Dairy DigiD: An Edge-Cloud Framework for Real-Time Cattle Biometrics and Health Classification

The advancement of precision livestock farming hinges not only on breakthroughs in artificial intelligence (AI), but also on overcoming practical challenges in deploying these technologies within real-world farm environments. To bridge this gap, we present Dairy DigiD, an integrated edge-cloud AI framework designed for real-time cattle biometric identification and physiological classification. Central to the system is the lightweight YOLOv11 model, optimized for deployment on NVIDIA Jetson devices through INT8 quantization and TensorRT acceleration, achieving 94.2% classification accuracy and 24 FPS in resource-constrained settings. Complementing this, a DenseNet121-based classifier enables accurate categorization of physiological states under varying farm conditions. A key innovation of Dairy DigiD lies in its active learning pipeline, powered by Roboflow, which enhances model adaptability by prioritizing low-confidence cases for annotation—reducing labeling overhead while maintaining model accuracy. The system also features a Gradio-based user interface that reduces technician onboarding time by 84%, improving accessibility for non-technical users. Validated across ten commercial dairy farms in Atlantic Canada, the framework addresses key barriers to AI adoption in agriculture—including hardware limitations, connectivity variability, and user training—while supporting energy-efficient, continuous monitoring. Rather than introducing new algorithms, Dairy DigiD demonstrates a replicable, systems-level integration of existing AI tools, offering a practical pathway for scalable, welfare-oriented livestock monitoring in commercial dairy operations.