CN117649598A - Offshore culture space distribution information monitoring method and system based on SAR (synthetic aperture radar) images - Google Patents
Offshore culture space distribution information monitoring method and system based on SAR (synthetic aperture radar) images Download PDFInfo
- Publication number
- CN117649598A CN117649598A CN202311379138.2A CN202311379138A CN117649598A CN 117649598 A CN117649598 A CN 117649598A CN 202311379138 A CN202311379138 A CN 202311379138A CN 117649598 A CN117649598 A CN 117649598A
- Authority
- CN
- China
- Prior art keywords
- image
- data set
- sar
- offshore
- principal component
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 21
- 238000007637 random forest analysis Methods 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000009364 mariculture Methods 0.000 claims abstract description 11
- 238000000513 principal component analysis Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 238000009360 aquaculture Methods 0.000 claims description 30
- 244000144974 aquaculture Species 0.000 claims description 30
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 230000003993 interaction Effects 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 239000013589 supplement Substances 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims 1
- 238000000605 extraction Methods 0.000 abstract description 9
- 238000011160 research Methods 0.000 description 6
- 238000009313 farming Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000013439 planning Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 241000208125 Nicotiana Species 0.000 description 1
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses an offshore culture space distribution information monitoring method and system based on SAR images, wherein the method comprises the steps of obtaining a data set, wherein the data set comprises an SAR image data set, a land area mask and a mariculture area sample data set; performing principal component analysis and calculation on the SAR image dataset to obtain a principal component image, and taking a land area mask as a mask of a principal component result non-calculation area; interpreting the principal component images in combination with the marine culture area sample data set to determine a classification data set; classifying the determined data set by using a random forest classifier according to a predefined class label to obtain test data; training a random forest model using the mariculture area sample dataset; and classifying each pixel in the test data by using the trained random forest model to obtain a classified image. The invention can improve the reliability of offshore culture space distribution information extraction and reduce risk and uncertainty.
Description
Technical Field
The invention relates to a remote sensing technology, in particular to an offshore culture space distribution information monitoring method and system based on SAR images.
Background
Offshore culture is an activity of carrying out aquaculture by utilizing ocean resources, and has important significance in the aspects of guaranteeing national grain safety, promoting fishery economic development, maintaining ecological balance and the like. The offshore culture can improve the yield and quality of aquatic products, meet the increasing demands of people for marine products, increase the income and employment opportunities of fishermen, and promote the social and economic development of coastal areas. The offshore culture can also improve the marine ecological environment, increase the diversity of marine organisms and maintain the stability and health of a marine ecological system.
However, offshore farming also faces challenges such as control of the scale of farming, monitoring of the farming environment, assessment of the farming benefits, etc. Excessive offshore culture may cause problems such as marine pollution, disease outbreak, resource competition, biological invasion and the like, and the safety of marine ecology and the sustainable development of fishery are jeopardized. In order to effectively solve these problems, accurate and real-time monitoring of the spatial distribution of offshore farms is required. By monitoring the spatial distribution of the offshore culture, the scale, structure, distribution, change and other conditions of the offshore culture can be known, and data support and decision basis are provided for planning management, environmental protection, benefit evaluation and the like of the offshore culture. However, the cloud and rain weather in offshore areas is frequent, and one disadvantage of conventional optical remote sensing monitoring is variable ocean weather and large image extraction quality. In addition, the single optical image data source can provide limited information, and can not meet the requirements of offshore culture extraction and dynamic monitoring.
The synthetic aperture radar (Synthetic Aperture Radar, SAR) is an active earth observation satellite, has strong penetrating power, can penetrate through atmospheric phenomena such as cloud cover, haze, rain and snow, and can realize high-resolution imaging of the earth surface all the time and all the weather. SAR satellites have unique advantages in disaster monitoring, environmental monitoring, marine monitoring, resource exploration, and the like, particularly in offshore farming. The research based on SAR monitoring of the spatial distribution of the offshore aquaculture has important theoretical significance and practical value, and can provide scientific basis and technical support for planning management, environmental protection, benefit evaluation and the like of the offshore aquaculture.
Currently, the field has some challenges and problems, such as complexity and diversity of SAR images, identification accuracy and stability of offshore culture areas, fusion and analysis of multi-source data, and the like. Thus, there is a need for further research into monitoring the spatial distribution of offshore farms based on SAR, exploring more efficient and intelligent methods and techniques.
The research purpose of the offshore culture space distribution information monitoring based on SAR images is to grasp information such as the position, the area, the number, the type and the like of an offshore culture area and the mutual images of the offshore culture area and the surrounding environment. This information is of great importance for planning, management, evaluation and protection of the offshore aquaculture industry. For example, artificial facilities such as an offshore aquaculture net cage, a fence, a buoy and the like can be identified by SAR images, and images of natural factors such as water quality, water flow, sediment and the like of offshore aquaculture can be detected. The current research is mainly due to meteorological condition limitation of optical remote sensing and microwave remote sensing, and although some progress has been made, some challenges and problems still exist, such as: some difficulties and uncertainties exist in SAR image preprocessing, such as terrain distortion and motion errors in geometric correction, atmospheric effects and scattering mechanisms in radiation correction, signal-to-noise ratio and scattering coefficients in denoising, and the like. There are some difficulties and complexities in the detection of offshore farmed targets, such as confusion and occlusion of the offshore farmed targets with other targets (e.g., vessels, islands, bridges, etc.), variations and inconsistencies of the offshore farmed targets under different wavebands, polarizations, angles of incidence, etc., diversity and heterogeneity of the offshore farmed targets, etc.
In addition, there are some errors and inaccuracy in the extraction of the information of the spatial distribution of the offshore aquaculture, such as blurring and irregularity of the boundaries and shapes of the offshore aquaculture areas, estimation and statistics of the area and number of the offshore aquaculture areas, division and identification of the types of the offshore aquaculture areas, etc
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide an offshore culture space distribution information monitoring method and system based on SAR images, so as to improve the reliability of offshore culture space distribution information extraction and reduce risks and uncertainty.
In order to achieve the above purpose, the technical scheme of the invention is as follows:
in a first aspect, the present invention provides a method for monitoring information of distribution of an offshore aquaculture space based on SAR images, comprising:
acquiring a data set, wherein the data set comprises an SAR image data set, a land area mask and a mariculture area sample data set;
performing principal component analysis and calculation on the SAR image dataset to obtain a principal component image, and taking the land area mask as a mask of a principal component result non-calculation area;
interpreting the principal component images in combination with the marine culture area sample data set to determine a classification data set;
classifying the determined data set by using a random forest classifier according to a predefined class label to obtain test data;
training a random forest model using the mariculture area sample dataset;
and classifying each pixel in the test data by using the trained random forest model to obtain a classified image.
In a second aspect, the present invention provides an offshore aquaculture space distribution information monitoring system based on SAR images, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method as described above when executing the computer program.
In a third aspect, the present invention provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as described above.
Compared with the prior art, the invention has the beneficial effects that:
in order to solve or alleviate the fuzzy and irregular conditions in SAR images, and estimate and count the complicated conditions of the areas and the numbers in SAR images, the offshore culture space distribution information monitoring method based on SAR images, provided by the invention, realizes the information extraction of the marine culture space distribution in an offshore range, solves the problem of data volume redundancy in the traditional time sequence data analysis process, can save more manpower, material resources and time, provides accurate data and scientific management and control for marine culture industry and precise agriculture, and provides data support and decision support for guaranteeing grain safety.
Drawings
Fig. 1 is a flowchart of an offshore aquaculture space distribution information monitoring method based on SAR images provided in embodiment 1 of the present invention;
fig. 2 is a flowchart of performing principal component analysis calculation on a SAR image dataset in embodiment 1 of the present invention;
FIG. 3 is a spatial distribution diagram of the extraction results of a mariculture facility in a partial area of a river city in example 1 of the present invention;
fig. 4 is a schematic diagram of the composition of the system for monitoring the spatial distribution information of the offshore aquaculture based on the SAR image according to embodiment 2 of the present invention.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples.
Example 1:
referring to fig. 1, the method for monitoring the distribution information of the offshore aquaculture space based on the SAR image according to the present embodiment mainly includes the following steps:
s1: a dataset is acquired, the dataset comprising an offshore aquaculture area SAR image dataset, a land area mask, and a mariculture area sample dataset.
Specifically, in this embodiment, the SAR image dataset of the offshore cultivation area is a GRD data source observed by the C-band Level1 interference broad-width (IW) of a 10 m Sentinel-1 satellite with a multi-temporal phase resolution of 2022 years 1-12 months in coastal areas of the jiang city, the repetition period of the data is 12 days, 25 scenes in total, and the data is preprocessed, that is, orbit file correction, thermal noise removal, radiometric calibration, speckle noise filtering (Lee-Sigma) and topography correction, so as to obtain VV/VH backscattering coefficient (dB) data required for research, and in addition, the time sequence data is calculated by a percentile to reject extremum interference greater than 90% and less than 10%. The SAR image dataset of the offshore culture area is obtained in the mode, the problem of data volume redundancy in the traditional time series data analysis process is solved, and more manpower, material resources and time can be saved.
The land area mask is obtained by: and acquiring a land cover data set of the coastal region of the Jiangmen city, and realizing land region masking of the coastal region of the Jiangmen city based on classification result data of the Sentinel-2 high-resolution optical satellite image.
The mariculture area sample data set comprises a field investigation sample data set and a sample data set supplement obtained by combining high-resolution satellite data on the basis of the field investigation sample data set through a man-machine interaction method, so that the comprehensiveness of sample data sources can be ensured. Specifically, the field survey sample dataset is obtained by: and carrying out field investigation on a research area by means of a handheld GNSS, recording main earth surface coverage including water bodies, construction lands, bare lands, forest lands, tobacco fields and other crop earth surface coverage, collecting a large number of field sample points, and photographing and evidence obtaining.
S2, performing principal component analysis and calculation on the SAR image dataset to obtain a principal component image, and using a land area mask as a mask of a principal component result non-calculation area.
In this step, by using the land area mask as the mask of the principal component result non-calculation area, since the non-calculation area is masked, the accuracy of principal component analysis calculation can be ensured and the efficiency of analysis calculation can be improved.
S3, judging the main component image combined with the marine culture area sample data set to determine a classification data set;
because different main components of the main component calculation results of different images contain information with different meanings in different areas, in order to realize that the images contain the most mariculture information, a final classification data set is determined through visual observation and samples.
S4, classifying the determined data set by using a random forest classifier according to a predefined class label to obtain test data;
s5, training a random forest model by utilizing the marine culture area sample data set;
before training the random forest model, parameters of the random forest are set first. The main parameters are: the number of trees (n_detectors), the maximum depth of the tree (max_depth), the maximum number of features considered at each node split (max_features), the minimum number of samples each leaf node contains (min_samples_leaf), etc., and in this embodiment, the default parameters are used for classification.
And S6, classifying each pixel in the test data by using the trained random forest model to obtain a classified image. The classification result of each pixel is generated by voting by a plurality of decision trees, and the category with the highest voting number is the category of the pixel. Thus, the offshore culture space distribution information can be accurately obtained.
Therefore, in order to solve or alleviate the fuzzy and irregular conditions in SAR images and estimate and count the complicated conditions of the areas and the numbers in SAR images, the offshore culture space distribution information monitoring method based on SAR images provided by the invention realizes the information extraction of the marine culture space distribution in the offshore range, solves the problem of data volume redundancy in the traditional time sequence data analysis process, can save more manpower, material resources and time, provides accurate data and scientific management and control for the marine culture industry and precise agriculture, and provides data support and decision support for grain safety.
In a specific embodiment, in the step S2, the performing principal component analysis calculation on the SAR image dataset to obtain a principal component image includes:
s21, carrying out mean and variance standardization on each wave band of the SAR image dataset to enable the wave bands to have the same dimension and statistical characteristics, and obtaining a standardized image;
s22, calculating a covariance matrix or a correlation coefficient matrix between all wave bands of the standardized image to reflect the correlation between all the wave bands;
s23, carrying out eigenvalue decomposition on the covariance matrix or the correlation coefficient matrix to obtain eigenvalues and eigenvectors; the eigenvalue represents the variance of each principal component, and the eigenvector represents the linear relation between each principal component and the original wave band;
s24, arranging the characteristic vectors in descending order according to the magnitudes of the characteristic values, and selecting the characteristic vectors corresponding to the first several largest characteristic values as a coefficient matrix of principal component transformation;
s25, performing linear transformation on the standardized image by using the coefficient matrix to obtain a new image, namely a main component image. The specific calculation code is as follows:
the main component image can be accurately and efficiently obtained by the calculation mode.
In a specific embodiment, the mariculture area sample dataset is according to set 7:3 dividing the training set into a training set verification set; the training set is used for training the random forest model, and the verification set is used for verifying the classification accuracy of the trained random forest model. Specifically, the classification result is evaluated by calculating the form of the confusion matrix, and thereby obtaining the overall classification accuracy OA (OverallAccuracy) and kappa coefficient. The calculation mode is as follows:
wherein r is the number of samples with correct classification, and x ii For the samples with correct classification in the ith class, x is the number of all samples, k is the total classification class number, x ii The number of samples belonging to class i in the field sampling class for classifying the result class i. xi+ and x+i are sums of columns and rows of the confusion matrix, x ii Is the sum of the diagonals of the confusion matrix.
The final classification accuracy and kappa coefficient are both above 90%. The spatial distribution condition of the classification result is shown in fig. 3, so that the method can improve the reliability of offshore culture spatial distribution information extraction and reduce risk and uncertainty.
Example 2:
referring to fig. 4, the system for monitoring the distribution information of the offshore aquaculture space based on the SAR image according to the present embodiment includes a processor 41, a memory 42, and a computer program 43, such as a redundant manipulator motion planning program, stored in the memory 42 and executable on the processor 41. The processor 41 implements the steps of embodiment 1 described above, such as the steps shown in fig. 1, when executing the computer program 43.
Illustratively, the computer program 43 may be partitioned into one or more modules/units that are stored in the memory 42 and executed by the processor 41 to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program 43 in the SAR image based offshore aquaculture spatial distribution information monitoring system.
The processor 41 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (FieldProgrammable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 42 may be an internal storage element of the SAR image-based offshore aquaculture spatial distribution information monitoring system, such as a hard disk or a memory of the SAR image-based offshore aquaculture spatial distribution information monitoring system. The memory 42 may be an external storage device of the SAR image-based offshore aquaculture spatial distribution information monitoring system, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like provided on the SAR image-based offshore aquaculture spatial distribution information monitoring system. Further, the memory 42 may also include both an internal memory unit and an external memory device of the SAR image-based offshore aquaculture spatial distribution information monitoring system. The memory 42 is used for storing the computer program and other programs and data required by the SAR image-based offshore aquaculture spatial distribution information monitoring system. The memory 42 may also be used to temporarily store data that has been output or is to be output.
Example 3:
the present embodiment provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method described in embodiment 1.
The computer readable medium can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer readable medium may even be paper or another suitable medium upon which the program is printed, such as by optically scanning the paper or other medium, then editing, interpreting, or otherwise processing as necessary, and electronically obtaining the program, which is then stored in a computer memory.
The above embodiments are only for illustrating the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement the same, and are not intended to limit the scope of the present invention. All equivalent changes or modifications made in accordance with the essence of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. An offshore culture space distribution information monitoring method based on SAR images is characterized by comprising the following steps:
acquiring a data set, wherein the data set comprises an SAR image data set, a land area mask and a mariculture area sample data set;
performing principal component analysis and calculation on the SAR image dataset to obtain a principal component image, and taking the land area mask as a mask of a principal component result non-calculation area;
interpreting the principal component images in combination with the marine culture area sample data set to determine a classification data set;
classifying the determined data set by using a random forest classifier according to a predefined class label to obtain test data;
training a random forest model using the mariculture area sample dataset;
and classifying each pixel in the test data by using the trained random forest model to obtain a classified image.
2. The method for monitoring the distribution information of the offshore aquaculture space based on the SAR image according to claim 1, wherein the step of performing principal component analysis calculation on the SAR image dataset to obtain a principal component image comprises the steps of:
the average value and the variance of each wave band of the SAR image dataset are standardized, so that the SAR image dataset has the same dimension and statistical characteristics, and a standardized image is obtained;
calculating covariance matrix or correlation coefficient matrix between each wave band of the standardized image to reflect the correlation between each wave band;
performing eigenvalue decomposition on the covariance matrix or the correlation coefficient matrix to obtain eigenvalues and eigenvectors; the eigenvalue represents the variance of each principal component, and the eigenvector represents the linear relation between each principal component and the original wave band;
according to the descending order of the eigenvalues, selecting the eigenvectors corresponding to the first several largest eigenvalues as the coefficient matrix of the principal component transformation;
and linearly transforming the standardized image by using the coefficient matrix to obtain a main component image.
3. The method for monitoring the distribution information of the offshore aquaculture space based on the SAR image as set forth in claim 1, wherein said SAR image dataset is obtained by:
acquiring an SAR image data source, carrying out orbit file correction, thermal noise removal, radiometric calibration, speckle noise filtering and terrain correction on the AR image data source to obtain required VV/VH backscattering coefficient data, and then removing temporary objects and data extremum errors through time sequence to obtain the SAR image data set.
4. The SAR image-based offshore culture space distribution information monitoring method of claim 1, wherein the marine culture area sample dataset is divided into a training set verification set according to a set proportion; the training set is used for training the random forest model, and the verification set is used for verifying the classification accuracy of the trained random forest model.
5. The method for monitoring the distribution information of the offshore aquaculture space based on the SAR image as set forth in claim 4, wherein the calculation mode of the verification set for verifying the classification accuracy of the trained random forest model is as follows:
where OA is the overall classification accuracy, kappa is the coefficient,r is the number of samples with correct classification, and x ii For the samples with correct classification in the ith class, x is the number of all samples, k is the total classification class number, x ii The number of samples belonging to class i in the field sampling class for classifying the result class i, xi+ and x+i being the sum of the columns of the rows of the confusion matrix, x ii Is the sum of the diagonals of the confusion matrix.
6. The method for monitoring the distribution information of the offshore aquaculture space based on the SAR image as set forth in claim 2, wherein the specific calculation mode for performing the linear transformation on the original image by using the coefficient matrix is as follows:
7. the method for monitoring information of offshore aquaculture space distribution based on SAR images according to claim 1, wherein said land area mask is obtained by:
and obtaining a land cover data set, and obtaining a land area mask of the coastal area based on the remote sensing image classification data for the obtained land cover data set.
8. The SAR image-based offshore culture space distribution information monitoring method according to claim 1, wherein the marine culture region sample dataset comprises a field survey sample dataset and a sample dataset supplement obtained by a man-machine interaction method in combination with satellite data on the basis of the field survey sample dataset.
9. An offshore aquaculture spatial distribution information monitoring system based on SAR images, comprising a memory, a processor and a computer program stored in said memory and executable on said processor, wherein said processor, when executing said computer program, implements the steps of the method according to any one of claims 1 to 8.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311379138.2A CN117649598A (en) | 2023-10-23 | 2023-10-23 | Offshore culture space distribution information monitoring method and system based on SAR (synthetic aperture radar) images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311379138.2A CN117649598A (en) | 2023-10-23 | 2023-10-23 | Offshore culture space distribution information monitoring method and system based on SAR (synthetic aperture radar) images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117649598A true CN117649598A (en) | 2024-03-05 |
Family
ID=90045739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311379138.2A Pending CN117649598A (en) | 2023-10-23 | 2023-10-23 | Offshore culture space distribution information monitoring method and system based on SAR (synthetic aperture radar) images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117649598A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673586A (en) * | 2021-08-10 | 2021-11-19 | 北京航天创智科技有限公司 | Mariculture area classification method fusing multi-source high-resolution satellite remote sensing images |
| CN113837123A (en) * | 2021-09-28 | 2021-12-24 | 大连海事大学 | Mid-resolution remote sensing image offshore culture area extraction method based on spectral-spatial information combination |
| CN114494882A (en) * | 2022-02-07 | 2022-05-13 | 中国科学院空天信息创新研究院 | Winter wheat remote sensing identification analysis method and system based on random forest |
| CN116503755A (en) * | 2023-05-19 | 2023-07-28 | 中国科学院空天信息创新研究院 | Automatic recognition analysis method for shoreline remote sensing based on cloud platform and deep learning |
| CN116645603A (en) * | 2023-05-10 | 2023-08-25 | 杭州师范大学 | Soybean planting area identification and area measurement method |
-
2023
- 2023-10-23 CN CN202311379138.2A patent/CN117649598A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673586A (en) * | 2021-08-10 | 2021-11-19 | 北京航天创智科技有限公司 | Mariculture area classification method fusing multi-source high-resolution satellite remote sensing images |
| CN113837123A (en) * | 2021-09-28 | 2021-12-24 | 大连海事大学 | Mid-resolution remote sensing image offshore culture area extraction method based on spectral-spatial information combination |
| CN114494882A (en) * | 2022-02-07 | 2022-05-13 | 中国科学院空天信息创新研究院 | Winter wheat remote sensing identification analysis method and system based on random forest |
| CN116645603A (en) * | 2023-05-10 | 2023-08-25 | 杭州师范大学 | Soybean planting area identification and area measurement method |
| CN116503755A (en) * | 2023-05-19 | 2023-07-28 | 中国科学院空天信息创新研究院 | Automatic recognition analysis method for shoreline remote sensing based on cloud platform and deep learning |
Non-Patent Citations (4)
| Title |
|---|
| COMING: "GEE 学习笔记 20：主成分分析例子(Principal Components Analysis)", pages 1 - 3, Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/148247214> * |
| 岳朝龙 等: "SAS与现代经济统计分析", 28 February 2017, 《中国科学技术大学出版社》, pages: 376 - 389 * |
| 张悦琦 等: "融合特征优选与随机森林算法的GF-6影像东北一季稻遥感提取", 遥感学报, vol. 27, no. 09, 30 September 2023 (2023-09-30), pages 2153 - 2164 * |
| 杨明星 等: "基于Sentinel-1A雷达影像的思茅松林蓄积量估测", 西部林业科学, vol. 48, no. 02, 4 April 2019 (2019-04-04), pages 52 - 58 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rossi et al. | UAV-derived multispectral bathymetry | |
| Liu et al. | Satellite-based monitoring and statistics for raft and cage aquaculture in China’s offshore waters | |
| Canisius et al. | SAR backscatter and InSAR coherence for monitoring wetland extent, flood pulse and vegetation: A study of the Amazon lowland | |
| CN102194127B (en) | Multi-frequency synthetic aperture radar (SAR) data crop sensing classification method | |
| Xu et al. | Comparison and assessment of NDVI time series for seasonal wetland classification | |
| CN116883853B (en) | Crop space-time information remote sensing classification method based on transfer learning | |
| Liu et al. | Estimating maize seedling number with UAV RGB images and advanced image processing methods | |
| CN117437538A (en) | Tropical rainforest ecosystem space-time pattern feature extraction and prediction method | |
| CN117197668A (en) | Crop lodging level prediction method and system based on deep learning | |
| CN117456367A (en) | Crop planting area identification method, device, equipment and storage medium | |
| Zhang et al. | Water quality parameters retrieval of coastal mariculture ponds based on UAV multispectral remote sensing | |
| Yang et al. | High-resolution UAV mapping for investigating eelgrass beds along the west coast of north America | |
| D'iorio et al. | Optimizing remote sensing and GIS tools for mapping and managing the distribution of an invasive mangrove (Rhizophora mangle) on South Molokai, Hawaii | |
| CN117649598A (en) | Offshore culture space distribution information monitoring method and system based on SAR (synthetic aperture radar) images | |
| Yelwa | Broadscale vegetation change assessment across Nigeria from coarse spatial and high temporal resolution AVHRR data | |
| Norris et al. | Effect of textural features for landcover classification of UAV multispectral imagery of a salt marsh restoration site | |
| Kustiyanto | Estimating Aboveground Biomass/Carbon Stock and Carbon Sequestration Using UAV (Unmanned Aerial Vehicle) in Mangrove Forest, Mahakam Delta, Indonesia | |
| Xhimitiku et al. | Anomaly detection in plant growth in a controlled environment using 3D scanning techniques and deep learning | |
| Gnanappazham et al. | Geospatial tools for mapping and monitoring coastal mangroves | |
| Chen et al. | Deep-learning-based marine aquaculture zone extractions from dual-polarimetric SAR imagery | |
| Khallaghi | Posidonia Oceanica habitat mapping in shallow coastal waters along Losinj Island, Croatia using Geoeye-1 multispectral imagery | |
| CN118397481B (en) | Dish-shaped lake change monitoring method based on time sequence remote sensing image | |
| Wilson | Using unmanned aerial systems to classify land cover and assess productivity in forested wetlands in Nova Scotia | |
| Douglas et al. | Mapping Eelgrass Cover and Biomass at Izembek Lagoon, Alaska, Using In-situ Field Data and Sentinel-2 Satellite Imagery | |
| Saint | Multitemporal remote sensing: satellites provide a new tool for Earth resources management |
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 |