Radar sequence signal detection method and system based on LSTM

Abstract

The invention discloses a radar sequence signal detection method and system based on LSTM. The method comprises the following steps: acquiring radar signal data of a to-be-detected area; calculating the amplitude of the radar signal data; dividing the radar signal data into a training data set and a test data set; constructing an LSTM model; training the LSTM model through the training data set toobtain a trained LSTM model; predicting the test set through the trained LSTM model to obtain a predicted value; calculating a relative error between the predicted value and an actual value, whereinthe actual value is the amplitude of the radar signal data; and detecting the radar sequence signal according to the relative error. According to the method, subsequent moment signals are predicted through the trained LSTM model, points with large relative errors are regarded as abnormal values by comparing the relative errors of predicted values and actual values, radar target detection can be achieved, and clutter influences can be reduced.

Description

technical field [0001] The invention relates to the field of target detection, in particular to an LSTM-based radar sequence signal detection method and system. Background technique [0002] Radar target detection is of great value in many fields such as national defense maritime surveillance, transportation, and resource and environmental protection. Due to the complexity of the detection environment, the diversity of clutter and target signal models, reliable and robust target detection and classification technology has always been a key technology. At present, the difficulties in the detection and recognition of radar weak targets mainly lie in clutter suppression, target high-resolution feature extraction, and complex feature classification. Most of the existing detection methods are based on statistical theory, that is, the clutter is regarded as a random process, and it is assumed that it obeys a specific distribution model, such as: K distribution, Rayleigh distribut...

AI Technical Summary

Problems solved by technology

However, in practical application scenarios, the types of targets are complex, including stationary, slow-moving targets, and moving targets. Not fixed in the same distance unit, the accumulation time is short, and the types of clutter models are increasing day by day. In complex environments, the existing clutter distribution models are often difficult to match with the actual signal, resulting in the performance of classical target detection methods being seriously affected by the environment. Difficult to achieve high performance detection

[0003] In addition, due to the non-uniform and non-stationary characteristics of clutter in complex environments, such as sea clutter, it cannot be completely suppressed, and the detection performance is unstable

Haykin et al. used a method based on chaos and fractals to use feature quantities such as correlation dimension and box dimension for the detection of weak targets in the background of sea clutter. This method still has the problem of weak detection performance under low SCR, and it is not effective for moving targets. low ability to detect

Images