A Study on Multi-Scale Behavior Recognition of Dairy Cows in Complex Background Based on Improved YOLOv5
The daily behaviors of dairy cows, including standing, drinking, eating, and lying down, are closely associated with their physical health. Efficient and accurate recognition of dairy cow behaviors is crucial for timely monitoring of their health status and enhancing the economic efficiency of farms...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/2/213 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589490485460992 |
|---|---|
| author | Zheying Zong Zeyu Ban Chunguang Wang Shuai Wang Wenbo Yuan Chunhui Zhang Lide Su Ze Yuan |
| author_facet | Zheying Zong Zeyu Ban Chunguang Wang Shuai Wang Wenbo Yuan Chunhui Zhang Lide Su Ze Yuan |
| author_sort | Zheying Zong |
| collection | DOAJ |
| description | The daily behaviors of dairy cows, including standing, drinking, eating, and lying down, are closely associated with their physical health. Efficient and accurate recognition of dairy cow behaviors is crucial for timely monitoring of their health status and enhancing the economic efficiency of farms. To address the challenges posed by complex scenarios and significant variations in target scales in dairy cow behavior recognition within group farming environments, this study proposes an enhanced recognition method based on YOLOv5. Four Shuffle Attention (SA) modules are integrated into the upsampling and downsampling processes of the YOLOv5 model’s neck network to enhance deep feature extraction of small-scale cow targets and focus on feature information, while maintaining network complexity and real-time performance. The C3 module of the model was enhanced by incorporating Deformable convolution (DCNv3), which improves the accuracy of cow behavior characteristic identification. Finally, the original detection head was replaced with a Dynamic Detection Head (DyHead) to improve the efficiency and accuracy of cow behavior detection across different scales in complex environments. An experimental dataset comprising complex backgrounds, multiple behavior categories, and multi-scale targets was constructed for comprehensive validation. The experimental results demonstrate that the improved YOLOv5 model achieved a mean Average Precision (mAP) of 97.7%, representing a 3.7% improvement over the original YOLOv5 model. Moreover, it outperformed comparison models, including YOLOv4, YOLOv3, and Faster R-CNN, in complex background scenarios, multi-scale behavior detection, and behavior type discrimination. Ablation experiments further validate the effectiveness of the SA, DCNv3, and DyHead modules. The research findings offer a valuable reference for real-time monitoring of cow behavior in complex environments throughout the day. |
| format | Article |
| id | doaj-art-a77cbca514564726a70007311ce5ddd2 |
| institution | Kabale University |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-a77cbca514564726a70007311ce5ddd22025-01-24T13:16:09ZengMDPI AGAgriculture2077-04722025-01-0115221310.3390/agriculture15020213A Study on Multi-Scale Behavior Recognition of Dairy Cows in Complex Background Based on Improved YOLOv5Zheying Zong0Zeyu Ban1Chunguang Wang2Shuai Wang3Wenbo Yuan4Chunhui Zhang5Lide Su6Ze Yuan7College of Electromechanical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaCollege of Electromechanical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaCollege of Electromechanical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaCollege of Electromechanical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaCollege of Electromechanical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaCollege of Electromechanical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaCollege of Electromechanical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaCollege of Electromechanical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaThe daily behaviors of dairy cows, including standing, drinking, eating, and lying down, are closely associated with their physical health. Efficient and accurate recognition of dairy cow behaviors is crucial for timely monitoring of their health status and enhancing the economic efficiency of farms. To address the challenges posed by complex scenarios and significant variations in target scales in dairy cow behavior recognition within group farming environments, this study proposes an enhanced recognition method based on YOLOv5. Four Shuffle Attention (SA) modules are integrated into the upsampling and downsampling processes of the YOLOv5 model’s neck network to enhance deep feature extraction of small-scale cow targets and focus on feature information, while maintaining network complexity and real-time performance. The C3 module of the model was enhanced by incorporating Deformable convolution (DCNv3), which improves the accuracy of cow behavior characteristic identification. Finally, the original detection head was replaced with a Dynamic Detection Head (DyHead) to improve the efficiency and accuracy of cow behavior detection across different scales in complex environments. An experimental dataset comprising complex backgrounds, multiple behavior categories, and multi-scale targets was constructed for comprehensive validation. The experimental results demonstrate that the improved YOLOv5 model achieved a mean Average Precision (mAP) of 97.7%, representing a 3.7% improvement over the original YOLOv5 model. Moreover, it outperformed comparison models, including YOLOv4, YOLOv3, and Faster R-CNN, in complex background scenarios, multi-scale behavior detection, and behavior type discrimination. Ablation experiments further validate the effectiveness of the SA, DCNv3, and DyHead modules. The research findings offer a valuable reference for real-time monitoring of cow behavior in complex environments throughout the day.https://www.mdpi.com/2077-0472/15/2/213dairy cowbehavior recognitionimproved YOLOv5Shuffle Attentiondeformable convolutionDynamic Detection Head |
| spellingShingle | Zheying Zong Zeyu Ban Chunguang Wang Shuai Wang Wenbo Yuan Chunhui Zhang Lide Su Ze Yuan A Study on Multi-Scale Behavior Recognition of Dairy Cows in Complex Background Based on Improved YOLOv5 Agriculture dairy cow behavior recognition improved YOLOv5 Shuffle Attention deformable convolution Dynamic Detection Head |
| title | A Study on Multi-Scale Behavior Recognition of Dairy Cows in Complex Background Based on Improved YOLOv5 |
| title_full | A Study on Multi-Scale Behavior Recognition of Dairy Cows in Complex Background Based on Improved YOLOv5 |
| title_fullStr | A Study on Multi-Scale Behavior Recognition of Dairy Cows in Complex Background Based on Improved YOLOv5 |
| title_full_unstemmed | A Study on Multi-Scale Behavior Recognition of Dairy Cows in Complex Background Based on Improved YOLOv5 |
| title_short | A Study on Multi-Scale Behavior Recognition of Dairy Cows in Complex Background Based on Improved YOLOv5 |
| title_sort | study on multi scale behavior recognition of dairy cows in complex background based on improved yolov5 |
| topic | dairy cow behavior recognition improved YOLOv5 Shuffle Attention deformable convolution Dynamic Detection Head |
| url | https://www.mdpi.com/2077-0472/15/2/213 |
| work_keys_str_mv | AT zheyingzong astudyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT zeyuban astudyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT chunguangwang astudyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT shuaiwang astudyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT wenboyuan astudyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT chunhuizhang astudyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT lidesu astudyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT zeyuan astudyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT zheyingzong studyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT zeyuban studyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT chunguangwang studyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT shuaiwang studyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT wenboyuan studyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT chunhuizhang studyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT lidesu studyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 AT zeyuan studyonmultiscalebehaviorrecognitionofdairycowsincomplexbackgroundbasedonimprovedyolov5 |