Classic track similar track identification method

Abstract

The invention discloses a classic track similar track identification method, and aims to provide a classic track identification method with a high similar track identification rate and capable of processing unstable tracks; the method comprises the following steps: reading classic tracks from a classic track knowledge base, and reading real time tracks from a real time track database; using a Douglas-Peucker algorithm to compress the real time track; primarily determining track similarity according to track features; if the primary determination succeeds, using the distance between points of the classic track and a line segment of the real time track to calculate the multi-to-1 longest common substring distance; using the multi-to-1 longest common substring distance as the multi-to-1 longest common substring distance between points and line of the classic track and the real time track; using the ratio between the point-to-line multi-to-1 longest common substring distance and the classic track length as the track similarity; precisely determining track similarity according to the obtained track similarity, and outputting a result if the track similarity precise determination succeeds.

Description

technical field [0001] The invention belongs to the field of pattern recognition, and relates to the classic track recognition technology in the field of intelligent intelligence and big data of intelligence. Background technique [0002] The classic track is the movement track of the classic target in the field of technical reconnaissance and intelligence. The classic target travels more regularly each time, and the trajectory is relatively stable. The typical trajectory of this classical target is the classical track. Classical tracks play a very important role in the analysis of target recognition, target warning, and target behavior intention. The similar track recognition of classic track is to identify the similar track of real-time track in the classic track library. In actual situations, the obtained real-time track is very unstable, mainly reflected in: [0003] 1) The obtained track is discontinuous, which is easy to be missed and broken, forming an incomplete ...

AI Technical Summary

Problems solved by technology

[0009] 3) The calculation of the longest common substring distance is time-consuming, and the algorithm needs to be optimized to reduce the amount of calculation

[0010] At present, when the longest common substring distance is applied to asynchronous and non-isoperiodic track recognition, the main solution is to convert the comparison between points into line segment and line segment comparison, although it solves the problem of real-time track and classic track sampling The cycle is not synchronized, but it cannot solve the problem that the classic track and the real-time track are not equal, causing multiple line segments or points of the classic track to match a line segment of the real-time track, and it does not solve the problem that the longest common substring distance is used for the track. The time-consuming nature of track recognition; there is another solution to the time-consuming track. This method forms a multi-layer grid on the plane where the point is located, and replaces each grid with a character to form a multi-layer character string recognition structure. Fast, but this method cannot solve the identification of asynchronous and non-isoperiodic tracks

Images