Traffic zone center point selection method based on taxi boarding-alighting point space clustering

Abstract

A traffic zone center point selection method based on taxi boarding-alighting point space clustering includes: acquiring taxi GPS (global positioning system) data, and performing data washing; extracting boarding and alighting points of each taxi, and using boarding and alighting point data of each place as sample data; subjecting the boarding and alighting point data of taxies to map matching, and eliminating errors due to poor GPS precision; performing a meshing process to divide a city space into a limited amount of mesh units to form traffic zones in mesh structure, and bringing the boarding and alighting point data of taxies having the map matching corrected to the traffic zones, clustering the boarding and alighting points belonging to each traffic zone, extracting core object pointdata, subjecting the boarding and alighting point clustering cores of the traffic zones and nearest sections of road to matching, selecting the section closest to the clustering cores, and projectingcore object points to the section, wherein the projection points are center points of the traffic zones. The method herein allows the center points to be selected reasonably.

Description

technical field [0001] The invention relates to the field of intelligent transportation, and relates to a method for selecting a center point of a traffic area based on spatial clustering of taxi pick-up and drop-off points, so as to realize more reasonable selection of the center point of the traffic area and improve the level of traffic management. Background technique [0002] Due to the increasing popularity of GPS geographic sensing devices, the amount of movement trajectory data of vehicles and people has increased dramatically. Analyzing these data can help people recognize the cities around them and provide rich and accurate auxiliary information for relevant department personnel. [0003] As an important part of urban traffic, taxis play an important indicator role in reflecting the spatial and temporal patterns of residents' travel. A lot of important traffic information can be mined from the taxi GPS trajectory data, such as the distribution of taxi pick-up and dr...

AI Technical Summary

Problems solved by technology

This method is relatively simple and has a fast processing speed, but the selected center point cannot represent the optimal taxi stop station in the traffic area. Solve passenger travel needs

At present, there is no method for selecting the center point of the traffic area based on the spatial clustering of taxi passenger pick-up and drop-off points.

Images