A Lightweight Neural Network-Based Method for Detecting Estrus Behavior in Ewes
We propose a lightweight neural network-based method to detect the estrus behavior of ewes. Our suggested method is mainly proposed to solve the problem of not being able to detect ewe estrus behavior in a timely and accurate manner in large-scale meat sheep farms. The three main steps of our propos...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/12/8/1207 |
| _version_ | 1827601182130962432 |
|---|---|
| author | Longhui Yu Yuhai Pu Honglei Cen Jingbin Li Shuangyin Liu Jing Nie Jianbing Ge Linze Lv Yali Li Yalei Xu Jianjun Guo Hangxing Zhao Kang Wang |
| author_facet | Longhui Yu Yuhai Pu Honglei Cen Jingbin Li Shuangyin Liu Jing Nie Jianbing Ge Linze Lv Yali Li Yalei Xu Jianjun Guo Hangxing Zhao Kang Wang |
| author_sort | Longhui Yu |
| collection | DOAJ |
| description | We propose a lightweight neural network-based method to detect the estrus behavior of ewes. Our suggested method is mainly proposed to solve the problem of not being able to detect ewe estrus behavior in a timely and accurate manner in large-scale meat sheep farms. The three main steps of our proposed methodology include constructing the dataset, improving the network structure, and detecting the ewe estrus behavior based on the lightweight network. First, the dataset was constructed by capturing images from videos with estrus crawling behavior, and the data enhancement was performed to improve the generalization ability of the model at first. Second, the original Darknet-53 was replaced with the EfficientNet-B0 for feature extraction in YOLO V3 neural network to make the model lightweight and the deployment easier, thus shortening the detection time. In order to further obtain a higher accuracy of detecting the ewe estrus behavior, we joined the feature layers to the SENet attention module. Finally, the comparative results demonstrated that the proposed method had higher detection accuracy and FPS, as well as a smaller model size than the YOLO V3. The precision of the proposed scheme was 99.44%, recall was 95.54%, F1 value was 97%, AP was 99.78%, FPS was 48.39 f/s, and Model Size was 40.6 MB. This study thus provides an accurate, efficient, and lightweight detection method for the ewe estrus behavior in large-scale mutton sheep breeding. |
| first_indexed | 2024-03-09T04:50:37Z |
| format | Article |
| id | doaj.art-1a642214d8394d27a2d92e07bcebe103 |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-09T04:50:37Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-1a642214d8394d27a2d92e07bcebe1032023-12-03T13:10:45ZengMDPI AGAgriculture2077-04722022-08-01128120710.3390/agriculture12081207A Lightweight Neural Network-Based Method for Detecting Estrus Behavior in EwesLonghui Yu0Yuhai Pu1Honglei Cen2Jingbin Li3Shuangyin Liu4Jing Nie5Jianbing Ge6Linze Lv7Yali Li8Yalei Xu9Jianjun Guo10Hangxing Zhao11Kang Wang12College of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaWe propose a lightweight neural network-based method to detect the estrus behavior of ewes. Our suggested method is mainly proposed to solve the problem of not being able to detect ewe estrus behavior in a timely and accurate manner in large-scale meat sheep farms. The three main steps of our proposed methodology include constructing the dataset, improving the network structure, and detecting the ewe estrus behavior based on the lightweight network. First, the dataset was constructed by capturing images from videos with estrus crawling behavior, and the data enhancement was performed to improve the generalization ability of the model at first. Second, the original Darknet-53 was replaced with the EfficientNet-B0 for feature extraction in YOLO V3 neural network to make the model lightweight and the deployment easier, thus shortening the detection time. In order to further obtain a higher accuracy of detecting the ewe estrus behavior, we joined the feature layers to the SENet attention module. Finally, the comparative results demonstrated that the proposed method had higher detection accuracy and FPS, as well as a smaller model size than the YOLO V3. The precision of the proposed scheme was 99.44%, recall was 95.54%, F1 value was 97%, AP was 99.78%, FPS was 48.39 f/s, and Model Size was 40.6 MB. This study thus provides an accurate, efficient, and lightweight detection method for the ewe estrus behavior in large-scale mutton sheep breeding.https://www.mdpi.com/2077-0472/12/8/1207behavior detectiondeep learningEfficientNetewe estrusYOLO v3 |
| spellingShingle | Longhui Yu Yuhai Pu Honglei Cen Jingbin Li Shuangyin Liu Jing Nie Jianbing Ge Linze Lv Yali Li Yalei Xu Jianjun Guo Hangxing Zhao Kang Wang A Lightweight Neural Network-Based Method for Detecting Estrus Behavior in Ewes Agriculture behavior detection deep learning EfficientNet ewe estrus YOLO v3 |
| title | A Lightweight Neural Network-Based Method for Detecting Estrus Behavior in Ewes |
| title_full | A Lightweight Neural Network-Based Method for Detecting Estrus Behavior in Ewes |
| title_fullStr | A Lightweight Neural Network-Based Method for Detecting Estrus Behavior in Ewes |
| title_full_unstemmed | A Lightweight Neural Network-Based Method for Detecting Estrus Behavior in Ewes |
| title_short | A Lightweight Neural Network-Based Method for Detecting Estrus Behavior in Ewes |
| title_sort | lightweight neural network based method for detecting estrus behavior in ewes |
| topic | behavior detection deep learning EfficientNet ewe estrus YOLO v3 |
| url | https://www.mdpi.com/2077-0472/12/8/1207 |
| work_keys_str_mv | AT longhuiyu alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT yuhaipu alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT hongleicen alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT jingbinli alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT shuangyinliu alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT jingnie alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT jianbingge alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT linzelv alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT yalili alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT yaleixu alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT jianjunguo alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT hangxingzhao alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT kangwang alightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT longhuiyu lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT yuhaipu lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT hongleicen lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT jingbinli lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT shuangyinliu lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT jingnie lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT jianbingge lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT linzelv lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT yalili lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT yaleixu lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT jianjunguo lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT hangxingzhao lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes AT kangwang lightweightneuralnetworkbasedmethodfordetectingestrusbehaviorinewes |