Method and system for rail transit video surveillance based on cloud-edge collaboration

Abstract

The embodiment of the present invention provides a rail transit video monitoring method and system based on cloud-edge collaboration. The video monitoring module of the cloud computing center uses an auction algorithm to determine the resource information allocated to each edge monitoring device according to the obtained resource demand request. , send the computing resource in the resource information to the corresponding edge monitoring device, so that the edge monitoring device can process the key data in the received rail transit video through the resource corresponding to the computing resource, and can process a large amount of key data in the shortest time , can meet the real-time requirements of the rail transit video surveillance system for rapid response to key data, optimize the work scheduling process of the cloud computing center, and improve task processing efficiency. Moreover, it does not need to occupy too many computing resources and network resources of the cloud computing center, which can reduce the business load of the system.

Description

technical field [0001] The invention relates to the technical field of railway and urban rail transit, and more specifically, to a method and system for rail transit video monitoring based on cloud-edge collaboration. Background technique [0002] As an effective way to solve urban traffic congestion and improve people's travel efficiency and safety, rail transit has been fully applied in the process of urban development. The rail transit video surveillance system is an important guarantee to ensure the safe and orderly operation of urban rail transit. With the Internet of Things , big data, cloud computing, edge computing scene applications, and the integration of new technologies and video surveillance systems are also accelerating. [0003] Due to the complex and diverse types of monitoring objects of the rail transit video surveillance system, the large number and wide distribution, it brings many challenges to the system in terms of computing storage, operation and main...

AI Technical Summary

Problems solved by technology

[0003] Due to the complex and diverse types of monitoring objects of the rail transit video surveillance system, the large number and wide distribution, it brings many challenges to the system in terms of computing storage, operation and maintenance management, etc.

In recent years, data entering the cloud has gradually become a development trend, but the centralized cloud computing architecture cannot actually solve all IoT problems such as resource utilization, data fusion, application compatibility, and unified operation and maintenance. Multi-source heterogeneous data will bring huge pressure to the network bandwidth, computing power and storage capacity of the cloud computing architecture

In the prior art, the rail transit video monitoring system based on the cloud computing architecture adopts the cloud computing center as the computing resource to centralize the calculation and processing of the monitoring objects, which will cause the following problems: 1) The mass data of the rail transit video surveillance system is transmitted to the cloud computing The center will have higher requirements on the network bandwidth of the cloud computing architecture, which will cause delays in the processing of data by the cloud computing center; Construction cost of traffic video surveillance system

[0004] Taking the closed-circuit television (CCTV) video surveillance system as an example, the cloud computing center not only needs the flexible response of the edge devices, but also needs to gather the data of the edge devices nearby, control the video viewing, and manage the complex collection , storage, computing and other equipment, the traditional technical solutions are difficult to meet the real-time requirements of the rapid response of the CCTV video surveillance system, and occupy too many computing resources and network resources, increasing the invalid business load

Images