Edge-Based Video Surveillance With Graph-Assisted Reinforcement Learning in Smart Construction

The smart construction site is developing repidly with the intelligentization of industrial management. Intelligent devices are beening widely deployed in construction industry to support artificial intelligence applications. Video surveillance is a core function of smart construction, which demands both high accuracy and low latency. The challenge is that the computation and networking resources in a construction site are often limited, and the inefficient scheduling policies create congestions in network and brings additional delay that is unbearable to realtime surveillance. Adaptive video configuration and edge computing have been proposed to improve accuracy and reduce latency with limited resources. However, optimizing the video configuration and task scheduling in edge computing involves several factors that often interfere with each other, which significantly decreases the performance of video surveillance. In this paper, we present an edge-based solution of video surveillance in smart construction site assisted by Graph Neural Network. It leverages the distributed computing model to realize flexible allocation of resources. A graph-assisted hierarchical reinforcement learning algorithm is developed to illustrate the feature of mobile edge network and optimize the scheduling policy by Deep-Q Network. We implement and test the proposed solution in the commercial residential buildings of a fortune global 500 real estate company, and observe that the proposed algorithm is efficient to maintain a reliable accuracy and keep lower delay. We further conduct a case study to demonstrate the superiority of the proposed solution by comparing it with traditional mechanisms.