Individual Identification of Cattle Based on RGB-D Images

被引：0
作者：
Liu S. [1 ,2 ]
Chang R. [3 ]
Li B. [1 ,2 ]
Wei Y. [2 ]
Wang H. [1 ]
Jia N. [1 ]
机构：
[1] Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing
[2] College of Engineering and Technology, Tianjin Agricultural University, Tianjin
[3] Chinese Academy of Agricultural Mechanization Sciences Group Co., Ltd., Beijing
来源：
Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2023年 / 54卷
关键词：
convolutional neural network; cow face recognition; RGB; —; D; deep learning;
D O I：
10.6041/j.issn.1000-1298.2023.S1.028
中图分类号：
学科分类号：
摘要：
Individual identification is the foundation for achieving digital management of cattle. In order to achieve non-contact and high -precision individual identification, a dairy cow face recognition method based on RGB — D information fusion was proposed. Totally 108 Holstein cows aged 28 months to 30 months were selected as the research subjects, and 2 334 color/depth images of cattle faces were collected by using the Intel RealSense D455 depth camera as the original dataset. Firstly, image preprocessing was carried out by using redundant image elimination and adaptive threshold background separation algorithms. After enhancement, a total of 8 344 cattle face images was obtained as the dataset. Then, three feature extraction networks, including Inception ResNet vl, Inception ResNet v2, and Squeeze Net, were selected to extract the facial features of the cattle face. The optimal backbone feature extraction network of the FaceNet model was determined through comparative analysis. Finally, the extracted dairy cow face image features were L2 regularization and mapped to the same feature space. A classifier was trained to achieve individual classification of dairy cows. The test results showed that using Inception ResNet v2 as the backbone feature extraction network of the FaceNet model had the best performance. After testing the cow face recognition accuracy on the preprocessed dataset with background separation, the accuracy reached 98. 6%, the verification rate was 81.9%, and the misidentification rate was 0. 10%. Compared with that of Inception ResNet vl and SqueezeNet networks, the accuracy was improved by 1 percentage points and 2. 9 percentage points, respectively. Compared with that of the dataset without background separation, the accuracy was improved by 2. 3 percentage points. The research result can provide a method for dairy cow face recognition. © 2023 Chinese Society of Agricultural Machinery. All rights reserved.
引用
收藏
页码：260 / 266
页数：6
相关论文
共 30 条
  • [1] HE Dongjian, LIU Chang, XIONG Hongting, Design and experiment of implantable sensor and real-time detection system for temperature monitoring of cow, Transactions of the Chinese Society for Agricultural Machinery, 49, 12, pp. 195-202, (2018)
  • [2] LIU Zhongchao, HE Dongjian, Recognition method of cow estrus behavior based on convolutional neural network, Transactions of the Chinese Society for Agricultural Machinery, 50, 7, pp. 186-193, (2019)
  • [3] TSAI D M, HUANG C Y., A motion and image analysis method for automatic detection of estrus and mating behavior in cattle, Computers and Electronics in Agriculture, 104, pp. 25-31, (2014)
  • [4] LESLIE E, HERNANDEZ-JOVER M, NEWMAN R, Et al., Assessment of acute pain experienced by piglets from ear tagging, ear notching and intraperitoneal injectable transponders[J], Applied Animal Behaviour Science, 127, 3 - 4, pp. 86-95, (2010)
  • [5] ZIN T T, MISAWA S, PWINT M Z, Et al., Cow identification system using ear tag recognition[C], 2020 IEEE 2nd Global Conference on Life Sciences and Technologies (LifeTech), pp. 65-66, (2020)
  • [6] AWAD A I., From classical methods to animal biometrics: a review on cattle identification and tracking [J], Computers and Electronics in Agriculture, 123, pp. 423-435, (2016)
  • [7] RUIZ-GARCIA L, LUNADEI L., The role of RFID in agriculture: applications, limitations and challenges[J], Computers and Electronics in Agriculture, 79, 1, pp. 42-50, (2011)
  • [8] LI Chao, ZHAO Lindu, Research on cattle iris localization algorithm and its application in meat food tracking and traceability system, China Safety Science Journal, 21, 3, pp. 124-130, (2011)
  • [9] BARRY B, GONZALES-BARRON U A, MCDONNELL K, Et al., Using muzzle pattern recognition as a biometric approach for cattle identification [J], Transactions of the ASABE, 50, 3, pp. 1073-1080, (2007)
  • [10] KUMAR S, SINGH S K, ABIDI A I, Et al., Group sparse representation approach for recognition of cattle on muzzle point images[J], International Journal of Parallel Programming, 46, 5, pp. 812-837, (2018)
123