Subway pedestrian flow network fusion method based on video pedestrian identification, and pedestrian flow prediction method

Abstract

The invention discloses a subway pedestrian flow network fusion method based on video pedestrian identification, and a pedestrian flow prediction method, video data of a subway station are used to carry out statistical analysis on a specific direction of pedestrian flow entering and exiting from the subway station, and fusion of a subway network and a ground traffic network enables crowd movementto be carried out in a huge network. Each subway station will become a node in the network, and each subway line and each overground road traffic line will become sides of the network. And the pedestrian flow change of the whole traffic network is deduced by using the graph neural network, thereby analyzing and predicting each station, the pedestrian flow quantity and the pedestrian flow destination. According to the method, deeper people flow analysis at entrances and exits of all subway stations is realized, resource scheduling of all stations and entrances and exits is facilitated, and mutual influence of overground and underground people flows can be pre-judged in time, so that traffic early warning on the ground or underground can be carried out in time, traffic jam is avoided, and station security measures are deployed in advance.

Description

Technical field [0001] The invention belongs to the technical field of smart city, and in particular, the present invention relates to a method of fusion method and a human flow prediction method based on video pedestrian recognition. Background technique [0002] The application of video surveillance is increasingly applying in the field of digital security guards. Through video, the statistics are also increasingly important, such as the use of data in the station, tourist attractions, exhibition areas, commercial streets, and the data of people's current statistics can be effectively carried out. Personnel mobilization, resource allocation, and provide better security. [0003] The existing metro flow prediction is generally based on the import and export credit card data of each site, and the resulting results can only be obtained by the flow prediction of the station. Generally, by analyzing the historical credit card data of the subway station and the road network map, cons...

AI Technical Summary

Problems solved by technology

[0004] However, the existing schemes have the following problems: each station generally has many entrances and exits, and there are many situations in the direction of each entrance and exit. The current scheme cannot analyze the subdivision direction of the flow of people entering and exiting the subway station, so that As a result, the above-ground and underground transportation networks cannot be deeply integrated, so there is a situation where the resources of each entrance and exit of the site cannot be reasonably allocated; at the same time, the impact of the flow of people entering and exiting the site on the ground traffic cannot be obtained

Images