CattleFaceNet: A cattle face identification approach based on RetinaFace and ArcFace loss
文献类型： 外文期刊
作者： Xu, Beibei 1 ; Wang, Wensheng 1 ; Guo, Leifeng 1 ; Chen, Guipeng 2 ; Li, Yongfeng 1 ; Cao, Zhen 1 ; Wu, Saisai 1 ;
作者机构： 1.Chinese Acad Agr Sci, Agr Informat Inst, Beijing 100086, Peoples R China
2.Jiangxi Acad Agr Sci, Agr Econ & Informat Inst, Nanchang 330200, Jiangxi, Peoples R China
3.Wageningen Univ & Res, Informat Technol Grp, NL-6708 PB Wageningen, Netherlands
关键词： Face recognition; RetinaFace; ArcFace loss; Deep learning; Precision livestock
期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：6.757； 五年影响因子：6.817 ）
ISSN： 0168-1699
年卷期： 2022 年 193 卷
页码：
收录情况： SCI
摘要： Cattle identification is crucial to be registered for breeding association, food quality tracing, disease prevention and control and fake insurance claims. Traditional non-biometrics methods for cattle identification is not really satisfactory in providing reliability due to theft, fraud, and duplication. In this study, a computer vision technique was proposed to facilitate precision animal management and improve livestock welfare. This paper presents a novel face identification framework by integrating light-weight RetinaFace-mobilenet with Additive Angular Margin Loss (ArcFace), namely CattleFaceNet. RetinaFace-mobilenet is designed for face detection and location, and ArcFace is adopted to strengthen the within-class compactness and also between-class discrepancy during training. Experiments on real-word scenarios dataset prove that RetinaFace-mobilenet achieves superior detection performance and significantly accelerates the computation time against RetinaNet. Three loss functions utilized in human face recognition combined with RetinaFace-mobilenet are compared and results indict that the proposed CattleFaceNet outperforms others with identification accuracy of 91.3% and processing time of 24 frames per second (FPS). This research work demonstrates the potential candidate of CattleFaceNet for livestock identification in real time in practical production scenarios.
- 相关文献
作者其他论文 更多>>
-
Research on SPAD Inversion of Rice Leaves at a Field Scale Based on Machine Vision and Leaf Segmentation Techniques
作者：Yue, Bailin;Jin, Yong;Chen, Youxing;Wu, Shangrong;Zhong, Hu;Wu, Shangrong;Zhong, Hu;Tan, Jieyang;Chen, Guipeng;Deng, Yingbin
关键词：SPAD inversion; machine vision; leaf segmentation; U-Net network model; feature optimization
-
Rape Yield Estimation Considering Non-Foliar Green Organs Based on the General Crop Growth Model
作者：Ruan, Shiwei;Ma, Yujing;Jin, Yong;Cao, Hong;Wu, Shangrong;Li, Wenjuan;Deng, Hui;Wu, Wenbin;Yang, Peng;Cao, Hong;Wu, Shangrong;Li, Wenjuan;Deng, Hui;Wu, Wenbin;Yang, Peng;Chen, Guipeng
关键词：
-
An Assessment of Soil Loss by Water Erosion in No-Tillage and Mulching, China
作者：Cao, Zhen;Chen, Guohui;Huang, Shangshu;Jiang, Fahui;Cao, Zhen;Cao, Zhen;Chen, Guohui;Zhang, Song;Huang, Shangshu;Wu, Yan;Dong, Fangjin;Guo, Yuming;Wang, Jianhao
关键词：soil erosion; water erosion; RUSLE; crop residue; conservation tillage
-
A Large-Scale Dataset of Conservation and Deep Tillage in Mollisols, Northeast Plain, China
作者：Jiang, Fahui;Huang, Shangshu;Huang, Shangshu;Wu, Yan;Ul Islam, Mahbub;Dong, Fangjin;Cao, Zhen;Chen, Guohui;Guo, Yuming
关键词：conservation tillage; deep tillage; conventional tillage; random forest; meta-analysis; subsoiling; no-tillage; straw mulching; crop yield
-
CattleFaceNet: A cattle face identification approach based on RetinaFace and ArcFace loss
作者：Xu, Beibei;Wang, Wensheng;Guo, Leifeng;Li, Yongfeng;Cao, Zhen;Wu, Saisai;Chen, Guipeng;Cao, Zhen
关键词：Face recognition; RetinaFace; ArcFace loss; Deep learning; Precision livestock
-
Recognition of Cattle's Feeding Behaviors Using Noseband Pressure Sensor With Machine Learning
作者：Chen, Guipeng;Li, Cong;Guo, Yang;Shu, Hang;Cao, Zhen;Xu, Beibei
关键词：noseband pressure sensor; machine learning; XGB; behavior classification; feeding behaviors
-
Recognition of Cattle's Feeding Behaviors Using Noseband Pressure Sensor With Machine Learning
作者：Chen, Guipeng;Li, Cong;Guo, Yang;Shu, Hang;Cao, Zhen;Xu, Beibei
关键词：noseband pressure sensor; machine learning; XGB; behavior classification; feeding behaviors
