Unmanned aerial vehicle classification method and device based on radar multipath signal time-frequency feature fusion

Abstract

The invention discloses an unmanned aerial vehicle classification method and device based on radar multipath signal time-frequency characteristic fusion. The method includes collecting radar data of multiple UAVs; radar data are processed by Fourier transform to obtain radar echoes of different range units and different time, and static clutter of echo signals is suppressed by high-pass filter toextract different multipath echo signals of different range units. The multi-path echo signal is analyzed by short-time Fourier transform to obtain the time-frequency map of each UAV's multi-path echosignal. Extracting Time-Frequency Features of Multipath Echo Signal from Time-Frequency Diagram; and fusing the time-frequency characteristics of the multipath echo signals to obtain the classification results of each unmanned aerial vehicle. This method can acquire the data of different targets for learning and training, and does not need to modify the hardware, so as to accurately distinguish between bird and UAV, different types of UAV function, and high accuracy is achieved.

Description

technical field [0001] The invention relates to the field of radar technology, in particular to a method and device for classifying unmanned aerial vehicles based on time-frequency feature fusion of radar multipath signals. Background technique [0002] A drone is an unmanned aircraft that uses radio equipment for control and manipulation. In recent years, with the mature development of materials, communication and other technologies, the cost of spare parts such as sensors and cameras has been reduced, making the drone market maintain rapid growth. In addition, the role of drones in agriculture and forestry, surveying and mapping, power inspection, disaster relief, and security has become increasingly apparent. However, with the increasing use of drones, the number has increased significantly, and it has also caused some safety concerns. For example, the frequent incidents of "black flight disturbance" of drones have repeatedly threatened the safety of traffic management i...

AI Technical Summary

Problems solved by technology

[0008] In related technologies, images obtained based on optical imaging or monitoring data transmitted by sensors have high requirements on the surrounding environment, are greatly affected by climate, temperature and light conditions, and also have the problem of low recognition accuracy.

In addition, the use of radar to observe low-altitude flying or flying drone targets in urban buildings is often affected by the multipath effect of radar signals, resulting in relatively large errors in target tracking and detection.

Images