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

Graphical Abstract

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.

Cited By

Cited by

Periodical cited type(1)

唐睿，吴涛，王贵芳，张雨，程玉成，江晓，布海丽且姆·阿卜杜热合曼. 慕萨莱思发酵过程中真菌菌群多样性分析及优良酿酒酵母的筛选与鉴定. 中国酿造. 2025(04): 120-126 .

Other cited types(0)

Get Citation

PDF

XML

Article views (376) PDF downloads (33) Cited by(1)

Turn off MathJax

Article Contents

Abstract

References

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

Abstract

References

Cited by

Periodical cited type(1)

Other cited types(0)

Catalog

Export File

Citation

Format

Content