Abstract

The blockchain-based audio-visual transmission systems have been constructed to develop a distributed and adaptable smart transport system (STS), which gives consumers, video producers, and service providers direct contact. Blockchain-based STS devices need substantial computer resources to transcode diverse quality and formats of video feed into multiple versions and structures following varied user needs. Existing blockchains, however, cannot support live streaming because of their limited computing capability and high processing times. Large video data transfer and extensive analysis even put an excessive load on vehicular networks. In this work, a video surveillance approach has been proposed to optimize the blockchain system’s traffic performance and reduce the latency throughout the multiple access edge computing (MEC) system. Integration of MEC and blockchain for video surveillance in autonomous vehicles (IMEC-BVS) has been proposed. To address this challenge, the joint optimization problem is represented based on the profound reinforcement training as a Markov Choice Progression (MCP) and the actor-critical asynchronous advantage (ACAA) method. Simulation findings show that the proposed method rapidly converges and enhances integrated MEC and blockchain performance for video surveillance in autonomous vehicles than existing methods.

Keywords: Blockchain, Multiple Access Edge Computing, Video Surveillance, Autonomous Vehicles