Detection of dairy cow feeding behavior based on video and BCE-YOLO model

ZHANG Liyin; ZHANG Ji; YANG Qinglu; LI Yudao; YU Zhenwei; TIAN Fuyang; YU Sufang

doi:10.7671/j.issn.1001-411X.202404009

Journal of South China Agricultural University > 2024 > 45(5): 782-792. > DOI: 10.7671/j.issn.1001-411X.202404009

ZHANG Liyin, ZHANG Ji, YANG Qinglu, et al. Detection of dairy cow feeding behavior based on video and BCE-YOLO model[J]. Journal of South China Agricultural University, 2024, 45(5): 782-792. DOI: 10.7671/j.issn.1001-411X.202404009

Citation:

PDF (4356 KB)

Detection of dairy cow feeding behavior based on video and BCE-YOLO model

1.
College of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian 271000, China
2.
College of Life Sciences, Shandong Agricultural University, Taian 271000, China

More Information

Received Date: April 02, 2024
Available Online: June 23, 2024
Published Date: June 30, 2024

Graphical Abstract

Abstract

Abstract

Objective
Animal feeding behavior serves as an essential indicator of animal welfare. This study aims to address the issues of poor recognition accuracy and insufficient feature extraction in cow feeding behavior under complex farming environments, aiming to achieve automatic monitoring of cow feeding behavior.
Method
This paper proposed a recognition method based on the improved BCE-YOLO model. By adding three enhancement modules of BiFormer, CoT, and EMA, the feature extraction capability of the YOLOv8 model was enhanced. Furthermore, it was combined with the Deep SORT algorithm, which outperforms Staple and SiameseRPN algorithms, to track the head trajectory of cows during feeding. A total of 11 288 images were extracted from overhead and frontal videos of cows during feeding, divided into training and test sets at a ratio of 6∶1, to form a feeding dataset.
Result
The improved BCE-YOLO model achieved precision of 77.73% and 76.32% on the frontal and overhead datasets, respectively, with recall rates of 82.57% and 86.33%, as well as mean average precision values of 83.70% and 76.81%. Compared to the YOLOv8 model, the overall performance of the proposed model was improved by six to eight percentage points. The Deep SORT algorithm also demonstrated one to four percentage points improvement in comprehensive performance compared to Staple and SiameseRPN algorithms. The combination of the improved BCE-YOLO model and Deep SORT target tracking algorithm achieved accurate tracking of cow feeding behavior and effectively suppressed cow ID (Identity document) changes.
Conclusion
The proposed method effectively addresses the issues of poor recognition accuracy and insufficient feature extraction in cow feeding behavior under complex farming environments. It provides an important reference for intelligent animal husbandry and precision farming.
- Dairy cow,
- Feeding behavior identification,
- Optimized YOLOv8 model,
- Deep SORT

FullText(HTML)

References (22)

References

[1]	何东健, 刘冬, 赵凯旋. 精准畜牧业中动物信息智能感知与行为检测研究进展[J]. 农业机械学报, 2016, 47(5): 231-244.
[2]	胡国政. 基于计算机视觉的奶牛身份及采食行为识别研究[D]. 泰安: 山东农业大学, 2023.
[3]	黄吉峰. 高产奶牛饲养管理技术措施探讨[J]. 中国乳业, 2024(1): 37-40.
[4]	徐国忠. 奶牛跛足原因与预防管理[J]. 中国乳业, 2017(4): 63-64.
[5]	刘娜, 安晓萍, 王园, 等. 机器视觉技术在奶牛精准化管理中的应用研究进展[J/OL]. 中国畜牧杂志, (2024-03-29) [2024-04-01]. https://doi.org/10.19556/j.0258-7033.20230803-07.
[6]	梁家璇. 基于惯导的奶牛行为识别及其传感器电路中低功耗运放设计与实现[D]. 泰安: 山东农业大学, 2022.
[7]	安健, 程宇森, 桂小林, 等. 多场景下基于传感器的行为识别[J]. 计算机工程与设计, 2024, 45(1): 244-251.
[8]	AOUGHLIS S, SADDAOUI R, ACHOUR B, et al. Dairy cows’ localisation and feeding behaviour monitoring using a combination of IMU and RFID network[J]. International Journal of Sensor Networks, 2021, 37(1): 23-35. doi: 10.1504/IJSNET.2021.117962
[9]	卫阳森. 基于深度学习的牲畜行为识别研究与应用[D]. 秦皇岛: 河北科技师范学院, 2023.
[10]	白强, 高荣华, 赵春江, 等. 基于改进YOLOV5s网络的奶牛多尺度行为识别方法[J]. 农业工程学报, 2022, 38(12): 163-172.
[11]	杨阿庆. 基于计算机视觉的哺乳母猪行为识别研究[D]. 广州: 华南农业大学, 2019.
[12]	王政, 许兴时, 华志新, 等. 融合YOLO v5n与通道剪枝算法的轻量化奶牛发情行为识别[J]. 农业工程学报, 2022, 38(23): 130-140.
[13]	BEZEN R, EDAN Y, HALACHMI I. Computer vision system for measuring individual cow feed intake using RGB-D camera and deep learning algorithms[J]. Computers and Electronics in Agriculture, 2020, 172: 105345. doi: 10.1016/j.compag.2020.105345
[14]	LAO F, BROWN-BRANDL T, STINN J P, et al. Automatic recognition of lactating sow behaviors through depth image processing[J]. Computers and Electronics in Agriculture, 2016, 125: 56-62. doi: 10.1016/j.compag.2016.04.026
[15]	SHELLEY A N, LAU D L, STONE A E, et al. Short communication: Measuring feed volume and weight by machine vision[J]. Journal of Dairy Science, 2016, 99(1): 386-391. doi: 10.3168/jds.2014-8964
[16]	ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: Faster and better learning for bounding box regression[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 12993-13000. doi: 10.1609/aaai.v34i07.6999
[17]	LIN T Y, DOLLÁR P, GIRSHICK R B, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017.
[18]	曹小喜. 基于深度学习的口罩佩戴实时检测算法研究与系统实现[D]. 芜湖: 安徽工程大学, 2022.
[19]	ZHU L, WANG X, KE Z, et al. BiFormer: Vision transformer with Bi-Level routing attention[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver: IEEE, 2023: 10323-10333.
[20]	RAMACHANDRAN P, PARMAR N, VASWANI A, et al. Stand-alone self-attention in vision models[EB/OL]. arXiv: 1906.05909 (2019-06-13) [2024-04-01]. https://doi.org/10.48550/arXiv.1906.05909.
[21]	OUYANG D L, HE S, ZHANG G Z, et al. Efficient multi-scale attention module with cross-spatial learning[C]//ICASSP 2023. 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Rhodes: IEEE, 2023: 1-5.
[22]	WOJKE N, BEWLEY A, PAULUS D. Simple online and realtime tracking with a deep association metric[C]//2017 IEEE International Conference on Image Processing (ICIP). Beijing: IEEE, 2017: 3645-3649.

Cited By

Cited by

Periodical cited type(15)

1.	王楠，廖永琴，施竹凤，申云鑫，杨童雨，冯路遥，矣小鹏，唐加菜，陈齐斌，杨佩文. 三株无量山森林土壤芽孢杆菌鉴定及其生物活性挖掘. 生物技术通报. 2024(02): 277-288 .
2.	甘林，代玉立，刘晓菲，兰成忠，杨秀娟. 香蕉枯萎病高效拮抗土著细菌的筛选及其防效. 西北农林科技大学学报(自然科学版). 2024(06): 95-105 .
3.	梅耀天，赵霞，杨淞杰，封传红. 解淀粉芽孢杆菌在农业病害防治中的应用及发展建议. 农药科学与管理. 2024(08): 28-32 .
4.	熊新颖，韩树全，罗立娜，卢加举，贺尔奇，齐炳森，魏鹏程，卢振亚. 生防菌对香蕉防病及促生作用的研究进展. 农技服务. 2024(09): 35-40 .
5.	杨东亚，祁瑞雪，李昭轩，林薇，马慧，张雪艳. 黄瓜茄病镰刀菌拮抗芽孢杆菌的筛选、鉴定及促生效果. 生物技术通报. 2023(02): 211-220 .
6.	佟德利，刘静华，于鑫，朱广鹏，李梦琦，贺海升. 水稻恶苗病拮抗细菌的筛选及生防机制. 沈阳师范大学学报(自然科学版). 2023(02): 186-192 .
7.	虞凡枫，赵进，孙铭悦，樊子婧，陈芳，牛世全. 黄瓜枯萎病拮抗芽孢杆菌A7-3-14的筛选及鉴定. 北方园艺. 2022(03): 41-46 .
8.	朱咏珊，罗晓欣，梁浩然，陈正桐，刘成，曹凯，刘少群，周而勋，舒灿伟，郑鹏. 一株茶树根际细菌的鉴定与生防效果研究. 茶叶科学. 2022(01): 87-100 .
9.	周智博，王卿惠，郭欣欣，徐婧怡，苑世伟，陈彦龙，王世伟. 解淀粉芽孢杆菌抑菌蛋白研究进展. 高师理科学刊. 2022(04): 64-69 .
10.	刘连金，李正令，李雪理，李兴田，侯青，杨友联，廖旺姣，严凯，张晓勇. 八角炭疽病生防菌株筛选及发酵条件研究. 植物保护. 2022(05): 204-211 .
11.	张强，王胜光，吴利民，姜志龙，孟洁，陆宁海. 小麦茎基腐病生防菌HB-081的鉴定及抑菌活性. 河南科技学院学报(自然科学版). 2022(06): 7-14 .
12.	凌晓宁，鄢陆琪，张荣，章启慧，李昆太. 一株拮抗柑橘绿霉病海洋微生物的分离筛选鉴定及其所产活性物质稳定性研究. 江西农业大学学报. 2022(06): 1529-1537 .
13.	陶雪菊，苟兴华，何成霞. 脂肽微生物的研究进展. 成都大学学报(自然科学版). 2021(02): 119-127 .
14.	陈斌，韩海亮，侯俊峰，包斐，谭禾平，王桂跃，赵福成. 玉米细菌性茎腐病研究进展. 中国植保导刊. 2021(08): 25-29+65 .
15.	黄小琴，杨潇湘，张蕾，张重梅，鲜赟曦，周西全，刘勇. 解淀粉芽孢杆菌Bam22促进茶树抽芽及蚧壳虫防治效果. 四川农业科技. 2021(11): 56-57+62 .

Other cited types(7)

Get Citation

PDF

XML

Article views (604) PDF downloads (39) Cited by(22)

Turn off MathJax

Article Contents

Abstract

References

Detection of dairy cow feeding behavior based on video and BCE-YOLO model

Abstract

References

Cited by

Periodical cited type(15)

Other cited types(7)

Catalog

Export File

Citation

Format

Content