A crowd group evacuation simulation method and system based on the half-dbscan clustering algorithm

Abstract

The present invention relates to a crowd group evacuation simulation method and system based on a half DBSCAN clustering algorithm. The method includes: creating an evacuation scene model and a crowd individual model, respectively initializing the evacuation scene information and the crowd individual information to obtain initialization parameters; The initialization parameters are divided into several groups by using the half DBSCAN algorithm, and the grouping results are obtained; the grouping results are used as the initialization state of the crowd movement, and the social force model is used for local path planning to obtain the movement path of each individual in the evacuation scene. Carry out crowd evacuation simulation. The invention combines the half DBSCAN clustering algorithm and the social force model to complete the simulation of crowd evacuation in complex scenes, truly and effectively realize the simulation of crowd evacuation in complex scenes, improve the accuracy of crowd evacuation simulation, and realistically demonstrate the evacuation Grouping phenomenon in the process.

Description

technical field [0001] The invention belongs to the technical field of crowd evacuation simulation, and in particular relates to a crowd group evacuation simulation method and system based on a half DBSCAN clustering algorithm. Background technique [0002] With the growth of the global population and the acceleration of the world's urbanization process, in mainland China, urban development has entered a period of rapid growth, the scale of the city is expanding rapidly, and high-rise and large buildings are increasing day by day. People are highly dense, and crowding and stampede accidents are most likely to occur in open places and in densely built areas when sudden fires, earthquakes, and terrorist attacks occur, which poses severe challenges to social public safety and the safety of people's lives and property. Deeply excavate the action rules of dense crowds under emergencies, conduct hidden danger investigations that may cause crowded riots or even trampled incidents, ...

AI Technical Summary

Problems solved by technology

However, the k-Medoids algorithm based on distance and relational multi-influencing factors to group people is not satisfactory in terms of accuracy.

[0005] To sum up, in the crowd evacuation simulation of the prior art, there is still a lack of an effective solution to the problem of how to improve the simulation accuracy of the group movement among relatives, friends and colleagues in crowd evacuation in an emergency

Images