面向边缘计算的轻量级母猪分娩识别模型  

Recognizing sow parturition using lightweight model with edge computing

作　　者：尹令[1,3,4] 蒋圣政 叶诚至 吴珍芳 杨杰[2,3,4] 张素敏 蔡更元[2,3,4] YIN Ling;JIANG Shengzheng;YE Chengzhi;WU Zhenfang;YANG Jie;ZHANG Sumin;CAI Gengyuan(College of Mathematics and Informatics,South China Agricultural University,Guangzhou 510642,China;College of Animal Science,South China Agricultural University,Guangzhou 510642,China;National Engineering Research Center for Swine Breeding Industry,Guangzhou 510642,China;State Key Laboratory of Swine and Poultry Breeding Industry,Guangzhou 510640,China)

机构地区：[1]华南农业大学数学与信息学院,广州510642 [2]华南农业大学动物科学学院,广州510642 [3]国家生猪种业工程技术研究中心,广州510642 [4]猪禽种业全国重点实验室,广州510640

出　　处：《农业工程学报》2024年第17期205-215,共11页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家自然科学基金项目(32172780);国家重点研发计划项目:引进猪种高效选育关键共性技术及产品研发(2023YFD1300202)。

摘　　要：为实时监测母猪分娩过程并准确分析记录其完整产程的产仔数、产仔间隔和产程等信息,该研究运用知识蒸馏和剪枝,结合了ResNet50高准确率和MobileNetV3高检测效率的优势设计了一种轻量级网络。采用数据增强提高教师模型ResNet50对分娩特征的提取能力,通过掩模生成蒸馏(maskedgenerativedistillation,MGD)提高学生模型MobileNetV3-S对分娩关键区域的表达能力,并通过依赖关系图(dependency graph)显式建模学生网络层间的依赖关系,结合分组耦合参数对学生模型进行剪枝。剪枝得到的MobileNetV3-S(MGD)_Prune参数量为0.74 M,在DELL OptiPlex微型机上检测速度为83.10帧/s,单栏视角测试准确度为91.48%,相比于ResNet50的检测速度提升了67.13帧/s,测试准确度下降0.98个百分点。试验结果表明,单栏视角对监测母猪分娩更为有效,模型对于产仔平均间隔的检测误差为0.31 s,仔猪出生事件的平均持续时长检测误差为0.02 s,能够高效监测母猪分娩全过程。The reproductive performance of sows can play a critical role in animal breeding,particularly in the efficiency and effectiveness of selection.However,manual recordings of piglet births and their survival rates cannot fully meet the large-scale production in recent years.The high precision is often required to capture more nuanced data,such as the intervals between births.The advanced technologies can be expected to enhance both the accuracy and efficiency of animal breeding programs.In this study,a lightweight network was developed to rapidly and accurately monitor the sow birthing in real time.Specifically,essential birthing metrics were engineered to analyze,such as the number of piglets born and the precise intervals between each birth.The lightweight network was tailored for the real-time monitoring of sow birthing activities.The critical birthing parameters were obtained to significantly enhance the efficiency and accuracy of breeding programs.Initially,the efficacy of different monitoring views-specifically,single versus double-column views-were evaluated on the accuracy of the improved model.A single-column view was significantly improved to accurately monitor the birthing events.The real-time decision-making and direct implications were obtained from the breeding outcomes.Advanced video processing techniques were incorporated,such as horizontal and vertical flipping.Some challenges were remained on the dynamic changes in the sow posture and varying camera perspectives during monitoring.Moreover,different lighting conditions were adapted to capture the inherent motion blur of active piglets during birth.Color jittering and Gaussian blur were then employed to significantly enhance the robustness of the model.The reliable performance was obtained under diverse operational conditions.Further advancements were achieved through a comparative analysis of classification networks.The results revealed that ResNet50 was greatly contributed to the recognition accuracy.MobileNetV3-S was performed the best with the co

关 键 词：母猪 分娩 监测 图像分类 知识蒸馏 结构剪枝 

分 类 号：S126[农业科学—农业基础科学]