Intelligent video surveillance with edge-cloud collaboration based on scheduling policy

Abstract

With the continuous development of network and communication technology, edge-cloud collaboration can combine the advantages of cloud computing and edge computing to provide efficient safety monitoring services for factories. How to realize efficient edge-cloud collaborative computing for security monitoring is an urgent problem. To this end, this paper proposes a video redundant frame elimination mechanism to images with higher possibility of abnormal events and reduce the system computation overhead; designs a difference threshold-based edge-cloud collaborative scheduling strategy to automatically control the number of image at the edge and cloud according to the difference threshold parameter; designs an edge server intelligent scheduling strategy to assign images to the optimal edge server for processing, thus reducing image queuing time. Simulation results show that the scheduling strategy proposed in this paper can effectively reduce the processing delay and improve the efficiency of edge-cloud collaboration for security surveillance.