A systematic review of machine learning techniques for cattle identification:Datasets,methods and future directions

作     者：Md Ekramul Hossain Muhammad Ashad Kabir Lihong Zheng Dave L.Swain Shawn McGrath Jonathan Medway 

作者机构：School of ComputingMathematics and EngineeringCharles Sturt UniversityBathurstNSW 2795Australia Gulbali Institute for AgricultureWater and EnvironmentCharles Sturt UniversityWagga WaggaNSW 2678Australia TerraCipher Pty.Ltd.Alton DownsQLD 4702Australia Fred Morley CentreSchool of Animal and Veterinary SciencesCharles Sturt UniversityWagga WaggaNSW 2678Australia Food Agility CRC LtdSydneyNSW 2000Australia 

出 版 物：《Artificial Intelligence in Agriculture》 (农业人工智能（英文）)

年 卷 期：2022年第6卷第1期

页      面：138-155页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by funding from Food Agility CRC Ltd funded under the Commonwealth Government CRC Program 

主　　题：Cattle identification Cattle detection Machine learning Deep learning Cattle farming 

摘      要：Increased biosecurity and food safety requirements may increase demand for efficient traceability and identification systems of livestock in the supply *** advanced technologies of machine learning and computer vision have been applied in precision livestock management,including critical disease detection,vaccination,production management,tracking,and health *** paper offers a systematic literature review(SLR)of vision-based cattle *** specifically,this SLR is to identify and analyse the research related to cattle identification using Machine Learning(ML)and Deep Learning(DL).This study retrieved 731 studies from four online scholarly ***-five articles were subsequently selected and investigated in *** the two main applications of cattle detection and cattle identification,all the ML based papers only solve cattle identification ***,both detection and identification problems were studied in the DL based *** on our survey report,the most used ML models for cattle identification were support vector machine(SVM),k-nearest neighbour(KNN),and artificial neural network(ANN).Convolutional neural network(CNN),residual network(ResNet),Inception,You Only Look Once(YOLO),and Faster R-CNN were popular DL models in the selected *** these papers,the most distinguishing features were the muzzle prints and coat patterns of *** binary pattern(LBP),speeded up robust features(SURF),scaleinvariant feature transform(SIFT),and Inception or CNN were identified as the most used feature extraction *** paper details important factors to consider when choosing a technique or *** also identified major challenges in cattle *** are few publicly available datasets,and the quality of those datasets are affected by the wild environment and movement while collecting *** processing time is a critical factor for a real-time cattle identification ***,a recommendati