Autonomous tracking method for solving passive warning picture target track intersection

Abstract

The invention discloses an autonomous tracking method for solving passive warning picture target track intersection. The autonomous tracking method mainly comprises the steps of broadband spectrum background normalization, extreme value extraction, feature association, tracking updating and the like. According to the method, wide and narrow band spectrum characteristics are combined, a whole set of complete and ordered processing flow is designed, the characteristic spectrum information of the target can be effectively utilized, and association and category classification between current peaksearch suspected target characteristics and historical track target characteristics are realized through a dimensionality reduction and clustering processing form; therefore, real-time characteristicspectrum label classification and stable and continuous tracking can be realized leisurely, and continuous tracks of target classification can be realized under the condition of target track intersection.

Description

technical field [0001] The invention relates to the field of passive sonar target detection and tracking processing technology, in particular to an autonomous tracking method for solving target track crossing in passive warning pictures. Background technique [0002] Passive sonar target detection mainly obtains the azimuth information of the target. However, there are often several targets at different distances in the same azimuth in the environment. On the passive broadband warning display and control screen, the track intersection of different targets is often encountered, resulting in instability. Reliable and persistent tracking of the same target, which in turn impacts single beam processing guided by track-associated bearing information and passive target recognition performance in the backend. At present, the common methods to solve the situation of passive target track intersection are based on the track situation characteristics and the method based on Kalman filt...

AI Technical Summary

Problems solved by technology

[0002] Passive sonar target detection mainly obtains the azimuth information of the target. However, there are often several targets at different distances in the same azimuth in the environment. On the passive broadband warning display and control screen, the track intersection of different targets is often encountered, resulting in instability. Reliable and persistent tracking of the same target, which in turn impacts single beam processing guided by track-associated bearing information and passive target recognition performance in the backend

At present, the common methods to solve the situation of passive target track intersection are based on the track situation characteristics and the method based on Kalman filter. However, such methods need to establish an accurate and reliable target motion model, and at the same time require that the track characteristics of the target are continuous and different. greater resistance, otherwise the performance will drop sharply or even fail

Images