Bus Arrival Time Prediction Method Using OBD Data Fusion

Abstract

The bus arrival time prediction method adopting OBD data fusion comprises the steps that 1, OBD data are acquired, and vehicle n driving data at the t moment are acquired through a vehicle-mounted OBD; 2, acquiring video checkpoint data, and capturing the data through upstream and downstream video checkpoints to obtain the traffic flow of the current road section, namely the number of vehicles which are shot by the upstream and downstream checkpoints at the same time and have travel time within an effective range; 3, performing data fusion processing, namely obtaining fusion data of the same time sequence and sampling frequency through matching of the time sequence and the space sequence by combining the data acquired by the OBD and the video bayonet data with actual road information; 4, constructing a prediction model (DS-GPR); in the model, input data is historical driving state information of the vehicle; wherein the output is the arrival time of a certain later point, the optimal value point of the global trust distribution function in the prediction distribution represents that the support degree of all data in the cognitive framework to the value of the optimal value point ismaximum, namely, the predicted value of the point is considered to be closest to a real value, and the value of the point is output, namely, the predicted arrival time of the bus.

Description

technical field [0001] The invention relates to a bus arrival time prediction method using OBD data fusion, which belongs to the field of intelligent transportation. Background technique [0002] With the continuous development of modern cities, the city's economy has been developed, and the population and vehicles have also increased significantly, which has caused a series of traffic problems, making urban traffic face more and more demands and challenges. Public transportation has the characteristics of large capacity and low energy consumption, and it is the most effective solution to the severe traffic situation in our country. Therefore, the realization of smart public transport is of great significance for optimizing urban traffic and promoting the construction of smart cities. Real-time and accurate prediction of bus arrival time can not only realize the intelligent dispatching of the bus system, but also meet the requirements of citizens for smart travel. Accurate...

AI Technical Summary

Problems solved by technology

[0003] None of the existing prediction methods can well meet the real-time and accuracy requirements of bus arrival time prediction

Images