Mass Taxi Trajectory Data Retrieval Method and Case Study

Authors: Yanbing Zhu*, East China Normal University, Xiang Li, East China Normal University
Topics: Transportation Geography, Geographic Information Science and Systems, Quantitative Methods
Keywords: vehicle trajectory, data retrieval, facility location, selection evaluation
Session Type: Paper
Day: 4/7/2019
Start / End Time: 9:55 AM / 11:35 AM
Room: Marshall West, Marriott, Mezzanine Level
Presentation File: No File Uploaded


With the rapid development of the urban economy and the rapid increase in population, people's demand for travel has increased. The mobility of the car is high, and it saves time on walking and becomes the first choice for people in many big cities. In the morning and evening peak periods of first-tier cities, the demand for travel increased sharply, buses and subways were full, and taxis were in short supply. Usually after the driver delivers the passengers to their destination, the company canteens are far away and it is too expensive to return to the company cafeteria. This caused the problem that it was difficult for taxi drivers to return to the cafeteria. Taxi drivers have limited dietary restrictions. Irregular diets and poor dining conditions have become important factors affecting the physical health and mental health of taxi drivers. This paper proposes a scheme to calculate the dining demand using taxi trajectory data, and then to optimize the site selection. A topological map of Shanghai taxi canteens and road network was constructed. This study uses the trip data model to describe the taxi trajectory. By equating the equidistant difference of the trajectory points of the same vehicle, the disorderly stored original data is changed into trajectory data that can be quickly queried. This article extracts the passenger status of each taxi dining time and calculates the demand for meals. Then, under the different spatial granularity and spatial resolution, this paper verifies the regularity of deman

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login