Road network-based spatio-temporal trajectory clustering method

Abstract

The invention discloses a road network-based spatio-temporal trajectory clustering method. The method comprises the steps of data acquisition, spatio-temporal trajectory expression, spatio-temporal similarity measurement, sub-trajectory clustering and clustering result output. Through a trajectory recording device, spatio-temporal trajectory data of a moving object is acquired; a spatio-temporal trajectory model is built based on trajectory expression of a line segment; a trajectory file is output after linear interpolation and semantic expansion and is subjected to feature point selection; sub-trajectories are divided through feature points to perform trajectory reconstruction; a network distance between the sub-trajectories is calculated as a spatio-temporal similarity measurement basis; sub-trajectory clustering is realized by applying a label propagation algorithm; and finally a clustering result is output. According to the method, similarity and abnormal features in the spatio-temporal trajectory data can be extracted by performing clustering analysis on various spatio-temporal trajectory data, and meaningful trajectory modes in the data can be conveniently discovered.

Description

technical field [0001] The invention relates to the technical field of data mining, in particular to a road network-based spatio-temporal trajectory clustering method. Background technique [0002] With the development of technologies such as remote sensing, GPS, wireless communication, intelligent terminals, and the Internet of Things, people can obtain a large amount of space-time trajectory data, and better guide anti-terrorism activities by analyzing the activities of terrorists; by studying the movement of cars in cities Trajectory, improve urban road planning to alleviate urban congestion; through the study of hurricane trajectory data, find its movement pattern, so as to do disaster prevention work before the arrival of the wind, animal migration trajectory, intelligent transportation Management, the trajectories of sperm movement and human handwriting in the field of biology, the trajectories of molecules in the field of chemistry, the trajectories of players in the ...

AI Technical Summary

Problems solved by technology

[0007] (1) Most of the current spatio-temporal trajectory data clustering methods still regard time as an additional dimension of the original space object. This processing method inevitably separates time and space, which is inconsistent with people's intuitive understanding of things;

[0008] (2) Existing clustering methods are not fully applicable to certain trajectory data types, such as population migration trajectory data. The time dimension of this type of data is not equal in length, but due to the semantics of age, the time dimension cannot be stretched. There is currently no good way to handle this situation;

[0009] (3) There are some problems in the process of converting clustering results into knowledge, for example, the discovered knowledge is either too simple, close to common sense, or too complex for people to understand intuitively;

When the trajectory data increases, the amount of calculation using hausdorffdistance will increase, and the efficiency will decrease rapidly

Images