A Cloud-Edge Collaborative Framework for Object Detection Using Kubeedge

This paper introduces a cloud-edge collaborative framework for object detection using the KubeEdge platform, addressing the challenges of real-time data processing and resource limitations in object detection applications. The proposed framework leverages edge devices for data collection and the cloud for computationally intensive tasks, optimizing task allocation. By offloading heavy processing to the cloud and utilizing the edge for local data handling, the framework reduces dependency on network bandwidth, alleviates the load on cloud resources, and ensures real-time performance for object detection. Experimental evaluations demonstrate significant improvements in computational efficiency and bandwidth utilization, achieving high detection accuracy. The system is validated across various scenarios, highlighting its potential for real-time object detection in bandwidth-constrained environments. This work emphasizes the benefits of cloud-edge collaboration and offers valuable insights for future optimization in data transmission and resource management.