Meta-learning-based vehicle trajectory clustering method and system

Abstract

The invention discloses a meta-learning-based vehicle trajectory clustering method and system, belongs to the technical field of vehicle trajectory clustering, and solves the problem that an optimal clustering result cannot be obtained due to the fact that multiple different types of trajectory data adopt a single trajectory clustering algorithm in the prior art. A meta-learning-based vehicle trajectory clustering method comprises the following steps: collecting different types of GPS vehicle trajectory data, and obtaining an optimal DBSCAN clustering algorithm corresponding to the different types of GPS vehicle trajectory data; collecting GPS vehicle trajectory data, and obtaining a meta-learning device used for vehicle trajectory type division through training; and acquiring a vehicle trajectory type corresponding to the GPS vehicle trajectory data by using the meta-learning device, and clustering the GPS vehicle trajectory data by using an optimal DBSCAN clustering algorithm corresponding to the vehicle trajectory type to obtain a clustering result of the GPS vehicle trajectory data. The optimal clustering result can be obtained for various different types of trajectory data.

Description

technical field [0001] The invention relates to the technical field of vehicle trajectory clustering, in particular to a meta-learning-based vehicle trajectory clustering method and system. Background technique [0002] In recent years, with people's travel needs and extensive transportation of goods, more and more vehicles including cars and different types of trucks have appeared in people's lives, and a large amount of GPS trajectory data is generated every day during the driving of vehicles. Trajectory data is the spatiotemporal data sequence left by moving objects in space over time. It contains a large amount of information, which enables us to understand the behavior of moving objects more intuitively. Based on the GPS trajectory data of massive vehicles, trajectory clustering can be performed. Carry out data mining to discover potential utilization value. [0003] Due to the characteristics of the trajectory, the trajectory is composed of several trajectory sequence...

AI Technical Summary

Problems solved by technology

[0003] Due to the characteristics of the trajectory, the trajectory is composed of several trajectory sequences. If the clustering is based on the trajectory points or the entire trajectory segment, the historical driving route and comprehensive information cannot be observed from the clustering results. Therefore, we need to cluster GPS trajectories in the form of trajectory segments, and the existing trajectory segment clustering methods are different in the way of dividing trajectories and the measurement of similar distance between trajectories. The trajectory data types can be completely different trajectories formed by various vehicles. However, if a single trajectory clustering algorithm is used for multiple different types of trajectory data, the best clustering results cannot be obtained.

Images