A Recognition Method of Ewe Estrus Crawling Behavior Based on Multi-Target Detection Layer Neural Network
There are some problems with estrus detection in ewes in large-scale meat sheep farming: mainly, the manual detection method is labor-intensive and the contact sensor detection method causes stress reactions in ewes. To solve the abovementioned problems, we proposed a multi-objective detection layer...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/13/3/413 |
| _version_ | 1827760651476402176 |
|---|---|
| author | Longhui Yu Jianjun Guo Yuhai Pu Honglei Cen Jingbin Li Shuangyin Liu Jing Nie Jianbing Ge Shuo Yang Hangxing Zhao Yalei Xu Jianglin Wu Kang Wang |
| author_facet | Longhui Yu Jianjun Guo Yuhai Pu Honglei Cen Jingbin Li Shuangyin Liu Jing Nie Jianbing Ge Shuo Yang Hangxing Zhao Yalei Xu Jianglin Wu Kang Wang |
| author_sort | Longhui Yu |
| collection | DOAJ |
| description | There are some problems with estrus detection in ewes in large-scale meat sheep farming: mainly, the manual detection method is labor-intensive and the contact sensor detection method causes stress reactions in ewes. To solve the abovementioned problems, we proposed a multi-objective detection layer neural network-based method for ewe estrus crawling behavior recognition. The approach we proposed has four main parts. Firstly, to address the problem of mismatch between our constructed ewe estrus dataset and the YOLO v3 anchor box size, we propose to obtain a new anchor box size by clustering the ewe estrus dataset using the K-means++ algorithm. Secondly, to address the problem of low model recognition precision caused by small imaging of distant ewes in the dataset, we added a 104 × 104 target detection layer, making the total target detection layer reach four layers, strengthening the model’s ability to learn shallow information and improving the model’s ability to detect small targets. Then, we added residual units to the residual structure of the model, so that the deep feature information of the model is not easily lost and further fused with the shallow feature information to speed up the training of the model. Finally, we maintain the aspect ratio of the images in the data-loading module of the model to reduce the distortion of the image information and increase the precision of the model. The experimental results show that our proposed model has 98.56% recognition precision, while recall was 98.04%, F1 value was 98%, mAP was 99.78%, FPS was 41 f/s, and model size was 276 M, which can meet the accurate and real-time recognition of ewe estrus behavior in large-scale meat sheep farming. |
| first_indexed | 2024-03-11T09:54:33Z |
| format | Article |
| id | doaj.art-f8509912940a466d93e6e3b2a2a9d30e |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-03-11T09:54:33Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-f8509912940a466d93e6e3b2a2a9d30e2023-11-16T16:00:30ZengMDPI AGAnimals2076-26152023-01-0113341310.3390/ani13030413A Recognition Method of Ewe Estrus Crawling Behavior Based on Multi-Target Detection Layer Neural NetworkLonghui Yu0Jianjun Guo1Yuhai Pu2Honglei Cen3Jingbin Li4Shuangyin Liu5Jing Nie6Jianbing Ge7Shuo Yang8Hangxing Zhao9Yalei Xu10Jianglin Wu11Kang Wang12College 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, 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, ChinaThere are some problems with estrus detection in ewes in large-scale meat sheep farming: mainly, the manual detection method is labor-intensive and the contact sensor detection method causes stress reactions in ewes. To solve the abovementioned problems, we proposed a multi-objective detection layer neural network-based method for ewe estrus crawling behavior recognition. The approach we proposed has four main parts. Firstly, to address the problem of mismatch between our constructed ewe estrus dataset and the YOLO v3 anchor box size, we propose to obtain a new anchor box size by clustering the ewe estrus dataset using the K-means++ algorithm. Secondly, to address the problem of low model recognition precision caused by small imaging of distant ewes in the dataset, we added a 104 × 104 target detection layer, making the total target detection layer reach four layers, strengthening the model’s ability to learn shallow information and improving the model’s ability to detect small targets. Then, we added residual units to the residual structure of the model, so that the deep feature information of the model is not easily lost and further fused with the shallow feature information to speed up the training of the model. Finally, we maintain the aspect ratio of the images in the data-loading module of the model to reduce the distortion of the image information and increase the precision of the model. The experimental results show that our proposed model has 98.56% recognition precision, while recall was 98.04%, F1 value was 98%, mAP was 99.78%, FPS was 41 f/s, and model size was 276 M, which can meet the accurate and real-time recognition of ewe estrus behavior in large-scale meat sheep farming.https://www.mdpi.com/2076-2615/13/3/413behavior recognitiondeep learningewe estrustarget detectionYOLO v3 |
| spellingShingle | Longhui Yu Jianjun Guo Yuhai Pu Honglei Cen Jingbin Li Shuangyin Liu Jing Nie Jianbing Ge Shuo Yang Hangxing Zhao Yalei Xu Jianglin Wu Kang Wang A Recognition Method of Ewe Estrus Crawling Behavior Based on Multi-Target Detection Layer Neural Network Animals behavior recognition deep learning ewe estrus target detection YOLO v3 |
| title | A Recognition Method of Ewe Estrus Crawling Behavior Based on Multi-Target Detection Layer Neural Network |
| title_full | A Recognition Method of Ewe Estrus Crawling Behavior Based on Multi-Target Detection Layer Neural Network |
| title_fullStr | A Recognition Method of Ewe Estrus Crawling Behavior Based on Multi-Target Detection Layer Neural Network |
| title_full_unstemmed | A Recognition Method of Ewe Estrus Crawling Behavior Based on Multi-Target Detection Layer Neural Network |
| title_short | A Recognition Method of Ewe Estrus Crawling Behavior Based on Multi-Target Detection Layer Neural Network |
| title_sort | recognition method of ewe estrus crawling behavior based on multi target detection layer neural network |
| topic | behavior recognition deep learning ewe estrus target detection YOLO v3 |
| url | https://www.mdpi.com/2076-2615/13/3/413 |
| work_keys_str_mv | AT longhuiyu arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT jianjunguo arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT yuhaipu arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT hongleicen arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT jingbinli arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT shuangyinliu arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT jingnie arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT jianbingge arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT shuoyang arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT hangxingzhao arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT yaleixu arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT jianglinwu arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT kangwang arecognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT longhuiyu recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT jianjunguo recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT yuhaipu recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT hongleicen recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT jingbinli recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT shuangyinliu recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT jingnie recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT jianbingge recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT shuoyang recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT hangxingzhao recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT yaleixu recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT jianglinwu recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork AT kangwang recognitionmethodofeweestruscrawlingbehaviorbasedonmultitargetdetectionlayerneuralnetwork |