CN113408538A - SVM-based radar RD image weak target detection method and system, storage medium and electronic terminal - Google Patents
SVM-based radar RD image weak target detection method and system, storage medium and electronic terminal Download PDFInfo
- Publication number
- CN113408538A CN113408538A CN202110785957.1A CN202110785957A CN113408538A CN 113408538 A CN113408538 A CN 113408538A CN 202110785957 A CN202110785957 A CN 202110785957A CN 113408538 A CN113408538 A CN 113408538A
- Authority
- CN
- China
- Prior art keywords
- svm
- target detection
- radar
- image
- network
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a radar RD image weak target detection method based on an SVM, which comprises the steps of obtaining radar echo data, preprocessing the data and generating a radar range-Doppler dimensional image; preprocessing an original image and labeling to obtain a data set; constructing a Support Vector Machine (SVM) network aiming at weak target detection under low signal-to-noise ratio; carrying out target detection and cross validation on the constructed Support Vector Machine (SVM) network; obtaining a target detection accuracy result of the test set; the method for detecting the radar RD image target provided by the invention is based on a large number of radar RD image data containing targets under different signal-to-noise ratios, and the target detection network is obtained through the repeated training of the SVM network.
Description
Technical Field
The invention relates to the technical field of image target detection, in particular to a radar RD image weak target detection method and system based on an SVM, a storage medium and an electronic terminal.
Background
In recent years, target detection is widely applied in many fields, and radar is used as an important means for target detection, and can analyze and process echoes in an irradiation area, detect target information from signals such as clutter, interference and noise, and determine parameters such as distance, speed and angle of the target information.
The existing radar target detection method comprises a constant false alarm rate detection algorithm and the like, wherein the constant false alarm rate detection algorithm is based on a statistical model, a background model is often difficult to accurately describe, and serious constant false alarm rate loss and detection performance are reduced under a non-uniform background, especially under low signal-to-noise ratios with different types and variable forms. In conclusion, the existing radar RD image target detection method has the problems of simple model, low universality, weak learning ability and the like, and the problem of weak target detection ability of the radar RD image is difficult to fundamentally solve.
The disclosure number is CN111913158A, which provides a radar signal processing method for detecting a low-slow small target under a complex clutter background, and a constant false alarm detection algorithm is used to obtain a target point trace in a reference window, so as to obtain the speed, pitch, azimuth, distance, and the like of the target according to the point trace information, where the constant false alarm algorithm is based on a statistical model, and often difficult to accurately describe a background model, and under a non-uniform background, especially under a low signal-to-noise ratio with various types and shapes, a serious constant false alarm loss occurs, and the detection performance is degraded, so that the existing radar RD image target detection method has the problems of simple model, low universality, weak learning capability, and the like, and is difficult to fundamentally solve the problem of weak small target detection capability of a radar RD image.
Disclosure of Invention
The invention aims to provide a radar RD image weak target detection method, a radar RD image weak target detection system, a storage medium and an electronic terminal based on an SVM (support vector machine), so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a radar RD image weak target detection method based on SVM includes the following steps:
s1, radar echo data are obtained, and radar range-Doppler dimensional images are generated after the data are preprocessed;
s2, preprocessing the original image and labeling to obtain a data set;
s3, constructing a Support Vector Machine (SVM) network aiming at weak target detection under low signal-to-noise ratio;
s4, carrying out target detection and cross validation on the constructed Support Vector Machine (SVM) network;
and S5, obtaining the target detection accuracy result of the test set.
Preferably, the preprocessing of the radar echo data in step S1 includes:
s101, generating radar echo data through simulation, and adding random noises with different signal-to-noise ratios into the data;
and S102, randomly generating the number, the position and the speed of the targets in the radar echo data within a certain range.
Preferably, the specific steps of preprocessing the original image and labeling in step S2 are as follows:
s201, standardizing an original image, and adjusting the resolution to be suitable for the learning size of a Support Vector Machine (SVM);
s202, acquiring a specific coordinate value of the position of the target;
and S203, setting a label according to the coordinate value of the position of the target to generate standard label data.
Preferably, the Support Vector Machine (SVM) network in step S3 includes a transmission form of the SVM network, a network architecture mode, an excitation function adopted and a detection parameter.
Preferably, the target detection in step S3 is specifically to perform classification detection on different targets in different backgrounds, and to detect feature differences between the targets and the clutter.
Preferably, the cross validation in step S3 includes the specific steps of:
s501, dividing a training sample set into n sub-sample sets with the same size;
s502, selecting n-1 sub-sample sets to train a support vector machine, and taking the rest sub-sample set as a subset of a verification model;
s503, checking the model obtained by training on the verification subset, and recording a checking error;
s504, repeating the above processes until each subset is only used as a verification subset;
and S505, counting the verification error of each experiment, and taking the error as a standard for evaluating the generalization capability of the support vector machine, namely a standard for selecting parameters of the support vector machine.
Preferably, the accuracy in step S5 includes a detection rate and a false alarm rate, and the calculation formula is as follows:
in the formula PdFor detection of the rate, PfFor false alarm rate, TP is true, FN is false, and FP is false.
In order to achieve the above object, the present invention further provides a radar RD image weak target detection system based on SVM, wherein the system includes:
the image generation module is used for acquiring radar echo data, preprocessing the data and generating a radar range-Doppler dimensional image;
the image processing module is used for preprocessing the original image, labeling the original image and then obtaining a data set;
the network construction module is used for constructing a Support Vector Machine (SVM) network aiming at weak target detection under low signal-to-noise ratio;
the detection and verification module is used for carrying out target detection and cross verification on the constructed Support Vector Machine (SVM) network; and;
and the accuracy module is used for obtaining a target detection accuracy result of the test set.
In order to achieve the above object, the present invention further provides a radar RD image weak target detection storage medium based on an SVM, wherein the storage medium stores therein computer instructions, and when the computer instructions are run on an electronic terminal, the electronic terminal is caused to execute the above weak target detection method.
In order to achieve the above object, the present invention further provides an SVM-based radar RD image weak target detection electronic terminal, wherein the electronic terminal includes a processor and a memory, the memory is used for storing instructions, and the processor is used for calling the instructions in the memory, so that the electronic device executes the above weak target detection method.
Compared with the prior art, the invention has the beneficial effects that:
the method for detecting the radar RD image target provided by the invention is based on a large number of radar RD image data containing targets under different signal-to-noise ratios, and the target detection network is obtained through the repeated training of the SVM network.
Drawings
FIG. 1 is a flow chart of a radar RD image weak target detection method of the present invention;
FIG. 2 is a schematic structural diagram of a radar RD image weak target detection system of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example (b):
referring to fig. 1, the present invention provides a technical solution:
a radar RD image weak target detection method based on SVM includes the following steps:
and S1, radar echo data are obtained, and radar Range-Doppler (RD) images are generated after the data are preprocessed.
The radar echo data comprise target information including the number, position, speed and the like of targets, and target parameters are ensured to be random within a certain range; the method comprises the steps of generating radar echo data through simulation on the radar echo data, adding random noise with different signal to noise ratios into the data, enabling a certain amount of low signal to noise ratio data to exist, randomly generating the number, position and speed of targets in the radar echo data within a certain range, converting original echo data into an image in a distance dimension and a Doppler dimension, and ensuring that the targets and interference (noise, clutter and the like) in the image exist at the same time, wherein the targets occupy one pixel point, the resolution of the generated RD image is 256 × 225, the distance dimension is 225 units, and the Doppler dimension is 256 units, so that the original RD image of the radar is obtained.
And S2, preprocessing the original image and labeling to obtain a data set.
The specific steps of preprocessing the original image and labeling in step S2 are as follows:
s201, standardizing an original image, and adjusting the resolution to be suitable for the learning size of a Support Vector Machine (SVM);
s202, acquiring the specific coordinate value of the position of the target.
And S203, setting a label according to the coordinate value of the position of the target to generate standard label data.
Wherein, step S201 adjusts resolutionThe resolution of the original image needs to be adjusted to 1024 x 900, and the pixels occupied by the target are changed into 4 x 4, so that the method is more suitable for an SVM network to extract target characteristic information; in step S202, acquiring the position coordinates of the target in the image, i.e. the positions of the range cell and the doppler cell, after the acquisition of the specific coordinate values needs to be standardized; the setting and generating of the standard tag data in step S202 specifically includes generating a tag frame with a size of 10 × 10 with the target center as a center point, and recording X of the tag framemin、Xmax、Ymin、YmaxAnd the number of labels, namely manufacturing a standardized label data xml file, wherein the xml file comprises the size of an image, the number of targets in the image and position information, the position of the target can be found in the image according to the position marked by the xml file, and the image data sets correspond to the label data sets one by one.
And S3, constructing a Support Vector Machine (SVM) network aiming at weak target detection under low signal-to-noise ratio.
The Support Vector Machine (SVM) network comprises a transmission form of the SVM network, a network architecture mode, an adopted excitation function and detection parameters.
The SVM algorithm within a vector machine (SVM) network contains three parameters: a kernel function, a regularization parameter C, and an insensitive parameter epsilon.
Commonly used kernel functions are: polynomial kernel, Sigmoid kernel, and radial basis kernel. The support vector corresponding to the polynomial kernel function is a polynomial surface in a sample space; the Sigmoid kernel function meets the Mercer condition only when the parameters k and sigma take specific values, namely the kernel function cannot be used as the kernel function of the SVM under certain conditions; the radial basis kernel function is the most widely applied kernel function, has a wider convergence domain, has strong adaptability no matter in the conditions of low dimension, high dimension, small samples, large samples and the like, particularly can reflect the nonlinear characteristics of a time sequence in the prediction of the time sequence, has fewer parameters compared with other kernel functions, and reduces the complexity of a corresponding model.
The regularization parameter C controls the error and complexity of the model, and can select appropriate parameters according to actual needs so as to compromise between the error and complexity of the model. The larger the C value is, the better the model fits the data, but if the C value is too large, the weight is correspondingly reduced, the generalization capability of the SVM model is deteriorated, the overfitting phenomenon is easy to occur, and if the C value is smaller, the punishment factor of the data exceeding the epsilon-insensitive zone in the sample data is smaller, the training error is larger, and the under-fitting phenomenon is caused. Therefore, the appropriate value of C is selected to maximize the generalization capability of the SVM model.
And S4, carrying out target detection and cross validation on the constructed Support Vector Machine (SVM) network.
The cross validation is to obtain the optimal parameters of the support vector machine so as to obtain the optimal classifier or predictor, and the specific process of the method is as follows:
s501, dividing a training sample set into n sub-sample sets with the same size;
s502, selecting n-1 sub-sample sets to train a support vector machine, and taking the rest sub-sample set as a subset of a verification model;
s503, checking the model obtained by training on the verification subset, and recording a checking error;
s504, repeating the above processes until each subset is only used as a verification subset;
and S505, counting the verification error of each experiment, and taking the error as a standard for evaluating the generalization capability of the support vector machine, namely a standard for selecting parameters of the support vector machine.
And S5, obtaining the target detection accuracy result of the test set.
The accuracy in step S5 includes a detection rate and a false alarm rate, and the calculation formula is as follows:
in the formula PdFor detection of the rate, PfFor false alarm rate, TP is true, FN is false, and FP is false.
The method for detecting the target converts target detection of radar echo data into a binary problem, analyzes difference between the target and clutter, in the binary problem, we call True Positive (TP) cases that real conditions are targets and are predicted as targets by a neural network, call True Negative (TN) cases that the real conditions are targets and are not predicted as targets by the neural network, and know definitions of False Positive (FP) cases and False Negative (FN) cases according to the same way, and detect rate PdThe false alarm rate P is the proportion of true cases to all true targetsfThe false positive case accounts for the proportion of all detection results.
Referring to fig. 2, to achieve the above object, the present invention further provides a radar RD image weak target detection system based on SVM, wherein the system includes:
the image generation module is used for acquiring radar echo data, preprocessing the data and generating a radar range-Doppler dimensional image;
the image processing module is used for preprocessing the original image, labeling the original image and then obtaining a data set;
the network construction module is used for constructing a Support Vector Machine (SVM) network aiming at weak target detection under low signal-to-noise ratio;
the detection and verification module is used for carrying out target detection and cross verification on the constructed Support Vector Machine (SVM) network; and;
and the accuracy module is used for obtaining a target detection accuracy result of the test set.
In order to achieve the above object, the present invention further provides a radar RD image weak target detection storage medium based on an SVM, wherein the storage medium stores therein computer instructions, and when the computer instructions are run on an electronic terminal, the electronic terminal is caused to execute the above weak target detection method.
The storage medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer memory, Read Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, in accordance with legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunications signals.
In order to achieve the above object, the present invention further provides an SVM-based radar RD image weak target detection electronic terminal, wherein the electronic terminal includes a processor and a memory, the memory is used for storing instructions, and the processor is used for calling the instructions in the memory, so that the electronic device executes the above weak target detection method.
The electronic terminal can be a desktop computer, an industrial computer, a numerical control device, an industrial robot, a server and other computing devices. It will be appreciated by those skilled in the art that the electronic terminal includes a processor and a memory, and the description of the memory for storing instructions is merely an example of the electronic terminal and is not a limitation of the electronic terminal, and may include more or less components, or combine certain components, or different components, for example, the electronic terminal may further include input and output devices, network access devices, buses, etc.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A radar RD image weak target detection method based on SVM is characterized by comprising the following steps:
s1, radar echo data are obtained, and radar range-Doppler dimensional images are generated after the data are preprocessed;
s2, preprocessing the original image and labeling to obtain a data set;
s3, constructing a Support Vector Machine (SVM) network aiming at weak target detection under low signal-to-noise ratio;
s4, carrying out target detection and cross validation on the constructed Support Vector Machine (SVM) network;
and S5, obtaining the target detection accuracy result of the test set.
2. The SVM-based radar RD image weak target detection method as claimed in claim 1, wherein: the specific steps of preprocessing the radar echo data in step S1 are as follows:
s101, generating radar echo data through simulation, and adding random noises with different signal-to-noise ratios into the data;
and S102, randomly generating the number, the position and the speed of the targets in the radar echo data within a certain range.
3. The SVM-based radar RD image weak target detection method as claimed in claim 1, wherein: the specific steps of preprocessing the original image and labeling in step S2 are as follows:
s201, standardizing an original image, and adjusting the resolution to be suitable for the learning size of a Support Vector Machine (SVM);
s202, acquiring a specific coordinate value of the position of the target;
and S203, setting a label according to the coordinate value of the position of the target to generate standard label data.
4. The SVM-based radar RD image weak target detection method as claimed in claim 1, wherein: the Support Vector Machine (SVM) network in step S3 includes a transmission form of the SVM network, a network architecture mode, an excitation function adopted, and a detection parameter.
5. The SVM-based radar RD image weak target detection method as claimed in claim 1, wherein: the target detection in step S3 is specifically to perform classification detection on different targets under different backgrounds and detect feature differences between the targets and the clutter.
6. The SVM-based radar RD image weak target detection method as claimed in claim 1, wherein: the specific steps of the cross validation in the step S3 are as follows:
s501, dividing a training sample set into n sub-sample sets with the same size;
s502, selecting n-1 sub-sample sets to train a support vector machine, and taking the rest sub-sample set as a subset of a verification model;
s503, checking the model obtained by training on the verification subset, and recording a checking error;
s504, repeating the above processes until each subset is only used as a verification subset;
and S505, counting the verification error of each experiment, and taking the error as a standard for evaluating the generalization capability of the support vector machine, namely a standard for selecting parameters of the support vector machine.
7. The SVM-based radar RD image weak target detection method as claimed in claim 1, wherein: the accuracy in step S5 includes a detection rate and a false alarm rate, and the calculation formula is as follows:
in the formula PdFor detection of the rate, PfFor false alarm rate, TP is true, FN is false, and FP is false.
8. A radar RD image weak target detection system based on SVM, characterized in that the system comprises:
the image generation module is used for acquiring radar echo data, preprocessing the data and generating a radar range-Doppler dimensional image;
the image processing module is used for preprocessing the original image, labeling the original image and then obtaining a data set;
the network construction module is used for constructing a Support Vector Machine (SVM) network aiming at weak target detection under low signal-to-noise ratio;
the detection and verification module is used for carrying out target detection and cross verification on the constructed Support Vector Machine (SVM) network; and;
and the accuracy module is used for obtaining a target detection accuracy result of the test set.
9. A radar RD image weak target detection storage medium based on SVM is characterized in that: the storage medium internally stores computer instructions which, when run on an electronic terminal, cause the electronic terminal to perform the weak object detection method according to any one of claims 1-7.
10. A radar RD image weak target detection electronic terminal based on SVM is characterized in that: the electronic terminal comprises a processor and a memory, the memory is used for storing instructions, and the processor is used for calling the instructions in the memory so as to enable the electronic equipment to execute the weak target detection method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110785957.1A CN113408538A (en) | 2021-07-12 | 2021-07-12 | SVM-based radar RD image weak target detection method and system, storage medium and electronic terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110785957.1A CN113408538A (en) | 2021-07-12 | 2021-07-12 | SVM-based radar RD image weak target detection method and system, storage medium and electronic terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113408538A true CN113408538A (en) | 2021-09-17 |
Family
ID=77686063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110785957.1A Pending CN113408538A (en) | 2021-07-12 | 2021-07-12 | SVM-based radar RD image weak target detection method and system, storage medium and electronic terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408538A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114660598A (en) * | 2022-02-07 | 2022-06-24 | 安徽理工大学 | InSAR and CNN-AFSA-SVM fused mining subsidence basin automatic detection method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107728115A (en) * | 2017-09-11 | 2018-02-23 | 电子科技大学 | Ambient interferences suppressing method based on SVM after a kind of radar target imaging |
| CN111722199A (en) * | 2020-08-10 | 2020-09-29 | 上海航天电子通讯设备研究所 | Radar signal detection method based on convolutional neural network |
-
2021
- 2021-07-12 CN CN202110785957.1A patent/CN113408538A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107728115A (en) * | 2017-09-11 | 2018-02-23 | 电子科技大学 | Ambient interferences suppressing method based on SVM after a kind of radar target imaging |
| CN111722199A (en) * | 2020-08-10 | 2020-09-29 | 上海航天电子通讯设备研究所 | Radar signal detection method based on convolutional neural network |
Non-Patent Citations (2)
| Title |
|---|
| 张暄 等: "基于卷积神经网络的雷达目标检测方法", 《计算机测量与控制》 * |
| 陈云霁: "《智能计算系统》", 29 February 2020 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114660598A (en) * | 2022-02-07 | 2022-06-24 | 安徽理工大学 | InSAR and CNN-AFSA-SVM fused mining subsidence basin automatic detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kong et al. | YOLOv3-DPFIN: A dual-path feature fusion neural network for robust real-time sonar target detection | |
| Wang et al. | Ship detection in SAR images via local contrast of Fisher vectors | |
| US9953244B2 (en) | Apparatus and method for single look main lobe and sidelobe discrimination in spectral domain images | |
| CN113486961A (en) | Radar RD image target detection method and system based on deep learning under low signal-to-noise ratio and computer equipment | |
| CN112561940B (en) | Dense multi-target parameter extraction method and device and terminal equipment | |
| Gao et al. | A high-effective implementation of ship detector for SAR images | |
| Tings et al. | Dynamically adapted ship parameter estimation using TerraSAR-X images | |
| US20200065664A1 (en) | System and method of measuring the robustness of a deep neural network | |
| CN113009442B (en) | Method and device for identifying multipath target of radar static reflecting surface | |
| Liu et al. | Afdet: Toward more accurate and faster object detection in remote sensing images | |
| Liu et al. | Radar signal recognition based on triplet convolutional neural network | |
| CN113408538A (en) | SVM-based radar RD image weak target detection method and system, storage medium and electronic terminal | |
| Li et al. | Evaluation method for impact of jamming on radar based on expert knowledge and data mining | |
| Tian et al. | SAR object classification using the DAE with a modified triplet restriction | |
| CN112418187A (en) | Lane line recognition method and apparatus, storage medium, and electronic device | |
| Pan et al. | Ship detection using online update of clutter map based on fuzzy statistics and spatial property | |
| Cao et al. | Deep representation method for radar emitter signal using wavelet packets decomposition | |
| Zhao et al. | Corner‐based object detection method for reactivating box constraints | |
| CN115578647A (en) | SVM-based radar RD image weak target detection method | |
| Xie et al. | Lightweight and anchor-free frame detection strategy based on improved CenterNet for multiscale ships in SAR images | |
| Vishwakarma et al. | Two‐dimensional DFT with sliding and hopping windows for edge map generation of road images | |
| Wu et al. | Ship HRRP target recognition against decoy jamming based on CNN‐BiLSTM‐SE model | |
| Horvath et al. | Performance prediction of quantized SAR ATR algorithms | |
| CN115047419A (en) | Constant false alarm rate detection method and device for millimeter wave radar | |
| Liu et al. | Research on Small Target Pedestrian Detection Algorithm Based on Improved YOLOv3 |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210917 |
|
| RJ01 | Rejection of invention patent application after publication |