Vehicle running track reconstruction method based on multiple probability matching under sparse sampling

Abstract

The invention provides a vehicle running track reconstruction method based on multiple probability matching under sparse sampling, which is characterized in that a historical data statistics sparse sampling point tolerance distribution is used, and a search area is determined; then a candidate match object (road section or intersection) is searched in a region of search, and can be divided into various types according to the characteristics of the candidate object, if no match object is in the search area, the sampling point is not considerate, if only one object is in the search area, then the sampling point couples to the only object, if various candidate objects is in the search area, a double layer probability matching model is used for further processing; the double layer probability matching model can calculate the coupling probability of each possible track according to matching probability of the sampling point and the selection probability of the reasonable path, and the track with utmost possible probability can be selected for being taken as a reconstruction track of the sparse sampling point. The vehicle running track reconstruction method can reduce the matching error of the sparse sampling data, and can effectively increase the precision and speed of reconstructed vehicle running track in a complex road net.

Description

technical field [0001] The present invention relates to the technical field of traffic geography information, and more specifically, relates to a vehicle trajectory reconstruction method based on multiple probability matching applied to sparse sampling in complex road networks. Background technique [0002] The urban road network structure is complex, and it is often difficult to accurately match the positioning data in areas with high road network density and complex overpasses, especially when the sampling points are sparse and the positioning accuracy is not high, which greatly increases the difficulty of vehicle trajectory reconstruction. [0003] The current vehicle trajectory reconstruction methods can be divided into two categories: one is to match the sampling points to points or lines through map matching, and then connect them to form the vehicle trajectory through the shortest path algorithm; the other is the global vehicle trajectory matching The algorithm consid...

AI Technical Summary

Problems solved by technology

The first type of method generally uses geometric matching, topology analysis, weight matching, etc. when matching sampling points, but sparse sampling points are difficult to guarantee the accuracy of sampling point matching, and the accuracy of sampling point matching further affects the reconstruction of vehicle trajectory the accuracy of

The second type of method improves the accuracy by introducing probability matching model, delay matching model, parallel road matching model, etc., and the complexity is high; if a certain position is wrongly matched, it is easy to cause matching errors in subsequent sampling points; due to simple considerations The characteristics of the sampling point data do not consider the choice behavior of the creator of the vehicle trajectory. When facing a complex road network, especially between elevated and ordinary roads, the reconstruction effect of the vehicle trajectory is not ideal.

Images