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.
Existing push robots mainly use magnetic induction technology. These devices are susceptible to external electromagnetic interference and have a low degree of intelligence. To make up for the insufficiency of the existing material pushing robots, and at the same time solve the problems of labor-intensive, labor-intensive, and inability to push material in time at night, etc., in this study, an autonomous navigation pusher robot based on 3D lidar is designed, and an obstacle avoidance strategy based on the improved artificial potential field method is proposed. Firstly, the 3D point cloud data of the barn is collected by the self-designed pushing robot, the point cloud data of the area of interest is extracted using a direct-pass filtering algorithm, and the 3D point cloud of the barn is segmented using a height threshold. Secondly, the Least-Squares Method (LSM) and Random Sample Consensus (RANSAC) were used to extract fence lines, and then the boundary contour features were extracted by projection onto the ground. Finally, a target influence factor is added to the repulsive potential field function to determine the principle of optimal selection of the parameters of the improved artificial potential field method and the repulsive direction, and to clarify the optimal obstacle avoidance strategy for the pusher robot. It can verify the obstacle avoidance effect of the improved algorithm. The experimental results showed that under three different environments: no noise, Gaussian noise, and artificial noise, the fence lines were extracted using RANSAC. Taking the change in the slope as an indicator, the obtained results were about −0.058, 0.058, and −0.061, respectively. The slope obtained by the RANSAC method has less variation compared to the no-noise group. Compared with LSM, the extraction results did not change significantly, indicating that RANSAC has a certain resistance to various noises, but RANSAC performs better in extraction effect and real-time performance. The simulation and actual test results show that the improved artificial potential field method can select reasonable parameters and repulsive force directions. The optimized path increases the shortest distance of the obstacle point cloud from the navigation path from 0.18 to 0.41 m, where the average time is 0.059 s, and the standard deviation is 0.007 s. This shows that the optimization method can optimize the path in real time to avoid obstacles, basically meet the requirements of security and real-time performance, and effectively avoid the local minimum problem. This research will provide corresponding technical references for pusher robots to overcome the problems existing in the process of autonomous navigation and pushing operation in complex open scenarios.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.