Work

A new tool to improve the computation of animal kinetic activity indices in precision poultry farming

Year: 2025

Type: article

Abstract: Precision Livestock Farming (PLF) emerges as a promising solution for revolutionising farming by enabling real-time automated monitoring of animals through smart technologies. PLF provides farmers with precise data to enhance farm management, increasing productivity and profitability. For instance, it allows for non-intrusive health assessments, contributing to maintaining a healthy herd while reducing stress associated with handling. In the poultry sector, image analysis can be utilised to monitor and analyse the behaviour of each hen in real time. Researchers have recently used machine learning algorithms to monitor the behaviour, health, and positioning of hens through computer vision techniques. Convolutional neural networks, a type of deep learning algorithm, have been utilised for image analysis to identify and categorise various hen behaviours and track specific activities like feeding and drinking. This research presents an automated system for analysing laying hen movement using video footage from surveillance cameras. With a customised implementation of object tracking, the system can efficiently process hundreds of hours of videos while maintaining high measurement precision. Its modular implementation adapts well to optimally exploit the GPU computing capabilities of the hardware platform it is running on. The use of this system is beneficial for both real-time monitoring and post-processing, contributing to improved monitoring capabilities in precision livestock farming. • Image analysis can be utilised to monitor and analyse the behaviour of individual hens in real time. • The manuscript presents a study on the optimization of kinetic indices based on object tracking techniques. • Conducting object detection in parallel with the YOLOv11n deep neural network improves GPU utilisation. • This tool reduces computational demands and benefits real-time monitoring and post-processing tasks.

Source: Artificial Intelligence in Agriculture

DOI: 10.1016/j.aiia.2025.03.005