Air flight target classification and identification method based on radar track data

A flying target, classification and recognition technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve the problems of poor generality and low recognition rate of radar data, and achieve low cost, good classification accuracy, and good popularization and application. Foreground effect

CN113947105APending Publication Date: 2022-01-18THE 724TH RES INST OF CHINA SHIPBUILDING IND
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2022-01-18

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention belongs to the field of radar data processing, and provides an air flight target classification and identification method based on radar track data. The method comprises the following steps: carrying out data preprocessing on flight path data of an air flight target collected by a radar, and eliminating the influence of data differences caused by different dimensions of data on a training model; and then reducing the data dimension of the obtained flight data through principal component analysis, extracting key data features, and improving the modeling speed and precision. The time sequence of the flight data is considered, a model is established for the data through the recurrent neural network, the test data is classified and identified, and the good classification performance is obtained. According to the invention, additional hardware is not needed, and classification and identification of radar aerial flying targets such as light and small unmanned aerial vehicles, birds, helicopters and civil aircraft are realized in a single radar antenna period.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of radar data processing. Background technique

[0002] The study of air flight target recognition has important guiding significance in long-range early warning operations and tactical defense. In modern information warfare, the accurate identification of the enemy's incoming target is conducive to our accurate threat estimation and reasonable firepower allocation in battlefield decision-making, and plays an important role in improving the combat effectiveness of weapon systems.

[0003] Among them, light and small UAVs are similar in size to flying birds. They are typical slow and small targets with a small scattering area. The flight speed, echo amplitude, scattering cross-sectional area, flight height and trajectory characteristics of the passing target cannot be clearly distinguished. For high-resolution radar, it is more difficult to classify and identify light and small UAVs and flying birds, which p...

Examples

Embodiment Construction

[0023] figure 1 For the realization process of the present invention, the present invention is illustrated below in conjunction with examples.

[0024] 1. In order to verify the effectiveness of the present invention, the air target data used in the experiment comes from the real data collected by a certain type of radar. The track data of four airborne targets including light and small unmanned aerial vehicles (DJI Phantom 4Pro), birds, helicopters, and civil aircraft were collected through radar as training samples, and the true class labels of each target were confirmed through optoelectronic equipment. The characteristics of target track data mainly include: batch number, period, azimuth, distance, elevation angle, time, course, speed, track azimuth, track distance, track elevation angle, predicted azimuth, predicted distance, predicted elevation angle, track quality, track Eighteen feature dimensions, such as trace state, point trace amplitude, and elevation angle qualit...