Radar target detection method based on dual-channel convolutional neural network false alarm controllability

Abstract

The invention relates to a radar target detection method based on dual-channel convolutional neural network false alarm controllability, and belongs to the technical field of radar signal processing.The method comprises the following steps of firstly, preprocessing radar echo signals, and constructing a training data set by using signal time-frequency information and amplitude information; then,constructing a dual-channel convolutional neural network model which comprises a dual-channel feature extraction network, a feature fusion network and a false alarm controllable classifier, and inputting a training data set to carry out iterative optimization training on the dual-channel convolutional neural network model to obtain an optimal network parameter and a judgment threshold; and finally, preprocessing a real-time radar echo signal, and inputting the preprocessed real-time radar echo signal into the trained dual-channel convolutional neural network model for testing to complete target detection. The method is suitable for radar target detection in a complex environment. According to the method, radar signal multi-dimensional features are intelligently extracted and fused. The detection performance is improved. The false alarm rate control is achieved. The actual demands of radar target detection are met.

Description

technical field [0001] The invention belongs to the technical field of radar signal processing. More specifically, the invention relates to a radar target detection method based on a dual-channel convolutional neural network with controllable false alarms, which can be used for intelligent processing of radar target detection. Background technique [0002] The detection and classification of radar targets are widely used in military and civilian fields, but affected by the clutter or noise generated by complex environments and the diversity of target types, reliable and robust radar target detection and classification is always a key technology that needs to be studied one. At present, the difficulties in radar target detection and recognition mainly lie in background suppression, target high-resolution feature extraction, and complex feature classification. Traditional detection methods are usually based on statistical theory and regard the background as a random process, ...

AI Technical Summary

Problems solved by technology

[0004] Different from other image classifications, there are two issues that need to be considered when using CNN for radar signal detection and classification in clutter or noise backgrounds: First, due to complex environmental effects, backgrounds sometimes appear on the time-Doppler spectrum Due to the similar characteristics of the target, the accuracy rate is low when only using the time-frequency map to classify the target background signal

The second is that radar target detection should not only improve the detection performance as much as possible, but also ensure that false alarms are controllable. The traditional Constant False Alarm Rate (CFAR) is an adaptive threshold determined based on the statistical distribution characteristics of background units, while CNN The output of each layer of the network is difficult to obtain the definite statistical characteristics of the characteristics. The existing CNN detection method mostly counts the false alarm performance from the image itself, such as SAR image CNN detection. There are few researches on the CNN detection method for the echo signal itself. Most of the combination does not consider the influence of false alarms, so it does not meet the needs of actual radar applications

Images