Research on Video Behavior Detection and Analysis Model for Sow Estrus Cycle Based on Deep Learning

Against the backdrop of precision livestock farming, sow behavior analysis holds significant theoretical and practical value. Traditional production methods face challenges such as low production efficiency, high labor intensity, and increased disease prevention risks. With the rapid advancement of...

Full description

Saved in:
Bibliographic Details
Main Authors: Kaidong Lei, Bugao Li, Shan Zhong, Hua Yang, Hao Wang, Xiangfang Tang, Benhai Xiong
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/9/975
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312922103185408
author Kaidong Lei
Bugao Li
Shan Zhong
Hua Yang
Hao Wang
Xiangfang Tang
Benhai Xiong
author_facet Kaidong Lei
Bugao Li
Shan Zhong
Hua Yang
Hao Wang
Xiangfang Tang
Benhai Xiong
author_sort Kaidong Lei
collection DOAJ
description Against the backdrop of precision livestock farming, sow behavior analysis holds significant theoretical and practical value. Traditional production methods face challenges such as low production efficiency, high labor intensity, and increased disease prevention risks. With the rapid advancement of optoelectronic technology and deep learning, more technologies are being integrated into smart agriculture. Intelligent large-scale pig farming has become an effective means to improve sow quality and productivity, with behavior recognition technology playing a crucial role in intelligent pig farming. Specifically, monitoring sow behavior enables an effective assessment of health conditions and welfare levels, ensuring efficient and healthy sow production. This study constructs a 3D-CNN model based on video data from the sow estrus cycle, achieving analysis of SOB, SOC, SOS, and SOW behaviors. In typical behavior classification, the model attains accuracy, recall, and F1-score values of (1.00, 0.90, 0.95; 0.96, 0.98, 0.97; 1.00, 0.96, 0.98; 0.86, 1.00, 0.93), respectively. Additionally, under conditions of multi-pig interference and non-specifically labeled data, the accuracy, recall, and F1-scores for the semantic recognition of SOB, SOC, SOS, and SOW behaviors based on the 3D-CNN model are (1.00, 0.90, 0.95; 0.89, 0.89, 0.89; 0.91, 1.00, 0.95; 1.00, 1.00, 1.00), respectively. These findings provide key technical support for establishing the classification and semantic recognition of typical sow behaviors during the estrus cycle, while also offering a practical solution for rapid video-based behavior detection and welfare monitoring in precision livestock farming.
format Article
id doaj-art-c391cf7c9ea24c659709ac491bbdcac3
institution Kabale University
issn 2077-0472
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-c391cf7c9ea24c659709ac491bbdcac32025-08-20T03:52:56ZengMDPI AGAgriculture2077-04722025-04-0115997510.3390/agriculture15090975Research on Video Behavior Detection and Analysis Model for Sow Estrus Cycle Based on Deep LearningKaidong Lei0Bugao Li1Shan Zhong2Hua Yang3Hao Wang4Xiangfang Tang5Benhai Xiong6College of Information Science and Engineering, Shanxi Agricultural University, Taiyuan 030800, ChinaCollege of Information Science and Engineering, Shanxi Agricultural University, Taiyuan 030800, ChinaCollege of Information Science and Engineering, Shanxi Agricultural University, Taiyuan 030800, ChinaCollege of Information Science and Engineering, Shanxi Agricultural University, Taiyuan 030800, ChinaCollege of Engineering, China Agricultural University, Beijing 100083, ChinaState Key Laboratory of Animal Nutrition, Institute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaState Key Laboratory of Animal Nutrition, Institute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaAgainst the backdrop of precision livestock farming, sow behavior analysis holds significant theoretical and practical value. Traditional production methods face challenges such as low production efficiency, high labor intensity, and increased disease prevention risks. With the rapid advancement of optoelectronic technology and deep learning, more technologies are being integrated into smart agriculture. Intelligent large-scale pig farming has become an effective means to improve sow quality and productivity, with behavior recognition technology playing a crucial role in intelligent pig farming. Specifically, monitoring sow behavior enables an effective assessment of health conditions and welfare levels, ensuring efficient and healthy sow production. This study constructs a 3D-CNN model based on video data from the sow estrus cycle, achieving analysis of SOB, SOC, SOS, and SOW behaviors. In typical behavior classification, the model attains accuracy, recall, and F1-score values of (1.00, 0.90, 0.95; 0.96, 0.98, 0.97; 1.00, 0.96, 0.98; 0.86, 1.00, 0.93), respectively. Additionally, under conditions of multi-pig interference and non-specifically labeled data, the accuracy, recall, and F1-scores for the semantic recognition of SOB, SOC, SOS, and SOW behaviors based on the 3D-CNN model are (1.00, 0.90, 0.95; 0.89, 0.89, 0.89; 0.91, 1.00, 0.95; 1.00, 1.00, 1.00), respectively. These findings provide key technical support for establishing the classification and semantic recognition of typical sow behaviors during the estrus cycle, while also offering a practical solution for rapid video-based behavior detection and welfare monitoring in precision livestock farming.https://www.mdpi.com/2077-0472/15/9/9753D-CNNvideo processingsow cyclebehavior recognitionanimal welfareprecision livestock farming
spellingShingle Kaidong Lei
Bugao Li
Shan Zhong
Hua Yang
Hao Wang
Xiangfang Tang
Benhai Xiong
Research on Video Behavior Detection and Analysis Model for Sow Estrus Cycle Based on Deep Learning
Agriculture
3D-CNN
video processing
sow cycle
behavior recognition
animal welfare
precision livestock farming
title Research on Video Behavior Detection and Analysis Model for Sow Estrus Cycle Based on Deep Learning
title_full Research on Video Behavior Detection and Analysis Model for Sow Estrus Cycle Based on Deep Learning
title_fullStr Research on Video Behavior Detection and Analysis Model for Sow Estrus Cycle Based on Deep Learning
title_full_unstemmed Research on Video Behavior Detection and Analysis Model for Sow Estrus Cycle Based on Deep Learning
title_short Research on Video Behavior Detection and Analysis Model for Sow Estrus Cycle Based on Deep Learning
title_sort research on video behavior detection and analysis model for sow estrus cycle based on deep learning
topic 3D-CNN
video processing
sow cycle
behavior recognition
animal welfare
precision livestock farming
url https://www.mdpi.com/2077-0472/15/9/975
work_keys_str_mv AT kaidonglei researchonvideobehaviordetectionandanalysismodelforsowestruscyclebasedondeeplearning
AT bugaoli researchonvideobehaviordetectionandanalysismodelforsowestruscyclebasedondeeplearning
AT shanzhong researchonvideobehaviordetectionandanalysismodelforsowestruscyclebasedondeeplearning
AT huayang researchonvideobehaviordetectionandanalysismodelforsowestruscyclebasedondeeplearning
AT haowang researchonvideobehaviordetectionandanalysismodelforsowestruscyclebasedondeeplearning
AT xiangfangtang researchonvideobehaviordetectionandanalysismodelforsowestruscyclebasedondeeplearning
AT benhaixiong researchonvideobehaviordetectionandanalysismodelforsowestruscyclebasedondeeplearning