A method and device for enhancing through-the-wall radar signals of human motion

By using a network model training method based on spectral processing, the semantics and intensity of through-wall radar signals are decoupled. The enhanced through-wall spectrogram generated by the generator has signal intensity and distribution similar to free space in complex environments, which improves the accuracy of signal enhancement and the accuracy of downstream identification tasks.

CN119988837BActive Publication Date: 2026-05-29TIANJIN UNIV
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TIANJIN UNIV
Filing Date
2025-01-26
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

In existing technologies, signal enhancement methods for through-wall radar signals have poor adaptability in complex environments, and signal semantic extraction and recognition are difficult. In particular, they are affected by wall clutter and multipath effects, which lead to signal attenuation and make it difficult to effectively enhance signal strength and distribution.

Method used

A network model training method based on spectral processing is adopted. By acquiring free space and through-wall spectral datasets, flipping and pre-training are performed. A loss function is constructed using generators and discriminators, and the generators and discriminators are optimized to generate enhanced through-wall spectra. The semantics and intensity of the spectra are decoupled, and the attenuation effect of wall clutter and multipath effects is overcome.

Benefits of technology

It improves the similarity of signal strength and distribution and semantic accuracy of through-wall radar signals, enhances the accuracy of downstream identification tasks, and effectively overcomes the signal attenuation problem.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119988837B_ABST
    Figure CN119988837B_ABST
Patent Text Reader

Abstract

The application relates to a through-wall radar signal enhancement method and device for human motion, wherein the method comprises the following steps: acquiring a to-be-enhanced through-wall spectrogram; inputting the to-be-enhanced through-wall spectrogram into a generator in a network model based on spectrogram processing to obtain an enhanced through-wall spectrogram, so as to monitor human motion. The training method of the network model comprises the following steps: training a pre-training model through free space spectrograms and corresponding free space flip spectrograms in a data set; inputting a through-wall spectrogram into the generator to obtain a corresponding enhanced through-wall spectrogram; inputting the enhanced through-wall spectrogram and a non-paired free space spectrogram into the pre-training model which has been trained to obtain corresponding channel dimension autocorrelation matrices; inputting the enhanced through-wall spectrogram and the non-paired free space spectrogram into a discriminator to obtain a discrimination result; and constructing a loss function to optimize the generator and the discriminator, so that the generator can perform signal enhancement and improve the accuracy of downstream semantic recognition.
Need to check novelty before this filing date? Find Prior Art