A Track Clustering Method Based on the Distance from Point to Line Segment Set

Abstract

The invention discloses a track clustering method based on the distance from a point to a line segment set, and uses a self-defined distance to measure the similarity between tracks; for each pair of tracks in all track data, calculate the distance between the two Distance, mainly includes: calculate the distance from each track point to another track, integrate the distance corresponding to all track points to get the one-way distance from one track to another track, and integrate the one-way distance between two track points The distance is calculated to obtain the two-way distance between tracks; according to the two-way distance matrix, the similarity matrix is ​​calculated; according to the similarity matrix, all tracks are clustered; and the clustering labels of each track are obtained. The invention can realize the automatic clustering of flight tracks, the measurement of flight track distance is more reasonable, and the clustering result is more in line with the actual situation. The invention has broad application prospects in the fields of air traffic management and airspace planning.

Description

Technical field [0001] The invention relates to a track clustering method, in particular to a track clustering method based on the distance from a point to a line segment set. Background technique [0002] In recent years, economic development has promoted the rapid increase in people's travel demand, resulting in more complex traffic flow and increasing congestion. In order to solve this problem, in the intelligent transportation system, a large number of various positioning devices are put into use, such as sensor networks, GPS, mobile phones, etc., which makes it more and more convenient to obtain real-time location information of moving objects. For air traffic, a large number of surveillance equipment, such as radar, ADS-B, etc., provide track data of aircraft movement. In air traffic management, the track clustering analysis is performed on the track data describing the actual geographic location of the flight, and the valuable flight mode is discovered, which helps to inc...

AI Technical Summary

Problems solved by technology

The longest common subsequence (LCSS) distance measures the distance between two tracks by finding the longest common part, but it needs a parameter to judge whether two waypoints match, and the setting of this parameter is not simple, Need to debug repeatedly

For the above reasons, these track distances do not perform well in track clustering

Images