您好，欢迎访问广东省农业科学院 机构知识库！
广东省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

MACA-Net: Mamba-Driven Adaptive Cross-Layer Attention Network for Multi-Behavior Recognition in Group-Housed Pigs

文献类型： 外文期刊

作者： Zeng, Zhixiong 1 ; Wu, Zaoming 2 ; Xie, Runtao 3 ; Lin, Kai 3 ; Tan, Shenwen 1 ; He, Xinyuan 1 ; Luo, Yizhi 1 ;

作者机构： 1.South China Agr Univ, Coll Engn, Key Lab Agr Equipment Technol, Guangzhou 510642, Peoples R China

2.South China Agr Univ, Sch Elect Engn, Guangzhou 510642, Peoples R China

3.South China Agr Univ, Coll Math & Informat, Guangzhou 510642, Peoples R China

4.Guangdong Acad Agr Sci, Inst Facil Agr, Guangzhou 510640, Peoples R China

5.State Key Lab Swine & Poultry Breding Ind, Guangzhou 510640, Peoples R China

关键词： pig behaviors; Mamba; deep learning; object detection

期刊名称：AGRICULTURE-BASEL （ 影响因子：3.6； 五年影响因子：3.8 ）

ISSN：

年卷期： 2025 年 15 卷 9 期

页码：

收录情况： SCI

摘要： The accurate recognition of pig behaviors in intensive farming is crucial for health monitoring and growth assessment. To address multi-scale recognition challenges caused by perspective distortion (non-frontal camera angles), this study proposes MACA-Net, a YOLOv8n-based model capable of detecting four key behaviors: eating, lying on the belly, lying on the side, and standing. The model incorporates a Mamba Global-Local Extractor (MGLE) Module, which leverages Mamba to capture global dependencies while preserving local details through convolutional operations and channel shuffle, overcoming Mamba's limitation in retaining fine-grained visual information. Additionally, an Adaptive Multi-Path Attention (AMPA) mechanism integrates spatial-channel attention to enhance feature focus, ensuring robust performance in complex environments and low-light conditions. To further improve detection, a Cross-Layer Feature Pyramid Transformer (CFPT) neck employs non-upsampled feature fusion, mitigating semantic gap issues where small target features are overshadowed by large target features during feature transmission. Experimental results demonstrate that MACA-Net achieves a precision of 83.1% and mAP of 85.1%, surpassing YOLOv8n by 8.9% and 4.4%, respectively. Furthermore, MACA-Net significantly reduces parameters by 48.4% and FLOPs by 39.5%. When evaluated in comparison to leading detectors such as RT-DETR, Faster R-CNN, and YOLOv11n, MACA-Net demonstrates a consistent level of both computational efficiency and accuracy. These findings provide a robust validation of the efficacy of MACA-Net for intelligent livestock management and welfare-driven breeding, offering a practical and efficient solution for modern pig farming.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：广东省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台