This is the authors' abstract. We don't add key points for this paper.
Aiming at solving the problems of high latency, data transmission bandwidth limitation and privacy security faced by traditional object detection methods in the Internet of Things, a cloud-edge collaborative system for object detection based on KubeEdge is proposed. It takes advantage of cloud-edge collaboration technology and edge computing platform to perform tasks on edge devices to achieve faster response times. Firstly, through the deployment of KubeEdge edge computing platform, the cloud edge collaboration function is realized. Then, the object detection model is trained on the cloud server, and the trained model is deployed on the edge device to perform the model inference task. Finally, the edge device transmits the inference results to a cloud server, which stores the results for further analysis. The system has significant advantages in realizing low delay calculation, collaborative assurance, and privacy protection, etc. Taking mask detection as an example, it validated the practicality and reliability of the system, which provides strong support for the application of cloud-edge collaborative technology in the field of object detection and holds significant importance in meeting the growing demands of edge computing.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Pei et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: