CN116719003B - Target detection method and system for millimeter wave radar detection - Google Patents
Target detection method and system for millimeter wave radar detection Download PDFInfo
- Publication number
- CN116719003B CN116719003B CN202311003351.3A CN202311003351A CN116719003B CN 116719003 B CN116719003 B CN 116719003B CN 202311003351 A CN202311003351 A CN 202311003351A CN 116719003 B CN116719003 B CN 116719003B
- Authority
- CN
- China
- Prior art keywords
- target
- signal
- compensation
- early warning
- module
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 117
- 238000000034 method Methods 0.000 claims abstract description 30
- 230000003044 adaptive effect Effects 0.000 claims abstract description 16
- 230000035605 chemotaxis Effects 0.000 claims abstract description 7
- 238000012795 verification Methods 0.000 claims description 57
- 230000003068 static effect Effects 0.000 claims description 35
- 238000003066 decision tree Methods 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 19
- 238000013507 mapping Methods 0.000 claims description 12
- 230000010287 polarization Effects 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 230000003399 chemotactic effect Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 2
- 230000008685 targeting Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000005684 electric field Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/411—Identification of targets based on measurements of radar reflectivity
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The application provides a target detection method and a target detection system for millimeter wave radar detection, which relate to the technical field of intelligent detection, wherein the method comprises the following steps: the method comprises the steps of building a wave loss database, acquiring echo compensation signals from an echo baseband signal input signal compensation model to determine target parameters, extracting signal frequencies, carrying out target grouping based on wave frequency chemotaxis states to determine target sets, determining target information based on signal intensity and signal triplets, inputting the wave frequency chemotaxis states, the target sets and the target information into an adaptive early warning analysis model, outputting target detection results to carry out detection warning of a target vehicle.
Description
Technical Field
The application relates to the technical field of intelligent detection, in particular to a target detection method and system for millimeter wave radar detection.
Background
With the development of radar field, radar is an abbreviation of radio detection and ranging, which means that distance can be detected and estimated by electromagnetic waves, which is the signal detection and parameter estimation of radar. The millimeter waves are electromagnetic waves between infrared light waves and microwave frequency bands, different classification methods are applied to millimeter wave radars of different categories, and the technical problem of low target recognition precision is caused by insufficient control when targets are detected in the prior art.
Disclosure of Invention
The application provides a target detection method and system for millimeter wave radar detection, which are used for solving the technical problem of low target recognition precision caused by insufficient control when targets are detected in the prior art.
In view of the above problems, the present application provides a method and a system for detecting a millimeter wave radar target.
In a first aspect, the present application provides a target detection method for millimeter wave radar detection, the method comprising: based on the propagation characteristics of millimeter waves, weather propagation loss analysis under a multi-element scene is carried out, and a wave loss database is built; based on the vehicle system terminal, transmitting frequency modulation continuous waves and receiving received wave baseband signals, inputting the received wave baseband signals into a signal compensation model to obtain echo compensation signals, wherein the signal compensation model is embedded with the wave loss database; determining a target parameter based on the echo compensation signal, wherein the target parameter comprises a signal frequency, a signal intensity and a signal triplet; extracting signal frequency and performing target grouping based on wave frequency chemotaxis state, and determining a target set, wherein the target set comprises a static target group and a dynamic target group; determining target information based on the signal strength and the signal triplet; inputting the wave frequency chemotaxis state, the target set and the target information into an adaptive early warning analysis model, and outputting a target detection result, wherein the adaptive early warning analysis model comprises a static analysis channel and a dynamic analysis channel, and the target detection result comprises an early warning target and early warning information marked with the early warning target meeting the early warning limit; and detecting and warning the target vehicle according to the target detection result.
In a second aspect, the present application provides an object detection system for millimeter wave radar detection, the system comprising: the loss analysis module is used for analyzing meteorological propagation loss in a multi-element scene based on the propagation characteristics of millimeter waves and constructing a wave loss database; the first input module is used for transmitting frequency modulation continuous waves and receiving echo baseband signals based on the vehicle system terminal, acquiring echo compensation signals from a signal compensation model, and embedding the wave loss database into the signal compensation model; the parameter determining module is used for determining a target parameter based on the echo compensation signal, wherein the target parameter comprises a signal frequency, a signal intensity and a signal triplet; the target grouping module is used for extracting signal frequency and performing target grouping based on wave frequency chemotactic states, and determining a target set, wherein the target set comprises a static target group and a dynamic target group; the information determining module is used for determining target information based on the signal strength and the signal triples; the second input module is used for inputting the wave frequency chemotactic state, the target set and the target information into an adaptive early warning analysis model and outputting a target detection result, the adaptive early warning analysis model comprises a static analysis channel and a dynamic analysis channel, and the target detection result comprises early warning targets and early warning information marked with the early warning targets meeting early warning limits; and the detection warning module is used for warning the target detection result to detect the target vehicle.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the application provides a target detection method and system for millimeter wave radar detection, relates to the technical field of intelligent detection, solves the technical problem of low target recognition precision caused by insufficient control when targets are detected in the prior art, realizes accurate control when targets are detected, and improves target recognition precision.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting targets by millimeter wave radar;
FIG. 2 is a schematic diagram showing the flow of the output echo compensation signal in the target detection method of millimeter wave radar detection;
fig. 3 is a schematic diagram of a process of screening out target information corresponding to a detected target in a target detection method for millimeter wave radar detection according to the present application;
FIG. 4 is a schematic flow chart of a self-adaptive early warning analysis model generated in a target detection method for millimeter wave radar detection;
fig. 5 is a schematic diagram of a structure of an object detection system for millimeter wave radar detection according to the present application.
Reference numerals illustrate: the system comprises a loss analysis module 1, a first input module 2, a parameter determination module 3, a target grouping module 4, an information determination module 5, a second input module 6 and a detection and warning module 7.
Detailed Description
The application provides a target detection method and a target detection system for millimeter wave radar detection, which are used for solving the technical problem of low target recognition precision caused by insufficient control when targets are detected in the prior art.
Example 1
As shown in fig. 1, an embodiment of the present application provides a target detection method of millimeter wave radar detection, which is applied to a vehicle system terminal, the method including:
step S100: based on the propagation characteristics of millimeter waves, weather propagation loss analysis under a multi-element scene is carried out, and a wave loss database is built;
specifically, the object detection method for millimeter wave radar detection provided by the embodiment of the application is applied to an object detection system for millimeter wave radar detection, and the object detection system for millimeter wave radar detection is applied to a vehicle system terminal for acquiring object parameters.
In order to ensure the accuracy of millimeter wave radar detection on a target object in the later stage, the propagation loss generated when the millimeter wave propagates under different environments is required to be analyzed, because the millimeter wave is a very high frequency band and propagates in space in the form of an irradiation wave, the wave beam is very narrow, so that the directivity is better, and under different scenes, on one hand, the millimeter wave is seriously influenced by atmospheric absorption and precipitation drop, and on the other hand, the single-hop communication interval is shorter, and on the other hand, the frequency band is high, the interference source is few, and the propagation is stable and reliable. Therefore, the meteorological propagation loss data of millimeter waves in a multi-element scene are summarized through the propagation characteristics of the millimeter waves, a loss data flow is carded, a data model conforming to the loss data is built, a data application layer, a data middle layer and a data source layer of the loss data are deduced, the construction of a wave loss database based on the millimeter wave propagation loss data is completed, and the detection of targets through millimeter wave radar detection is achieved in the later stage and serves as an important reference basis.
Step S200: based on the vehicle system terminal, transmitting frequency modulation continuous waves and receiving received wave baseband signals, inputting the received wave baseband signals into a signal compensation model to obtain echo compensation signals, wherein the signal compensation model is embedded with the wave loss database;
further, as shown in fig. 2, step S200 of the present application further includes:
step S210: collecting a meteorological propagation scene and determining a signal loss source;
step S220: performing compensation unit matching and calling based on the signal loss source to determine a temporary unit module;
step S230: inputting the echo baseband signal into the temporary unit module of the signal compensation model, and carrying out compensation analysis by combining the wave loss database embedded in the compensation unit to determine multi-source compensation information;
step S240: fitting the multisource compensation information and outputting the echo compensation signal.
Specifically, the vehicle system terminal connected through the system communication transmits the frequency modulation continuous wave of the millimeter wave radar, the frequency signal changes along with time according to the rule of the triangular wave, meanwhile, the echo baseband signal reflected back is received, the echo baseband signal is a signal which directly expresses information to be transmitted, further, in order to ensure the data integrity of the callback baseband signal, the weather scene where the vehicle system terminal is located is firstly collected, after the millimeter wave radar is matched with the current weather scene, the propagation loss of the millimeter wave radar in the weather scene is obtained, so that the signal loss source is determined, meanwhile, the compensation unit is matched with the compensation unit at the determined signal loss source, the compensation unit is used for compensating the loss signal during millimeter wave transmission, and therefore, the temporary unit module is determined to compensate the loss of the millimeter wave by the called compensation unit.
The method comprises the steps of inputting echo baseband signals into a temporary unit module of a signal compensation model, and simultaneously carrying out compensation analysis by combining with a wave loss database embedded in a compensation unit, wherein the wave loss database is based on wave loss data for compensating millimeter waves in the built wave loss database, determining the wave loss compensation data by the input echo baseband signals and the compensation unit in the combined temporary unit module, and simultaneously determining multi-source compensation information of millimeter waves according to different meteorological scenes corresponding to the wave loss compensation data, fitting the multi-source compensation information, namely applying a statistical model to the multi-source compensation information to estimate a group of compensation parameter values, so that the model can describe the compensation data as accurately as possible, outputting the fitted data as echo compensation signals, and guaranteeing target detection by millimeter wave radar detection.
Further, the step S200 of the present application further includes:
step S250: dividing the wave loss database based on wave loss characteristics to generate a plurality of wave loss database sub-databases, wherein the wave loss database sub-databases are used for storing mapping identifications of the wave loss characteristics and meteorological propagation conditions;
step S260: the signal compensation model is built, and comprises an attenuation compensation unit, a scattering compensation unit, a polarization compensation unit and a noise reduction processing unit which are arranged in parallel;
step S270: and matching and embedding the signal compensation model execution unit based on the wave loss database.
Further, step S220 of the present application includes:
step S261: invoking historical detection data, and identifying and extracting sample echo signals and sample attenuation compensation information, wherein the sample echo signals are marked with weather propagation scenes and feedback delay information;
step S262: based on the meteorological propagation scene and the feedback time delay information, randomly extracting a group of the first decision nodes and constructing a first decision layer for classifying the sample echo signals;
step S263: continuing to determine an Nth decision node, constructing an Nth decision layer, performing hierarchical association from the first decision layer to the Nth decision layer, and targeting a decision tree;
step S264: performing mapping matching and identification on the target decision tree based on the sample attenuation compensation information to generate an attenuation compensation decision tree;
step S265: the attenuation compensation unit is generated based on the attenuation compensation decision tree.
Specifically, the wave loss characteristics of millimeter waves are taken as references, when the vibration direction of the reflected light when leaving a reflection point is exactly opposite to the vibration direction when the incident light reaches the incidence point in the process of being reflected, the vibration direction characteristics in the process are taken as wave loss characteristics, the wave loss databases are divided according to different wave loss characteristics, wave loss data are extracted from the wave loss databases according to each wave loss characteristic to generate a plurality of wave loss data sub-databases, mapping identifications of the wave loss characteristics and weather propagation conditions exist in the wave loss data sub-databases, one value is taken in the weather propagation conditions, the wave loss characteristics have one value and only one value corresponds to the wave loss characteristics, the weather propagation conditions have a plurality of values corresponding to the vibration direction, a signal compensation model is further built, the signal compensation model is built by an attenuation compensation unit, a scattering compensation unit, a polarization compensation unit and noise reduction processing unit, the attenuation compensation unit is used for gradually compensating the echo signals in different scenes by the base band signal propagation units, the attenuation compensation unit is used for compensating the echo signals in the base band signal propagation process under different scenes, even when the echo signals are distributed on the base band with a large electric field, and the object with a large transient polarization is distributed in the direction, and the object is a smooth, and the object is in the direction of the base band has a large curvature when the object is distributed on the base band. The polarization of the echo baseband signal is usually compensated by a track which is traced by an electric field intensity vector endpoint in space along with time, and the noise reduction processing unit is used for eliminating or weakening noise components in the echo baseband signal so as to improve the quality and reliability of the echo baseband signal.
Further, the attenuation compensation unit in the signal compensation model is used for calling historical detection data of the millimeter wave radar, namely extracting data of detection feedback of the millimeter wave radar on a target object in the historical detection data, identifying and marking sample echo signals and sample attenuation compensation information contained in the historical detection data, meanwhile, the sample echo signal identification contains weather propagation scenes and feedback delay information, the weather propagation scenes refer to weather environments of current signal propagation, the feedback delay information refers to propagation time length of the current signal, further, a group of weather propagation scenes and feedback delay information contained in the sample echo signal identification are randomly extracted to serve as first decision nodes, the first decision nodes are used for constructing the first decision layers, the first decision layers are used for conducting second classification of the sample echo signals, namely, two categories exist in classification tasks of the sample echo signals, the sample echo signals are classified, accordingly, iteration is continued to determine an N decision node and a first decision layer until the N decision layer is associated with each decision tree, all associated decision tree levels are used as expected decision tree levels, the probability values can be found out on the basis of a new class of the new decision tree, the probability value can be analyzed by the method, and the probability value of the new class is larger than the expected value of the new class node. The first decision layer to the Nth decision layer can be used as internal nodes of the multi-level care decision tree, the characteristics with the minimum entropy value can be classified preferentially by calculating the information entropy of the internal nodes, the target decision tree is constructed recursively by the method until the last characteristic leaf node cannot be subdivided, and the target decision tree is formed after the classification is finished.
Finally, taking sample attenuation compensation information as a basis, carrying out mapping matching and identification on a target decision tree, namely taking one value in the sample attenuation compensation information, wherein the target decision tree has one value and only one value corresponds to the sample attenuation compensation information, taking one value in the target decision tree, the sample attenuation compensation information can have a plurality of values corresponding to the sample attenuation compensation information, identifying the mapped and matched data to generate an attenuation compensation decision tree, simultaneously completing construction of an attenuation compensation unit based on the attenuation compensation decision tree, constructing a scattering compensation unit, a polarization compensation unit and a noise reduction processing unit in a similar way on the basis, completing construction of a signal compensation model according to the constructed attenuation compensation unit, the scattering compensation unit, the polarization compensation unit and the noise reduction processing unit, sequentially embedding an obtained wave loss database into the signal compensation model, and improving the accuracy of signal compensation, thereby realizing ramming detection of a target through millimeter wave radar detection.
Step S300: determining a target parameter based on the echo compensation signal, wherein the target parameter comprises a signal frequency, a signal intensity and a signal triplet;
specifically, the echo compensation signal in the signal compensation model is used as data compensation, the target parameters of the millimeter radar are determined, the determined target parameters comprise signal frequency, signal strength and signal triplets, the signal frequency refers to the width of a signal spectrum, namely the difference between the highest frequency component and the lowest frequency component of the signal, the signal strength refers to the energy or the power of the signal, the signal strength is usually expressed in unit decibel (dB), further, the parameters such as the size, the shape and the distance of the target object can be determined through the signal strength and the radar power, the signal triplets refer to the distance between the signal and the target object, the azimuth of the signal relative to the target object and the pitch angle of the signal relative to the target object, and the detection of the target through millimeter wave radar is realized.
Step S400: extracting the signal frequency, and performing target grouping based on the wave frequency chemotactic state, so as to determine a target set, wherein the target set comprises a static target group and a dynamic target group;
specifically, the object is classified based on the wave-frequency trend state by extracting the signal frequency in the object parameter alone, which means that the wave is compressed by the doppler effect, that is, in front of the wave source of the moving vehicle, and the wave becomes shorter, and the frequency becomes higher, that is, blue-shifted, and the opposite effect occurs behind the wave source of the moving vehicle. The longer the wavelength becomes, the lower the frequency becomes, i.e. the red-shift, the higher the velocity of the wave source, the greater the effect produced. According to the degree of the wave red or blue shift, the speed of the wave source moving the vehicle along the observation direction can be calculated to determine the relative state of the vehicle and the detection target, namely, the received wave is increased compared with the frequency of the emitted wave, namely, the relative position is gradually approaching, the target approaches the vehicle, otherwise, the received wave is reduced compared with the frequency of the emitted wave, namely, the relative position is gradually separating, the target is far away from the vehicle, further, the analysis of the relative motion is carried out based on the trend state of the millimeter wave frequency, namely, the state of the target is stationary or moving is determined by combining the speed of the vehicle and the relative speed, and the determined state is defined at the same time, so that a plurality of targets which are completely divided are output as a target set, a static target set and a static target set are contained in the target set, the target state contained in the static target set is the static state, and the target state contained in the dynamic target set is the moving state, so that the target is detected by the millimeter wave radar at the later stage to be used as reference data.
Step S500: determining target information based on the signal strength and the signal triplet;
further, as shown in fig. 3, step S500 of the present application includes:
step S510: inputting the target information into a target verification module, wherein the target verification module comprises a plurality of target verification branches configured in parallel, and the plurality of target verification branches are generated by BP neural network training based on different target detection algorithms and sample data;
step S520: verifying the target information based on the target verification branches, adding verification results, and determining verification characteristic values, wherein the verification results are marked as 1 or 0;
step S530: and judging whether the verification characteristic value meets a threshold value standard, and if not, screening out the target information corresponding to the detection target.
Specifically, to ensure the accuracy of target monitoring, determining target information based on a signal strength and signal triplets, namely determining parameters such as a distance between a target object and a signal, a shape of the target object and the like according to the strength of a signal return and the power of a radar, then integrating and recording the parameters as target information, simultaneously inputting the target information into a target verification module for verifying the target object, wherein the target verification module comprises a plurality of target verification branches which are configured in parallel, the plurality of target verification branches perform BP neural network training generation based on different target detection algorithms and sample data, when echo signals exist, the detection of the targets, namely, the signal contact feedback of the targets, are further performed, for example, a constant false alarm monitor, an energy detection method, high-order statistic detection and the like are used, and meanwhile, based on the BP neural network, the BP neural network is a multi-layer feedforward neural network trained according to an error reverse propagation algorithm, the input data of the plurality of target verification branches comprise the target information, and an input layer, an implicit layer and an output layer are further constructed in the plurality of target verification branches.
Further, the multiple target verification branch construction process is as follows: inputting each group of training data in the training data set into a plurality of target verification branches, performing output supervision adjustment of the plurality of target verification branches through supervision data corresponding to the group of training data, wherein the supervision data set is supervision data corresponding to the training data set one by one, when the output results of the plurality of target verification branches are consistent with the supervision data, the current group training is finished, all the training data in the training data set are trained, and the plurality of target verification branches are trained.
In order to ensure the convergence and accuracy of the target verification branches, the convergence process may be that when the output data in the target verification branches are converged to one point, the convergence is performed when the output data approaches to a certain value, the accuracy may be tested by the test data set for the target verification branches, for example, the test accuracy may be set to 80%, and when the test accuracy of the test data set meets 80%, the construction of the target verification branches is completed.
And verifying the target information based on a plurality of target verification branches, namely, whether the detected target is in a warning range or not, so as to screen the target. According to the target verification branches, verification results based on different algorithms are determined and added and judged, so that the accuracy of the verification results can be effectively ensured. The verification result can be qualified or unqualified, the verification result mark of the qualified verification is 1, the verification mark result of the unqualified verification is 0, the verification result is added on the basis, the added result is recorded as a verification characteristic value, meanwhile, whether the verification characteristic value meets a threshold standard or not is judged, wherein the threshold standard is preset by related technicians according to the characteristic value of target verification data, if the verification characteristic value does not meet the threshold standard, target information corresponding to a currently detected target is screened out in a system, and the detection accuracy of the target through millimeter wave radar detection is improved.
Step S600: inputting the wave frequency chemotaxis state, the target set and the target information into a self-adaptive early warning analysis model, and outputting a target detection result, wherein the self-adaptive early warning analysis model comprises a static analysis channel and a dynamic analysis channel, and the target detection result comprises an early warning target and early warning information marked with the early warning target meeting the early warning limit;
further, as shown in fig. 4, step S600 of the present application includes:
step S610: a first early warning definition function and a second early warning definition function are configured aiming at a static target and a dynamic target, wherein the early warning definition function takes relative speed, relative direction and target distance as response parameters, takes a road standard as constraint and takes interaction time limit as a response target;
step S620: invoking sample static target early warning information based on the first early warning definition function, and training to generate the static analysis channel;
step S630: invoking sample dynamic target early warning information based on the second early warning definition function, and training to generate the dynamic analysis channel;
step S640: and generating the self-adaptive early warning analysis model based on the static analysis channel and the dynamic analysis channel.
Further, step S640 of the present application includes:
step S641: based on the interaction risk, configuring a layer of early warning standard comprising early warning types and early warning information;
step S642: based on the target difference, configuring a two-layer early warning standard;
step S643: and carrying out the first-layer early warning standard and the second-layer early warning standard, configuring diversified early warning information and embedding the adaptive early warning analysis model.
Specifically, in order to ensure the accuracy of warning according to the detected target finally, the wave frequency trend change state, the target set and the target information need to be input into the adaptive early warning analysis model, and the adaptive early warning analysis model may be constructed by firstly configuring a first early warning defining function and a second early warning defining function according to the static target and the dynamic target contained in the target set, wherein the first early warning defining function takes the relative speed, the relative direction and the target distance of the static target as response parameters, and takes the line standard as constraint, takes the interaction time limit as a function obtained by responding to the target, and the second early warning defining function takes the relative speed, the relative direction and the target distance of the dynamic target as response parameters, takes the line standard as constraint, and takes the interaction time limit as a function obtained by responding to the target.
Further, based on the first early warning definition function, sample static target early warning information is called, the sample static target early warning information is substituted into the first early warning definition function to conduct data comparison training, a static analysis channel corresponding to the static target is obtained, based on the second early warning definition function, sample dynamic target early warning information is called, sample dynamic target early warning information is substituted into the second early warning definition function to conduct data comparison training, a dynamic analysis channel corresponding to the dynamic target is obtained, and a self-adaptive early warning analysis model is generated based on the static analysis channel and the dynamic analysis channel.
And the method comprises the steps of configuring a first layer of early warning standard in the self-adaptive early warning analysis model according to the mutual risk between vehicles or between people and vehicles, configuring a second layer of early warning standard in the self-adaptive early warning analysis model according to the difference between detected targets, wherein the higher the difference between the targets is, the higher the early warning grade is, and finally taking the configured first layer of early warning standard and second layer of standard as diversified early warning information and embedding the diversified early warning information into the self-adaptive early warning analysis model to improve early warning accuracy, so that detection targets under the screening preset risk standard are used as detection results to carry out warning, and finally outputting target detection results through the self-adaptive early warning analysis model, wherein the target detection results comprise early warning targets and early warning information marked with the early warning limit, namely the target detection results reaching the first layer of early warning standard or the second layer of early warning standard, thereby ensuring that later detection is better through millimeter wave radar detection.
Step S700: and detecting and warning the target vehicle according to the target detection result.
Specifically, the target detection result which is output by the self-adaptive early-warning analysis model and contains the early-warning target and the early-warning information which meet the early-warning limit is used as early-warning basic data, the target vehicle is detected and warned according to the target information contained in the early-warning target in the target detection result and the early-warning level contained in the early-warning information, the warning level is in a direct proportion relation with the early-warning target, the early-warning type and the early-warning information, if the early-warning target, the early-warning type and the early-warning information are higher than the early-warning limit, and the higher the early-warning level is, the higher the detection and warning of the target vehicle are completed on the basis, and the more accurate detection of the target is achieved based on the warning level.
In summary, the target detection method for millimeter wave radar detection provided by the embodiment of the application at least has the following technical effects that accurate control is realized when targets are detected, and target recognition accuracy is improved.
Example two
Based on the same inventive concept as the target detection method of millimeter wave radar detection in the foregoing embodiments, as shown in fig. 5, the present application provides a target detection system of millimeter wave radar detection, the system comprising:
the loss analysis module 1 is used for analyzing meteorological propagation loss in a multi-element scene based on the propagation characteristics of millimeter waves, and constructing a wave loss database;
the first input module 2 is used for transmitting frequency modulation continuous waves and receiving echo baseband signals based on the vehicle system terminal, acquiring echo compensation signals from a signal compensation model, and embedding the wave loss database into the signal compensation model;
a parameter determining module 3, where the parameter determining module 3 is configured to determine a target parameter based on the echo compensation signal, where the target parameter includes a signal frequency, a signal strength, and a signal triplet;
the target grouping module 4 is used for extracting signal frequency and performing target grouping based on wave frequency trend state, and determining a target set, wherein the target set comprises a static target group and a dynamic target group;
an information determining module 5, where the information determining module 5 is configured to determine target information based on the signal strength and the signal triplet;
the second input module 6 is used for inputting the wave frequency chemotactic state, the target set and the target information into an adaptive early warning analysis model and outputting a target detection result, the adaptive early warning analysis model comprises a static analysis channel and a dynamic analysis channel, and the target detection result comprises early warning targets and early warning information marked with the early warning targets meeting early warning limits;
and the detection warning module 7 is used for warning the target detection result to detect the target vehicle.
Further, the system further comprises:
the dividing module is used for dividing the wave loss database based on wave loss characteristics to generate a plurality of wave loss database sub-databases, wherein the wave loss database sub-databases are used for storing mapping identifications of the wave loss characteristics and weather propagation conditions;
the unit configuration module is used for constructing the signal compensation model, and the signal compensation model comprises an attenuation compensation unit, a scattering compensation unit, a polarization compensation unit and a noise reduction processing unit which are configured in parallel;
and the first embedding module is used for matching and embedding the signal compensation model execution unit based on the wave loss database.
Further, the system further comprises:
the recognition module is used for calling historical detection data, recognizing and extracting sample echo signals and sample attenuation compensation information, and the sample echo signals are marked with weather propagation scenes and feedback delay information;
the extraction module is used for randomly extracting a group of nodes serving as a first decision node and constructing a first decision layer based on the meteorological propagation scene and the feedback time delay information, and is used for classifying the sample echo signals;
the hierarchical association module is used for continuously determining an Nth decision node, constructing an Nth decision layer and carrying out hierarchical association from the first decision layer to the Nth decision layer to a target decision tree;
the mapping matching module is used for performing mapping matching and identification on the target decision tree based on the sample attenuation compensation information to generate an attenuation compensation decision tree;
and the unit generation module is used for generating the attenuation compensation unit based on the attenuation compensation decision tree.
Further, the system further comprises:
the loss source determining module is used for collecting a meteorological propagation scene and determining a signal loss source;
the calling module is used for carrying out compensation unit matching and calling based on the signal loss source and determining a temporary unit module;
the compensation analysis module is used for inputting the echo baseband signal into the temporary unit module of the signal compensation model, carrying out compensation analysis by combining the wave loss database embedded in the compensation unit, and determining multi-source compensation information;
and the output module is used for fitting the multi-source compensation information and outputting the echo compensation signal.
Further, the system further comprises:
the branch configuration module is used for inputting the target information into the target verification module, and the target verification module comprises a plurality of target verification branches configured in parallel, wherein the plurality of target verification branches are generated by BP neural network training based on different target detection algorithms and sample data;
the adding module is used for carrying out verification of the target information based on the target verification branches, adding verification results, and determining verification characteristic values, wherein the verification result mark is 1 or 0;
and the judging module is used for judging whether the verification characteristic value meets a threshold value standard or not, and if not, screening out the target information corresponding to the detection target.
Further, the system further comprises:
the first configuration module is used for configuring a first early warning definition function and a second early warning definition function aiming at a static target and a dynamic target, wherein the early warning definition function takes relative speed, relative direction and target distance as response parameters, takes a road standard as constraint and takes interaction time limit as a response target;
the first calling module is used for calling sample static target early warning information based on the first early warning definition function and training to generate the static analysis channel;
the second calling module is used for calling sample dynamic target early warning information based on the second early warning definition function and training to generate the dynamic analysis channel;
the model generation module is used for generating the self-adaptive early warning analysis model based on the static analysis channel and the dynamic analysis channel.
Further, the system further comprises:
the second configuration module is used for configuring a layer of early warning standard based on the interaction risk, and comprises early warning types and early warning information;
the third configuration module is used for configuring two-layer early warning standards based on target difference;
the second embedding module is used for carrying out the first-layer early warning standard and the second-layer early warning standard, configuring diversified early warning information and embedding the adaptive early warning analysis model.
The present disclosure is directed to a millimeter wave radar detection target detection system according to the present embodiment, and the present disclosure is directed to a device according to the present disclosure, and the description thereof is relatively simple, and the relevant points are referred to in the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. A target detection method of millimeter wave radar detection, the method being applied to a vehicle system terminal, the method comprising:
based on the propagation characteristics of millimeter waves, weather propagation loss analysis under a multi-element scene is carried out, and a wave loss database is built, wherein the wave loss database is a data set for summarizing weather propagation loss data of millimeter waves under the multi-element scene through the propagation characteristics of the millimeter waves;
based on the vehicle system terminal, transmitting frequency modulation continuous waves and receiving received wave baseband signals, inputting the received wave baseband signals into a signal compensation model to obtain echo compensation signals, wherein the signal compensation model is embedded with the wave loss database;
determining a target parameter based on the echo compensation signal, wherein the target parameter comprises a signal frequency, a signal intensity and a signal triplet;
extracting signal frequency and performing target grouping based on wave frequency chemotaxis state, and determining a target set, wherein the target set comprises a static target group and a dynamic target group;
determining target information based on the signal strength and the signal triplet;
inputting the wave frequency chemotaxis state, the target set and the target information into an adaptive early warning analysis model, and outputting a target detection result, wherein the adaptive early warning analysis model comprises a static analysis channel and a dynamic analysis channel, and the target detection result comprises an early warning target and early warning information marked with the early warning target meeting the early warning limit;
detecting and warning the target vehicle according to the target detection result;
wherein, construct the signal compensation model, the method includes:
dividing the wave loss database based on wave loss characteristics to generate a plurality of wave loss database sub-databases, wherein the wave loss database sub-databases are used for storing mapping identifications of the wave loss characteristics and meteorological propagation conditions;
the signal compensation model is built, and comprises an attenuation compensation unit, a scattering compensation unit, a polarization compensation unit and a noise reduction processing unit which are arranged in parallel;
matching and embedding the signal compensation model execution unit based on the wave loss database;
constructing an attenuation compensation unit, the method comprising:
invoking historical detection data, and identifying and extracting sample echo signals and sample attenuation compensation information, wherein the sample echo signals are marked with weather propagation scenes and feedback delay information;
based on the meteorological propagation scene and the feedback time delay information, randomly extracting a group of the first decision nodes and constructing a first decision layer for classifying the sample echo signals;
continuing to determine an Nth decision node, constructing an Nth decision layer, performing hierarchical association from the first decision layer to the Nth decision layer, and targeting a decision tree;
performing mapping matching and identification on the target decision tree based on the sample attenuation compensation information to generate an attenuation compensation decision tree;
generating the attenuation compensation unit based on the attenuation compensation decision tree;
the method comprises the steps of transmitting the frequency modulation continuous wave and receiving a back wave baseband signal, and obtaining an echo compensation signal from an input signal compensation model, wherein the method comprises the following steps:
collecting a meteorological propagation scene and determining a signal loss source;
performing compensation unit matching and calling based on the signal loss source to determine a temporary unit module;
inputting the echo baseband signal into the temporary unit module of the signal compensation model, and carrying out compensation analysis by combining the wave loss database embedded in the compensation unit to determine multi-source compensation information;
fitting the multisource compensation information and outputting the echo compensation signal.
2. The method of claim 1, wherein after the determining the target information, the method comprises:
inputting the target information into a target verification module, wherein the target verification module comprises a plurality of target verification branches configured in parallel, and the plurality of target verification branches are generated by BP neural network training based on different target detection algorithms and sample data;
verifying the target information based on the target verification branches, adding verification results, and determining verification characteristic values, wherein the verification results are marked as 1 or 0;
and judging whether the verification characteristic value meets a threshold value standard, and if not, screening out the target information corresponding to the detection target.
3. The method of claim 1, wherein the method comprises:
a first early warning definition function and a second early warning definition function are configured aiming at a static target and a dynamic target, wherein the early warning definition function takes relative speed, relative direction and target distance as response parameters, takes a road standard as constraint and takes interaction time limit as a response target;
invoking sample static target early warning information based on the first early warning definition function, and training to generate the static analysis channel;
invoking sample dynamic target early warning information based on the second early warning definition function, and training to generate the dynamic analysis channel;
and generating the self-adaptive early warning analysis model based on the static analysis channel and the dynamic analysis channel.
4. A method according to claim 3, wherein the method comprises:
based on the interaction risk, configuring a layer of early warning standard comprising early warning types and early warning information;
based on the target difference, configuring a two-layer early warning standard;
and carrying out the first-layer early warning standard and the second-layer early warning standard, configuring diversified early warning information and embedding the adaptive early warning analysis model.
5. An object detection system of millimeter wave radar detection, the system being applied to a vehicle system terminal, the system comprising:
the loss analysis module is used for analyzing the meteorological propagation loss under a multi-element scene based on the propagation characteristics of millimeter waves, and constructing a wave loss database which is a data set for summarizing the meteorological propagation loss data of millimeter waves under the multi-element scene through the propagation characteristics of the millimeter waves;
the first input module is used for transmitting frequency modulation continuous waves and receiving echo baseband signals based on the vehicle system terminal, acquiring echo compensation signals from a signal compensation model, and embedding the wave loss database into the signal compensation model;
the parameter determining module is used for determining a target parameter based on the echo compensation signal, wherein the target parameter comprises a signal frequency, a signal intensity and a signal triplet;
the target grouping module is used for extracting signal frequency and performing target grouping based on wave frequency chemotactic states, and determining a target set, wherein the target set comprises a static target group and a dynamic target group;
the information determining module is used for determining target information based on the signal strength and the signal triples;
the second input module is used for inputting the wave frequency chemotactic state, the target set and the target information into an adaptive early warning analysis model and outputting a target detection result, the adaptive early warning analysis model comprises a static analysis channel and a dynamic analysis channel, and the target detection result comprises early warning targets and early warning information marked with the early warning targets meeting early warning limits;
the detection warning module is used for warning the target detection result to detect the target vehicle;
the dividing module is used for dividing the wave loss database based on wave loss characteristics to generate a plurality of wave loss database sub-databases, wherein the wave loss database sub-databases are used for storing mapping identifications of the wave loss characteristics and weather propagation conditions;
the unit configuration module is used for constructing the signal compensation model, and the signal compensation model comprises an attenuation compensation unit, a scattering compensation unit, a polarization compensation unit and a noise reduction processing unit which are configured in parallel;
the first embedding module is used for matching and embedding the signal compensation model execution unit based on the wave loss database sub-database;
the recognition module is used for calling historical detection data, recognizing and extracting sample echo signals and sample attenuation compensation information, and the sample echo signals are marked with weather propagation scenes and feedback delay information;
the extraction module is used for randomly extracting a group of nodes serving as a first decision node and constructing a first decision layer based on the meteorological propagation scene and the feedback time delay information, and is used for classifying the sample echo signals;
the hierarchical association module is used for continuously determining an Nth decision node, constructing an Nth decision layer and carrying out hierarchical association from the first decision layer to the Nth decision layer to a target decision tree;
the mapping matching module is used for performing mapping matching and identification on the target decision tree based on the sample attenuation compensation information to generate an attenuation compensation decision tree;
the unit generation module is used for generating the attenuation compensation unit based on the attenuation compensation decision tree;
the loss source determining module is used for collecting a meteorological propagation scene and determining a signal loss source;
the calling module is used for carrying out compensation unit matching and calling based on the signal loss source and determining a temporary unit module;
the compensation analysis module is used for inputting the echo baseband signal into the temporary unit module of the signal compensation model, carrying out compensation analysis by combining the wave loss database embedded in the compensation unit, and determining multi-source compensation information;
and the output module is used for fitting the multi-source compensation information and outputting the echo compensation signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311003351.3A CN116719003B (en) | 2023-08-10 | 2023-08-10 | Target detection method and system for millimeter wave radar detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311003351.3A CN116719003B (en) | 2023-08-10 | 2023-08-10 | Target detection method and system for millimeter wave radar detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116719003A CN116719003A (en) | 2023-09-08 |
| CN116719003B true CN116719003B (en) | 2023-10-24 |
Family
ID=87866559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311003351.3A Active CN116719003B (en) | 2023-08-10 | 2023-08-10 | Target detection method and system for millimeter wave radar detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116719003B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08285943A (en) * | 1995-04-14 | 1996-11-01 | Nikon Corp | Radar apparatus |
| CN102486538A (en) * | 2010-12-05 | 2012-06-06 | 中国科学院沈阳自动化研究所 | Target detection method for millimeter-wave anticollision radar |
| CN102890272A (en) * | 2012-11-05 | 2013-01-23 | 中国航天科工集团第二研究院二十三所 | Method for processing millimeter wave cloud radar signal |
| CN103278804A (en) * | 2013-06-14 | 2013-09-04 | 张永刚 | Waveguide over-the-horizon radar |
| KR101329044B1 (en) * | 2013-08-30 | 2013-11-21 | 한국건설기술연구원 | Apparatus and mehod for meteorological observation of vihicle |
| CN110095757A (en) * | 2018-01-29 | 2019-08-06 | 株式会社万都 | For compensating the device and method and radar equipment of the return loss of the antenna of radar |
| CN111583671A (en) * | 2020-06-05 | 2020-08-25 | 南京信息职业技术学院 | Millimeter wave radar intersection traffic flow monitoring method and system |
| CN112198490A (en) * | 2020-09-11 | 2021-01-08 | 中国航空工业集团公司雷华电子技术研究所 | Ground clutter suppression method and device for airborne millimeter wave cloud detection radar and radar |
| CN115459868A (en) * | 2022-09-22 | 2022-12-09 | 利国智能科技(昆山)有限公司 | Millimeter wave communication performance evaluation method and system in complex environment |
-
2023
- 2023-08-10 CN CN202311003351.3A patent/CN116719003B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08285943A (en) * | 1995-04-14 | 1996-11-01 | Nikon Corp | Radar apparatus |
| CN102486538A (en) * | 2010-12-05 | 2012-06-06 | 中国科学院沈阳自动化研究所 | Target detection method for millimeter-wave anticollision radar |
| CN102890272A (en) * | 2012-11-05 | 2013-01-23 | 中国航天科工集团第二研究院二十三所 | Method for processing millimeter wave cloud radar signal |
| CN103278804A (en) * | 2013-06-14 | 2013-09-04 | 张永刚 | Waveguide over-the-horizon radar |
| KR101329044B1 (en) * | 2013-08-30 | 2013-11-21 | 한국건설기술연구원 | Apparatus and mehod for meteorological observation of vihicle |
| CN110095757A (en) * | 2018-01-29 | 2019-08-06 | 株式会社万都 | For compensating the device and method and radar equipment of the return loss of the antenna of radar |
| CN111583671A (en) * | 2020-06-05 | 2020-08-25 | 南京信息职业技术学院 | Millimeter wave radar intersection traffic flow monitoring method and system |
| CN112198490A (en) * | 2020-09-11 | 2021-01-08 | 中国航空工业集团公司雷华电子技术研究所 | Ground clutter suppression method and device for airborne millimeter wave cloud detection radar and radar |
| CN115459868A (en) * | 2022-09-22 | 2022-12-09 | 利国智能科技(昆山)有限公司 | Millimeter wave communication performance evaluation method and system in complex environment |
Non-Patent Citations (2)
| Title |
|---|
| Rural Macrocell Path Loss Models for Millimeter Wave Wireless Communications;George R. MacCartney 等;IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS;第35卷(第7期);全文 * |
| 基于深度学习的智能车前方目标识别与预警研究;郭阅;中国优秀硕士学位论文全文数据库;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116719003A (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113050045B (en) | Intelligent comprehensive main and side lobe interference resisting system and method | |
| CN115546608A (en) | Unmanned aerial vehicle data link electromagnetic interference classification and threat assessment method | |
| KR102440355B1 (en) | Deep Learning-based Ocean Cluster Data Measurement System Using Sea Level Wave Reflectance | |
| CN114564813A (en) | Electromagnetic environment multi-domain characteristic threat degree evaluation method | |
| Liu et al. | A two‐step abnormal data analysis and processing method for millimetre‐wave radar in traffic flow detection applications | |
| Fujita et al. | An approach for intelligent evaluation of the state of complex autonomous objects based on the wavelet analysis | |
| CN113159447B (en) | Laser radar electromagnetic environment effect prediction method and system | |
| CN116719003B (en) | Target detection method and system for millimeter wave radar detection | |
| Sinha et al. | Estimation of Doppler profile using multiparameter cost function method | |
| CN110874603A (en) | Deep confidence network information extraction device and method in cognitive information countermeasure | |
| KR102096941B1 (en) | Low RCS target classification apparatus based on PCL radar network and method thereof | |
| CN117029840A (en) | Mobile vehicle positioning method and system | |
| CN103076595A (en) | Abnormal type identifying method for multivariate discrete radar emitter signal | |
| Avcioglu et al. | Three dimensional volume coverage in multistatic sonar sensor networks | |
| CN115481667A (en) | UWB fuze target identification method based on multi-scale UDA and feature learning | |
| CN109031212A (en) | A kind of working frequency optimization method under radar tracking state | |
| US11288856B2 (en) | Method and system for wave propagation prediction | |
| CN113361639A (en) | Deep learning-based radiation source signal multi-model comprehensive classification method | |
| CN114966659B (en) | Radar target detection system and method based on machine learning | |
| CN116500618B (en) | Method for realizing high-frequency beyond-view-range radar ranging and fuzzy environment imaging | |
| CN113589269B (en) | Passive multi-base-station radar target detection method based on linear fusion | |
| CN115508793A (en) | Radar interference effect online evaluation intelligent method based on countermeasure analysis feature screening | |
| KR102280403B1 (en) | Method for determining channel bandwidth of underwater acoustic communication band and apparatus using the same | |
| CN116165446B (en) | Electromagnetic wave signal management system and method for anechoic chamber | |
| CN116500578B (en) | Weather Radar Data Processing Method Based on Neural Network Model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |