False trace point multi-dimensional hierarchical suppression method based on risk assessment

Abstract

The invention relates to a false trace point multi-dimensional hierarchical suppression method based on risk assessment, and belongs to the technical field of radar data processing. The method comprises four steps, extracting multi-dimensional attribute features of the condensed trace points; using an unsupervised clustering algorithm and an expert system to realize discrimination of a sample set,and using an artificial neural network ANN to train plots and labels thereof; constructing a classifier of the target trace points and the environmental false alarm trace points, calculating the score (representing the possibility generated by the target) of each trace point, and comparing the trace point score with a threshold so as to eliminate false trace points generated by environmental false alarm; according to the method, the multi-dimensional features of the trace points are mapped into trace point quality, extraction of the target trace points and elimination of clutter trace pointsare completed, operation is easy and convenient, and the elimination rate is high. The method solves a problem that it is difficult for a conventional trace point detection mode to distinguish a target trace point and a clutter trace point, improves the detection probability of small and medium-sized targets under the condition of equal false alarm rate, and reduces the possibility of false trackcorrelation and false track.

Description

technical field [0001] The invention belongs to the technical field of radar data processing. Background technique [0002] The existing active radar signal detection methods are all based on the research carried out under the theory that the radar signal is in a stationary random white noise. The detection threshold under the requirement of false alarm rate is determined by counting the amplitude probability density distribution of radar echoes. Typical sea clutter has low amplitude, large EP number, large saturation, low Doppler velocity, and low consistency; while the target has large amplitude, small EP number, small saturation, high Doppler velocity, and low consistency. high degree. Although there are differences between Shanghai clutter and target echo in these dimensions, the degree of distinction is not obvious. When the traditional constant false alarm detection method adopts a unified threshold for discrimination, it is easy to detect the heavy tail of sea clut...

AI Technical Summary

Problems solved by technology

The problems existing in the above-mentioned prior art are: the working environment of the radar is relatively complex, there is heavy tailing in the sea clutter area, and the signal variance is large, and the constant false alarm method will generate a large number of false traces, resulting in the failure of subsequent data processing. Effectively start and track the radar track, generate false tracks, and track wrong associations

Images