CN118050716B - Sodar signal processing method for multi-scale morphological processing - Google Patents
Sodar signal processing method for multi-scale morphological processing Download PDFInfo
- Publication number
- CN118050716B CN118050716B CN202410451159.9A CN202410451159A CN118050716B CN 118050716 B CN118050716 B CN 118050716B CN 202410451159 A CN202410451159 A CN 202410451159A CN 118050716 B CN118050716 B CN 118050716B
- Authority
- CN
- China
- Prior art keywords
- sodar
- signal
- echo signals
- clutter suppression
- depth
- 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.)
- Active
Links
- SDIXRDNYIMOKSG-UHFFFAOYSA-L disodium methyl arsenate Chemical group [Na+].[Na+].C[As]([O-])([O-])=O SDIXRDNYIMOKSG-UHFFFAOYSA-L 0.000 title claims abstract description 259
- 238000012545 processing Methods 0.000 title claims abstract description 116
- 230000000877 morphologic effect Effects 0.000 title claims abstract description 61
- 238000003672 processing method Methods 0.000 title claims description 15
- 230000001629 suppression Effects 0.000 claims abstract description 181
- 238000000034 method Methods 0.000 claims abstract description 53
- 238000001914 filtration Methods 0.000 claims abstract description 48
- 238000005457 optimization Methods 0.000 claims abstract description 18
- 230000007246 mechanism Effects 0.000 claims abstract description 9
- 230000000694 effects Effects 0.000 claims abstract description 8
- 238000013507 mapping Methods 0.000 claims description 49
- 238000000354 decomposition reaction Methods 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 25
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000010606 normalization Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000007499 fusion processing Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 230000007797 corrosion Effects 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 4
- 238000001228 spectrum Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 13
- 238000004891 communication Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 5
- 238000010586 diagram 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
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention relates to the technical field of sodar signal processing, and discloses a method for processing a sodar signal by multi-scale morphological processing, which comprises the following steps: collecting multi-path echo signals of the sodar and carrying out frequency domain clutter suppression; carrying out signal enhancement on the sodar multipath echo signals after the frequency domain clutter suppression; and carrying out optimization solution on the constructed depth clutter suppression model, and carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by utilizing the depth clutter suppression model obtained by the solution. According to the method, sub-signal fusion is carried out based on frequency domain energy information of the sodar multipath echo sub-signals under different scales, the frequency domain clutter sub-signals are weakened, suppression of non-impact components in the signals is carried out by adopting a morphological filtering mode of a self-adaptive scale, clutter effects caused by medium heterogeneity of the echo signals of different paths are removed based on an attention mechanism, and deep clutter suppression processing of the sodar multipath echo signals is realized, so that pure sodar signals are obtained.
Description
Technical Field
The invention relates to the technical field of sodar signal processing, in particular to a method for processing sodar signals by multi-scale morphological processing.
Background
Sodar technology can extract useful information from radar acoustic signals and analyze the useful information to realize ultra-remote target detection. The performance of target detection and positioning is improved by fully utilizing the multiple echo path information contained in the radar echo. Through analyzing radar signals reflected on a plurality of different paths, the method is beneficial to analyzing and knowing the interrelationship between the target and surrounding structures, such as the distance and the position relationship between the target and the ground, the wall and the like, realizes effective detection of hidden targets in 'vision' blind areas such as city street corners, vehicle shielding and the like, can provide services for various applications such as intelligent driving and the like, and has important practical significance and research value. Although the sodar signal echoes from multiple paths carry much information, there is still a great difficulty in how to properly utilize such echo signals, especially where such echo signals are often affected by environmental, clutter and other disturbances, making target detection and localization difficult. Therefore, how to cancel interference information in echo signals is an important issue to be solved.
Disclosure of Invention
In view of the above, the present invention provides a sodar signal processing method for multi-scale morphological processing, which aims to: 1) Carrying out multi-scale decomposition on the acquired sodar multipath echo signals, carrying out sub-signal fusion based on frequency domain energy information of the sodar multipath echo sub-signals under different scales, weakening the frequency domain clutter sub-signals, realizing frequency domain clutter suppression, determining morphological filtering scales of different signal values according to the amplitude values of local extremum points in the sodar multipath echo signals and nonlinear mapping parameters, configuring smaller morphological filtering scales for the local extremum points with larger amplitude values, keeping the smaller morphological filtering scales as much as possible, configuring larger morphological filtering scales for the local extremum points with smaller amplitude values, and suppressing the larger morphological filtering scales as much as possible, thereby realizing suppression of non-impact components and obtaining the enhanced sodar multipath echo signals; 2) And (3) constructing an optimized solution objective function and constraint conditions of a depth clutter suppression model, constructing the constraint conditions as a projection matrix, generating an iteration step length by combining gradients of the objective function, optimizing parameters of the depth clutter suppression model, removing clutter effects caused by medium heterogeneity of echo signals of different paths based on an attention mechanism, and realizing depth clutter suppression processing of the sodar multipath echo signals to obtain pure sodar signals.
In order to achieve the above object, the present invention provides a sodar signal processing method for multi-scale morphological processing, including the following steps:
s1: collecting a sodar multipath echo signal and performing frequency domain clutter suppression to obtain a sodar multipath echo signal after the frequency domain clutter suppression;
s2: performing signal enhancement on the sodar multipath echo signals subjected to frequency domain clutter suppression, wherein the signal morphological filtering of the adaptive scale transformation is a main implementation method of the signal enhancement;
S3: constructing a depth clutter suppression model, wherein the depth clutter suppression model takes the enhanced sodar multipath echo signals as input, removes clutter effects caused by medium heterogeneity of echo signals of different paths based on an attention mechanism, and takes pure sodar multipath echo signals as output;
s4: and carrying out optimization solution on the constructed depth clutter suppression model, and carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by utilizing the depth clutter suppression model obtained by the solution.
As a further improvement of the present invention:
Optionally, the step S1 of collecting sodar multi-path echo signals includes:
Collecting sodar multipath echo signals, and carrying out frequency domain clutter suppression on the sodar multipath echo signals to obtain sodar multipath echo signals after the frequency domain clutter suppression, wherein the sodar multipath echo signals represent signals obtained by fusing the sodar echo signals of different echo paths, the sodar echo signals represent echo signals received by directional sound pulses emitted by the sodar to a target object, the echo signals contact different mediums in the returning process, the contacted mediums are echo paths of the sodar echo signals, and the collected sodar multipath echo signals are in the form of:
；
Wherein:
representing sodar multipath echo signals, t representing timing information;
representing sodar multipath echo signals At the nth signal timeIs used for the signal value of (a),Representing sodar multipath echo signalsIs set, is provided for the N signal instants of (a).
Optionally, in the step S1, performing frequency domain clutter suppression on the sodar multipath echo signal includes:
performing frequency domain clutter suppression on the sodar multipath echo signals, wherein the frequency domain clutter suppression flow of the sodar multipath echo signals is as follows:
S11: performing multi-scale decomposition processing on the sodar multi-path echo signals to obtain sodar multi-path echo sub-signals under K scales;
s12: calculating to obtain frequency domain energy information of sodar multipath echo sub-signals under different decomposition scales, wherein the sodar multipath echo signals Sodar multipath echo sub-signal at kth decomposition scaleThe frequency domain energy information calculation formula is:
；
Wherein:
Representing sodar multipath echo sub-signals At the moment of signalIs a signal value of (2);
Representing sodar multipath echo sub-signals Is a frequency of (2);
Representing sodar multipath echo sub-signals Frequency domain energy information of (a);
S13: and carrying out signal fusion processing on the sodar multipath echo sub-signals under different decomposition scales based on the frequency domain energy information to obtain the sodar multipath echo signals after frequency domain clutter suppression, wherein the signal fusion processing formula is as follows:
；
；
Wherein:
An exponential function that is based on a natural constant;
Representing the sodar multipath echo signals after the frequency domain clutter suppression;
Multi-path echo signal of sodar after representing frequency domain clutter suppression At the moment of signalIs a signal value of (a).
Optionally, in the step S11, the multi-scale decomposition processing is performed on the sodar multi-path echo signal, including:
Sodar multipath echo signals The multi-scale decomposition processing flow is as follows:
S111: multipath echo signal of sodar As a signal to be decomposed, setting the current decomposition scale as K, wherein the initial value of K is 1, and the maximum value is K;
S112: acquiring all local extreme points of a signal to be decomposed, wherein the local extreme points comprise minimum value points and maximum value points;
S113: respectively carrying out interpolation processing on the minimum value point set and the maximum value point set by using a cubic spline interpolation method, calculating the average value of the upper envelope line and the lower envelope line to obtain an average value signal, and calculating a difference value signal between a signal to be decomposed and the average value signal;
S114: if the difference between the zero point number and the total number of local extreme points of the difference signal is less than or equal to 1 and the average value of the upper envelope and the lower envelope of the difference signal is 0, the difference signal is used as a sodar multipath echo signal Sodar multipath echo sub-signals at a decomposition scale kLet k=k+1, willAs a signal to be decomposed, return to step S112 until k=k, resulting in a sodar multipath echo signalSodar multipath echo sub-signals at K decomposition scales；
Otherwise, the difference signal is the signal to be decomposed, and the step S112 is returned.
Optionally, in the step S2, signal enhancement is performed on the sodar multipath echo signal after the frequency domain clutter suppression, including:
and carrying out signal enhancement on the sodar multipath echo signals after the frequency domain clutter suppression, wherein the signal enhancement flow is as follows:
s21: acquiring multiple paths of echo signals of sodar after frequency domain clutter suppression And constructing and obtaining an amplitude set of the local extreme points:
；
Wherein:
representing sodar multipath echo signals The amplitude corresponding to the mth local extreme point in the range, M represents the sodar multipath echo signalIs defined by the total number of local extremal points;
s22: normalizing the amplitude values in the amplitude value set, wherein the amplitude values The normalization processing formula of (2) is as follows:
；
Wherein:
Representing amplitude Is a normalization processing result of (a);
representing the maximum value in the set of magnitudes, Representing the minimum value in the set of magnitudes;
s23: calculating to obtain the signal time number average value between adjacent local extreme points ；
S24: acquiring multiple paths of echo signals of sodar after frequency domain clutter suppressionAmplitude values of signal values at different signal moments in the spectrum, and calculating to obtain morphological filtering scales of the different signal values, whereinThe morphological filtering scale of (2) is:
；
；
Wherein:
Representing signal values Normalized amplitude values corresponding to local extremum points on the left side and the right side;
Representing signal values Is subjected to normalization processing;
Representing signal values Is used for mapping the non-linear mapping parameters of the (a);
Representation of Morphology filtering scale of (a);
s25: based on morphological filtering scale of signal values, performing morphological filtering processing of adaptive scale on signal values at different signal moments, wherein the signal moments Signal value of (2)The morphological filtering processing formula is as follows:
；
；
；
；
；
Wherein:
Representing signal values Morphological filtering processing results of (2);
Representing signal values Is a result of the forward pulse suppression in (c),Representing signal valuesNegative going pulse suppression results in (2);
Representing a scale of Is provided with a morphological filtering template of (a),Representing morphological filtering templatesThe b-th element value of (b);
the expansion process is represented by the process of expansion, Indicating a corrosion treatment;
constructing enhanced sodar multipath echo signals 。
Optionally, constructing a depth clutter suppression model in the step S3 includes:
The method comprises the steps of constructing a depth clutter suppression model, wherein the depth clutter suppression model takes an enhanced sodar multipath echo signal as an input, removes clutter effects caused by medium heterogeneity of echo signals of different paths based on an attention mechanism, and takes a pure sodar multipath echo signal as an output, and the depth clutter suppression model comprises an input layer, a residual mapping layer, an attention calculation layer, a clutter suppression layer and an output layer;
The input layer is used for receiving the enhanced sodar multipath echo signals;
The residual mapping layer is used for carrying out multi-scale residual mapping processing on the enhanced sodar multipath echo signals to obtain depth clutter representation of the sodar multipath echo signals;
The attention calculating layer is used for calculating attention weights of depth clutter representations under different scales;
The clutter suppression layer is used for performing clutter suppression processing on the depth clutter representation based on the attention weight to obtain a clean sodar signal for output.
Optionally, in the step S4, the optimizing and solving the constructed deep clutter suppression model includes:
Carrying out optimization solution on the constructed depth clutter suppression model, and carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by utilizing the depth clutter suppression model obtained by the solution, wherein the optimization solution flow of the depth clutter suppression model is as follows:
s41: r groups of sodar multipath echo signals are obtained and enhanced, so that a training set data in the optimization solving process of the deep clutter suppression model is formed: Wherein Representing the acquired sodar multipath echo signals after the r group enhancement processing;
S42: constructing an optimized solving objective function of a depth clutter suppression model and constraint conditions:
；
；
Wherein:
an optimization solving objective function representing a depth clutter suppression model, Representing a to-be-optimized solving parameter of a depth clutter suppression model; in the embodiment of the invention, the to-be-optimized solving parameters of the depth clutter suppression model comprise a mapping matrix in a residual mapping layer;
Sodar multipath echo signal after r group enhancement processing in training set data Frequency domain energy information of (a);
Representing the presentation to be Inputting the frequency domain energy information of signals output by a depth clutter suppression model constructed based on the solution parameters to be optimized;
The constraint condition is represented by a constraint condition, Representing a preset frequency domain energy information threshold;
s43: generating to-be-optimized solving parameters meeting constraint conditions as initial solutions ; Setting the current iteration number of the parameter to be optimized as D, setting the maximum iteration number as D, setting the initial value of D as 0, and setting the D iteration result of the parameter to be optimized as；
S44: establishing a projection matrix in the (d+1) th iteration process：
；
；
；
Wherein:
E represents an identity matrix;
T represents a transpose;
representing a constraint matrix incorporating constraint conditions;
Representing projection matrix parameters;
s45: generating an iteration step in the (d+1) th iteration process ：
；
；
Wherein:
Representation of Is a gradient of (2);
representation is such that Reaching a minimum a;
S46: iterating the solving parameters to be optimized, wherein an iteration formula is as follows:
；
Let d=d+1, return to step S44 until d+1=d, will And constructing and obtaining the depth clutter suppression model as model parameters of the depth clutter suppression model.
Optionally, in the step S4, the performing depth clutter suppression processing on the enhanced sodar multi-path echo signal by using the depth clutter suppression model obtained by solving includes:
And carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by using the depth clutter suppression model obtained by solving, wherein the depth clutter suppression processing flow is as follows:
Receiving enhanced sodar multipath echo signals by input layer ；
The residual mapping layer carries out multi-scale residual mapping processing on the enhanced sodar multipath echo signals to obtain depth clutter representation of the sodar multipath echo signals, wherein the sodar multipath echo signalsThe multi-scale residual mapping processing formula is as follows:
；
Wherein:
representing sodar multipath echo signals Mapping results at the u +1 scale, where the initial value of u is 0,；
Representation pairIs a mapping matrix of (a);
Will be A multi-scale depth clutter representation as sodar multi-path echo signals, wherein U represents a maximum residual mapping scale;
The attention calculating layer calculates attention weights of the depth clutter representations under different scales, wherein the attention weights of the depth clutter representations under the u scale are as follows:
；
Wherein:
Attention weights representing depth clutter representation at the u scale;
The clutter suppression layer performs clutter suppression processing on the depth clutter representation based on the attention weight, and a pure sodar signal is obtained and output by the output layer, wherein the clutter suppression processing formula is as follows:
；
Wherein:
indicating a clean sodar signal after clutter suppression processing.
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 a processor executing the instructions stored in the memory to implement the sodar signal processing method of multi-scale morphological processing described above.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored therein at least one instruction that is executed by a processor in an electronic device to implement the sodar signal processing method of multi-scale morphological processing described above.
Compared with the prior art, the invention provides a sodar signal processing method for multi-scale morphological processing, which has the following advantages:
Firstly, the scheme provides a signal enhancement method for enhancing the signal of the sodar multipath echo signal after the frequency domain clutter suppression, wherein the signal enhancement flow is as follows: acquiring multiple paths of echo signals of sodar after frequency domain clutter suppression And constructing and obtaining an amplitude set of the local extreme points:
；
Wherein: representing sodar multipath echo signals The amplitude corresponding to the mth local extreme point in the range, M represents the sodar multipath echo signalIs defined by the total number of local extremal points; normalizing the amplitude values in the amplitude value set, wherein the amplitude valuesThe normalization processing formula of (2) is as follows:
；
Wherein: Representing amplitude Is a normalization processing result of (a); representing the maximum value in the set of magnitudes, Representing the minimum value in the set of magnitudes; calculating to obtain the signal time number average value between adjacent local extreme points; Acquiring multiple paths of echo signals of sodar after frequency domain clutter suppressionAmplitude values of signal values at different signal moments in the spectrum, and calculating to obtain morphological filtering scales of the different signal values, whereinThe morphological filtering scale of (2) is:
；
；
Wherein: Representing signal values Normalized amplitude values corresponding to local extremum points on the left side and the right side; Representing signal values Is subjected to normalization processing; Representing signal values Is used for mapping the non-linear mapping parameters of the (a); Representation of Morphology filtering scale of (a); based on morphological filtering scale of signal values, performing morphological filtering processing of adaptive scale on signal values at different signal moments, wherein the signal momentsSignal value of (2)The morphological filtering processing formula is as follows:
；
；
；
；
；
Wherein: Representing signal values Morphological filtering processing results of (2); Representing signal values Is a result of the forward pulse suppression in (c),Representing signal valuesNegative going pulse suppression results in (2); Representing a scale of Is provided with a morphological filtering template of (a),Representing morphological filtering templatesThe b-th element value of (b); the expansion process is represented by the process of expansion, Indicating a corrosion treatment; constructing enhanced sodar multipath echo signals. According to the scheme, multi-scale decomposition is carried out on the acquired sodar multipath echo signals, sub-signal fusion is carried out on the basis of frequency domain energy information of the sodar multipath echo sub-signals under different scales, frequency domain clutter sub-signals are weakened, frequency domain clutter suppression is achieved, morphological filtering scales of different signal values are determined according to amplitude values and nonlinear mapping parameters of local extremum points in the sodar multipath echo signals, smaller morphological filtering scales are configured for the local extremum points with larger amplitude values, the smaller morphological filtering scales are reserved as much as possible, larger morphological filtering scales are configured for the local extremum points with smaller amplitude values, the larger morphological filtering scales are suppressed as much as possible, and therefore suppression of non-impact components is achieved, and the enhanced sodar multipath echo signals are obtained.
Meanwhile, the scheme provides a depth clutter suppression processing method, and the residual mapping layer carries out multi-scale residual mapping processing on the enhanced sodar multipath echo signals to obtain depth clutter representation of the sodar multipath echo signals, wherein the sodar multipath echo signalsThe multi-scale residual mapping processing formula is as follows:
；
Wherein: representing sodar multipath echo signals Mapping results at the u +1 scale, where the initial value of u is 0,；Representation pairIs a mapping matrix of (a); will beA multi-scale depth clutter representation as sodar multi-path echo signals, wherein U represents a maximum residual mapping scale; the attention calculating layer calculates attention weights of the depth clutter representations under different scales, wherein the attention weights of the depth clutter representations under the u scale are as follows:
；
Wherein: Attention weights representing depth clutter representation at the u scale; the clutter suppression layer performs clutter suppression processing on the depth clutter representation based on the attention weight, and a pure sodar signal is obtained and output by the output layer, wherein the clutter suppression processing formula is as follows:
；
Wherein: indicating a clean sodar signal after clutter suppression processing.
According to the scheme, the objective function and the constraint condition are optimized and solved through constructing the depth clutter suppression model, the constraint condition is constructed as a projection matrix, iteration step length is generated by combining gradients of the objective function, parameter optimization of the depth clutter suppression model is performed, clutter influence caused by medium heterogeneity of echo signals of different paths is removed based on an attention mechanism, depth clutter suppression processing of the sodar multipath echo signals is achieved, and pure sodar signals are obtained.
Drawings
FIG. 1 is a flow chart of a method for processing sodar signals with multi-scale morphological processing according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an electronic device for implementing a sodar signal processing method for multi-scale morphological processing 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 a 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 sodar signal processing method for multi-scale morphological processing. The execution main body of the sodar signal processing method of the multi-scale morphological processing includes, but is not limited to, at least one of a server, a terminal and the like which can be configured to execute the electronic equipment of the method provided by the embodiment of the application. In other words, the sodar signal processing method of the multi-scale morphological processing 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 the sodar multipath echo signals and performing frequency domain clutter suppression to obtain the sodar multipath echo signals after the frequency domain clutter suppression.
The step S1 of collecting the sodar multipath echo signals comprises the following steps:
Collecting sodar multipath echo signals, and carrying out frequency domain clutter suppression on the sodar multipath echo signals to obtain sodar multipath echo signals after the frequency domain clutter suppression, wherein the sodar multipath echo signals represent signals obtained by fusing the sodar echo signals of different echo paths, the sodar echo signals represent echo signals received by directional sound pulses emitted by the sodar to a target object, the echo signals contact different mediums in the returning process, the contacted mediums are echo paths of the sodar echo signals, and the collected sodar multipath echo signals are in the form of:
；
Wherein: representing sodar multipath echo signals, t representing timing information;
representing sodar multipath echo signals At the nth signal timeIs used for the signal value of (a),Representing sodar multipath echo signalsIs set, is provided for the N signal instants of (a).
In the step S1, performing frequency domain clutter suppression on the sodar multipath echo signal includes:
performing frequency domain clutter suppression on the sodar multipath echo signals, wherein the frequency domain clutter suppression flow of the sodar multipath echo signals is as follows:
S11: performing multi-scale decomposition processing on the sodar multi-path echo signals to obtain sodar multi-path echo sub-signals under K scales;
s12: calculating to obtain frequency domain energy information of sodar multipath echo sub-signals under different decomposition scales, wherein the sodar multipath echo signals Sodar multipath echo sub-signal at kth decomposition scaleThe frequency domain energy information calculation formula is:
；
Wherein:
Representing sodar multipath echo sub-signals At the moment of signalIs a signal value of (2);
Representing sodar multipath echo sub-signals Is a frequency of (2);
Representing sodar multipath echo sub-signals Frequency domain energy information of (a);
S13: and carrying out signal fusion processing on the sodar multipath echo sub-signals under different decomposition scales based on the frequency domain energy information to obtain the sodar multipath echo signals after frequency domain clutter suppression, wherein the signal fusion processing formula is as follows:
；
；
Wherein:
An exponential function that is based on a natural constant;
Representing the sodar multipath echo signals after the frequency domain clutter suppression;
Multi-path echo signal of sodar after representing frequency domain clutter suppression At the moment of signalIs a signal value of (a).
In the step S11, the multi-scale decomposition processing is performed on the sodar multipath echo signals, including:
Sodar multipath echo signals The multi-scale decomposition processing flow is as follows:
S111: multipath echo signal of sodar As a signal to be decomposed, setting the current decomposition scale as K, wherein the initial value of K is 1, and the maximum value is K;
S112: acquiring all local extreme points of a signal to be decomposed, wherein the local extreme points comprise minimum value points and maximum value points;
S113: respectively carrying out interpolation processing on the minimum value point set and the maximum value point set by using a cubic spline interpolation method, calculating the average value of the upper envelope line and the lower envelope line to obtain an average value signal, and calculating a difference value signal between a signal to be decomposed and the average value signal;
S114: if the difference between the zero point number and the total number of local extreme points of the difference signal is less than or equal to 1 and the average value of the upper envelope and the lower envelope of the difference signal is 0, the difference signal is used as a sodar multipath echo signal Sodar multipath echo sub-signals at a decomposition scale kLet k=k+1, willAs a signal to be decomposed, return to step S112 until k=k, resulting in a sodar multipath echo signalSodar multipath echo sub-signals at K decomposition scales; Otherwise, the difference signal is the signal to be decomposed, and the step S112 is returned.
S2: and carrying out signal enhancement on the sodar multipath echo signals after the frequency domain clutter suppression.
In the step S2, signal enhancement is performed on the sodar multipath echo signal after the frequency domain clutter suppression, which includes:
and carrying out signal enhancement on the sodar multipath echo signals after the frequency domain clutter suppression, wherein the signal enhancement flow is as follows:
s21: acquiring multiple paths of echo signals of sodar after frequency domain clutter suppression And constructing and obtaining an amplitude set of the local extreme points:
；
Wherein:
representing sodar multipath echo signals The amplitude corresponding to the mth local extreme point in the range, M represents the sodar multipath echo signalIs defined by the total number of local extremal points;
s22: normalizing the amplitude values in the amplitude value set, wherein the amplitude values The normalization processing formula of (2) is as follows:
；
Wherein:
Representing amplitude Is a normalization processing result of (a);
representing the maximum value in the set of magnitudes, Representing the minimum value in the set of magnitudes;
s23: calculating to obtain the signal time number average value between adjacent local extreme points ；
S24: acquiring multiple paths of echo signals of sodar after frequency domain clutter suppressionAmplitude values of signal values at different signal moments in the spectrum, and calculating to obtain morphological filtering scales of the different signal values, whereinThe morphological filtering scale of (2) is:
；
；
Wherein:
Representing signal values Normalized amplitude values corresponding to local extremum points on the left side and the right side;
Representing signal values Is subjected to normalization processing;
Representing signal values Is used for mapping the non-linear mapping parameters of the (a);
Representation of Morphology filtering scale of (a);
s25: based on morphological filtering scale of signal values, performing morphological filtering processing of adaptive scale on signal values at different signal moments, wherein the signal moments Signal value of (2)The morphological filtering processing formula is as follows:
；
；
；
；
；
Wherein:
Representing signal values Morphological filtering processing results of (2);
Representing signal values Is a result of the forward pulse suppression in (c),Representing signal valuesNegative going pulse suppression results in (2);
Representing a scale of Is provided with a morphological filtering template of (a),Representing morphological filtering templatesThe b-th element value of (b);
the expansion process is represented by the process of expansion, Indicating a corrosion treatment;
constructing enhanced sodar multipath echo signals 。
And constructing a depth clutter suppression model, wherein the depth clutter suppression model takes the enhanced sodar multipath echo signals as input, removes clutter effects caused by medium heterogeneity of echo signals of different paths based on an attention mechanism, and takes the pure sodar multipath echo signals as output.
And in the step S3, a depth clutter suppression model is constructed, which comprises the following steps:
The method comprises the steps of constructing a depth clutter suppression model, wherein the depth clutter suppression model takes an enhanced sodar multipath echo signal as an input, removes clutter effects caused by medium heterogeneity of echo signals of different paths based on an attention mechanism, and takes a pure sodar multipath echo signal as an output, and the depth clutter suppression model comprises an input layer, a residual mapping layer, an attention calculation layer, a clutter suppression layer and an output layer;
The input layer is used for receiving the enhanced sodar multipath echo signals;
The residual mapping layer is used for carrying out multi-scale residual mapping processing on the enhanced sodar multipath echo signals to obtain depth clutter representation of the sodar multipath echo signals;
The attention calculating layer is used for calculating attention weights of depth clutter representations under different scales;
The clutter suppression layer is used for performing clutter suppression processing on the depth clutter representation based on the attention weight to obtain a clean sodar signal for output.
S4: and carrying out optimization solution on the constructed depth clutter suppression model, and carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by utilizing the depth clutter suppression model obtained by the solution.
And in the step S4, the constructed deep clutter suppression model is optimized and solved, and the method comprises the following steps:
Carrying out optimization solution on the constructed depth clutter suppression model, and carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by utilizing the depth clutter suppression model obtained by the solution, wherein the optimization solution flow of the depth clutter suppression model is as follows:
s41: r groups of sodar multipath echo signals are obtained and enhanced, so that a training set data in the optimization solving process of the deep clutter suppression model is formed: Wherein Representing the acquired sodar multipath echo signals after the r group enhancement processing;
S42: constructing an optimized solving objective function of a depth clutter suppression model and constraint conditions:
；
；
Wherein:
an optimization solving objective function representing a depth clutter suppression model, Representing a to-be-optimized solving parameter of a depth clutter suppression model; in the embodiment of the invention, the to-be-optimized solving parameters of the depth clutter suppression model comprise a mapping matrix in a residual mapping layer;
Sodar multipath echo signal after r group enhancement processing in training set data Frequency domain energy information of (a);
Representing the presentation to be Inputting the frequency domain energy information of signals output by a depth clutter suppression model constructed based on the solution parameters to be optimized;
The constraint condition is represented by a constraint condition, Representing a preset frequency domain energy information threshold;
s43: generating to-be-optimized solving parameters meeting constraint conditions as initial solutions ; Setting the current iteration number of the parameter to be optimized as D, setting the maximum iteration number as D, setting the initial value of D as 0, and setting the D iteration result of the parameter to be optimized as；
S44: establishing a projection matrix in the (d+1) th iteration process：
；
；
；
Wherein:
E represents an identity matrix;
T represents a transpose;
representing a constraint matrix incorporating constraint conditions;
Representing projection matrix parameters;
s45: generating an iteration step in the (d+1) th iteration process ：
；
；
Wherein:
Representation of Is a gradient of (2);
representation is such that Reaching a minimum a;
S46: iterating the solving parameters to be optimized, wherein an iteration formula is as follows:
；
Let d=d+1, return to step S44 until d+1=d, will And constructing and obtaining the depth clutter suppression model as model parameters of the depth clutter suppression model.
And in the step S4, the depth clutter suppression model obtained by solving is utilized to carry out depth clutter suppression processing on the enhanced sodar multipath echo signals, and the method comprises the following steps:
And carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by using the depth clutter suppression model obtained by solving, wherein the depth clutter suppression processing flow is as follows:
Receiving enhanced sodar multipath echo signals by input layer ；
The residual mapping layer carries out multi-scale residual mapping processing on the enhanced sodar multipath echo signals to obtain depth clutter representation of the sodar multipath echo signals, wherein the sodar multipath echo signalsThe multi-scale residual mapping processing formula is as follows:
；
Wherein:
representing sodar multipath echo signals Mapping results at the u +1 scale, where the initial value of u is 0,；
Representation pairIs a mapping matrix of (a);
Will be A multi-scale depth clutter representation as sodar multi-path echo signals, wherein U represents a maximum residual mapping scale;
The attention calculating layer calculates attention weights of the depth clutter representations under different scales, wherein the attention weights of the depth clutter representations under the u scale are as follows:
；
Wherein:
Attention weights representing depth clutter representation at the u scale;
The clutter suppression layer performs clutter suppression processing on the depth clutter representation based on the attention weight, and a pure sodar signal is obtained and output by the output layer, wherein the clutter suppression processing formula is as follows:
；
Wherein:
indicating a clean sodar signal after clutter suppression processing.
Example 2
Fig. 2 is a schematic structural diagram of an electronic device for implementing a sodar signal processing method for multi-scale morphological processing 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 memory card (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 sodar signal processing of multi-scale morphological processing, 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 the 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 a sodar multipath echo signal and performing frequency domain clutter suppression to obtain a sodar multipath echo signal after the frequency domain clutter suppression;
Carrying out signal enhancement on the sodar multipath echo signals after the frequency domain clutter suppression;
and carrying out optimization solution on the constructed depth clutter suppression model, and carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by utilizing the depth clutter suppression model obtained by the solution.
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 (5)
1. A method of sodar signal processing for multi-scale morphological processing, the method comprising:
s1: collecting a sodar multipath echo signal and performing frequency domain clutter suppression to obtain a sodar multipath echo signal after the frequency domain clutter suppression;
collecting sodar multipath echo signals, comprising:
Collecting sodar multipath echo signals, and carrying out frequency domain clutter suppression on the sodar multipath echo signals to obtain sodar multipath echo signals after the frequency domain clutter suppression, wherein the sodar multipath echo signals represent signals obtained by fusing the sodar echo signals of different echo paths, the sodar echo signals represent echo signals received by directional sound pulses emitted by the sodar to a target object, the echo signals contact different mediums in the returning process, the contacted mediums are echo paths of the sodar echo signals, and the collected sodar multipath echo signals are in the form of:
；
Wherein:
representing sodar multipath echo signals, t representing timing information;
representing sodar multipath echo signals At the nth signal timeIs used for the signal value of (a),Representing sodar multipath echo signalsN signal moments of (a);
performing frequency domain clutter suppression on the sodar multipath echo signals, wherein the frequency domain clutter suppression flow of the sodar multipath echo signals is as follows:
S11: performing multi-scale decomposition processing on the sodar multi-path echo signals to obtain sodar multi-path echo sub-signals under K scales;
s12: calculating to obtain frequency domain energy information of sodar multipath echo sub-signals under different decomposition scales, wherein the sodar multipath echo signals Sodar multipath echo sub-signal at kth decomposition scaleThe frequency domain energy information calculation formula is:
；
Wherein:
Representing sodar multipath echo sub-signals At the moment of signalIs a signal value of (2);
Representing sodar multipath echo sub-signals Is a frequency of (2);
Representing sodar multipath echo sub-signals Frequency domain energy information of (a);
S13: and carrying out signal fusion processing on the sodar multipath echo sub-signals under different decomposition scales based on the frequency domain energy information to obtain the sodar multipath echo signals after frequency domain clutter suppression, wherein the signal fusion processing formula is as follows:
；
；
Wherein:
An exponential function that is based on a natural constant;
Representing the sodar multipath echo signals after the frequency domain clutter suppression;
Multi-path echo signal of sodar after representing frequency domain clutter suppression At the moment of signalIs a signal value of (2);
Sodar multipath echo signals The multi-scale decomposition processing flow is as follows:
S111: multipath echo signal of sodar As a signal to be decomposed, setting the current decomposition scale as K, wherein the initial value of K is 1, and the maximum value is K;
S112: acquiring all local extreme points of a signal to be decomposed, wherein the local extreme points comprise minimum value points and maximum value points;
S113: respectively carrying out interpolation processing on the minimum value point set and the maximum value point set by using a cubic spline interpolation method, calculating the average value of the upper envelope line and the lower envelope line to obtain an average value signal, and calculating a difference value signal between a signal to be decomposed and the average value signal;
S114: if the difference between the zero point number and the total number of local extreme points of the difference signal is less than or equal to 1 and the average value of the upper envelope and the lower envelope of the difference signal is 0, the difference signal is used as a sodar multipath echo signal Sodar multipath echo sub-signals at a decomposition scale kLet k=k+1, willAs a signal to be decomposed, return to step S112 until k=k, resulting in a sodar multipath echo signalSodar multipath echo sub-signals at K decomposition scales；
Otherwise, the difference signal is made to be the signal to be decomposed, and the step S112 is returned;
s2: carrying out signal enhancement on the sodar multipath echo signals after the frequency domain clutter suppression;
S3: constructing a depth clutter suppression model, wherein the depth clutter suppression model takes the enhanced sodar multipath echo signals as input, removes clutter effects caused by medium heterogeneity of echo signals of different paths based on an attention mechanism, and takes pure sodar multipath echo signals as output;
s4: and carrying out optimization solution on the constructed depth clutter suppression model, and carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by utilizing the depth clutter suppression model obtained by the solution.
2. The method for processing sodar signals according to claim 1, wherein in step S2, the signal enhancement is performed on the sodar multipath echo signals after the frequency domain clutter suppression, and the method comprises the following steps:
and carrying out signal enhancement on the sodar multipath echo signals after the frequency domain clutter suppression, wherein the signal enhancement flow is as follows:
s21: acquiring multiple paths of echo signals of sodar after frequency domain clutter suppression And constructing and obtaining an amplitude set of the local extreme points:
；
Wherein:
representing sodar multipath echo signals The amplitude corresponding to the mth local extreme point in the range, M represents the sodar multipath echo signalIs defined by the total number of local extremal points;
s22: normalizing the amplitude values in the amplitude value set, wherein the amplitude values The normalization processing formula of (2) is as follows:
；
Wherein:
Representing amplitude Is a normalization processing result of (a);
representing the maximum value in the set of magnitudes, Representing the minimum value in the set of magnitudes;
s23: calculating to obtain the signal time number average value between adjacent local extreme points ；
S24: acquiring multiple paths of echo signals of sodar after frequency domain clutter suppressionAmplitude values of signal values at different signal moments in the spectrum, and calculating to obtain morphological filtering scales of the different signal values, whereinThe morphological filtering scale of (2) is:
；
；
Wherein:
Representing signal values Normalized amplitude values corresponding to local extremum points on the left side and the right side;
Representing signal values Is subjected to normalization processing;
Representing signal values Is used for mapping the non-linear mapping parameters of the (a);
Representation of Morphology filtering scale of (a);
s25: based on morphological filtering scale of signal values, performing morphological filtering processing of adaptive scale on signal values at different signal moments, wherein the signal moments Signal value of (2)The morphological filtering processing formula is as follows:
；
；
；
；
；
Wherein:
Representing signal values Morphological filtering processing results of (2);
Representing signal values Is a result of the forward pulse suppression in (c),Representing signal valuesNegative going pulse suppression results in (2);
Representing a scale of Is provided with a morphological filtering template of (a),Representing morphological filtering templatesThe b-th element value of (b);
the expansion process is represented by the process of expansion, Indicating a corrosion treatment;
constructing enhanced sodar multipath echo signals 。
3. The sodar signal processing method of claim 1, wherein the step S3 of constructing a depth clutter suppression model comprises:
The method comprises the steps of constructing a depth clutter suppression model, wherein the depth clutter suppression model takes an enhanced sodar multipath echo signal as an input, removes clutter effects caused by medium heterogeneity of echo signals of different paths based on an attention mechanism, and takes a pure sodar multipath echo signal as an output, and the depth clutter suppression model comprises an input layer, a residual mapping layer, an attention calculation layer, a clutter suppression layer and an output layer;
The input layer is used for receiving the enhanced sodar multipath echo signals;
The residual mapping layer is used for carrying out multi-scale residual mapping processing on the enhanced sodar multipath echo signals to obtain depth clutter representation of the sodar multipath echo signals;
The attention calculating layer is used for calculating attention weights of depth clutter representations under different scales;
The clutter suppression layer is used for performing clutter suppression processing on the depth clutter representation based on the attention weight to obtain a clean sodar signal for output.
4. The sodar signal processing method of claim 3, wherein in step S4, the optimizing solution of the constructed depth clutter suppression model comprises:
Carrying out optimization solution on the constructed depth clutter suppression model, and carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by utilizing the depth clutter suppression model obtained by the solution, wherein the optimization solution flow of the depth clutter suppression model is as follows:
s41: r groups of sodar multipath echo signals are obtained and enhanced, so that a training set data in the optimization solving process of the deep clutter suppression model is formed: Wherein Representing the acquired sodar multipath echo signals after the r group enhancement processing;
S42: constructing an optimized solving objective function of a depth clutter suppression model and constraint conditions:
；
；
Wherein:
an optimization solving objective function representing a depth clutter suppression model, Representing a to-be-optimized solving parameter of a depth clutter suppression model; the parameters to be optimized of the depth clutter suppression model comprise a mapping matrix in a residual mapping layer;
Sodar multipath echo signal after r group enhancement processing in training set data Frequency domain energy information of (a);
Representing the presentation to be Inputting the frequency domain energy information of signals output by a depth clutter suppression model constructed based on the solution parameters to be optimized;
The constraint condition is represented by a constraint condition, Representing a preset frequency domain energy information threshold;
s43: generating to-be-optimized solving parameters meeting constraint conditions as initial solutions ; Setting the current iteration number of the parameter to be optimized as D, setting the maximum iteration number as D, setting the initial value of D as 0, and setting the D iteration result of the parameter to be optimized as；
S44: establishing a projection matrix in the (d+1) th iteration process：
；
；
；
Wherein:
E represents an identity matrix;
T represents a transpose;
representing a constraint matrix incorporating constraint conditions;
Representing projection matrix parameters;
s45: generating an iteration step in the (d+1) th iteration process ：
；
；
Wherein:
Representation of Is a gradient of (2);
representation is such that Reaching a minimum a;
S46: iterating the solving parameters to be optimized, wherein an iteration formula is as follows:
；
Let d=d+1, return to step S44 until d+1=d, will And constructing and obtaining the depth clutter suppression model as model parameters of the depth clutter suppression model.
5. The method for processing sodar signals according to claim 4, wherein in step S4, the depth clutter suppression model obtained by solving is used to perform depth clutter suppression processing on the enhanced sodar multipath echo signals, and the method comprises the following steps:
And carrying out depth clutter suppression processing on the enhanced sodar multipath echo signals by using the depth clutter suppression model obtained by solving, wherein the depth clutter suppression processing flow is as follows:
Receiving enhanced sodar multipath echo signals by input layer ；
The residual mapping layer carries out multi-scale residual mapping processing on the enhanced sodar multipath echo signals to obtain depth clutter representation of the sodar multipath echo signals, wherein the sodar multipath echo signalsThe multi-scale residual mapping processing formula is as follows:
；
Wherein:
representing sodar multipath echo signals Mapping results at the u +1 scale, where the initial value of u is 0,；
Representation pairIs a mapping matrix of (a);
Will be A multi-scale depth clutter representation as sodar multi-path echo signals, wherein U represents a maximum residual mapping scale;
The attention calculating layer calculates attention weights of the depth clutter representations under different scales, wherein the attention weights of the depth clutter representations under the u scale are as follows:
；
Wherein:
Attention weights representing depth clutter representation at the u scale;
The clutter suppression layer performs clutter suppression processing on the depth clutter representation based on the attention weight, and a pure sodar signal is obtained and output by the output layer, wherein the clutter suppression processing formula is as follows:
；
Wherein:
indicating a clean sodar signal after clutter suppression processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410451159.9A CN118050716B (en) | 2024-04-16 | 2024-04-16 | Sodar signal processing method for multi-scale morphological processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410451159.9A CN118050716B (en) | 2024-04-16 | 2024-04-16 | Sodar signal processing method for multi-scale morphological processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118050716A CN118050716A (en) | 2024-05-17 |
| CN118050716B true CN118050716B (en) | 2024-07-02 |
Family
ID=91046919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410451159.9A Active CN118050716B (en) | 2024-04-16 | 2024-04-16 | Sodar signal processing method for multi-scale morphological processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118050716B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103308919A (en) * | 2012-03-12 | 2013-09-18 | 中国科学院声学研究所 | Fish identification method and system based on wavelet packet multi-scale information entropy |
| CN113640768A (en) * | 2021-08-13 | 2021-11-12 | 北京理工大学 | Low-resolution radar target identification method based on wavelet transformation |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11726184B2 (en) * | 2019-03-08 | 2023-08-15 | Leddartech Inc. | Component for a LIDAR sensor system, LIDAR sensor system, LIDAR sensor device, method for a LIDAR sensor system and method for a LIDAR sensor device |
| CN115113163A (en) * | 2022-06-15 | 2022-09-27 | 北京理工大学 | Multi-resolution low-rank sparse decomposition clutter suppression method for ground penetrating radar |
| CN117805756A (en) * | 2023-11-28 | 2024-04-02 | 中国电子科技集团公司第十四研究所 | Noise interference identification method and system with low false alarm rate in clutter |
-
2024
- 2024-04-16 CN CN202410451159.9A patent/CN118050716B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103308919A (en) * | 2012-03-12 | 2013-09-18 | 中国科学院声学研究所 | Fish identification method and system based on wavelet packet multi-scale information entropy |
| CN113640768A (en) * | 2021-08-13 | 2021-11-12 | 北京理工大学 | Low-resolution radar target identification method based on wavelet transformation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118050716A (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108318129A (en) | The true and false discriminating method of bridge structure modal parameter and terminal device | |
| CN108921162A (en) | Licence plate recognition method and Related product based on deep learning | |
| CN117388835B (en) | Multi-spelling fusion sodar signal enhancement method | |
| CN118050716B (en) | Sodar signal processing method for multi-scale morphological processing | |
| CN117195059B (en) | Quick detection method for water pollution of water supply pipe network | |
| CN117172135B (en) | Intelligent noise monitoring management method and system | |
| CN112206541B (en) | Game plug-in identification method and device, storage medium and computer equipment | |
| CN115984269B (en) | Non-invasive local water ecological safety detection method and system | |
| CN115393251A (en) | Defect detection method and device for printed circuit board, storage medium and electronic equipment | |
| CN115796231B (en) | Temporal analysis ultra-short term wind speed prediction method | |
| CN115578431B (en) | Image depth processing method and device, electronic equipment and medium | |
| CN116720101A (en) | On-line intelligent monitoring method and device for propeller faults of underwater propeller | |
| CN115731273A (en) | Pose graph optimization method and device, electronic equipment and storage medium | |
| CN111141263A (en) | Method and device for analyzing and operating perspective between two points | |
| CN114330221B (en) | Score board implementation method, score board, electronic device and storage medium | |
| CN109459760A (en) | A kind of Laser Radar Observation data processing method and device | |
| CN113721240A (en) | Target association method and device, electronic equipment and storage medium | |
| CN113379884A (en) | Map rendering method and device, electronic equipment, storage medium and vehicle | |
| CN115494455B (en) | Self-adaptive wind radar signal anti-interference processing method | |
| CN116930973B (en) | Scene-adaptive sodar wind power accurate prediction method | |
| CN108229668B (en) | Operation implementation method and device based on deep learning and electronic equipment | |
| CN117826113B (en) | Depth perception radar micro-signal detection method | |
| CN116524201B (en) | Feature extraction method, device, equipment and medium of multi-scale gating fusion unit | |
| CN114092874B (en) | Training method of target detection model, target detection method and related equipment thereof | |
| CN115293100B (en) | Accurate evaluation method for residual electric quantity of new energy battery |
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 |