Open Collections

UBC Faculty Research and Publications

Division of Cow Production Groups Based on SOLOv2 and Improved CNN-LSTM Cui, Guanying; Qiao, Lulu; Li, Yuhua; Chen, Zhilong; Liang, Zhenyu; Xin, Chengrui; Xiao, Maohua; Zou, Xiuguo

Abstract

Udder conformation traits interact with cow milk yield, and it is essential to study the udder characteristics at different levels of production to predict milk yield for managing cows on farms. This study aims to develop an effective method based on instance segmentation and an improved neural network to divide cow production groups according to udders of high- and low-yielding cows. Firstly, the SOLOv2 (Segmenting Objects by LOcations) method was utilized to finely segment the cow udders. Secondly, feature extraction and data processing were conducted to define several cow udder features. Finally, the improved CNN-LSTM (Convolution Neural Network-Long Short-Term Memory) neural network was adopted to classify high- and low-yielding udders. The research compared the improved CNN-LSTM model and the other five classifiers, and the results show that CNN-LSTM achieved an overall accuracy of 96.44%. The proposed method indicates that the SOLOv2 and CNN-LSTM methods combined with analysis of udder traits have the potential for assigning cows to different production groups.

Item Metadata

Title
Division of Cow Production Groups Based on SOLOv2 and Improved CNN-LSTM
Creator
Cui, Guanying; Qiao, Lulu; Li, Yuhua; Chen, Zhilong; Liang, Zhenyu; Xin, Chengrui; Xiao, Maohua; Zou, Xiuguo
Publisher
Multidisciplinary Digital Publishing Institute
Date Issued
2023-08-04
Description
Udder conformation traits interact with cow milk yield, and it is essential to study the udder characteristics at different levels of production to predict milk yield for managing cows on farms. This study aims to develop an effective method based on instance segmentation and an improved neural network to divide cow production groups according to udders of high- and low-yielding cows. Firstly, the SOLOv2 (Segmenting Objects by LOcations) method was utilized to finely segment the cow udders. Secondly, feature extraction and data processing were conducted to define several cow udder features. Finally, the improved CNN-LSTM (Convolution Neural Network-Long Short-Term Memory) neural network was adopted to classify high- and low-yielding udders. The research compared the improved CNN-LSTM model and the other five classifiers, and the results show that CNN-LSTM achieved an overall accuracy of 96.44%. The proposed method indicates that the SOLOv2 and CNN-LSTM methods combined with analysis of udder traits have the potential for assigning cows to different production groups.
Subject
cow udder classification; udder features; instance segmentation; CNN-LSTM; udder conformation
Genre
Article
Type
Text
Language
eng
Date Available
2023-09-27
Provider
Vancouver : University of British Columbia Library
Rights
CC BY 4.0
DOI
10.14288/1.0436902
URI
http://hdl.handle.net/2429/86035
Affiliation
Applied Science, Faculty of; Alumni; Non UBC; Engineering, School of (Okanagan)
Citation
Agriculture 13 (8): 1562 (2023)
Publisher DOI
10.3390/agriculture13081562
Peer Review Status
Reviewed
Scholarly Level
Faculty; Researcher; Other
Rights URI
https://creativecommons.org/licenses/by/4.0/
Aggregated Source Repository
DSpace

Item Media

Item Citations and Data

Rights

CC BY 4.0