CN117216500A - Electromagnetic information noise reduction method and device, electronic equipment and storage medium - Google Patents
Electromagnetic information noise reduction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117216500A CN117216500A CN202311242712.XA CN202311242712A CN117216500A CN 117216500 A CN117216500 A CN 117216500A CN 202311242712 A CN202311242712 A CN 202311242712A CN 117216500 A CN117216500 A CN 117216500A
- Authority
- CN
- China
- Prior art keywords
- layer
- electromagnetic information
- noise reduction
- space
- grid
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000009467 reduction Effects 0.000 title claims abstract description 47
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000013136 deep learning model Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000010586 diagram Methods 0.000 claims abstract description 16
- 210000002569 neuron Anatomy 0.000 claims abstract description 11
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 7
- 238000013499 data model Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 230000005855 radiation Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 102100037651 AP-2 complex subunit sigma Human genes 0.000 description 1
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 235000002566 Capsicum Nutrition 0.000 description 1
- 101000806914 Homo sapiens AP-2 complex subunit sigma Proteins 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000005670 electromagnetic radiation Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000005433 ionosphere Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides an electromagnetic information noise reduction method and device, electronic equipment and a storage medium. The electromagnetic information noise reduction method comprises the following steps: acquiring electromagnetic information in a space-time grid in an electromagnetic information space-time grid diagram; and regarding each space-time grid as a neuron in the neural network, and performing noise reduction processing on electromagnetic information in the space-time grid by utilizing the pre-constructed deep learning model and the grid map attribute. The electromagnetic information in each grid is noise-reduced through the pre-constructed deep learning model, so that the noise type can be automatically identified, the corresponding noise-reducing strategy is adapted, the electromagnetic information in each grid is respectively identified, the noise-reducing precision can be improved, and the purpose of simple and accurate noise reduction is achieved.
Description
Technical Field
The invention belongs to the technical field of electromagnetic information processing, and particularly relates to an electromagnetic information noise reduction method, an electromagnetic information noise reduction device, electronic equipment and a storage medium.
Background
The principle of the electromagnetic information space-time grid graph application calculation is based on the electromagnetic information space-time grid graph, the encoding identification of the grid graph and the calculability of tensor expression are utilized, a basic operator is provided for high-efficiency calculation through the grid graph attribute calculation operator of the identified encoding algebra space-time and field attribute, and a query algorithm, a superposition algorithm, a prediction algorithm and a planning algorithm formed by combining the basic operators are utilized to solve space-time analysis calculation and intelligent decision calculation tasks in electromagnetic information.
The intelligent decision is to assist or automatically make decisions by utilizing methods such as data analysis, machine learning, optimization algorithm and the like, so that the efficiency and accuracy of the decisions are improved. The intelligent decision of the electromagnetic information space-time grid graph is to express, analyze and process electromagnetic information in grid attributes by utilizing the space-time grid graph, and the electromagnetic information grid graph calculation algorithm formed by the grid graph attribute calculation operators is used for solving the tasks such as situation assessment, path planning, interpolation prediction and the like in electromagnetic tasks so as to assist a decision maker to make more effective and reasonable decisions.
When modeling the radar radiation range at low altitude, the radar radiation range is interfered by natural background noise such as ionosphere radiation or artificial factors, so that the radar radiation value is noisy or missing, and complete electromagnetic information cannot be acquired, and therefore, the radar echo image formed by the space-time grid image through an echo signal processing algorithm also has the condition that noise exists in the echo value.
Currently, radar echo is generally solved in two ways: signal level and functional image level. However, the current method for denoising radar echo is mainly to solve the problem of special processing of noise signals through various signal processing filtering methods, and the filtering and smoothing methods cannot effectively remove noise, but lose part of signal details, which is usually applied to a specific scene. The method for denoising from the image level still uses methods such as filtering matching, and the like, and because the radar echo image has various noise types including salt and pepper noise, gaussian noise, speckle noise and the like, different noise types need different denoising methods.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an electromagnetic information noise reduction method, an electromagnetic information noise reduction device, electronic equipment and a storage medium, which at least partially solve the problem of complex noise removal in the prior art.
In a first aspect, an embodiment of the present disclosure provides a method for noise reduction of electromagnetic information, including:
acquiring electromagnetic information of a space-time grid in an electromagnetic information space-time grid diagram;
and regarding each space-time grid as a neuron in the neural network, and performing noise reduction processing on electromagnetic information in the space-time grid by utilizing the pre-constructed deep learning model and the grid map attribute.
Optionally, the pre-constructed deep learning model includes two coding layers and two decoding layers; the data samples of the deep learning model are expressed using a data model of a mesh map tensor.
Optionally, the two coding layers are a first coding layer and a second coding layer;
the first layer of coding layer comprises a multi-layer convolution module, and the result processed by the multi-layer convolution module is output to the decoding layer after the down-sampling operation.
Optionally, the multi-layer convolution module is composed of 4 layers of Conv2d+Relu+B2d, conv2d is two-dimensional CNN convolution, BN2d is BatchNorm regularization operation, relu is a nonlinear activation function, and the downsampling operation adopts maximum downsampling operation.
Optionally, the two decoding layers are a first decoding layer and a second decoding layer;
the first layer decoding layer includes a first multi-layer deconvolution module and the second layer decoding layer includes a second multi-layer deconvolution module.
Optionally, the first multi-layer deconvolution module is composed of 4 layers of ConvTrans2d+Relu+BN2d, and the second multi-layer deconvolution module is composed of 2 layers of ConvTrans2d+Relu+BN2d and 1 layer of ConvTrans2d+Relu;
ConvTrans2d is a two-dimensional CNN deconvolution, relu is a nonlinear activation function, BN2d is a BatchNorm regularization operation.
Optionally, the step size of the ConvTrans2d of one layer in the first multi-layer deconvolution module is 2, the feature map size is 50, the channel number is 64, the step size of the last ConvTrans2d in the second multi-layer deconvolution module is 2, the output size is 100, and the channel number is 1.
In a second aspect, an embodiment of the present disclosure further provides an electromagnetic information noise reduction apparatus, including:
the acquisition module is used for acquiring electromagnetic information of the space-time grids in the electromagnetic information space-time grid diagram;
and the noise reduction module is used for taking each space-time grid as a neuron in the neural network, and performing noise reduction processing on electromagnetic information in the space-time grid by utilizing the pre-constructed deep learning model and the grid map attribute.
In a third aspect, embodiments of the present disclosure further provide an electronic device, including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the electromagnetic information noise reduction method of any one of the first aspects.
In a fourth aspect, embodiments of the present disclosure further provide a computer-readable storage medium storing computer instructions for causing a computer to perform the electromagnetic information noise reduction method of any one of the first aspects.
The invention provides an electromagnetic information noise reduction method, an electromagnetic information noise reduction device, electronic equipment and a storage medium. According to the electromagnetic information noise reduction method, the electromagnetic information in each grid is subjected to noise reduction through the pre-built deep learning model, the noise type can be automatically identified, the corresponding noise reduction strategy is adapted, the electromagnetic information in each grid is respectively identified, the noise reduction precision can be improved, and the purpose of simple and accurate noise reduction is achieved.
Drawings
The foregoing and other objects, features and advantages of the disclosure will be apparent from the following more particular descriptions of exemplary embodiments of the disclosure as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the disclosure.
Fig. 1 is a schematic diagram of a denoising principle of a denoising self-encoder according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a radar echo denoising model according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a verification set test effect provided by an embodiment of the present disclosure;
fig. 4 is a schematic block diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
It should be appreciated that the following specific embodiments of the disclosure are described in order to provide a better understanding of the present disclosure, and that other advantages and effects will be apparent to those skilled in the art from the present disclosure. It will be apparent that the described embodiments are merely some, but not all embodiments of the present disclosure. The disclosure may be embodied or practiced in other different specific embodiments, and details within the subject specification may be modified or changed from various points of view and applications without departing from the spirit of the disclosure. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the following claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the present disclosure, one skilled in the art will appreciate that one aspect described herein may be implemented independently of any other aspect, and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. In addition, such apparatus may be implemented and/or such methods practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
It should also be noted that the illustrations provided in the following embodiments merely illustrate the basic concepts of the disclosure by way of illustration, and only the components related to the disclosure are shown in the illustrations, rather than being drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complex.
In addition, in the following description, specific details are provided in order to provide a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects may be practiced without these specific details.
The electromagnetic information space-time grid image prediction algorithm is a data analysis and prediction method for predicting the change of the future electromagnetic environment based on the electromagnetic information space-time grid image, and comprises electromagnetic cavity area interpolation completion, electromagnetic radiation area extrapolation prediction, radar echo image interpolation denoising and the like. The prediction algorithm uses the characteristic of unified expression of discrete tensors of the grid map, each grid is regarded as a neuron in the neural network, and the traditional electromagnetic calculation problem is converted into the deep learning problem of the corresponding grid neuron by using the deep learning thought through the space-time grid map attribute calculation operator.
The space-time grid graph is based on tensor unified expression, and the real echo intensity is restored from the encoder model in the deep learning from the radar echo image level. The prediction algorithm uses the characteristic of unified expression of discretization tensors of the space-time grid graph, each grid is regarded as a neuron in the neural network, and the traditional electromagnetic calculation problem is converted into the deep learning problem of the corresponding grid neuron by using the thinking of deep learning through a space-time grid graph attribute calculation operator.
The embodiment discloses an electromagnetic information noise reduction method, which comprises the following steps:
acquiring electromagnetic information of a space-time grid in an electromagnetic information space-time grid diagram, wherein the electromagnetic information space-time grid diagram expresses, analyzes and processes the electromagnetic information in grid attributes by using the space-time grid diagram;
and regarding each space-time grid as a neuron in the neural network, and performing noise reduction processing on electromagnetic information in the space-time grid by utilizing the pre-constructed deep learning model and the grid map attribute.
Optionally, the pre-constructed deep learning model includes two coding layers and two decoding layers; the data samples of the deep learning model are expressed using a data model of a mesh map tensor.
Optionally, the two coding layers are a first coding layer and a second coding layer;
the first layer of coding layer comprises a multi-layer convolution module, and the result processed by the multi-layer convolution module is output to the decoding layer after the down-sampling operation.
Optionally, the multi-layer convolution module is composed of 4 layers of Conv2d+Relu+B2d, conv2d is two-dimensional CNN convolution, BN2d is BatchNorm regularization operation, relu is a nonlinear activation function, and the downsampling operation adopts maximum downsampling operation.
Optionally, the two decoding layers are a first decoding layer and a second decoding layer;
the first layer decoding layer includes a first multi-layer deconvolution module and the second layer decoding layer includes a second multi-layer deconvolution module.
Optionally, the first multi-layer deconvolution module is composed of 4 layers of ConvTrans2d+Relu+BN2d, and the second multi-layer deconvolution module is composed of 2 layers of ConvTrans2d+Relu+BN2d and 1 layer of ConvTrans2d+Relu;
ConvTrans2d is a two-dimensional CNN deconvolution, relu is a nonlinear activation function, BN2d is a BatchNorm regularization operation.
Optionally, the step size of the ConvTrans2d of one layer in the first multi-layer deconvolution module is 2, the feature map size is 50, the channel number is 64, the step size of the last ConvTrans2d in the second multi-layer deconvolution module is 2, the output size is 100, and the channel number is 1.
A noise-reducing self-encoder (denoise AutoEncoder, DAE) deep learning model is a deep learning model that can automatically learn and extract features from data for noise reduction and signal quality improvement. The model is widely applied to the field of intelligent calculation of electromagnetic information so as to improve the quality and the accuracy of radar echo signals, a mapping model from a noise image to a clean image is learned through training a large number of known clean images and corresponding noise images, and then the new noise image is denoised. Since the deep learning model is a data driven algorithm, the solution will demonstrate the algorithm flow with examples, including sample generation, data set generation, problem description, model selection, model structure, training and evaluation steps.
(1) Sample generation: initializing a 100 x 100 (1 degree) planar mesh space by using a data model expression form of a mesh map tensor; randomly generating 1-10 radiation sources in a region, simulating radar radiation distribution by using a Gaussian kernel function (mu= -130dbm, sigma 2 = 20), and carrying out numerical superposition on the region where multiple radiation sources coincide; for each mesh in the region, a uniform random noise with a scaling factor α= [ -0.5,0.5] is injected.
(2) Generating a data set: normal electromagnetic samples and noisy electromagnetic samples were generated in 5000 simulated regions, 2500 of which were used for training samples and the other 2500 were used for validation testing, as described above.
(3) Description of the problem: the normal original electromagnetic distribution is X, the electromagnetic distribution with noise isModel through learningTo minimize the error LH of the reduction values Z and X. Considering the sample non-tag property, the principle of the noise-reducing self-encoder (DAE) is shown in FIG. 1, < + >>Can be further described as->
(4) Model structure: the Encode module consists of a multi-layer CNN convolution network Conv2d+Bn2d+MaxPool2D+Relu and is used for simulating a nonlinear dimension-reduction mapping operation of fθ, wherein Conv2D is two-dimensional CNN convolution, BN2D is BatchNorm regularization operation, maxPool2D is maximum value downsampling operation, and Relu is a nonlinear activation function. Two encoder layers are designed firstly, wherein the first encoder layer 1 consists of 4 layers of Conv2d+Relu+BN2D, and finally MaxPool2D downsampling is carried out, the size of a convolution kernel is 3 multiplied by 3, the step length is 1, the number of channels is changed from 1 to 64, and the size of a feature map is reduced from 100 to 50. The second layer of encoder2 consists of 2 layers of Conv2d+Relu+BN2D and 1 layer of MaxPol2D+Conv2d+Relu, the convolution kernel and the step size are unchanged, and finally the output hidden variable h is a low-dimensional multichannel characteristic of 25 multiplied by 256; the decoding module consists of a multi-layer deconvolution module ConvTrans2d+Bn2d+Relu, wherein ConvTrans2d is two-dimensional CNN deconvolution, the decoding process corresponds to the decoding process and is also two-layer decoding, the first layer decoding 1 consists of 4 layers of ConvTrans2d+Relu+Bn2d, the final upsampling process is set by setting the step length of one layer of ConvTrans2d as 2, the feature map size is expanded from 25 to 50, the channel number is changed from 256 to 64, the second layer decoding 2 consists of 2 layers of ConvTrans2d+Relu+Bn2d and 1 layer of ConvTrans2d+Relu, the step length of the last ConvTrans2d is 2 for upsampling, the output size is restored to 100, the corresponding channel number is restored to 1, the two-layer decoding layer is used for simulating the reduction mapping operation of g theta', and the output Z is the target signal for removing noise. The overall structure of the model is shown in fig. 2.
(5) Training and evaluation: training was performed using an Adam gradient optimizer, with a loss function of the mean square error MSE of the predicted value Z and the true value X, a sample batch number of batch size=16, an initial learning rate of 0.002, and a total of 30 training rounds.
(6) And (3) verifying the trained model by a test set, wherein the visual effect is shown as a visual effect of the verification set in fig. 3, and the left middle and right in fig. 3 are respectively original radar echo data, noisy data and restored radar echo data.
The embodiment also discloses an electromagnetic information noise reduction device, comprising:
the acquisition module is used for acquiring electromagnetic information in the space-time grid;
and the noise reduction module is used for regarding each space-time grid as a neuron in the neural network and carrying out noise reduction processing on electromagnetic information in the space-time grid by utilizing the pre-constructed deep learning model.
The electronic device disclosed in the embodiment includes a memory and a processor. The memory is for storing non-transitory computer readable instructions. In particular, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like.
The processor may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device to perform the desired functions. In one embodiment of the present disclosure, the processor is configured to execute the computer readable instructions stored in the memory, so that the electronic device performs all or part of the steps of the electromagnetic information noise reduction method of the embodiments of the present disclosure described above.
It should be understood by those skilled in the art that, in order to solve the technical problem of how to obtain a good user experience effect, the present embodiment may also include well-known structures such as a communication bus, an interface, and the like, and these well-known structures are also included in the protection scope of the present disclosure.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. A schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure is shown. The electronic device shown in fig. 4 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 4, the electronic device may include a processing means (e.g., a central processing unit, a graphic processor, etc.), which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) or a program loaded from the storage means into a Random Access Memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processing device, ROM and RAM are connected to each other via a bus. An input/output (I/O) interface is also connected to the bus.
In general, the following devices may be connected to the I/O interface: input means including, for example, sensors or visual information gathering devices; output devices including, for example, display screens and the like; storage devices including, for example, magnetic tape, hard disk, etc.; a communication device. The communication means may allow the electronic device to communicate wirelessly or by wire with other devices, such as edge computing devices, to exchange data. While fig. 4 shows an electronic device having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from ROM. All or part of the steps of the electromagnetic information noise reduction method of the embodiments of the present disclosure are performed when the computer program is executed by a processing device.
The detailed description of the present embodiment may refer to the corresponding description in the foregoing embodiments, and will not be repeated herein.
A computer-readable storage medium according to an embodiment of the present disclosure has stored thereon non-transitory computer-readable instructions. When executed by a processor, perform all or part of the steps of the electromagnetic information noise reduction method of the various embodiments of the disclosure described previously.
The computer-readable storage medium described above includes, but is not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or removable hard disk), media with built-in rewritable non-volatile memory (e.g., memory card), and media with built-in ROM (e.g., ROM cartridge).
The detailed description of the present embodiment may refer to the corresponding description in the foregoing embodiments, and will not be repeated herein.
The basic principles of the present disclosure have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present disclosure. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, since the disclosure is not necessarily limited to practice with the specific details described.
In this disclosure, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions, and the block diagrams of devices, apparatuses, devices, systems involved in this disclosure are merely illustrative examples and are not intended to require or implicate that connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
In addition, as used herein, the use of "or" in the recitation of items beginning with "at least one" indicates a separate recitation, such that recitation of "at least one of A, B or C" for example means a or B or C, or AB or AC or BC, or ABC (i.e., a and B and C). Furthermore, the term "exemplary" does not mean that the described example is preferred or better than other examples.
It is also noted that in the systems and methods of the present disclosure, components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered equivalent to the present disclosure.
Various changes, substitutions, and alterations are possible to the techniques described herein without departing from the teachings of the techniques defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the particular aspects of the process, machine, manufacture, composition of matter, means, methods and acts described above. The processes, machines, manufacture, compositions of matter, means, methods, or acts, presently existing or later to be developed that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein may be utilized. Accordingly, the appended claims are intended to include within their scope such processes, machines, manufacture, compositions of matter, means, methods, or acts.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the disclosure to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (10)
1. A method of electromagnetic information noise reduction, comprising:
acquiring electromagnetic information of a space-time grid in an electromagnetic information space-time grid diagram;
and regarding each space-time grid as a neuron in the neural network, and performing noise reduction processing on electromagnetic information in the space-time grid by utilizing the pre-constructed deep learning model and the grid map attribute.
2. The electromagnetic information noise reduction method according to claim 1, wherein the pre-constructed deep learning model includes two encoding layers and two decoding layers; the data samples of the deep learning model are expressed using a data model of a mesh map tensor.
3. The method of noise reduction of electromagnetic information according to claim 2, wherein the two encoding layers are a first encoding layer and a second encoding layer;
the first layer of coding layer comprises a multi-layer convolution module, and the result processed by the multi-layer convolution module is output to the decoding layer after the down-sampling operation.
4. The electromagnetic information denoising method according to claim 3, wherein the multi-layer convolution module is composed of 4 layers of Conv2d+Relu+Bn2d, conv2d is two-dimensional CNN convolution, BN2d is a BatchNorm regularization operation, relu is a nonlinear activation function, and the downsampling operation adopts a maximum downsampling operation.
5. The method of electromagnetic information noise reduction according to claim 4, wherein the two decoding layers are a first decoding layer and a second decoding layer;
the first layer decoding layer includes a first multi-layer deconvolution module and the second layer decoding layer includes a second multi-layer deconvolution module.
6. The electromagnetic information noise reduction method of claim 5, wherein the first multi-layer deconvolution module consists of 4 layers convtrans2d+relu+bn2d and the second multi-layer deconvolution module consists of 2 layers convtrans2d+relu+bn2d and 1 layer convtrans2 d+relu;
ConvTrans2d is a two-dimensional CNN deconvolution, relu is a nonlinear activation function, BN2d is a BatchNorm regularization operation.
7. The method of noise reduction according to claim 6, wherein the step size of ConvTrans2d of one layer in the first multi-layer deconvolution module is 2, the feature map size is 50, the channel number is 64, the step size of the last ConvTrans2d in the second multi-layer deconvolution module is 2, the output size is 100, and the channel number is 1.
8. An electromagnetic information noise reduction device, characterized by comprising:
the acquisition module is used for acquiring electromagnetic information of the space-time grids in the electromagnetic information space-time grid diagram;
and the noise reduction module is used for taking each space-time grid as a neuron in the neural network, and performing noise reduction processing on electromagnetic information in the space-time grid by utilizing the pre-constructed deep learning model and the grid map attribute.
9. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the electromagnetic information noise reduction method of any one of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a computer to perform the electromagnetic information noise reduction method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311242712.XA CN117216500A (en) | 2023-09-25 | 2023-09-25 | Electromagnetic information noise reduction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311242712.XA CN117216500A (en) | 2023-09-25 | 2023-09-25 | Electromagnetic information noise reduction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117216500A true CN117216500A (en) | 2023-12-12 |
Family
ID=89038762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311242712.XA Pending CN117216500A (en) | 2023-09-25 | 2023-09-25 | Electromagnetic information noise reduction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117216500A (en) |
-
2023
- 2023-09-25 CN CN202311242712.XA patent/CN117216500A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Hf-neus: Improved surface reconstruction using high-frequency details | |
| JP7343963B2 (en) | Dataset for learning functions that take images as input | |
| CN111738265B (en) | Semantic segmentation method, system, medium, and electronic device for RGB-D image | |
| CN110599500A (en) | Tumor region segmentation method and system of liver CT image based on cascaded full convolution network | |
| KR102215101B1 (en) | Method and Apparatus for Generating Point Cloud Using Feature of Object Acquired from Image | |
| CN116958131B (en) | Image processing method, device, equipment and storage medium | |
| WO2006010105A2 (en) | Simulation of scanning beam images by combination of primitive features extracted from a surface model | |
| CN114930336A (en) | Method and system for estimating computational cost of a simulation | |
| CN113505830B (en) | Rotary machine fault diagnosis method, system, equipment and storage medium | |
| US20230325982A1 (en) | Methods, systems and computer programs for processing image data for generating a filter | |
| CN114266894A (en) | Image segmentation method and device, electronic equipment and storage medium | |
| CN111160459A (en) | Device and method for optimizing hyper-parameters | |
| CN113392937A (en) | 3D point cloud data classification method and related device thereof | |
| CA3143928C (en) | Dynamic image resolution assessment | |
| Wang et al. | Improved surface reconstruction using high-frequency details | |
| Spick et al. | Naive mesh-to-mesh coloured model generation using 3D GANs | |
| CN117788629A (en) | Image generation method, device and storage medium with style personalization | |
| Xu et al. | Amodal completion via progressive mixed context diffusion | |
| CN117351133A (en) | Data rendering method, device, equipment and computer readable storage medium | |
| CN115909016B (en) | GCN-based fMRI image analysis system, method, electronic equipment and medium | |
| CN117216500A (en) | Electromagnetic information noise reduction method and device, electronic equipment and storage medium | |
| Murdock et al. | Building dynamic cloud maps from the ground up | |
| Vetsch et al. | Neuralmeshing: Differentiable meshing of implicit neural representations | |
| CN113516670B (en) | Feedback attention-enhanced non-mode image segmentation method and device | |
| CN114615505A (en) | Point cloud attribute compression method and device based on depth entropy coding and storage medium |
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 |