CN116400307A - Calibration method for radar sea wave parameter measurement - Google Patents
Calibration method for radar sea wave parameter measurement Download PDFInfo
- Publication number
- CN116400307A CN116400307A CN202310277081.9A CN202310277081A CN116400307A CN 116400307 A CN116400307 A CN 116400307A CN 202310277081 A CN202310277081 A CN 202310277081A CN 116400307 A CN116400307 A CN 116400307A
- Authority
- CN
- China
- Prior art keywords
- radar
- wave
- surface image
- wave surface
- radar wave
- 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
- 238000005259 measurement Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 6
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 6
- 238000001228 spectrum Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 description 4
- 238000010183 spectrum analysis Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 241000282461 Canis lupus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
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
- G01S7/40—Means for monitoring or calibrating
- G01S7/4004—Means for monitoring or calibrating of parts of a radar system
- G01S7/4026—Antenna boresight
-
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
-
- 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
Abstract
The invention belongs to the technical field of ocean remote sensing, and relates to a calibration method for radar sea wave parameter measurement. Radar signal data under different sea conditions are measured through radar signals generated by incidence of radar antennas on sea surfaces and reflection, radar image data and a buoy database are analyzed and processed, a calibration model of the deep convolutional neural network is constructed, a calibration algorithm for sea wave parameter measurement is formed, and radar image data is calibrated. The invention reduces the error of inverting the wave parameters by adopting the radar wave surface image and improves the accuracy and reliability of the inversion of the wave parameters.
Description
Technical Field
The invention belongs to the technical field of ocean remote sensing, and relates to a calibration method for radar sea wave parameter measurement.
Background
The observation and real-time prediction of sea wave information is important for various offshore and open sea activities, such as ship navigation, offshore engineering and ocean resource development. Since the navigation radar has high image resolution and can reflect the change of the sea surface in space and time, the navigation radar gradually develops into a remote sensing means for measuring wave height. In recent years, methods for extracting sea wave parameters by utilizing radar wave surface images mainly comprise a spectrum analysis method and an image statistics method. The spectrum analysis method calculates wave number energy spectrums of images and sea waves based on three-dimensional spectrum transformation, calculates a signal-to-noise ratio of the sea waves by adopting a dispersion filter, estimates an effective wave height by utilizing a linear empirical relationship between the effective wave height and the signal-to-noise ratio, wherein an empirical coefficient is closely related to radar characteristics, and is usually calibrated by utilizing field actual measurement wave height data. Since the spectral analysis is based on three-dimensional fourier transform, based on the assumption that the wave field is superimposed in linear wavelength, and the actual wave field is superimposed in nonlinear wave field, the effective wave height measurement accuracy based on the spectral analysis has a limitation. The basic principle of the sea wave parameter measurement method based on the image statistics method is that physical modulation in sea wave remote sensing imaging is characterized in radar gray level image statistics, sea wave height parameters can be obtained by utilizing the characteristics, but the measurement accuracy is limited due to the fact that the method has an empirical statistical method problem. In order to eliminate errors caused by traditional wave parameter estimation, the deep learning method can replace the complex calculation process of the traditional wave parameter estimation method, the wave parameters are inverted by adopting a method based on deep learning, a reference database of radar wave surface images is established, the radar wave surface images and data in a standard buoy database are marked, so that the radar wave surface image data are corrected, and a calibration method for radar wave parameter measurement is provided.
Disclosure of Invention
The invention provides a calibration method for radar sea wave parameter measurement. Radar signal data under different sea conditions are measured through radar signals generated by incidence of radar antennas on sea surfaces and reflection, radar image data and a buoy database are analyzed and processed, a calibration model of a deep convolutional neural network is constructed, a calibration algorithm for measuring sea wave parameters is formed, radar image data is calibrated, estimation errors of a traditional sea wave parameter method are reduced, and accurate measurement of radar sea wave parameters is achieved.
The technical scheme adopted by the invention is as follows:
a radar sea wave parameter measurement calibration method comprises the following specific steps:
step 1, acquiring radar wave surface images
The method comprises the steps of fixing a shore-based radar antenna on the ground, acquiring a radar wave surface image sequence by using a radar, storing according to a radar protocol, and generating a radar wave surface image I (r, theta) under polar coordinates, wherein r is the distance from a sea surface point to the radar antenna, and theta is an azimuth angle. Meanwhile, selecting a distance range d1 d2 region I (r ', theta'), and then adding I (r) under polar coordinates ′ ,θ ′ ) And converting the radar wave surface image area I into Cartesian coordinates to obtain the radar wave surface image area I (x, y). And finally, processing noise on the radar wave surface image, including co-channel interference, target object interference and sea wave texture detection, so as to obtain a radar wave surface image I (x ', y').
Step 2, obtaining the measurement information of the buoy device
The buoy device is required to be placed in the irradiation range of the radar antenna and generates an effective sea wave area, the radar wave surface image and buoy measurement information are synchronously recorded, the time sequence value of the buoy measurement information is counted, and drift data caused by machine faults or measurement errors are removed. The measurement information of the float device includes: effective wave height, wave period, wave direction, one-dimensional wave spectrum, two-dimensional wave direction spectrum and the like.
Step 3, calibrating sea wave information corresponding to the radar wave surface image
Step 3.1 data tagging
Marking the radar wave surface image I (x ', y') obtained in the step 1 and the measurement information of the buoy device obtained in the corresponding step 2, setting the tag information of the radar wave surface image, forming a one-to-many radar wave surface image calibration database, taking the radar wave surface image as the input of a calibration model, and taking the measurement information of the buoy device as the output of the calibration model.
Step 3.2, establishing a neural network calibration model
Carrying out standardization processing on the radar wave surface image, and constructing a deep convolutional neural network calibration model, wherein the method comprises the following steps of: the radar wave surface image I (x ', y') is taken as an input layer of a model, and the intermediate model calculation layer comprises: convolution layer, pooling layer and full-connection layer, draw radar wave surface image characteristic, buoy device measurement information is as the output layer, and output layer buoy measurement information includes: effective wave height, wave period, wave direction, one-dimensional wave spectrum, two-dimensional wave direction spectrum, and the like. And repeatedly training and fitting weight parameters in the middle calculation layer through the information of the input layer and the output layer until the model fitting converges. And establishing a deep convolution neural network calibration model of the relation between the radar wave surface image and buoy measurement information, forming a calibration algorithm of radar wave parameter measurement, and realizing the calibration of the radar wave surface image.
The invention has the beneficial effects that: according to the invention, the radar wave surface image is obtained by adopting the radar, a calibration algorithm for measuring the wave parameters is formed, the radar wave surface image is calibrated, the error of inverting the wave parameters by adopting the radar wave surface image can be reduced, and the accuracy and the reliability of the wave parameter inversion are improved.
Drawings
FIG. 1 is an original radar wavefront image;
FIG. 2 is a selected inversion region;
fig. 3 is co-channel interference;
FIG. 4 is a target disturbance;
FIG. 5 is a rain disturbance;
fig. 6 (a) and 6 (b) are diagrams of the preprocessing of radar wavefront images before and after comparison;
FIG. 7 is a model of a deep convolutional neural network calibration.
Detailed Description
The following describes specific embodiments of the present invention in detail with reference to the technical scheme and the accompanying drawings.
The calibration method for radar sea wave parameter measurement in the embodiment specifically comprises the following steps:
1) Acquiring radar wavefront images
The radar antenna is fixed on a support frame with a height of more than one meter from the ground, the radar antenna is installed to be about thirty meters from the sea level, the sea area needs to be tested in a large sea state, the sea area water depth is about 50 meters, the radar imaging area is about 5 kilometers in the radial direction, and the dat file of the radar wave surface image shown in fig. 1 is acquired. A radar wave surface image I (r, θ) in polar coordinates is generated, r=5000 m, θ being within 0-10 °. And simultaneously selecting 256 x 256 pixel matrixes shown in fig. 2, and processing noise on the radar wave surface image, including co-channel interference, target object interference and wolf texture detection, so as to obtain a radar wave surface image I (x ', y').
2) The method comprises the steps of obtaining measurement information of a buoy device, arranging the buoy at a position about 1000 meters offshore, setting the collection frequency and collection time interval of the buoy, and collecting buoy measurement data in a wireless transmission mode, wherein the measurement information comprises effective wave height, wave period, wave direction, one-dimensional wave spectrum, two-dimensional wave direction spectrum and the like. 3) Calibrating sea wave information corresponding to radar wave surface image
Step 3.1): the noise processing of the 256×256 pixel radar wave surface image obtained in step 1 mainly includes: co-channel interference (as shown in fig. 3), target interference (as shown in fig. 4), rainfall interference (as shown in fig. 5), etc. Fig. 6 (a) and 6 (b) compare the effect diagrams before and after preprocessing the radar wave surface image, and the noise interference is obviously removed. The noise processing can prevent the noise characteristics from being used as wave information characteristics to study when the deep learning model learns the characteristics, and the accuracy of inverting the wave information is affected.
Step 3.2): and (3) marking the buoy measurement information obtained in the step (2) and the radar wave surface image obtained in the step (1) to form a multi-to-one radar wave surface image calibration database.
Step 3.3): carrying out standardization processing on the preprocessed radar wave surface image, and ensuring that the radar wave surface image of the input model is kept at the same scale, wherein the normalization function is as follows:
where x is the gray matrix of the radar wavefront image, μ is the mean of the image gray matrix, σ is the variance of the image gray matrix, g and b are constant coefficients in a nonlinear normalization function, M is the length of the image matrix, and h is the normalization result of the solution.
Step 3.4): a deep convolutional neural network calibration model (shown in fig. 7) is constructed, convolution, pooling, flattening and full connection operations are performed, a dropout layer is introduced, a radar wave surface image I (x ', y') in a radar calibration database is taken as input, buoy measurement information is taken as output, and image characteristics are extracted through convolution operations.
Step 3.5): in model calculation, an Adam optimizer is adopted to find an optimal solution for model convergence, and an MSE loss function is adopted to calculate an error between a predicted value and a target value, wherein the formula is as follows:
the wave information calculated by the f (x) radar wave surface image through the model and y are measurement information of the buoy device, and n is the data size.
Step 6: setting the circulation times until the loss rate MSE is not reduced, stopping training, storing weight parameters, completing training of a deep convolution neural network calibration model of radar wave surface images and buoy measurement information, forming a calibration algorithm for radar wave parameter measurement, calibrating the radar wave surface images, and realizing real-time correction of radar wave parameters.
Claims (1)
1. The radar sea wave parameter measurement calibration method is characterized by comprising the following specific steps:
step 1, acquiring radar wave surface images
Fixing a shore-based radar antenna on the ground, acquiring a radar wave surface image sequence by using a radar, storing according to a radar protocol, and generating a radar wave surface image I (r, theta) under polar coordinates, wherein r is the distance from a sea surface point to the radar antenna, and theta is an azimuth angle; meanwhile, selecting a distance range d1 d2 region I (r ', theta'), and then adding I (r) under polar coordinates ′ ,θ ′ ) Converting the radar wave surface image area I into Cartesian coordinates to obtain a radar wave surface image area I (x, y); finally, processing noise on the radar wave surface image, including co-channel interference, target interference and wave texture detection, so as to obtain a radar wave surface image I (x ', y');
step 2, obtaining the measurement information of the buoy device
The buoy device is placed in the irradiation range of the radar antenna and generates an effective sea wave area, the radar wave surface image and buoy measurement information are synchronously recorded, the time sequence value of the buoy measurement information is counted, and drift data caused by machine faults or measurement errors are removed; the measurement information of the float device includes: effective wave height, wave period, wave direction, one-dimensional wave spectrum and two-dimensional wave direction spectrum;
step 3, calibrating sea wave information corresponding to the radar wave surface image
Step 3.1 data tagging
Marking the radar wave surface image I (x ', y') obtained in the step 1 and the measurement information of the buoy device obtained in the corresponding step 2, setting the tag information of the radar wave surface image, forming a one-to-many radar wave surface image calibration database, taking the radar wave surface image as the input of a calibration model, and taking the measurement information of the buoy device as the output of the calibration model.
Step 3.2, establishing a neural network calibration model
Carrying out standardization processing on the radar wave surface image, and constructing a deep convolutional neural network calibration model, wherein the method comprises the following steps of: the radar wave surface image I (x ', y') is taken as an input layer of a model, and the intermediate model calculation layer comprises: convolution layer, pooling layer and full-connection layer, draw radar wave surface image characteristic, buoy device measurement information is as the output layer, and output layer buoy measurement information includes: effective wave height, wave period, wave direction, one-dimensional wave spectrum, two-dimensional wave direction spectrum and the like; repeatedly training and fitting weight parameters in the middle calculation layer through the information of the input layer and the output layer until model fitting converges; and establishing a deep convolution neural network calibration model of the relation between the radar wave surface image and buoy measurement information, forming a calibration algorithm of radar wave parameter measurement, and realizing the calibration of the radar wave surface image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310277081.9A CN116400307A (en) | 2023-03-21 | 2023-03-21 | Calibration method for radar sea wave parameter measurement |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310277081.9A CN116400307A (en) | 2023-03-21 | 2023-03-21 | Calibration method for radar sea wave parameter measurement |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116400307A true CN116400307A (en) | 2023-07-07 |
Family
ID=87019021
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310277081.9A Pending CN116400307A (en) | 2023-03-21 | 2023-03-21 | Calibration method for radar sea wave parameter measurement |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116400307A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100315284A1 (en) * | 2009-09-02 | 2010-12-16 | Trizna Dennis B | Method and apparatus for coherent marine radar measurements of properties of ocean waves and currents |
US20170315225A1 (en) * | 2016-04-28 | 2017-11-02 | Electronics And Telecommunications Research Institute | Apparatus and method for extracting ocean wave information |
CN109886217A (en) * | 2019-02-26 | 2019-06-14 | 上海海洋大学 | A method of it is high that wave being detected from Nearshore Wave video based on convolutional neural networks |
WO2021191148A1 (en) * | 2020-03-24 | 2021-09-30 | Thales | Method for generating a sea-clutter stream, associated programmable device and computer program |
CN114167423A (en) * | 2021-10-14 | 2022-03-11 | 上海广电通信技术有限公司 | Radar sea wave parameter measuring method based on depth regression network |
CN114296046A (en) * | 2021-12-29 | 2022-04-08 | 哈尔滨工业大学(威海) | HFSWR multi-sea-condition effective wave height extraction method and device based on artificial neural network |
CN114549925A (en) * | 2022-01-18 | 2022-05-27 | 大连理工大学 | Sea wave effective wave height time sequence prediction method based on deep learning |
-
2023
- 2023-03-21 CN CN202310277081.9A patent/CN116400307A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100315284A1 (en) * | 2009-09-02 | 2010-12-16 | Trizna Dennis B | Method and apparatus for coherent marine radar measurements of properties of ocean waves and currents |
US20170315225A1 (en) * | 2016-04-28 | 2017-11-02 | Electronics And Telecommunications Research Institute | Apparatus and method for extracting ocean wave information |
CN109886217A (en) * | 2019-02-26 | 2019-06-14 | 上海海洋大学 | A method of it is high that wave being detected from Nearshore Wave video based on convolutional neural networks |
WO2021191148A1 (en) * | 2020-03-24 | 2021-09-30 | Thales | Method for generating a sea-clutter stream, associated programmable device and computer program |
CN114167423A (en) * | 2021-10-14 | 2022-03-11 | 上海广电通信技术有限公司 | Radar sea wave parameter measuring method based on depth regression network |
CN114296046A (en) * | 2021-12-29 | 2022-04-08 | 哈尔滨工业大学(威海) | HFSWR multi-sea-condition effective wave height extraction method and device based on artificial neural network |
CN114549925A (en) * | 2022-01-18 | 2022-05-27 | 大连理工大学 | Sea wave effective wave height time sequence prediction method based on deep learning |
Non-Patent Citations (1)
Title |
---|
安卓: "基于三维卷积网络的海浪浪高反演算法研究", 《中国优秀硕士学位论文全文数据库 (基础科学辑)》, 15 January 2022 (2022-01-15), pages 010 - 21 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109100717B (en) | Multi-source microwave remote sensing sea surface wind field data fusion method and device | |
CN112965146B (en) | Quantitative precipitation estimation method combining meteorological radar and rainfall barrel observation data | |
CN109212500B (en) | High-precision KA-STAP (K-ary-based adaptive-noise) covariance matrix estimation method based on sparse reconstruction | |
CN111781146B (en) | Wave parameter inversion method using high-resolution satellite optical image | |
CN114200387B (en) | Flight verification and evaluation method for TACAN space signal field pattern | |
CN112013822A (en) | Multispectral remote sensing water depth inversion method based on improved GWR model | |
CN115048952A (en) | GNSS-IR soil humidity inversion method integrating robust estimation and machine learning | |
CN111950438B (en) | Depth learning-based effective wave height inversion method for Tiangong No. two imaging altimeter | |
CN102073037B (en) | Iterative current inversion method based on adaptive threshold selection technique | |
CN115979972B (en) | Real-time monitoring method and system for hyperspectral of crude oil film on sea surface | |
CN116029162B (en) | Flood disaster inundation range monitoring method and system by using satellite-borne GNSS-R data | |
CN116400307A (en) | Calibration method for radar sea wave parameter measurement | |
CN117274831A (en) | Offshore turbid water body depth inversion method based on machine learning and hyperspectral satellite remote sensing image | |
CN116953707A (en) | Tidal level monitoring radar device, and monitoring method and system | |
CN111951204A (en) | Sea surface wind speed inversion method for Tiangong No. two detection data based on deep learning | |
CN111505590A (en) | High-frequency ground wave radar channel calibration method and system | |
CN116500611A (en) | Deep learning-based radar wave surface image sea wave parameter inversion method | |
CN105334506B (en) | A kind of method and apparatus that ocean surface wind speed is estimated based on radar return center line spectral intensity | |
CN114296046B (en) | HFSWR multi-sea-condition effective wave height extraction method and device based on artificial neural network | |
CN112782690B (en) | Offshore non-ocean waveform detection classification method and system for spaceborne radar altimeter | |
CN112733906B (en) | Global high-resolution daily earth surface momentum roughness length estimation method | |
Tian et al. | Quality control of compact high-frequency radar-retrieved wave data | |
CN112880645A (en) | Sea wave surface three-dimensional model construction system and method based on three-dimensional mapping mode | |
Chen et al. | The significant wave height distribution retrieved from marine X-band radar images | |
CN112526464B (en) | Method for estimating azimuth beam width based on multi-channel radar measured data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |