A method for pig gait scoring based on 3D convolution video analysis

WU Zhenbang; CHEN Zekai; TIAN Xuhong; YANG Jie; YIN Ling; ZHANG Sumin

doi:10.7671/j.issn.1001-411X.202311019

Journal of South China Agricultural University > 2024 > 45(5): 743-753. > DOI: 10.7671/j.issn.1001-411X.202311019

WU Zhenbang, CHEN Zekai, TIAN Xuhong, et al. A method for pig gait scoring based on 3D convolution video analysis[J]. Journal of South China Agricultural University, 2024, 45(5): 743-753. DOI: 10.7671/j.issn.1001-411X.202311019

Citation:

PDF (1907 KB)

A method for pig gait scoring based on 3D convolution video analysis

WU Zhenbang^1,,
CHEN Zekai¹,
TIAN Xuhong¹,
YANG Jie^{2, 3, 4},
YIN Ling^{1, 2, 4, ,},
ZHANG Sumin^{1, 4}

1.
College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China
2.
National Engineering Research Center for Swine Breeding Industry, Guangzhou 510642, China
3.
College of Animal Science, South China Agricultural University, Guangzhou 510642, China
4.
State Key Laboratory of Swine and Poultry Breeding Industry, Guangzhou 510640, China

More Information

Received Date: November 17, 2023
Available Online: June 21, 2024
Published Date: July 14, 2024

Abstract

Abstract

Objective
Swine limb and hoof disease is one of the significant reasons for culling breeding swine, resulting in substantial economic losses for livestock farms. The diagnosis of swine limb and hoof disease typically relies on manual observation of pig gaits, which consumes high labor costs and has low efficiency. The aim of this study is to achieve automated pig gait scoring, and efficiently determine the health status of swine limb and hoof.
Method
This study proposed an “end-to-end” pig gait scoring method. Videos of individual breeding swine passing through designated channels were collected and a four-point gait dataset was created. Deep learning techniques were employed for video analysis. A time attention module (TAM) based on a 3D convolutional neural network was designed to effectively extract feature information between video frame images. By combining TAM with residual structures, the pig gait scoring model TA3D was constructed for feature extraction and gait classification scoring in the gait videos. To further improve model performance and achieve automation, the gait focus module (GFM) was designed. GFM could autonomously extract effective information from real-time video streams to synthesize high-quality gait videos, improving model performance while reducing computational costs.
Result
The experimental results demonstrated that GFM could operate in real-time and reduced the size of gait videos by over 90%, significantly reducing storage cost, and the gait scoring accuracy of the TA3D model was 96.43%. Moreover, the comparison test results with other classic video analysis models showed that TA3D achieved optimal levels of accuracy and inference speed.
Conclusion
This paper proposes a solution that can be applied to the automatic scoring of pig gait, providing a reference for the automatic detection of swine limb and hoof disease.
- Image processing,
- Deep learning,
- Pig,
- Gait scoring,
- Attention mechanism,
- Video analysis,
- Limb and hoof disease

FullText(HTML)

References (26)

References

[1]	黄建平. 种猪肢蹄病的常见原因分析[J]. 猪业科学, 2020, 37(5): 106-107. doi: 10.3969/j.issn.1673-5358.2020.05.028
[2]	JØRGENSEN B. Influence of floor type and stocking density on leg weakness, osteochondrosis and claw disorders in slaughter pigs[J]. Animal Science, 2003, 77(3): 439-449. doi: 10.1017/S1357729800054382
[3]	刘瑞玲. 猪群肢蹄病发病症状、病因及防治措施[J]. 国外畜牧学(猪与禽), 2011, 31(1): 88-90.
[4]	王怀中, 张印, 孙海涛. 猪肢蹄病的预防[J]. 养猪, 2010(2): 39-40. doi: 10.3969/j.issn.1002-1957.2010.02.019
[5]	王超, 魏宏逵, 彭健. 广西公猪站公猪淘汰原因及在群猪肢蹄病发病规律调查研究[C]//中国畜牧兽医学会动物营养学分会. 第七届中国饲料营养学术研讨会论文集. 郑州: 中国农业大学出版社, 2014: 1.
[6]	杨亮, 王辉, 陈睿鹏, 等. 智能养猪工厂的研究进展与展望[J]. 华南农业大学学报, 2023, 44(1): 13-23. doi: 10.7671/j.issn.1001-411X.202209050
[7]	刘波, 朱伟兴, 杨建军, 等. 基于深度图像和生猪骨架端点分析的生猪步频特征提取[J]. 农业工程学报, 2014, 30(10): 131-137. doi: 10.3969/j.issn.1002-6819.2014.10.016
[8]	朱家骥, 朱伟兴. 基于星状骨架模型的猪步态分析[J]. 江苏农业科学, 2015(12): 453-457.
[9]	李前, 初梦苑, 康熙, 等. 基于计算机视觉的奶牛跛行识别技术研究进展[J]. 农业工程学报, 2022, 38(15): 159-169. doi: 10.11975/j.issn.1002-6819.2022.15.017
[10]	ZHAO K, BEWLEY J M, HE D, et al. Automatic lameness detection in dairy cattle based on leg swing analysis with an image processing technique[J]. Computers and Electronics in Agriculture, 2018, 148: 226-236. doi: 10.1016/j.compag.2018.03.014
[11]	康熙, 李树东, 张旭东, 等. 基于热红外视频的奶牛跛行运动特征提取与检测[J]. 农业工程学报, 2021, 37(23): 169-178. doi: 10.11975/j.issn.1002-6819.2021.23.020
[12]	JIANG B, SONG H, WANG H, et al. Dairy cow lameness detection using a back curvature feature[J]. Computers and Electronics in Agriculture, 2022, 194: 106729. doi: 10.1016/j.compag.2022.106729
[13]	POURSABERI A, BAHR C, PLUK A, et al. Online lameness detection in dairy cattle using Body Movement Pattern (BMP)[C]//IEEE. 2011 11th International Conference on Intelligent Systems Design and Applications. Cordoba, Spain: IEEE, 2011: 732-736.
[14]	TRAN D, BOURDEV L, FERGUS R, et al. Learning spatiotemporal features with 3d convolutional networks[C]//IEEE. Proceedings of the IEEE International Conference on Computer Vision (ICCV). Santiago, Chile: IEEE, 2015: 4489-4497.
[15]	YANG K, QIAO P, LI D, et al. Exploring temporal preservation networks for precise temporal action localization[C]//AAAI. Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, California, USA: AAAI, 2018: 7477-7484.
[16]	WANG X, GIRSHICK R, GUPTA A, et al. Non-local neural networks[C]//IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, UT, USA: IEEE, 2018: 7794-7803.
[17]	WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module[C]//Springer. Proceedings of the European Conference on Computer Vision (ECCV). Munich, Germany: Springer, 2018: 3-19.
[18]	HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, UT, USA: IEEE, 2018: 7132-7141.
[19]	ZHANG X, ZHOU X, LIN M, et al. Shufflenet: An extremely efficient convolutional neural network for mobile devices[C]//IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, UT, USA: IEEE, 2018: 6848-6856.
[20]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE, 2016: 770-778.
[21]	SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
[22]	CARREIRA J, ZISSERMAN A. Quo vadis, action recognition? a new model and the kinetics dataset[C]//IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA: IEEE, 2017: 6299-6308.
[23]	LIU Z, NING J, CAO Y, et al. Video swin transformer[C]//IEEE/CVF. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, LA, USA: IEEE, 2022: 3202-3211.
[24]	FEICHTENHOFER C, FAN H, MALIK J, et al. Slowfast networks for video recognition[C]//IEEE/CVF. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, Korea (South): IEEE, 2019: 6202-6211.
[25]	LIU Z, WANG L, WU W, et al. TAM: Temporal adaptive module for video recognition[C]//IEEE/CVF. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, QC, Canada: IEEE, 2021: 13688-13698.
[26]	LIU Z, LIN Y, CAO Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//IEEE/CVF. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, QC, Canada: IEEE, 2021: 10012-10022.

[1]	CHEN Xiao-wei, FAN Hui-ying, LIN Wen-yao, CHENG Xiao-liang, YE Yu, CHEN Chun-li, LIAO Ming. Construction of a Recombinant Baculovirus Surface Displaying S1 Protein of M41 Strain of Infectious Bronchitis Virus[J]. Journal of South China Agricultural University, 2012, 33(3): 398-402. DOI: 10.7671/j.issn.1001-411X.2012.03.025
[2]	Construction of a Pseudotype Baculovirus Expressing S1 Protein of Infectious Bronchitis Virus[J]. Journal of South China Agricultural University, 2010, 31(2). DOI: 10.7671/j.issn.1001-411X.2010.02.025
[3]	CHEN Hong-ying,CUI Bao-an,LI Xin-sheng,ZHAO Li,ZHENG Lan-lan,GUAN Qian. Cloning and Sequence Analysis of gB Gene of Chicken Infectious Laryngotracheitis Virus Henan Isolate[J]. Journal of South China Agricultural University, 2007, 28(2): 99-102. DOI: 10.7671/j.issn.1001-411X.2007.02.025
[4]	GUO Xiao-feng,FU Zhen-fang. Moving the Glycoprotein Gene of Rabies Virus to Promoter-Proximal Position and the Generation of the Virus[J]. Journal of South China Agricultural University, 2006, 27(1): 104-106. DOI: 10.7671/j.issn.1001-411X.2006.01.027
[5]	CHEN Feng, WU Kong-xing, ZHANG Qi, FENG Shou-hua, ZHANG Xiu-li, LIAO Qiu-sheng, CAO Yong-ehang. Identification and serotyping of five infectious bronchitis virus isolates[J]. Journal of South China Agricultural University, 2005, 26(4): 92-95. DOI: 10.7671/j.issn.1001-411X.2005.04.023
[6]	CAO Yong-chang,SHI Quan-cheng,MA Jing-yun,BI Ying-zuo. Fusion expression of viral structural protein VP2 of infectious bursal disease virus in E.coli[J]. Journal of South China Agricultural University, 2004, 25(4): 78-81. DOI: 10.7671/j.issn.1001-411X.2004.04.020
[7]	LIN Rui-qing,LUO Man-lin,HUANG Yu-mao,LIU Zhen-ming,XIN Chao-an. Cloning and expression of foot-and-mouth disease virus type O VP1 gene[J]. Journal of South China Agricultural University, 2004, 25(1): 92-95. DOI: 10.7671/j.issn.1001-411X.2004.01.025
[8]	WU Hong zhuan 1,LIU Fu an 1,ZHU Dao zhong 1,Yee wai CHAN 2,Frederick C.LEUNG 2. Cloning and Partial Sequencing gC Gene of Infectious Laryngotracheitis Virus Beijing E2 Strain[J]. Journal of South China Agricultural University, 2000, (4): 71-73. DOI: 10.7671/j.issn.1001-411X.2000.04.022
[9]	Lin YongqingSupervising Professor:Ou Shou-Zhu. ESTABLISHMENT OF HYBRIDOMA CELL LINES SECRETING MONOCLONAL ANTIBODIES AGAINST AVIAN INFECTIOUS BRONCHITIS VIRUS[J]. Journal of South China Agricultural University, 1989, (4): 93-98.
[10]	Xin Chaoan Gu Feixia Qiu Zhenfang. STUDIES ON VIRAL ARTHRITIS[J]. Journal of South China Agricultural University, 1989, (3): 52-57.

Cited By

Cited by

Periodical cited type(18)

1.	崔紫宁，陈建平，梁丽梅. “交叉融合”：“微生物天然产物化学”的跨界教育模式. 工业微生物. 2024(01): 194-196 .
2.	邓杰，尚楠. 芽孢杆菌群体感应系统研究进展. 生物加工过程. 2024(05): 492-499 .
3.	乔真，李佳霖，秦松. C6-HSL信号及群体淬灭对海洋聚球藻(Synechococcus)菌藻共栖体系的调控作用. 海洋科学. 2024(09): 52-62 .
4.	李凤兰，吴天祥，邓代霞，袁丹丹，江守发. 太子参乙醇提取物对灰树花菌体生长及胞外多糖的影响机理初步研究. 食品与发酵科技. 2023(02): 28-34 .
5.	欧凯玉，逄建龙，张一敏，董鹏程，罗欣，毛衍伟. 天然酚类化合物的抑菌作用及在肉与肉制品中的应用研究进展. 食品科学. 2023(09): 358-366 .
6.	高鑫，李博. 水产腐败群体感应系统与天然抑菌剂的研究进展. 保鲜与加工. 2023(06): 73-80 .
7.	郑爱娟，陈星，张广民，王泽栋，陈志敏，常文环，蔡辉益，刘国华. N-酰基高丝氨酸内酯酶对肉仔鸡生长性能、屠宰性能和养分表观代谢率的影响. 动物营养学报. 2023(06): 3607-3616 .
8.	熊儒恒，阎俊，谢晶. 生物被膜初始黏附调控机制及其在食品品质控制中的应用研究进展. 食品科学. 2023(13): 203-215 .
9.	杨约萍，高倩倩，宁静，宫佳，胡媛媛，施祖荣. 细菌群体通讯信号及其淬灭研究进展. 仲恺农业工程学院学报. 2022(01): 65-70 .
10.	廖才江，李会，王士源，熊静，梅翠，刘丹，何玉张，彭练慈，宋振辉，陈红伟. 生物被膜：益生菌肠道定植的新策略. 生物工程学报. 2022(08): 2821-2839 .
11.	乔真，李佳霖，秦松 . 海洋藻际环境中细菌群体感应研究进展. 生物学杂志. 2022(05): 93-97+107 .
12.	王亚军，司运美，李彦娟. 群体感应在生物强化功能菌定殖及降解能力增强中的作用研究进展. 应用生态学报. 2022(10): 2871-2880 .
13.	李艳群，陈柔雯，林宗豪，田新朋，尹浩. 一株群体感应抑制活性海洋放线菌的筛选与鉴定. 热带海洋学报. 2021(01): 75-81 .
14.	杨艳北，许晶，沈城辉，许继国，饶友生. N-酰基高丝氨酸内酯酶的生物信息学分析. 甘肃农业科技. 2021(02): 31-37 .
15.	杨艳北，许晶，李袁飞，贡继尚，饶友生. 沼泽红假单胞菌LuxR家族调控蛋白的生物信息学分析. 江苏农业科学. 2021(06): 40-45 .
16.	郑钰婷，胡宇如，胡方平，蔡学清. 利用aiiA基因筛选抗烟草青枯病生防菌株及其鉴定. 核农学报. 2021(06): 1322-1328 .
17.	宋凯，周莲，何亚文. DSF-家族群体感应信号生物合成途径与调控机制研究进展. 微生物学通报. 2021(04): 1239-1248 .
18.	赵祯，肖翎，戚建华，刘韵怡，王年，郁小娟，宋增福. 群体感应淬灭酶YtnP对草鱼肠道菌群结构的影响. 南方农业学报. 2020(11): 2817-2826 .

Other cited types(13)

ZHANG Sumin

1.
College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China
4.
State Key Laboratory of Swine and Poultry Breeding Industry, Guangzhou 510640, China

Get Citation

PDF

XML

Article views (441) PDF downloads (41) Cited by(31)

Turn off MathJax

Article Contents

Abstract

References

A method for pig gait scoring based on 3D convolution video analysis