Feed consumption status monitoring method of dairy cows based on Swin-Unet

ZHANG Bo; LUO Weiping

doi:10.7671/j.issn.1001-411X.202404003

Journal of South China Agricultural University > 2024 > 45(5): 754-763. > DOI: 10.7671/j.issn.1001-411X.202404003

ZHANG Bo, LUO Weiping. Feed consumption status monitoring method of dairy cows based on Swin-Unet[J]. Journal of South China Agricultural University, 2024, 45(5): 754-763. DOI: 10.7671/j.issn.1001-411X.202404003

Citation:

PDF (2004 KB)

Feed consumption status monitoring method of dairy cows based on Swin-Unet

ZHANG Bo,
LUO Weiping^,

School of Mechanical Engineering and Automation, Wuhan Textile University, Wuhan 430200, China

More Information

Received Date: March 31, 2024
Available Online: July 02, 2024
Published Date: July 07, 2024

Graphical Abstract

Abstract

Abstract

Objective
In view of the characteristics of the feed area in the monitoring image, which has a long structure, fuzzy boundaries, as well as complex and changeable shapes and sizes, the aim of this study was to more accurately segment the feed residual area and consumption area, and achieve the purpose of accurately monitoring the feed consumption status.
Method
This study proposed a semantic segmentation model based on Swin-Unet, which applied ConvNeXt block at the beginning of the Swin Transformer block to enhance the model’s ability of encoding feature information to provide better feature representation. The model used depth-wise convolution to replace linear attention projection to provide local spatial context information. At the same time, a novel wide receptive field module was proposed to replace the multi-layer perceptron to enrich multi-scale spatial context information. In addition, at the beginning of the encoder, the linear embedding layer was replaced with a convolutional embedding layer, which introduces more spatial context information between and within patches by compressing features in stages. Finally, a multi-scale input strategy, a deep supervision strategy and a feature fusion module were introduced to strengthen feature fusion.
Result
The mean intersection over union, accuracy, F1-score and operation speed of the proposed method were 86.46%, 98.60%, 92.29% and 23 frames/s respectively, which were 4.36, 2.90, 0.65 percentage points and 15% higher than those of Swin-Unet.
Conclusion
It is feasible to apply the method based on image semantic segmentation to the automatic monitoring of feed consumption status. This method effectively improves the segmentation accuracy and computing efficiency by introducing convolution into Swin-Unet, which is of great significance for improving production management efficiency.
- Feed consumption,
- Automatic monitoring,
- Semantic segmentation,
- Swin Transformer,
- Dairy cow,
- Deep convolution

FullText(HTML)

References (24)

References

[1]	张玉磊, 乔泓博. 畜牧业发展方式及其未来发展趋势[J]. 科技风, 2023, 25: 161-163.
[2]	RONNEBERGER O, FISCHER P, BROX T. U-net: Convolutional networks for biomedical image segmentation[M]//Lecture Notes in Computer Science. Springer International Publishing, 2015: 234-241.
[3]	ZHOU Z W, RAHMAN SIDDIQUEE M M, TAJBAKHSH N, et al. UNet++: A nested U-net architecture for medical image segmentation[M]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Springer International Publishing, 2018: 3-11.
[4]	HUANG H M, LIN L F, TONG R F, et al. UNet 3+: A full-scale connected UNet for medical image segmentation[C]//2020 IEEE International Conference on Acoustics, Speech and Signal Processing. Barcelona, Spain: IEEE, 2020: 1055-1059.
[5]	SCHLEMPER J, OKTAY O, SCHAAP M, et al. Attention gated networks: Learning to leverage salient regions in medical images[J]. Medical Image Analysis, 2019, 53: 197-207. doi: 10.1016/j.media.2019.01.012
[6]	KAUL C, MANANDHAR S, PEARS N. Focusnet: An attention-based fully convolutional network for medical image segmentation[C]//2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). Venice, Italy: IEEE, 2019: 455-458.
[7]	KAUL C, PEARS N, DAI H, et al. Focusnet++: Attentive aggregated transformations for efficient and accurate medical image segmentation[C]//2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI 2021). Nice, France: IEEE, 2021: 1042-1046.
[8]	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16 × 16 words: Transformers for image recognition at scale[EB/OL]. arXiv: 2010.11929 (2020-10-22) [2024-04-01]. https://doi.org/10.48550/arXiv.2010.11929.
[9]	OKTAY O, SCHLEMPER J, FOLGOC L L, et al. Attention U-Net: Learning where to look for the pancreas[EB/OL]. arXiv: 1804.03999 (2018-4-11) [2024-04-01]. https://doi.org/10.48550/arXiv.1804.03999.
[10]	PETIT O, THOME N, RAMBOUR C, et al. U-Net transformer: Self and cross attention for medical image segmentation[EB/OL]. arXiv: 2103.06104 (2021-03-10) [2024-04-01]. https://doi.org/10.48550/arXiv.2103.06104.
[11]	CHEN J, LU Y, YU Q, et al. TransUNet: Transformers make strong encoders for medical image segmentation[EB/OL]. arXiv: 2102.04306 (2021-02-08) [2024-04-01]. https://doi.org/10.48550/arXiv.2102.04306.
[12]	ZHANG Y D, LIU H Y, HU Q. TransFuse: Fusing transformers and CNNs for medical image segmentation[M]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2021. Springer International Publishing, 2021: 14-24.
[13]	VALANARASU J M J, OZA P, HACIHALILOGLU I, et al. Medical transformer: Gated axial-attention for medical image segmentation[EB/OL]. arXiv: 2102.10662 (2021-02-21) [2024-04-01]. https://doi.org/10.48550/arXiv.2102.10662.
[14]	KARIMI D, VASYLECHKO S D, GHOLIPOUR A. Convolution-free medical image segmentation using transformers[M]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2021. Springer International Publishing, 2021: 78-88.
[15]	CAO H, WANG Y Y, CHEN J, et al. Swin-Unet: Unet-like pure transformer for medical image segmentation[EB/OL]. arXiv: 2105.05537 (2021-05-12) [2024-04-01]. https://doi.org/10.48550/arXiv.2105.05537.
[16]	LIN A L, CHEN B Z, XU J Y, et al. DS-TransUNet: Dual swin transformer U-net for medical image segmentation[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-15.
[17]	HUANG X, DENG Z, LI D, et al. MISSFormer: An effective medical image segmentation transformer[EB/OL]. arXiv: 2109.07162 (2021-09-15) [2024-04-01]. https://doi.org/10.48550/arXiv.2109.07162.
[18]	ZHOU H Y, GUO J, ZHANG Y, et al. nnformer: Interleaved transformer for volumetric segmentation[EB/OL]. arXiv: 2109.03201 (2021-09-07) [2024-04-01]. https://doi.org/10.48550/arXiv.2109.03201.
[19]	WANG H Y, XIE S, LIN L F, et al. Mixed transformer U-Net for medical image segmentation[EB/OL]. arXiv: 2111.04734 (2021-11-08) [2024-04-01]. https://doi.org/10.48550/arXiv.2111.04734.
[20]	TRAGAKIS A, KAUL C, MURRAY-SMITH R, et al. The fully convolutional transformer for medical image segmentation[C]//2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Waikoloa, HI, USA: IEEE, 2023: 3660-3669.
[21]	LIU Z, LIN Y T, CAO Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, QC, Canada: IEEE, 2021: 10012-10022.
[22]	LIU Z, MAO H Z, WU C Y, et al. A ConvNet for the 2020s[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, LA, USA: IEEE, 2022: 11976-11986.
[23]	WU H P, XIAO B, CODELLA N, et al. Cvt: Introducing convolutions to vision transformers[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, QC, Canada: IEEE, 2021: 22-31.
[24]	GU Z W, CHENG J, FU H Z, et al. CE-net: Context encoder network for 2D medical image segmentation[J]. IEEE Transactions on Medical Imaging, 2019, 38(10): 2281-2292. doi: 10.1109/TMI.2019.2903562

[1]	LIU Guohai, WAN Yalian, SHEN Yue, LIU Hui, HE Siwei, ZHANG Yafei. Complete coverage path planning of irregular convex field for the high clearance unmanned sprayer based on improved particle swarm optimizer algorithm[J]. Journal of South China Agricultural University, 2025, 46(3): 390-398. DOI: 10.7671/j.issn.1001-411X.202409017
[2]	XIE Jinyan, LIU Lixing, YANG Xin, WANG Xiaosa, WANG Xu, LIU Shuteng. A path optimization algorithm for cooperative operation of multiple unmanned mowers in apple orchard[J]. Journal of South China Agricultural University, 2024, 45(4): 578-587. DOI: 10.7671/j.issn.1001-411X.202309010
[3]	ZHANG Yali, MO Zhenjie, TIAN Haoxin, LAN Yubin, WANG Linlin. Path planning algorithm of agricultural robot based on improved APF-FMT*[J]. Journal of South China Agricultural University, 2024, 45(3): 408-415. DOI: 10.7671/j.issn.1001-411X.202305030
[4]	YANG Chen, CHEN Jiyang, HU Qingsong, ZHANG Zheng, NIU Fengjie. Path planning of unmanned vehicle based on multi-objective PSO-ACO fusion algorithm[J]. Journal of South China Agricultural University, 2023, 44(1): 65-73. DOI: 10.7671/j.issn.1001-411X.202205005
[5]	WANG Wei, ZHANG Yanfei, GONG Jinliang, LAN Yubin. Whole area coverage strategy of agricultural robot based on adaptive heating simulated annealing algorithm[J]. Journal of South China Agricultural University, 2021, 42(6): 126-132. DOI: 10.7671/j.issn.1001-411X.202104022
[6]	WANG Wei, ZHANG Yanfei, GONG Jinliang. Study on the whole area coverage of agricultural robot in complex environment based on ant colony-BFS algorithm[J]. Journal of South China Agricultural University, 2021, 42(3): 119-125. DOI: 10.7671/j.issn.1001-411X.202009027
[7]	XIE Zhonghong, WANG Pei, GU Baoxing, JI Changying, TIAN Guangzhao. Application of genetic algorithm based on group and elite strategy for robot navigation[J]. Journal of South China Agricultural University, 2017, 38(5): 110-116. DOI: 10.7671/j.issn.1001-411X.2017.05.019
[8]	WANG Liu-yi,FU Yin-lian,JIN Ling-ling. Studies on Algorithms to Detect and Segment Licence Plate Figure[J]. Journal of South China Agricultural University, 2006, 27(3): 100-102. DOI: 10.7671/j.issn.1001-411X.2006.03.028
[9]	ZHENG Guo-qing,ZHANG Guo-quan. Parameter Estimations of Semi-Parametric Linear Regression Models Using Simulated Annealing Algorithm[J]. Journal of South China Agricultural University, 2006, 27(2): 115-117. DOI: 10.7671/j.issn.1001-411X.2006.02.030
[10]	LI Bo. A Distributed Routing Algorithm Based on Delay-Limiting[J]. Journal of South China Agricultural University, 2003, 24(4): 96-99. DOI: 10.7671/j.issn.1001-411X.2003.04.026

Cited By

Cited by

Periodical cited type(17)

1.	蒋沅均，刘红光，余立扬，廖新炜，余劼，陈宇佳，刘畅，秦文祥，郑炜超. 蛋鸡养殖智能巡检机器人设计概述与应用. 中国家禽. 2025(02): 89-97 .
2.	熊竹青，陈怡然，刘莹，孙雷，刘玉龙，闫银发，田野，冯泽猛，印遇龙. 畜禽养殖场舍电磁环境研究进展. 家畜生态学报. 2025(01): 98-107 .
3.	王晨晓，耿丹丹，毕瑜林，陈国宏，常国斌，白皓. 肠道微生物及其代谢产物对家禽饲料利用率影响的研究进展. 中国家禽. 2025(05): 152-160 .
4.	徐君鹏，时磊，王宇，杨文强，杨秋亚. 基于PLC的生猪养殖智能化环境监控及云平台系统设计. 河南科技学院学报(自然科学版). 2025(03): 44-53 .
5.	王祎娜，王鹏军，陈聪. 肉鸡福利养殖的发展现状与趋势. 智能化农业装备学报(中英文). 2025(02): 105-110 .
6.	韩雨晓，李帅，王宁，安娅军，张漫，李寒. 基于3D激光雷达的鸡舍通道中心线检测方法. 农业工程学报. 2024(09): 173-181 .
7.	邵润霖，白宇航，刘睿衡，张京，董梦玥，肖德琴，谢青梅，张新珩. 家禽疫病智能化检测技术研究进展. 中国家禽. 2024(07): 93-100 .
8.	肖德琴，黄一桂，熊悦淞，刘俊彬，谭祖杰，吕斯婷. 畜禽机器人技术研究进展与未来展望. 华南农业大学学报. 2024(05): 624-634+620 . 本站查看
9.	刘晓燕. 亚氨基二乙酸型螯合树脂柱-电感耦合等离子体质谱法测定家禽养殖废水中7种金属元素的残留量. 理化检验-化学分册. 2024(07): 744-748 .
10.	余志安，肖瑞全，李秋生，汤晋，陈恒，谢宁，刘小春. 江西省家禽产业数字化现实基础、制约因素及推进路径. 中国禽业导刊. 2024(08): 19-25 .
11.	孙杰，马凯欣，王佳乐，胡应宽. 禽舍智慧管家——基于数字农业的家禽养殖应用. 当代畜牧. 2024(06): 1-3 .
12.	宁小芬，陆美连，莫梅清，方燕，李梦玲，刘皓，王开胜. 我国智慧养殖关键技术、平台及其应用的研究进展. 玉林师范学院学报. 2024(03): 95-100 .
13.	肖德琴，曾瑞麟，周敏，黄一桂，王文策. 基于DH-YoloX的群养马岗鹅关键行为监测. 农业工程学报. 2023(02): 142-149 .
14.	冷婷婷. 家禽养殖设备专利分析. 现代畜牧科技. 2023(07): 132-135 .
15.	胡建平，赵新宇，冯汝广，范国华，赵翠敏. 传感器在设施农业中的应用. 南方农机. 2023(19): 59-61+91 .
16.	杨雨彤，句金，任守华. 基于深度卷积神经网络的蛋鸡体温监测系统. 现代畜牧科技. 2023(10): 51-55 .
17.	冉明霞，郑基坛，刘兴廷，谢龙，左二伟，陆阳清. 家禽基因编辑相关技术研究进展及应用. 中国畜禽种业. 2023(12): 36-48 .

Other cited types(16)

Get Citation

PDF

XML

Article views (568) PDF downloads (19) Cited by(33)

Turn off MathJax

Article Contents

Abstract

References

Feed consumption status monitoring method of dairy cows based on Swin-Unet