The feeding behaviour of cows is an essential sign of their health in dairy farming. For the impression of cow health status, precise and quick assessment of cow feeding behaviour is critical. This research presents a method for monitoring dairy cow feeding behaviour utilizing edge computing and deep learning algorithms based on the characteristics of dairy cow feeding behaviour. Images of cow feeding behaviour were captured and processed in real time using an edge computing device. A DenseResNet-You Only Look Once (DRN-YOLO) deep learning method was presented to address the difficulties of existing cow feeding behaviour detection algorithms’ low accuracy and sensitivity to the open farm environment. The deep learning and feature extraction enhancement of the model was improved by replacing the CSPDarknet backbone network with the self-designed DRNet backbone network based on the YOLOv4 algorithm using multiple feature scales and the Spatial Pyramid Pooling (SPP) structure to enrich the scale semantic feature interactions, finally achieving the recognition of cow feeding behaviour in the farm feeding environment. The experimental results showed that DRN-YOLO improved the accuracy, recall, and mAP by 1.70%, 1.82%, and 0.97%, respectively, compared to YOLOv4. The research results can effectively solve the problems of low recognition accuracy and insufficient feature extraction in the analysis of dairy cow feeding behaviour by traditional methods in complex breeding environments, and at the same time provide an important reference for the realization of intelligent animal husbandry and precision breeding.

In this study, an autonomous navigation robot for poultry house inspection was designed, and a path optimization and obstacle avoidance strategy was proposed. First, a filtering algorithm was used to extract regions of interest from the 3D point cloud data collected by the inspection robot in caged poultry houses. Then, the geometric structure of cage-row lines was estimated using the least-squares method and refined using the RANSAC algorithm. The refined lines were projected to obtain boundary contour features. Finally, the A* algorithm was improved by removing redundant nodes, reducing the number of turning points, shortening the total path length, and increasing the weight of the cost estimation. The improved A* algorithm was also validated through physical robot simulation tests. Experimental results showed that compared with the least-squares method (LSM), the RANSAC-based approach achieved cage-row line slope values of 0.223 and 0.224 under Gaussian noise and manually added noise, respectively, demonstrating superior noise robustness and real-time performance. The results further indicate that the improved A* algorithm enhances path planning efficiency, enabling the robot to make timely decisions when encountering static or dynamic obstacles, thereby improving overall stability and reliability.

In precision livestock farming, 3D point clouds provide important data support for analyzing pig behavior and monitoring their health. However, due to environmental occlusions, limited sensor viewpoints, and mutual shielding between pigs, the acquired point clouds are often severely partial, which affects the accuracy of body shape modeling and behavior recognition. To address these challenges, this study constructed a pig pose point cloud dataset using multi-view depth camera acquisition and point cloud registration techniques. Based on this dataset, an improved point cloud completion model, IIR-PoinTr, is proposed to enhance the reconstruction of geometric and topological structures in pig bodies. By strengthening local geometric perception and high-dimensional feature representation, the model improves the reconstruction quality of partial pig point clouds and produces more structurally consistent pig body shapes. Experimental results show that, on the self-constructed pig posture dataset, the proposed method reduces Chamfer Distance (CD-L1) by 3.6%, CD-L2 by 6.9%, and Earth Mover’s Distance (EMD) by 2.0%, while improving the F-score by 5.4% compared with the baseline model. In single-view point cloud completion tasks, the method is capable of reconstructing geometrically consistent pig body structures and increases downstream classification accuracy by 34.9%. These results indicate that the proposed method can improve the reconstruction quality of partial pig point clouds and provide preliminary technical support for posture analysis under occlusion.