Track predication method based on Gauss mixture time series model

Abstract

The invention discloses a track predication method based on a Gauss mixture time series model (GMTSM for short) to carry out model regression and analysis of road vehicle flow on a large quantity of vehicle historical tracks to realize vehicle track predication. The method mainly comprises the following steps: (1) carrying out unsupervised learning cluster on vehicle historical tracks through a k-means algorithm; (2) constructing a historical track probability distribution model through a Gauss mixture time series model; and (3) predicating tracks of mobile objects through a regressive processof the mixture model. An experiment result shows that the Gauss mixture time series model automatically adjusts the weight of sub-models and selects a predication track with the largest probability in a condition that road vehicle flows change suddenly.

Description

technical field [0001] The invention relates to a vehicle trajectory prediction method based on a Gaussian mixture time series model, which belongs to the technical application field of big data value mining, and mainly uses an intelligent transportation network system. By establishing a Gaussian mixture time series trajectory prediction model, a method for judging by a probability model , realize the optimal selection of user lines, reduce the probability of traffic congestion, and solve the problem of accurate prediction of traffic conditions by the intelligent transportation network system. Background technique [0002] Intelligent transportation system is an intelligent system formed in the process of urbanization, which alleviates urban traffic congestion. However, with the further expansion of urbanization, traffic congestion is still an urgent problem to be solved. To monitor and predict traffic conditions in advance, Recommending reasonable routes is a reasonable sol...

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: In view of the shortcomings of traditional models such as the existing Gaussian mixture model for trajectory prediction under the sudden change of road traffic flow during non-working days, the present invention analyzes the traditional Gaussian mixture model from the aspects of the dynamic historical trajectory model of the sample sequence and the traffic flow prediction model. The model is optimized, and a Gaussian mixture time series model is proposed to judge whether the historical trajectory is in a sensitive period of traffic flow by predicting the traffic flow of the road, so as to predict the trajectory of moving objects more accurately

Images