Vehicle driving track prediction method and system based on checkpoint snapshot data and equipment

Abstract

The invention discloses a vehicle driving track prediction method and system based on checkpoint snapshot data and equipment. The method comprises the steps: acquiring historical track data of a vehicle; aggregating the historical track data of the vehicle to obtain track data of each vehicle; aggregating the historical vehicle track data to obtain a vehicle track data set of each time interval;constructing a Markov state transition matrix of road network vehicles based on the vehicle track data set of each time interval; constructing a Markov state transition matrix of the individual vehicle based on the track data of each vehicle; and predicting the probability of passing through each check point according to the Markov state transition matrix of the individual vehicle and the Markov state transition matrix of the road network vehicle. According to the invention, the defect that the current vehicle trajectory prediction method cannot perform personalized prediction can be well overcome.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a vehicle trajectory prediction method, system and equipment based on bayonet snapshot data. Background technique [0002] With the rapid development of cities and the popularity of private cars, traffic congestion, illegal vehicle detection and control have brought enormous pressure to urban traffic. However, with the rapid development of the information technology industry, advanced image recognition, video surveillance and communication technologies are widely used in the transportation field. Relevant departments are gradually alleviating this situation through many means such as big data processing technology and intelligent analysis technology. At present, a large number of vehicle capture cameras are deployed at road checkpoints in various cities and on highways between cities, which will generate a large amount of road traffic information and vehicle traffic info...

AI Technical Summary

Problems solved by technology

[0004] However, at present, a large number of vehicle trajectory prediction methods, whether through vehicle GPS positioning data or bayonet capture data, only use road network vehicle trajectory data to predict the position and spatial distribution of vehicles in the future, and do not take advantage of the driving preferences of each vehicle. To make personalized predictions, more importantly, there is no prediction of the time it takes to reach the spatial location. If the vehicle's future spatial location can be personalized and the time point of arrival at the spatial location can be predicted, it will be of great significance to the development of intelligent transportation. Many applications have brought huge improvement, such as real-time traffic forecast at checkpoints, vehicle tracking, intelligent traffic lights, diversion command, etc.

Images