CN117826113A - Depth perception radar micro-signal detection method - Google Patents
Depth perception radar micro-signal detection method Download PDFInfo
- Publication number
- CN117826113A CN117826113A CN202410249293.0A CN202410249293A CN117826113A CN 117826113 A CN117826113 A CN 117826113A CN 202410249293 A CN202410249293 A CN 202410249293A CN 117826113 A CN117826113 A CN 117826113A
- Authority
- CN
- China
- Prior art keywords
- radar
- signal
- time domain
- mixed
- representing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000008447 perception Effects 0.000 title claims abstract description 95
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 238000001228 spectrum Methods 0.000 claims abstract description 73
- 238000012545 processing Methods 0.000 claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000009499 grossing Methods 0.000 claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims abstract description 23
- 238000006243 chemical reaction Methods 0.000 claims abstract description 14
- 239000000203 mixture Substances 0.000 claims description 52
- 230000003595 spectral effect Effects 0.000 claims description 23
- 230000003044 adaptive effect Effects 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000017105 transposition Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention relates to the technical field of radar signal detection, and discloses a depth perception radar micro-signal detection method, which comprises the following steps: performing time-frequency conversion, signal energy calculation and smoothing on radar mixed signals under different time domain windows; performing self-adaptive threshold depth perception processing on the smoothed radar mixed signals under different time domain windows; and calculating the cross-correlation coefficient between the radar mixed signal subjected to perception enhancement under different time domain windows and the original signal, and detecting to obtain a radar signal. According to the method, time-frequency division and frequency-domain division are sequentially adopted to carry out time-frequency division on the acquired radar mixed signal with mixed noise, multiple frequency-domain division of the signal and identification detection of an effective frequency spectrum representation result of the radar signal under the condition of low signal-to-noise ratio are realized, and the self-adaptive threshold depth perception processing mode is adopted to realize depth perception detection and enhancement processing of effective information in the smoothed radar mixed signal.
Description
Technical Field
The invention relates to the technical field of radar signal detection, in particular to a depth perception radar micro-signal detection method.
Background
Radar technology has wide application in the fields of military, aviation, weather, etc. The radar micro-signal refers to a weak echo signal received in a radar system, and has important significance for detecting targets, extracting features and judging performance. The traditional radar micro-signal detection method is mainly based on signal processing and statistical methods, but has a certain limitation under the condition of low signal-to-noise ratio due to the fact that radar environments are complex and changeable and the difference between weak signals and noise is small. In recent years, with rapid development of deep learning technology, a radar micro-signal detection method based on deep learning is attracting attention of researchers. The method utilizes models such as a Deep Neural Network (DNN) or a Convolutional Neural Network (CNN) and the like, and realizes accurate detection of radar micro-signals through automatic learning of feature representation and training of a classifier. Some of these studies use an end-to-end deep learning framework, where raw micropignal data is directly input for training and prediction. The method eliminates the need of manually designing features in the traditional method, and can better capture useful information in weak signals by training a network model through a large amount of data. In addition, some research efforts have explored methods that combine deep learning with traditional methods. For example, the deep learning model is combined with traditional signal processing methods such as wavelet transformation and time-frequency analysis, so as to improve the performance and the robustness of micro-signal detection. Although the depth perception radar micro-signal detection method has some breakthroughs to a certain extent, great detection difficulty still exists under the condition of low signal-to-noise ratio such as underwater, and particularly when noise has similar statistical characteristics with micro-signals, the performance of the deep learning method is greatly limited. Aiming at the problem, the invention provides a depth perception radar micro-signal detection method, which realizes accurate micro-signal perception detection in a low signal-to-noise ratio environment through two-stage signal enhancement.
Disclosure of Invention
In view of the above, the present invention provides a depth-sensing radar micro-signal detection method, which aims to: 1) Sequentially carrying out time-frequency division on the acquired radar mixed signals with mixed noise by adopting a time-domain division and Fourier transform point frequency domain division mode to obtain the representation results and signal energy of the radar mixed signals under different frequency spectrum conditions, wherein the signal energy is the weighted energy representation of the probability of the radar mixed signals with effective radar signals under the frequency spectrum conditions, the multiple frequency domain division of the signals and the identification and detection of the effective frequency spectrum representation results with the radar signals under the low signal-to-noise ratio conditions are realized, the spectrum sequences of the radar mixed signals are subjected to smoothing processing according to the signal energy calculation results to obtain smoothed radar mixed signals under different time domain windows, the signal denoising processing of the time domain and the frequency domain is realized, and the smoothed radar mixed signals are effective radar signals with less noise information; 2) Performing self-adaptive threshold depth perception processing on the smoothed radar mixed signal and the radar mixed signal to obtain depth semantic difference between the smoothed radar mixed signal and the original radar mixed signal, generating self-adaptive threshold depth perception characteristics to carry out perception enhancement on the smoothed radar mixed signal, realizing depth perception detection and enhancement processing of effective information in the smoothed radar mixed signal, calculating cross-correlation coefficients between the radar mixed signal subjected to perception enhancement under different time domain windows and the radar mixed signal, if the cross-correlation coefficients exceed a specified threshold, indicating that the radar signal exists in the current time domain window, extracting the radar signal in the time domain window, and realizing radar signal perception detection under the condition of low signal-to-noise ratio in combination with a depth perception mode.
The invention provides a depth perception radar micro-signal detection method, which comprises the following steps:
s1: collecting radar mixed signals and performing time domain division on the radar mixed signals to obtain radar mixed signals under different time domain windows;
s2: performing time-frequency conversion and signal energy calculation on the radar mixed signals under different time domain windows to obtain signal energy of the radar mixed signals under different frequency spectrum conditions;
s3: according to the signal energy of the radar mixed signal under different frequency spectrum conditions, smoothing the frequency spectrum sequence of the radar mixed signal to obtain a smoothed radar mixed signal under different time domain windows;
s4: performing self-adaptive threshold depth perception processing on the smoothed radar mixed signals and the radar mixed signals under different time domain windows to obtain radar mixed signals with enhanced perception under different time domain windows;
s5: and calculating cross-correlation coefficients between the radar mixed signals subjected to perception enhancement under different time domain windows, if the cross-correlation coefficients exceed a specified threshold value, indicating that radar signals exist in the current time domain window, and extracting the radar signals in the time domain window.
As a further improvement of the present invention:
Optionally, the step S1 of collecting the radar mixed signal and performing time domain division on the radar mixed signal includes:
the method comprises the steps of collecting radar mixed signals, wherein the radar mixed signals comprise mixed noise signals and radar signals which are sent out by a radar and used for detection, and the collected radar mixed signals are in the form of:
；
wherein:
representing a radar mixed signal, t representing timing information;
representing radar mixed signal +.>At the nth signal instant->Signal value of>Representing radar mixed signal +.>N signal moments of (a);
performing time domain division on the radar mixed signals to obtain the radar mixed signals under different time domain windows, wherein the time domain division flow of the radar mixed signals is as follows:
setting the frame length of a time domain window as the signal values of L signal moments, shifting the frame of the time domain window as the signal values of m signal moments, and mixing the radar signalsDivided into->The method comprises the steps of obtaining radar mixed signals under different time domain windows, wherein the length of the radar mixed signals under each time domain window is the signal value of L signal moments, and the number of overlapped signal values between the radar mixed signals under adjacent time domain windows is L-m:
；
wherein:
represents the radar mix signal under the ith time domain window,/- >Representing radar mixed signal +.>Timing information of (a);
representing radar mixed signal +.>The signal values of the L signal instants in the middle,representing radar mixed signal +.>The L-th signal of (3)Time of day.
Optionally, in the step S2, performing time-frequency conversion and signal energy calculation on the radar mixed signal under different time domain windows includes:
performing time-frequency conversion and signal energy calculation on radar mixed signals under different time domain windows, wherein the radar mixed signals under the ith time domain windowThe time-frequency conversion and signal energy calculation flow of (1) is as follows:
s21: mixing signals to radarPerforming L-point fast Fourier transform to form radar mixed signalIs represented by the spectrum of (a):
；
；
wherein:
representing radar mixed signal +.>Is a spectral representation of (2);
representing radar mixed signal +.>Fast fourier transform representation at s-point, < >>；
An exponential function that is based on a natural constant;
representing radar mixed signal +.>Is a center frequency of (a);
j represents an imaginary unit;
s22: calculating energy of the fast Fourier transform representation result under different Fourier transform points, whereinThe energy of (2) is:
；
；
wherein:
representation->Energy of (a), i.e. radar mix signal +. >Signal energy under the condition of fourier transform points s;
representing the result of the fast fourier transform representation +.>Probability of valid radar signals being present;
representing the decision parameters.
Optionally, in the step S3, smoothing the spectrum sequence of the radar mixed signal according to the signal energy of the radar mixed signal under different spectrum conditions includes:
according to the signal energy of the radar mixed signal under different spectrum conditions, carrying out smoothing processing on the spectrum sequence of the radar mixed signal, wherein the smoothing processing flow is as follows:
s31: acquiring a spectrum sequence of a radar mixed signal:
；
wherein:
representing radar mixed signal +.>Is a spectral representation of (2);
s32: calculating a spectral mean value for each spectral representation in the sequence of spectra, wherein the spectral representationsThe spectrum mean value calculation result of (1) is:
；
；
wherein:
representing radar mixed signal +.>A fast fourier transform representation at point s;
representation->Is determined by the energy sensing weight of (a);
representing the spectral representation +.>Is a spectrum mean value of (a);
constituting a spectrum mean value sequence:
；
s33: dividing a spectrum average value sequence into M subsequences, calculating the average value of each subsequence, comparing any data point in the subsequence with the average value of the subsequence, if the data point is smaller than the average value of the subsequence, marking the data point as a non-signal point, and modifying the data point as the average value of two adjacent non-signal points to obtain a subsequence after smoothing treatment;
S34: sequencing the subsequences after smoothing according to the sequence of the subsequences in the spectrum mean value sequence, and cutting into equal lengthsAnd carrying out inverse Fourier transform processing on each frequency spectrum to obtain a signal representation of each frequency spectrum, and forming a smoothed radar mixed signal under different time domain windows:
；
wherein:
representing the ith time domain windowLower smoothed radar mix signal, +.>Representing radar mixed signalsTiming information of (a);
representing a smoothed radar mix signal +>Signal values of L signal instants, +.>Representing a smoothed radar mix signal +>Signal value at the L-th signal time.
Optionally, in the step S4, performing adaptive threshold depth sensing processing on the smoothed radar mixed signal and the radar mixed signal under different time domain windows, including:
performing adaptive threshold depth sensing processing on the smoothed radar mixed signals under different time domain windows and the radar mixed signals, wherein the smoothed radar mixed signals under the ith time domain windowRadar mixed signal->The adaptive threshold depth perception processing flow is as follows:
s41: respectively calculating the smoothed radar mixed signalsRadar mixed signal- >Fast under L Fourier transform pointsThe fast fourier transform represents the result;
s42: generating a smoothed radar mixture signalDepth perception information entropy of (2):
；
wherein:
representing a smoothed radar mix signal +>Depth perception information entropy of (2);
represents an L1 norm;
representing radar mixed signal +.>In the fast fourier transform representation of the fourier transform points s,representing a smoothed radar mix signal +>A fast fourier transform representation at fourier transform points s;
s43: generating a smoothed radar mixture signalIs a self-adaptive threshold depth perception feature:
；
；
wherein:
representing an adaptive threshold;
representing a smoothed radar mix signal +>Is a self-adaptive threshold depth perception feature;
s44: and performing perception enhancement processing on the smoothed radar mixed signal according to the self-adaptive threshold depth perception characteristic of the smoothed radar mixed signal to form the radar mixed signal subjected to perception enhancement under different time domain windows.
Optionally, the step S44 forms a radar mixed signal with enhanced perception under different time domain windows, including:
s441: from smoothed radar mixed signalsIs a self-adaptive threshold depth perception feature of->For the smoothed radar mixed signal +.>The formula for performing perceptual enhancement is:
；
Wherein:
representing a smoothed radar mix signal +>Is a perceived enhancement of the (c);
representing a ReLU activation function;
t represents transposition, W represents a convolution parameter matrix;
s442: constructing radar mixed signals with enhanced perception under different time domain windows:
；
wherein:
representing the perceptually enhanced radar mixed signal in the ith time domain window.
Optionally, in the step S5, a cross-correlation coefficient between the radar mixed signal with enhanced perception under different time domain windows and the radar mixed signal is calculated, if the cross-correlation coefficient exceeds a specified threshold, it is indicated that the radar signal exists in the current time domain window, and the step of extracting the radar signal includes:
calculating cross-correlation coefficients between the radar mixed signals subjected to perception enhancement under different time domain windows and the radar mixed signals, wherein the radar mixed signals subjected to perception enhancement under the ith time domain windowMix signal with radar->The calculation flow of the cross-correlation coefficient is as follows:
s51: respectively to radar mixed signalsMix signal with radar->Performing wavelet transformation to obtain radar mixed signal +.>Mix signal with radar->Wavelet coefficients at scale a:
；
；
；
；
wherein:
representation function->Complex conjugate of (2);
representing radar mixed signal +.>Is a center frequency of (a);
Representing radar mixed signal +.>Is a center frequency of (a);
representation function->Complex conjugate of (2);
s52: calculating to obtain wavelet coefficientAnd->Cross-correlation coefficient between:
；
；
wherein:
representing wavelet coefficients +.>And->Cross-correlation coefficients between;
odd represents an odd number greater than 10;
representing wavelet coefficients +.>And->Phase angle between;
representing extracted imaginary part, ->Representing the extracted real part;
s53: if the cross-correlation coefficientIf the radar signal exceeds the preset threshold value, indicating that the radar signal exists in the ith time domain window;
selecting a time domain window in which radar signals exist, and extracting a smoothed radar mixed signal of the selected time domain window as the radar signals in the selected time domain window.
In order to solve the above-described problems, the present invention provides an electronic apparatus including:
a memory storing at least one instruction;
the communication interface is used for realizing the communication of the electronic equipment; and
And the processor executes the instructions stored in the memory to realize the depth perception radar micro-signal detection method.
In order to solve the above-mentioned problems, the present invention further provides a computer readable storage medium having at least one instruction stored therein, the at least one instruction being executed by a processor in an electronic device to implement the depth-aware radar micro-signal detection method described above.
Compared with the prior art, the invention provides a depth perception radar micro-signal detection method, which has the following advantages:
firstly, the scheme provides a signal smoothing noise reduction mode combining a time domain and a frequency domain, and according to signal energy of a radar mixed signal under different frequency spectrum conditions, a spectrum sequence of the radar mixed signal is subjected to smoothing processing, wherein the smoothing processing flow is as follows: acquiring a spectrum sequence of a radar mixed signal:
；
wherein:representing radar mixed signal +.>Is a spectral representation of (2); calculating a spectral mean value for each spectral representation in the sequence of spectra, wherein the spectral representation +.>The spectrum mean value calculation result of (1) is:
；
；
wherein:representing radar mixed signal +.>A fast fourier transform representation at point s;Representation ofIs determined by the energy sensing weight of (a);Representing the spectral representation +.>Is a spectrum mean value of (a); constituting a spectrum mean value sequence:
；
dividing the spectrum average value sequence into M subsequences, calculating the average value of each subsequence, comparing any data point in the subsequence with the average value of the subsequence, if the data point is smaller than the average value of the subsequence, marking the data point as a non-signal point, and modifying the data point to be adjacent to two non-signal pointsThe average value of the number points is obtained, and a sub-sequence after smoothing treatment is obtained; sequencing the subsequences after smoothing according to the sequence of the subsequences in the spectrum mean value sequence, and cutting into equal lengths And carrying out inverse Fourier transform processing on each frequency spectrum to obtain a signal representation of each frequency spectrum, and forming a smoothed radar mixed signal under different time domain windows:
；
wherein:representing the smoothed radar mix signal in the ith time domain window, < >>Representing radar mixed signalsTiming information of (a);Representing a smoothed radar mix signal +>Signal values of L signal instants, +.>Representing a smoothed radar mix signal +>Signal value at the L-th signal time. The method sequentially adopts a time domain division mode and a frequency domain division mode of Fourier transform point numbers to carry out time-frequency division on the acquired radar mixed signal with mixed noise to obtain a representation result of the radar mixed signal under different frequency spectrum conditions and signal energy, wherein the signal energy is the radar mixed signal representing that the result has an effective radar signal under the frequency spectrum conditionsAnd carrying out smoothing processing on the spectrum sequence of the radar mixed signal according to the signal energy calculation result to obtain smoothed radar mixed signals under different time domain windows, and carrying out signal denoising processing of the time domain and the frequency domain, wherein the smoothed radar mixed signal is an effective radar signal with less noise information.
Meanwhile, the scheme provides a perception enhancement mode of the radar signal under the condition of low signal-to-noise ratio, and adaptive threshold depth perception processing is carried out on the smoothed radar mixed signal under different time domain windows and the radar mixed signal, wherein the smoothed radar mixed signal under the ith time domain windowRadar mixed signal->The adaptive threshold depth perception processing flow is as follows: respectively calculating the radar mixed signal after smoothing +.>Radar mixed signal->The fast fourier transform at L fourier transform points represents the result; generating a smoothed radar mix signal +.>Depth perception information entropy of (2):；
Wherein:representing a smoothed radar mix signal +>Depth perception information entropy of (2);Represents an L1 norm;Representing radar mixed signal +.>Fast fourier transform representation at fourier transform points s, a->Representing a smoothed radar mix signal +>A fast fourier transform representation at fourier transform points s; generating a smoothed radar mix signal +.>Is a self-adaptive threshold depth perception feature:
；
；
wherein:representing an adaptive threshold;Representing a smoothed radar mix signal +>Is a self-adaptive threshold depth perception feature; and performing perception enhancement processing on the smoothed radar mixed signal according to the self-adaptive threshold depth perception characteristic of the smoothed radar mixed signal to form the radar mixed signal subjected to perception enhancement under different time domain windows. From smoothed radar mixture Signal->Is a self-adaptive threshold depth perception feature of->For the smoothed radar mixed signal +.>The formula for performing perceptual enhancement is:
；
wherein:representing a smoothed radar mix signal +>Is a perceived enhancement of the (c);Representing a ReLU activation function; t represents transposition, W represents a convolution parameter matrix; constructing radar mixed signals with enhanced perception under different time domain windows:
；
wherein:representing the perceptually enhanced radar mixed signal in the ith time domain window. The method carries out self-adaptive threshold depth perception processing on the smoothed radar mixed signal and the radar mixed signal to obtain depth semantic difference of the smoothed radar mixed signal and the original radar mixed signal, generates self-adaptive threshold depth perception characteristics to carry out perception enhancement on the smoothed radar mixed signal, realizes depth perception detection and enhancement processing of effective information in the smoothed radar mixed signal, and calculates the radar mixed signal and the radar after perception enhancement under different time domain windowsAnd if the cross correlation coefficient between the mixed signals exceeds a specified threshold value, indicating that radar signals exist in the current time domain window, extracting the radar signals in the time domain window, and realizing radar signal perception detection under the condition of low signal-to-noise ratio combined with a depth perception mode.
Drawings
Fig. 1 is a schematic flow chart of a depth-sensing radar micro-signal detection method according to an embodiment of the invention;
fig. 2 is a schematic structural diagram of an electronic device for implementing a depth-aware radar micro-signal detection method according to an embodiment of the present invention.
In the figure: 1. an electronic device; 10. a processor; 11. a memory; 12. a program; 13 communication interface.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a depth perception radar micro-signal detection method. The execution subject of the depth-aware radar micro-signal detection method includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiments of the present application. In other words, the depth-aware radar micro-signal detection method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Example 1
S1: and acquiring radar mixed signals and performing time domain division on the radar mixed signals to obtain radar mixed signals under different time domain windows.
The step S1 of collecting the radar mixed signal and performing time domain division on the radar mixed signal comprises the following steps:
the method comprises the steps of collecting radar mixed signals, wherein the radar mixed signals comprise mixed noise signals and radar signals which are sent out by a radar and used for detection, and the collected radar mixed signals are in the form of:
；
wherein:
representing a radar mixed signal, t representing timing information;
representing radar mixed signal +.>At the nth signal instant->Signal value of>Representing radar mixed signal +.>N signal moments of (a);
performing time domain division on the radar mixed signals to obtain the radar mixed signals under different time domain windows, wherein the time domain division flow of the radar mixed signals is as follows:
setting the frame length of a time domain window as the signal values of L signal moments, shifting the frame of the time domain window as the signal values of m signal moments, and mixing the radar signalsDivided into->Radar mixed signals under each time domain window, wherein the length of the radar mixed signal under each time domain window is the signal value of L signal moments, and the radar mixed signals under adjacent time domain windows are mutually mixed The number of the overlapped signal values is L-m, and radar mixed signals under different time domain windows are obtained:
；
wherein:
represents the radar mix signal under the ith time domain window,/->Representing radar mixed signal +.>Timing information of (a);
representing radar mixed signal +.>The signal values of the L signal instants in the middle,representing radar mixed signal +.>Is the L-th signal time.
S2: and performing time-frequency conversion and signal energy calculation on the radar mixed signals under different time domain windows to obtain the signal energy of the radar mixed signals under different frequency spectrum conditions.
In the step S2, performing time-frequency conversion and signal energy calculation on the radar mixed signals under different time domain windows, including:
performing time-frequency conversion and signal energy calculation on radar mixed signals under different time domain windows, wherein the radar mixed signals under the ith time domain windowTime-frequency conversion of (a)The signal energy calculation flow is as follows:
s21: mixing signals to radarPerforming L-point fast Fourier transform to form radar mixed signalIs represented by the spectrum of (a):
；
；
wherein:
representing radar mixed signal +.>Is a spectral representation of (2);
representing radar mixed signal +.>Fast fourier transform representation at s-point, < >>；
An exponential function that is based on a natural constant;
Representing radar mixed signal +.>Is a center frequency of (a);
j represents an imaginary unit;
s22: calculating energy of the fast Fourier transform representation result under different Fourier transform points, whereinThe energy of (2) is:
；
；
wherein:
representation->Energy of (a), i.e. radar mix signal +.>Signal energy under the condition of fourier transform points s;
representing the result of the fast fourier transform representation +.>Probability of valid radar signals being present;
representing the decision parameters.
S3: and carrying out smoothing processing on the frequency spectrum sequence of the radar mixed signal according to the signal energy of the radar mixed signal under different frequency spectrum conditions to obtain a smoothed radar mixed signal under different time domain windows.
In the step S3, smoothing the spectrum sequence of the radar mixed signal according to the signal energy of the radar mixed signal under different spectrum conditions, including:
according to the signal energy of the radar mixed signal under different spectrum conditions, carrying out smoothing processing on the spectrum sequence of the radar mixed signal, wherein the smoothing processing flow is as follows:
s31: acquiring a spectrum sequence of a radar mixed signal:
；
wherein:
representing radar mixed signal +.>Is a spectral representation of (2);
s32: calculating a spectral mean value for each spectral representation in the sequence of spectra, wherein the spectral representations The spectrum mean value calculation result of (1) is:
；
；/>
wherein:
representing radar mixed signal +.>A fast fourier transform representation at point s;
representation->Is determined by the energy sensing weight of (a);
representing the spectral representation +.>Is a spectrum mean value of (a);
constituting a spectrum mean value sequence:
；
s33: dividing a spectrum average value sequence into M subsequences, calculating the average value of each subsequence, comparing any data point in the subsequence with the average value of the subsequence, if the data point is smaller than the average value of the subsequence, marking the data point as a non-signal point, and modifying the data point as the average value of two adjacent non-signal points to obtain a subsequence after smoothing treatment;
s34: sequencing the subsequences after smoothing according to the sequence of the subsequences in the spectrum mean value sequence, and cutting into equal lengthsAnd carrying out inverse Fourier transform processing on each frequency spectrum to obtain a signal representation of each frequency spectrum, and forming a smoothed radar mixed signal under different time domain windows:
；
wherein:
representing the smoothed radar mix signal in the ith time domain window, < >>Representing radar mixed signalsTiming information of (a);
representing a smoothed radar mix signal +>Signal values of L signal instants, +.>Representing a smoothed radar mix signal + >Signal value at the L-th signal time.
S4: and performing self-adaptive threshold depth perception processing on the smoothed radar mixed signals and the radar mixed signals under different time domain windows to obtain radar mixed signals with enhanced perception under different time domain windows.
In the step S4, performing adaptive threshold depth sensing processing on the smoothed radar mixed signal and the radar mixed signal under different time domain windows, including:
performing adaptive threshold depth sensing processing on the smoothed radar mixed signals under different time domain windows and the radar mixed signals, wherein the smoothed radar mixed signals under the ith time domain windowRadar mixed signal->The adaptive threshold depth perception processing flow is as follows:
s41: respectively calculating the smoothed radar mixed signalsRadar mixed signal->Under L Fourier transform pointsThe fast fourier transform of (a) represents the result;
s42: generating a smoothed radar mixture signalDepth perception information entropy of (2):
；
wherein:
representing a smoothed radar mix signal +>Depth perception information entropy of (2);
represents an L1 norm;
representing radar mixed signal +.>In the fast fourier transform representation of the fourier transform points s,representing a smoothed radar mix signal + >A fast fourier transform representation at fourier transform points s;
s43: generating a smoothed radar mixture signalIs a self-adaptive threshold depth perception feature:
；
；
wherein:
representing an adaptive threshold;
representing a smoothed radar mix signal +>Is a self-adaptive threshold depth perception feature;
s44: and performing perception enhancement processing on the smoothed radar mixed signal according to the self-adaptive threshold depth perception characteristic of the smoothed radar mixed signal to form the radar mixed signal subjected to perception enhancement under different time domain windows.
The step S44 forms a radar mixed signal with enhanced perception under different time domain windows, which includes:
s441: from smoothed radar mixed signalsIs a self-adaptive threshold depth perception feature of->For the smoothed radar mixed signal +.>The formula for performing perceptual enhancement is:
；
wherein:
representing a smoothed radar mix signal +>Is a perceived enhancement of the (c);
representing a ReLU activation function;
t represents transposition, W represents a convolution parameter matrix;
s442: constructing radar mixed signals with enhanced perception under different time domain windows:
；
wherein:
representing the perceptually enhanced radar mixed signal in the ith time domain window.
In the step S5, a cross-correlation coefficient between the radar mixed signal and the radar mixed signal after the perception enhancement under different time domain windows is calculated, if the cross-correlation coefficient exceeds a specified threshold value, the existence of the radar signal in the current time domain window is indicated, and the radar signal extraction is performed, including:
Calculating cross-correlation coefficients between the radar mixed signals subjected to perception enhancement under different time domain windows and the radar mixed signals, wherein the radar mixed signals subjected to perception enhancement under the ith time domain windowMix signal with radar->The calculation flow of the cross-correlation coefficient is as follows:
s51: respectively to radar mixed signalsMix signal with radar->Performing wavelet transformation to obtain radar mixed signal +.>Mix signal with radar->Wavelet coefficients at scale a:
；
；
；
；
wherein:
representation function->Complex conjugate of (2);
representing radar mixed signal +.>Is a center frequency of (a);
representing radar mixed signal +.>Is a center frequency of (a);
representation function->Complex conjugate of (2);
s52: calculating to obtain wavelet coefficientAnd->Cross-correlation coefficient between:
；
；
wherein:
representing wavelet coefficients +.>And->Cross-correlation coefficients between;
odd represents an odd number greater than 10;
representing wavelet coefficients +.>And->Phase angle between;
representing extracted imaginary part, ->Representing the extracted real part;
s53: if the cross-correlation coefficientIf the radar signal exceeds the preset threshold value, indicating that the radar signal exists in the ith time domain window;
selecting a time domain window in which radar signals exist, and extracting a smoothed radar mixed signal of the selected time domain window as the radar signals in the selected time domain window.
Example 2
Fig. 2 is a schematic structural diagram of an electronic device for implementing a depth-aware radar micro-signal detection method according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication interface 13 and a bus, and may further comprise a computer program, such as program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of the program 12, but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects respective parts of the entire electronic device using various interfaces and lines, executes or executes programs or modules (a program 12 for realizing depth-aware radar micro-signal detection, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process data.
The communication interface 13 may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device 1 and other electronic devices and to enable connection communication between internal components of the electronic device.
The bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
Fig. 2 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 2 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The program 12 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, may implement:
collecting radar mixed signals and performing time domain division on the radar mixed signals to obtain radar mixed signals under different time domain windows;
performing time-frequency conversion and signal energy calculation on the radar mixed signals under different time domain windows to obtain signal energy of the radar mixed signals under different frequency spectrum conditions;
according to the signal energy of the radar mixed signal under different spectrum conditions, smoothing the spectrum sequence of the radar mixed signal;
performing self-adaptive threshold depth perception processing on the smoothed radar mixed signals and the radar mixed signals under different time domain windows to obtain radar mixed signals with enhanced perception under different time domain windows;
and calculating cross-correlation coefficients between the radar mixed signals subjected to perception enhancement under different time domain windows, if the cross-correlation coefficients exceed a specified threshold value, indicating that radar signals exist in the current time domain window, and extracting a radar signal pattern in the time domain window.
Specifically, the specific implementation method of the above instruction by the processor 10 may refer to descriptions of related steps in the corresponding embodiments of fig. 1 to 2, which are not repeated herein.
It should be noted that, the foregoing reference numerals of the embodiments of the present invention are merely for describing the embodiments, and do not represent the advantages and disadvantages of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (7)
1. A depth-aware radar micro-signal detection method, the method comprising:
s1: collecting radar mixed signals and performing time domain division on the radar mixed signals to obtain radar mixed signals under different time domain windows;
s2: performing time-frequency conversion and signal energy calculation on the radar mixed signals under different time domain windows to obtain signal energy of the radar mixed signals under different frequency spectrum conditions;
s3: according to the signal energy of the radar mixed signal under different frequency spectrum conditions, smoothing the frequency spectrum sequence of the radar mixed signal to obtain a smoothed radar mixed signal under different time domain windows;
s4: performing self-adaptive threshold depth perception processing on the smoothed radar mixed signals and the radar mixed signals under different time domain windows to obtain radar mixed signals with enhanced perception under different time domain windows;
S5: and calculating cross-correlation coefficients between the radar mixed signals subjected to perception enhancement under different time domain windows, if the cross-correlation coefficients exceed a specified threshold value, indicating that radar signals exist in the current time domain window, and extracting the radar signals in the time domain window.
2. The depth-aware radar micro-signal detection method according to claim 1, wherein the step S1 of acquiring radar mixed signals and performing time-domain division on the radar mixed signals comprises:
the method comprises the steps of collecting radar mixed signals, wherein the radar mixed signals comprise mixed noise signals and radar signals which are sent out by a radar and used for detection, and the collected radar mixed signals are in the form of:
；
wherein:
indicating lightningReaching a mixed signal, wherein t represents time sequence information;
representing radar mixed signal +.>At the nth signal instant->Signal value of>Representing radar mixed signal +.>N signal moments of (a);
performing time domain division on the radar mixed signals to obtain the radar mixed signals under different time domain windows, wherein the time domain division flow of the radar mixed signals is as follows:
setting the frame length of a time domain window as the signal values of L signal moments, shifting the frame of the time domain window as the signal values of m signal moments, and mixing the radar signals Divided into->The method comprises the steps of obtaining radar mixed signals under different time domain windows, wherein the length of the radar mixed signals under each time domain window is the signal value of L signal moments, and the number of overlapped signal values between the radar mixed signals under adjacent time domain windows is L-m:
；
wherein:
represents the radar mix signal under the ith time domain window,/->Representing radar mixed signal +.>Timing information of (a);
representing radar mixed signal +.>Signal values of L signal instants, +.>Representing radar mixed signal +.>Is the L-th signal time.
3. The method for detecting depth-aware radar micro-signals according to claim 2, wherein in the step S2, time-frequency conversion and signal energy calculation are performed on the radar mixed signals under different time domain windows, including:
performing time-frequency conversion and signal energy calculation on radar mixed signals under different time domain windows, wherein the radar mixed signals under the ith time domain windowThe time-frequency conversion and signal energy calculation flow of (1) is as follows:
s21: mixing signals to radarPerforming L-point fast Fourier transform to form radar mixed signalIs represented by the spectrum of (a):
；
；
wherein:
Representing radar mixed signal +.>Is a spectral representation of (2);
representing radar mixed signal +.>Fast fourier transform representation at s-point, < >>；
An exponential function that is based on a natural constant;
representing radar mixed signal +.>Is a center frequency of (a);
j represents an imaginary unit;
s22: calculating energy of the fast Fourier transform representation result under different Fourier transform points, whereinThe energy of (2) is:
；
；
wherein:
representation->Energy of (a), i.e. radar mix signal +.>Signal energy under the condition of fourier transform points s;
representing the result of the fast fourier transform representation +.>Probability of valid radar signals being present;
representing the decision parameters.
4. A depth-aware radar micro-signal detection method according to claim 3, wherein in the step S3, smoothing is performed on a spectrum sequence of the radar mixed signal according to signal energy of the radar mixed signal under different spectrum conditions, including:
according to the signal energy of the radar mixed signal under different spectrum conditions, carrying out smoothing processing on the spectrum sequence of the radar mixed signal, wherein the smoothing processing flow is as follows:
s31: acquiring a spectrum sequence of a radar mixed signal:
；
Wherein:
representing radar mixed signal +.>Is a spectral representation of (2);
s32: calculating a spectral mean value for each spectral representation in the sequence of spectra, wherein the spectral representationsThe spectrum mean value calculation result of (1) is:
；
；
wherein:
representing radar mixed signal +.>A fast fourier transform representation at point s;
representation->Is determined by the energy sensing weight of (a);
representing the spectral representation +.>Is a spectrum mean value of (a);
constituting a spectrum mean value sequence:
；
s33: dividing a spectrum average value sequence into M subsequences, calculating the average value of each subsequence, comparing any data point in the subsequence with the average value of the subsequence, if the data point is smaller than the average value of the subsequence, marking the data point as a non-signal point, and modifying the data point as the average value of two adjacent non-signal points to obtain a subsequence after smoothing treatment;
s34: sequencing the subsequences after smoothing according to the sequence of the subsequences in the spectrum mean value sequence, and cutting into equal lengthsAnd carrying out inverse Fourier transform processing on each frequency spectrum to obtain a signal representation of each frequency spectrum, and forming a smoothed radar mixed signal under different time domain windows:
；
wherein:
representing the smoothed radar mix signal in the ith time domain window, < > >Representing radar mixed signal +.>Timing information of (a);
representing a smoothed radar mix signal +>Signal values of L signal instants, +.>Representing a smoothed radar mix signal +>Signal value at the L-th signal time.
5. The method for detecting depth-aware radar micro-signals according to claim 1, wherein in the step S4, adaptive threshold depth-aware processing is performed on the smoothed radar mixed signals and the radar mixed signals under different time domain windows, including:
performing adaptive threshold depth sensing processing on the smoothed radar mixed signals under different time domain windows and the radar mixed signals, wherein the smoothed radar mixed signals under the ith time domain windowRadar mixed signal->The adaptive threshold depth perception processing flow is as follows:
s41: respectively calculating the smoothed radarsMixed signalRadar mixed signal->The fast fourier transform at L fourier transform points represents the result;
s42: generating a smoothed radar mixture signalDepth perception information entropy of (2):
；
wherein:
representing a smoothed radar mix signal +>Depth perception information entropy of (2);
represents an L1 norm;
representing radar mixed signal +.>Fast fourier transform representation at fourier transform points s, a- >Representing a smoothed radar mix signal +>A fast fourier transform representation at fourier transform points s;
s43: generating a smoothed radar mixture signalIs a self-adaptive threshold depth perception feature:
；
；
wherein:
representing an adaptive threshold;
representing a smoothed radar mix signal +>Is a self-adaptive threshold depth perception feature;
s44: and performing perception enhancement processing on the smoothed radar mixed signal according to the self-adaptive threshold depth perception characteristic of the smoothed radar mixed signal to form the radar mixed signal subjected to perception enhancement under different time domain windows.
6. The method for detecting depth-aware radar micro-signals according to claim 5, wherein in the step S44, the radar mixed signals with enhanced perception under different time domain windows are formed, and the method comprises the following steps:
s441: from smoothed radar mixed signalsIs of adaptive threshold depthDegree perception feature->For the smoothed radar mixed signal +.>The formula for performing perceptual enhancement is:
；
wherein:
representing a smoothed radar mix signal +>Is a perceived enhancement of the (c);
representing a ReLU activation function;
t represents transposition, W represents a convolution parameter matrix;
s442: constructing radar mixed signals with enhanced perception under different time domain windows:
；
Wherein:
representing the perceptually enhanced radar mixed signal in the ith time domain window.
7. The method for detecting radar micro-signals through depth perception according to claim 1, wherein in the step S5, a cross-correlation coefficient between the radar mixed signals after the perception enhancement under different time domain windows and the radar mixed signals is calculated, if the cross-correlation coefficient exceeds a specified threshold, it is indicated that radar signals exist in the current time domain window, and the radar signal extraction is performed, including:
calculating cross-correlation coefficients between the radar mixed signals subjected to perception enhancement under different time domain windows and the radar mixed signals, wherein the radar mixed signals subjected to perception enhancement under the ith time domain windowMix signal with radar->The calculation flow of the cross-correlation coefficient is as follows:
s51: respectively to radar mixed signalsMix signal with radar->Performing wavelet transformation to obtain radar mixed signal +.>Mix signal with radar->Wavelet coefficients at scale a:
；
；
；
；
wherein:
representation function->Complex conjugate of (2);
representing radar mixed signal +.>Is a center frequency of (a);
representing radar mixed signal +.>Is a center frequency of (a);
representation function->Complex conjugate of (2);
s52: calculating to obtain wavelet coefficientAnd->Cross-correlation coefficient between:
；
；
Wherein:
representing wavelet coefficients +.>And->Cross-correlation coefficients between;
odd represents an odd number greater than 10;
representing wavelet coefficients +.>And->Phase angle between;
representing extracted imaginary part, ->Representing the extracted real part;
s53: if the cross-correlation coefficientIf the radar signal exceeds the preset threshold value, indicating that the radar signal exists in the ith time domain window;
selecting a time domain window in which radar signals exist, and extracting a smoothed radar mixed signal of the selected time domain window as the radar signals in the selected time domain window.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410249293.0A CN117826113B (en) | 2024-03-05 | 2024-03-05 | Depth perception radar micro-signal detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410249293.0A CN117826113B (en) | 2024-03-05 | 2024-03-05 | Depth perception radar micro-signal detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117826113A true CN117826113A (en) | 2024-04-05 |
| CN117826113B CN117826113B (en) | 2024-05-10 |
Family
ID=90513937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410249293.0A Active CN117826113B (en) | 2024-03-05 | 2024-03-05 | Depth perception radar micro-signal detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117826113B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110102247A1 (en) * | 2009-10-30 | 2011-05-05 | Applied Signal Technology, Inc. | Adaptive Clutter Filter for Maritime Surface Search Radar |
| CN111175718A (en) * | 2019-12-18 | 2020-05-19 | 南京理工大学 | Time-frequency domain combined ground radar automatic target identification method and system |
| CN111624573A (en) * | 2020-07-20 | 2020-09-04 | 上海无线电设备研究所 | Time domain self-adaptive target detection method under sea clutter background |
| CN112859070A (en) * | 2021-01-20 | 2021-05-28 | 应急管理部四川消防研究所 | Life detection radar system based on multi-domain multi-feature and deep learning |
| CN112904282A (en) * | 2021-01-20 | 2021-06-04 | 北京理工大学 | Radar interference signal identification method based on PWVD and convolutional neural network |
| CN113848544A (en) * | 2021-08-03 | 2021-12-28 | 隔空微电子（广州）有限公司 | Human body existence induction detection method and device based on Doppler radar and storage medium |
| CN114429156A (en) * | 2022-01-21 | 2022-05-03 | 西安电子科技大学 | Radar interference multi-domain feature countermeasure learning and detection identification method |
| CN114814835A (en) * | 2022-04-24 | 2022-07-29 | 南京大学 | Vibration detection method based on millimeter wave radar and terminal |
| WO2024000610A1 (en) * | 2022-06-29 | 2024-01-04 | 珠海正和微芯科技有限公司 | Fmcw radar moving and micro-moving target detection and recognition method and system |
| CN117388835A (en) * | 2023-12-13 | 2024-01-12 | 湖南赛能环测科技有限公司 | Multi-spelling fusion sodar signal enhancement method |
-
2024
- 2024-03-05 CN CN202410249293.0A patent/CN117826113B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110102247A1 (en) * | 2009-10-30 | 2011-05-05 | Applied Signal Technology, Inc. | Adaptive Clutter Filter for Maritime Surface Search Radar |
| CN111175718A (en) * | 2019-12-18 | 2020-05-19 | 南京理工大学 | Time-frequency domain combined ground radar automatic target identification method and system |
| CN111624573A (en) * | 2020-07-20 | 2020-09-04 | 上海无线电设备研究所 | Time domain self-adaptive target detection method under sea clutter background |
| CN112859070A (en) * | 2021-01-20 | 2021-05-28 | 应急管理部四川消防研究所 | Life detection radar system based on multi-domain multi-feature and deep learning |
| CN112904282A (en) * | 2021-01-20 | 2021-06-04 | 北京理工大学 | Radar interference signal identification method based on PWVD and convolutional neural network |
| CN113848544A (en) * | 2021-08-03 | 2021-12-28 | 隔空微电子（广州）有限公司 | Human body existence induction detection method and device based on Doppler radar and storage medium |
| CN114429156A (en) * | 2022-01-21 | 2022-05-03 | 西安电子科技大学 | Radar interference multi-domain feature countermeasure learning and detection identification method |
| CN114814835A (en) * | 2022-04-24 | 2022-07-29 | 南京大学 | Vibration detection method based on millimeter wave radar and terminal |
| WO2024000610A1 (en) * | 2022-06-29 | 2024-01-04 | 珠海正和微芯科技有限公司 | Fmcw radar moving and micro-moving target detection and recognition method and system |
| CN117388835A (en) * | 2023-12-13 | 2024-01-12 | 湖南赛能环测科技有限公司 | Multi-spelling fusion sodar signal enhancement method |
Non-Patent Citations (2)
| Title |
|---|
| FAHAD JIBRIN ABDU 等: "Application of Deep Learning on Millimeter-Wave Radar Signals: A Review", 《SENSORS》, vol. 21, no. 06, 10 March 2021 (2021-03-10), pages 1 - 45 * |
| 张涛 等: "基于区域多帧联合处理的LFMCW雷达强散射源环境下微弱目标回波信号特征增强技术", 《点波科学学报》, vol. 36, no. 01, 28 February 2021 (2021-02-28), pages 142 - 149 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117826113B (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110503971A (en) | Time-frequency mask neural network based estimation and Wave beam forming for speech processes | |
| CN107563433B (en) | Infrared small target detection method based on convolutional neural network | |
| CN104506378B (en) | A kind of device and method of prediction data flow | |
| CN114416953B (en) | Question-answering processing method, question-answering model training method and device | |
| CN105190751B (en) | Keyboard input detection and inhibition | |
| WO2023231954A1 (en) | Data denoising method and related device | |
| KR20100090829A (en) | Apparatus for realtime face recognition | |
| CN117388835B (en) | Multi-spelling fusion sodar signal enhancement method | |
| CN111091147B (en) | Image classification method, device and equipment | |
| CN113988357B (en) | Advanced learning-based high-rise building wind induced response prediction method and device | |
| CN110969123A (en) | Electromagnetic information leakage detection method based on frequency domain, terminal equipment and storage medium | |
| CN118312329B (en) | Intelligent recommendation method for calculating force under heterogeneous calculating force integrated system | |
| CN114612651B (en) | ROI detection model training method, detection method, device, equipment and medium | |
| CN116704324A (en) | Target detection method, system, equipment and storage medium based on underwater image | |
| CN117826113B (en) | Depth perception radar micro-signal detection method | |
| Ding et al. | Full‐reference image quality assessment using statistical local correlation | |
| CN114519372A (en) | One-dimensional range profile target identification method based on support vector machine | |
| CN118070182A (en) | Energy consumption monitoring control system and method for green building | |
| CN116482680A (en) | Body interference identification method, device, system and storage medium | |
| CN115762555A (en) | Dynamic audio signal adjusting and transmitting method | |
| CN116230005B (en) | Remote voice signal delay estimation method | |
| Mousazadeh et al. | Two dimensional noncausal AR-ARCH model: Stationary conditions, parameter estimation and its application to anomaly detection | |
| CN115797787B (en) | SAR image water bloom region extraction method | |
| WO2023152882A1 (en) | Model training device, model training method, and non-transitory computer-readable medium | |
| CN116013091B (en) | Tunnel monitoring system and analysis method based on traffic flow big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |