Sea surface low-altitude small target detection method based on feature clutter map

Abstract

The invention discloses a sea surface low-altitude small target detection method based on a characteristic clutter map. The method comprises the following steps: S1, obtaining radar echo data in a plurality of CPIs in a pure sea clutter background, and obtaining a characteristic clutter map matrix under the pure sea clutter background; s2, acquiring to-be-measured echo data, and obtaining a to-be-measured echo feature matrix; and S3, performing clutter map judgment processing based on the feature clutter map matrix and the to-be-detected echo feature matrix, and extracting information of a distance unit where the to-be-detected target is located. And S4, carrying out speed measurement and angle measurement processing on the to-be-measured target based on the distance unit information. According to the method, the effective target and sea clutter distinguishing features are extracted, the feature clutter map under the pure sea clutter background is established, and the inter-frame accumulation clutter map is gradually stabilized, so that the distinguishing of the target and the sea clutter is not influenced by singular feature values, the dimension is controllable, and the occupied storage space is small. In addition, the detection probability and the false alarm probability are effectively controlled, the detection performance is ensured, and the problems of target missing detection and false alarm are reduced.

Description

technical field [0001] The invention belongs to the technical field of radar signal processing, in particular to a method for detecting low-altitude small targets on the sea surface based on characteristic clutter maps. Background technique [0002] Radar faces many problems when detecting low-altitude small targets on the sea surface: 1. The targets detected by radar have the characteristics of small RCS, slow flight speed, and low flight altitude; 2. The sea surface environment is complex, and small low-altitude targets will be submerged in strong sea clutter , leading to a serious decline in the detection performance of radar targets; 3. The real-time requirements for radar detection are very high, and radars are required to have real-time detection capabilities in each CPI (coherent processing cycle). [0003] In traditional radar signal processing, the target detection under the background of sea clutter is generally realized by frequency domain filtering. The broadeni...

AI Technical Summary

Problems solved by technology

[0002] Radar faces many problems when detecting low-altitude small targets on the sea surface: 1. The targets detected by radar have the characteristics of small RCS, slow flight speed, and low flight altitude; 2. The sea surface environment is complex, and small low-altitude targets will be submerged in strong sea clutter , leading to a serious decline in the detection performance of radar targets; 3. The real-time requirements for radar detection are very high, and radars are required to have real-time detection capabilities in each CPI (coherent processing cycle)

This type of method has obvious advantages for detecting low-altitude small targets on the sea surface, but this method can only be used in a three-dimensional feature space

In order to expand the feature dimension, the team introduced machine learning methods such as support vector machines, K neighbors, and neural networks into classification problems in high-dimensional feature spaces. This method has better robustness and detection effect, but the use of machine learning methods First of all, it is necessary to obtain a large number of training samples. For the low-altitude small targets on the sea surface detected by radar, the number of target samples that can be obtained is small, and it is difficult to obtain samples.

At the same time, when the machine learning method trains the feature detector, it will be affected by the characteristics of individual singular samples, and cannot effectively control the false alarm rate, which reduces the detection probability of radar low-altitude small targets on the sea surface and increases the false alarm rate.

Images