Research On Data Filtering And Repairing Method Of Floating Vehicle

Urban transport is an indispensable part of human survival activities,and people are closely related to travel activities,the development of the city and the improvement of living standards have an important role in promoting.The rapid growth of the national economy and the ever-expanding urban population scale,so that long-term growth in motor vehicle ownership,the existing road network size has been unable to meet the growing traffic demand,traffic congestion more and more prominent.In order to make reasonable use of existing resources,many cities began to build intelligent traffic information platform based on floating vehicle data,reflecting the road traffic in real time,and accurately provided travel reference and decision support for travelers and urban traffic managers.And high-quality traffic management and control rely on high-quality data,real-time and accurate traffic data is an important guarantee for the intelligent traffic information platform to effectively play its application function.The data obtained from the actual floating vehicle acquisition system inevitably exist,Error,redundancy and other quality problems,therefore,for the floating car data screening and repair processing is the follow-up analysis of the application work to be implemented on the basis of intelligent traffic information platform is the key to the successful implementation.Based on the discussion of the current situation at home and abroad,this paper analyzes the current requirements of skimming and repairing data,focusing on the rules and methods applicable to the data filtering and repairing of floating vehicles,including the anomaly data recognition method based on threshold method and logic judgment,Time series based data restoration method,data restoration method based on statistical method,data restoration method based on map matching.On the basis of the advantages of the commonly used repair method,the data restoration method based on the mean value statistic and the map matching is put forward,and the taxi track data of Beijing is used as the object of study to validate the method effectively.