.1016/j.compag.2020.105543

[15]

Ruchay "Accurate body measurement of live cattle using three depth cameras and non-rigid 3-D shape recovery" Comput. Electron. Agric. (2020) 10.1016/j.compag.2020.105821

[16]

Lina "Algorithm of body dimension measurement and its applications based on image analysis" Comput. Electron. Agric. (2018) 10.1016/j.compag.2018.07.033

[17]

Guo "LSSA_CAU: An interactive 3d point clouds analysis software for body measurement of livestock with similar forms of cows or pigs" Comput. Electron. Agric. (2017) 10.1016/j.compag.2017.04.014

[18]

Guo "A bilateral symmetry based pose normalization framework applied to livestock body measurement in point clouds" Comput. Electron. Agric. (2019) 10.1016/j.compag.2019.03.010

[19]

Zhao "Fine Segment Method of Cows’ Body Parts in Depth Images Based on Machine Learning" Nongye Jixie Xuebao (2017)

[20]

Jiang "FLYOLOv3 deep learning for key parts of dairy cow body detection" Comput. Electron. Agric. (2019) 10.1016/j.compag.2019.104982

[21]

Li "Group-housed pig detection in video surveillance of overhead views using multi-feature template matching" Biosyst. Eng. (2019) 10.1016/j.biosystemseng.2019.02.018

[22]

Song "Automated body condition scoring of dairy cows using 3-dimensional feature extraction from multiple body regions" J. Dairy Sci. (2019) 10.3168/jds.2018-15238

[23]

Zhang, J., Shan, S.G., Kan, M., and Chen, X.L. (2014, January 6–12). Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland. 10.1007/978-3-319-10605-2_1

[24]

Cozler "Volume and surface area of Holstein dairy cows calculated from complete 3D shapes acquired using a high-precision scanning system: Interest for body weight estimation" Comput. Electron. Agric. (2019) 10.1016/j.compag.2019.104977

[25]

Wang "Automated calculation of heart girth measurement in pigs using body surface point clouds" Comput. Electron. Agric. (2019) 10.1016/j.compag.2018.12.020

[26]

Weisheng "Sparse representation based image interpolation with nonlocal autoregressive modeling" IEEE Trans. Image Process. (2013) 10.1109/tip.2012.2231086

[27]

Hornácek, M., Rhemann, C., Gelautz, M., and Rother, C. (2013, January 23–28). Depth Super Resolution by Rigid Body Self-Similarity in 3D. Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA. 10.1109/cvpr.2013.149

[28]

Smoli, A., and Ohm, J.R. (2000, January 10–13). Robust Global Motion Estimation Using A Simplified M-Estimator Approach. Proceedings of the 2000 International Conference on Image Processing, Vancouver, BC, Canada.

[29]

Zhu, R., Yu, S.J., Xu, X.Y., and Yu, L. (2019, January 27–29). Dynamic Guidance for Depth Map Restoration. Proceedings of the 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP), Kuala Lumpur, Malaysia. 10.1109/mmsp.2019.8901804

[30]

Ojala "Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns" IEEE Trans. Pattern Anal. Mach. Intell. (2002) 10.1109/tpami.2002.1017623

[31]

Said "Analysis of focus measure operators for shape-from-focus" Pattern Recognit. (2013) 10.1016/j.patcog.2012.11.011

[32]

Misra, D. (2019, January 9–12). Mish: A Self Regularized Non-Monotonic Neural Activation Function. Proceedings of the British Machine Vision Conference, Cardiff, UK.

[33]

Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 14–19). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA. 10.1109/cvpr42600.2020.01155

[34]

Ghiasi, G., Lin, T.Y., and Le, Q.V. (2018). Dropblock: A regularization method for convolutional networks. arXiv.

[35]

Shibata "3D-Printed Visceral Aneurysm Models Based on CT Data for Simulations of Endovascular Embolization: Evaluation of Size and Shape Accuracy" Am. J. Roentgenol. (2017) 10.2214/ajr.16.17694

[36]

Carass "Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis" Sci. Rep. (2020) 10.1038/s41598-020-64803-w

[37]

Allan "An Efficient Algorithm for Calculating the Exact Hausdorff Distance" IEEE Trans. Pattern Anal. Mach. Intell. (2015) 10.1109/tpami.2015.2408351

[38]

Karimi "Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks" IEEE Trans. Med. Imaging (2020) 10.1109/tmi.2019.2930068

[39]

Stacked Hourglass Networks for Human Pose Estimation

Alejandro Newell, Kaiyu Yang, Jia Deng

Lecture Notes in Computer Science 10.1007/978-3-319-46484-8_29

[40]

Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., and Wang, X.G. (2017, January 21–26). Multi-Context Attention for Human Pose Estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA. 10.1109/cvpr.2017.601

[41]

Cao, Z., Simon, T., Wei, S.E., and Sheikh, Y. (2017, January 21–26). Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA. 10.1109/cvpr.2017.143

[42]

Deep Convolutional Network Cascade for Facial Point Detection

Yi Sun, Xiaogang Wang, Xiaoou Tang

2013 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2013.446

[43]

Ranjan "HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition" IEEE Trans. Pattern Anal. Mach. Intell. (2019) 10.1109/tpami.2017.2781233

[44]

Densely Connected Convolutional Networks

Gao Huang, Zhuang Liu, Laurens Van Der Maaten et al.

2017 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2017.243

[45]

Hua "Multipath affinage stacked-hourglass networks for human pose estimation" Front. Comput. Sci. (2020) 10.1007/s11704-019-8266-2

[46]

Bao "Multi-Residual Module Stacked Hourglass Networks for Human Pose Estimation" J. Beijing Inst. Technol. (2020)

[47]

Donner "The estimation of intraclass correlation in the analysis of family data" Biometrics (1980) 10.2307/2530491

[48]

Johannes "Joint bilateral upsampling" ACM Trans. Graph. (2007)

[49]

Camplani "Depth-Color Fusion Strategy for 3-D Scene Modeling With Kinect" IEEE Trans. Cybern. (2013) 10.1109/tcyb.2013.2271112

[50]

Yang "Color-guided depth recovery from RGB-D data using an adaptive autoregressive model" IEEE Trans. Image Process. (2014) 10.1109/tip.2014.2329776

Showing 50 of 53 references

Metrics

18

Citations

53

References

Details

Published: Mar 23, 2022
Vol/Issue: 11(7)
Pages: 993
License: View

Authors

K

Keqiang Li

School of Mechanical and Electrical Engineering, Hebei Agricultural University, Baoding 071001, China; School of Mathematics and Information Technology, Hebei Normal University of Science and Technology, Qinhuangdao 066004, China; Hebei Key Laboratory of Specialty Animal Germplasm Resources Exploration and Innovation, Hebei Normal University of Science and Technology, Qinhuangdao 066004, China; Hebei Agricultural Data Intelligent Perception and Application Technology Innovation Center, Hebei Normal University of Science and Technology, Qinhuangdao 066004, China

G

Guifa Teng

School of Information Science and Technology, Hebei Agricultural University, Baoding 071001, China; Hebei Key Laboratory of Agricultural Big Data, Baoding 071001, China

Funding

Hebei Graduate Student Innovation Project Award: CXZZBS2021045

Cite This Article

Keqiang Li, Guifa Teng (2022). Study on Body Size Measurement Method of Goat and Cattle under Different Background Based on Deep Learning. Electronics, 11(7), 993. https://doi.org/10.3390/electronics11070993

Study on Body Size Measurement Method of Goat and Cattle under Different Background Based on Deep Learning

You May Also Like