Research on individual recognition of dairy cows based on improved Mask R-CNN

LI Haoyue; CHEN Guifen; PEI Ao

doi:10.7671/j.issn.1001-411X.202003030

Journal of South China Agricultural University > 2020 > 41(6): 161-168. > DOI: 10.7671/j.issn.1001-411X.202003030

LI Haoyue, CHEN Guifen, PEI Ao. Research on individual recognition of dairy cows based on improved Mask R-CNN[J]. Journal of South China Agricultural University, 2020, 41(6): 161-168. DOI: 10.7671/j.issn.1001-411X.202003030

Citation:

PDF (983 KB)

Research on individual recognition of dairy cows based on improved Mask R-CNN

College of Information Technology, Jilin Agricultural University, Changchun 130118, China

More Information

Received Date: March 28, 2020
Available Online: May 17, 2023

Graphical Abstract

Abstract

Abstract

Objective
To propose an individual cow recognition method based on the improved Mask R-CNN algorithm, and solve the problem of low efficiency and strong subjectivity of artificially identifying individual cows in traditional dairy farming.

Method
This method optimizes the feature extraction network structure in Mask R-CNN, adopts ResNet-50 network embedded in SE block as backbone, and selects image channels by weighting strategy to improve feature utilization. For the problem of inaccurate target edge positioning during instance segmentation, a boundary weighted loss function is added to construct a new Mask loss function to improve the accuracy of boundary detection. A total of 3000 cow images are trained, validated and tested.

Result
The improved Mask R-CNN model had an average precision (AP) of 100% and IoU_Mask of 91.34%. Compared with the original Mask R-CNN model, AP increased by 3.28% and IoU_Mask increased by 5.92%.

Conclusion
The proposed method has strong segmentation accuracy and robustness, and can provide a reference for accurate recognition of cow images under complex farming environment.
- Mask R-CNN,
- SENet,
- IoU boundary loss,
- image recognition,
- cow recognition

FullText(HTML)

References (21)

References

[1]	郑国生, 施正香, 滕光辉. 基于不同行为时间的奶牛健康状况评价[J]. 农业工程学报, 2019, 35(19): 238-244. doi: 10.11975/j.issn.1002-6819.2019.19.029
[2]	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. doi: 10.6041/j.issn.1000-1298.2016.05.032
[3]	刘杰鑫, 姜波, 何东健, 等. 基于高斯混合模型与CNN的奶牛个体识别方法研究[J]. 计算机应用与软件, 2018, 35(10): 159-164.
[4]	张满囤, 单新媛, 于洋, 等. 基于小波变换和改进KPCA的奶牛个体识别研究[J]. 浙江农业学报, 2017, 29(12): 2000-2008. doi: 10.3969/j.issn.1004-1524.2017.12.07
[5]	刘忠超, 翟天嵩, 何东健. 精准养殖中奶牛个体信息监测研究现状及进展[J]. 黑龙江畜牧兽医, 2019(13): 30-33.
[6]	汪开英, 赵晓洋, 何勇. 畜禽行为及生理信息的无损监测技术研究进展[J]. 农业工程学报, 2017, 33(20): 197-209. doi: 10.11975/j.issn.1002-6819.2017.20.025
[7]	孙雨坤, 王玉洁, 霍鹏举, 等. 奶牛个体识别方法及其应用研究进展[J]. 中国农业大学学报, 2019, 24(12): 62-70.
[8]	陈娟娟, 刘财兴, 高月芳, 等. 基于改进特征袋模型的奶牛识别算法[J]. 计算机应用, 2016, 36(8): 2346-2351. doi: 10.11772/j.issn.1001-9081.2016.08.2346
[9]	张满囤, 米娜, 于洋, 等. 基于特征融合的奶牛个体识别[J]. 江苏农业科学, 2018, 46(24): 278-281.
[10]	杨阿庆, 薛月菊, 黄华盛, 等. 基于全卷积网络的哺乳母猪图像分割[J]. 农业工程学报, 2017, 33(23): 219-225. doi: 10.11975/j.issn.1002-6819.2017.23.028
[11]	蔡骋, 宋肖肖, 何进荣. 基于计算机视觉的牛脸轮廓提取算法及实现[J]. 农业工程学报, 2017, 33(11): 171-177. doi: 10.11975/j.issn.1002-6819.2017.11.022
[12]	赵凯旋, 何东健. 基于卷积神经网络的奶牛个体身份识别方法[J]. 农业工程学报, 2015, 31(5): 181-187. doi: 10.3969/j.issn.1002-6819.2015.05.026
[13]	王毅恒, 许德章. 基于YOLOv3算法的农场环境下奶牛目标识别[J]. 广东石油化工学院学报, 2019, 29(4): 31-35. doi: 10.3969/j.issn.2095-2562.2019.04.007
[14]	HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[J]. IEEE T Pattern Anal, 2017(99): 1.
[15]	REN S, HE K, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE T Pattern Anal, 2017, 39(6): 1137-1149. doi: 10.1109/TPAMI.2016.2577031
[16]	HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE T Pattern Anal, 2020, 42(8): 2011-2023.
[17]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]. IEEE. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas: IEEE Computer Society, 2016.
[18]	LUO Z, MISHRA A, ACHKAR A, et al. Non-local deep features for salient object detection[C]. IEEE. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii: IEEE Computer Society, 2017.
[19]	LIU F, LIU P Y, LI B, et al. Deep learning model design of video target tracking based on TensorFlow platform[J]. Laser & Optoelectronics Progress, 2017, 54(9): 091501.
[20]	SUN X D, WU P C, HOI S C H. Face detection using deep learning: An improved faster RCNN approach[J]. Neurocomputing, 2018, 299: 42-50. doi: 10.1016/j.neucom.2018.03.030
[21]	HUANG Z J, HUANG L C, GONG Y C, et al. Mask scoring R-CNN[C]. IEEE. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Los Angeles: IEEE Computer Society, 2019.

Cited By

Cited by

Periodical cited type(9)

1.	刘娜，安晓萍，王园，王步钰，齐景伟. 机器视觉技术在奶牛精准化管理中的应用研究进展. 中国畜牧杂志. 2024(07): 34-40 .
2.	宋怀波，王云飞，邓洪兴，许兴时，温毓晨，张姝瑾. 基于视频分析的规模化奶牛智能监测技术研究进展. 华南农业大学学报. 2024(05): 649-660 . 本站查看
3.	吴瑞志，罗维平. 基于深度学习的奶牛个体识别. 武汉纺织大学学报. 2024(06): 63-69 .
4.	付丽丽，李士军，孔朔琳，宫鹤，李思函. 基于Multi-Light模型的奶牛个体识别研究. 黑龙江畜牧兽医. 2023(03): 41-45+51+132-133 .
5.	李丹妮，栾静，穆金庆. 基于YOLOv5的香烟目标检测算法. 软件导刊. 2023(01): 229-235 .
6.	彭阳翔，杨振标，闫奎友，王瀚，呼德，王尊，刘宁，赵连生. 从人工到智能：牛个体识别技术研究进展. 中国畜牧兽医. 2023(05): 1855-1866 .
7.	王金星，马博，王震，刘双喜，慕君林，王云飞. 基于改进Mask R-CNN的苹果园害虫识别方法. 农业机械学报. 2023(06): 253-263+360 .
8.	肖哲非，沈建，郑晓伟，徐文其. 基于改进Mask R-CNN的花白鲢去鳞率计算方法研究. 渔业现代化. 2022(02): 85-93 .
9.	侯向宁，刘华春，侯宛贞. 基于改进VGG16网络模型的花卉分类. 计算机系统应用. 2022(07): 172-178 .

Other cited types(9)

Get Citation

PDF

XML

Article views (1026) PDF downloads (1715) Cited by(18)

Turn off MathJax

Article Contents

Abstract

References

Research on individual recognition of dairy cows based on improved Mask R-CNN

Abstract

References

Cited by

Periodical cited type(9)

Other cited types(9)

Catalog

Export File

Citation

Format

Content