CN114255395A - Crop classification method, system, equipment and medium with multi-source remote sensing data fusion - Google Patents
Crop classification method, system, equipment and medium with multi-source remote sensing data fusion Download PDFInfo
- Publication number
- CN114255395A CN114255395A CN202110762786.0A CN202110762786A CN114255395A CN 114255395 A CN114255395 A CN 114255395A CN 202110762786 A CN202110762786 A CN 202110762786A CN 114255395 A CN114255395 A CN 114255395A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- sensing data
- source remote
- data
- crop classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000004927 fusion Effects 0.000 title claims abstract description 36
- 238000013145 classification model Methods 0.000 claims abstract description 27
- 238000009826 distribution Methods 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 238000005457 optimization Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000007637 random forest analysis Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000008520 organization Effects 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 240000008042 Zea mays Species 0.000 claims description 2
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 claims description 2
- 235000002017 Zea mays subsp mays Nutrition 0.000 claims description 2
- 235000005822 corn Nutrition 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 235000013339 cereals Nutrition 0.000 description 3
- 238000002310 reflectometry Methods 0.000 description 3
- 230000002123 temporal effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 208000027066 STING-associated vasculopathy with onset in infancy Diseases 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000011835 investigation Methods 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
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
Abstract
The invention provides a crop classification method, a crop classification system, crop classification equipment and a crop classification medium with multi-source remote sensing data fusion. The method comprises the following steps: preprocessing and gridding subdivision are carried out on multi-source remote sensing data; image space-time optimization is respectively carried out on multi-source remote sensing data in the grid; calculating vegetation index features, and determining features participating in crop classification according to an automatic feature selection result; extracting features from multi-source remote sensing data in the grid, and merging the extracted feature sample data into a feature total set; extracting corresponding features from the feature total set one by one according to the data condition in the grids to form feature subsets, and training a crop classification model based on the feature subsets; inputting the multi-source remote sensing data of the target area into the trained crop classification model to obtain a crop classification result of each grid of the target area output by the crop classification model; and splicing the crop classification results of all grids of the target area to generate a crop distribution map of the target area.
Description
Technical Field
The invention relates to the field of remote sensing application, in particular to a crop classification method, a system, equipment and a medium based on multi-source remote sensing data fusion.
Background
The spatial information and the distribution condition of crops play a vital role in the prediction of grain yield, the establishment of agricultural policies and the development of national economy, and are also important components of national grain safety. The worldwide emphasis on agriculture has made increasing emphasis on the distribution and variety of crops. The remote sensing data has important significance for agricultural monitoring, dependence of people on field investigation is reduced to a great extent, and due to different growth cycles of different crops, growth conditions in a phenological period are different to a certain extent, so that the requirement of people for obtaining spatial information and distribution of the crops can be met to a certain extent by classifying the crops in the phenological period by using the time sequence of the remote sensing images.
However, the existing research on crop classification by remote sensing technology still has the reason of low precision. The method is mainly influenced by the following aspects: (1) the image time sequence is not high, and the spatial resolution and the time resolution of the remote sensing sensor are difficult to be considered due to the design of the image sensor; (2) because the optical sensor of the remote sensing satellite is greatly influenced by weather, high-quality remote sensing data are difficult to obtain continuously in a phenological period; (3) the number of the features extracted from the image has great influence on the precision result, the fewer features have no way of reflecting the difference between different crops, the more features have redundancy, the precision of the crops is reduced, and the type and the number of the features need to be reasonably decided.
Disclosure of Invention
The invention provides a crop classification method, a crop classification system, crop classification equipment and a crop classification medium for multi-source remote sensing data fusion, and aims to solve the problems that (1) an image time sequence is not high, and the spatial resolution and the temporal resolution of a remote sensing sensor are difficult to be considered due to the design of the image sensor; (2) because the optical sensor of the remote sensing satellite is greatly influenced by weather, high-quality remote sensing data are difficult to obtain continuously in a phenological period; (3) the number of the features extracted from the image has great influence on the precision result, the fewer features have no way of reflecting the difference between different crops, the more features have redundancy, the precision of the crops is reduced, and the type and the number of the features need to be reasonably decided. The method utilizes GF-1WFV and Sentinel-2 data to construct a vegetation characteristic time sequence with high time-space resolution, the time sequence covers the growth cycle of crops, and the high space-time characteristics of two images are fully utilized, so that higher precision is achieved through random forest-based characteristic selection and classification; meanwhile, the whole process does not need manual participation and automatic processing, and the automatic classification of crops is facilitated.
Specifically, the embodiment of the invention provides the following technical scheme:
in a first aspect, an embodiment of the present invention provides a crop classification method based on multi-source remote sensing data fusion, including:
collecting multi-source remote sensing data in a phenological period of a preset area, and preprocessing and meshing the multi-source remote sensing data;
performing image space-time optimization on the multi-source remote sensing data in the grid respectively;
calculating vegetation index features of the optimized images, and determining features participating in crop classification according to an automatic feature selection result;
extracting features from the multi-source remote sensing data in the grid, and merging the extracted feature sample data into a feature total set;
extracting corresponding features from the feature total set one by one according to the data condition in the grids to form feature subsets, and training a crop classification model based on the feature subsets;
inputting the multi-source remote sensing data of a target area into a trained crop classification model to obtain a crop classification result of each grid of the target area output by the crop classification model;
and splicing the crop classification results of all grids of the target area to generate a crop distribution map of the target area.
Further, the crop classification method based on multi-source remote sensing data fusion further comprises the following steps:
the preprocessing and gridding subdivision on the remote sensing data comprises the following steps:
performing radiation correction, orthorectification, cloud detection and projection transformation on the multi-source remote sensing data in the predetermined region;
and cutting the image into a grid with a preset size according to the distribution requirement of crops, and performing data organization management based on the grid.
Further, the crop classification method based on multi-source remote sensing data fusion further comprises the following steps:
the image space-time optimization of the remote sensing data in the grid respectively comprises the following steps:
discarding data with cloud coverage exceeding 20% in the grid;
comparing multi-scene data of the same time phase and the same sensor in the grid, and then using data with larger actual coverage area as use data using the time phase;
and for the data with lower actual coverage rate in the grid, splicing the two pieces of scene data of the same sensor in adjacent time phases to generate the data with larger coverage area.
Further, the crop classification method based on multi-source remote sensing data fusion further comprises the following steps:
calculating vegetation index features of the optimized images, and determining the features participating in crop classification according to an automatic feature selection result comprises the following steps:
respectively calculating vegetation characteristic indexes of the multi-source remote sensing data in the grid;
and selecting the features by using a random forest algorithm, and determining the optimal features participating in crop classification.
Further, the crop classification method based on multi-source remote sensing data fusion further comprises the following steps:
the method for extracting the features from the remote sensing data in the grid with the samples and combining the extracted feature sample data into a feature total set comprises the following steps:
filling time series images of the multi-source remote sensing data of the grid containing the samples by adopting a linear interpolation algorithm;
and sequentially extracting the characteristic value of the sample position in the characteristic data of each time phase according to the characteristic data in the grid containing the samples, and combining the extracted characteristic results to generate a characteristic total set.
Further, the crop classification method based on multi-source remote sensing data fusion further comprises the following steps:
the linear interpolation method includes: and solving the average value of each wave band pixel in two similar images before and after the time phase of the image to be interpolated.
Further, the crop classification method based on multi-source remote sensing data fusion further comprises the following steps:
the multi-source remote sensing data comprises GF-1WFV data and Sentinel-2 data.
In a second aspect, an embodiment of the present invention further provides a multi-source remote sensing data fused crop classification system, including:
the system comprises a preprocessing and gridding subdivision module, a data acquisition module, a data processing module and a data processing module, wherein the preprocessing and gridding subdivision module is used for collecting multi-source remote sensing data in a phenological period of a preset area and preprocessing and gridding subdivision is carried out on the multi-source remote sensing data;
the image space-time optimization module is used for respectively carrying out image space-time optimization on the multi-source remote sensing data in the grid;
the crop classification characteristic determination module is used for calculating vegetation index characteristics of the optimized images and determining the characteristics participating in crop classification according to an automatic characteristic selection result;
the characteristic extraction and combination module is used for extracting characteristics from the multi-source remote sensing data in the grid and combining extracted characteristic sample data into a characteristic total set;
the model training module is used for extracting corresponding features from the feature total set one by one according to the data condition in the grids to form a feature subset, and training a crop classification model based on the feature subset;
the result output module is used for inputting the multi-source remote sensing data of the target area into the trained crop classification model to obtain the crop classification result of each grid of the target area output by the crop classification model;
and the distribution map generation module is used for splicing the crop classification results of all grids of the target area to generate a crop distribution map of the target area.
In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the program to implement the steps of the above-mentioned multi-source remote sensing data fused crop classification method
According to the technical scheme, the crop classification method, the crop classification system, the crop classification equipment and the crop classification medium for multi-source remote sensing data fusion provided by the embodiment of the invention aim to solve the problems that (1) the image time sequence is not high, and the spatial resolution and the time resolution of a remote sensing sensor are difficult to be considered due to the design of the image sensor; (2) because the optical sensor of the remote sensing satellite is greatly influenced by weather, high-quality remote sensing data are difficult to obtain continuously in a phenological period; (3) the number of the features extracted from the image has great influence on the precision result, the fewer features have no way of reflecting the difference between different crops, the more features have redundancy, the precision of the crops is reduced, and the type and the number of the features need to be reasonably decided. According to the invention, the data are organized and managed based on grid subdivision, the observation period of a research area is prolonged by reserving high spatial resolution of image data and simultaneously using time sequences of two types of data, the problem of low crop identification precision caused by weather influence is effectively solved, and the real reflectivity of ground objects is well reserved. In addition, the characteristic category and the number of the classification characteristics can be automatically determined, so that the method has the characteristic of accurately and quickly extracting the spatial distribution of crops, and is favorable for agricultural management and planning. The method utilizes GF-1WFV and Sentinel-2 data to construct a vegetation characteristic time sequence with high time-space resolution, the time sequence covers the growth cycle of crops, and the high space-time characteristics of two images are fully utilized, so that higher precision is achieved through random forest-based characteristic selection and classification; meanwhile, the whole process does not need manual participation and automatic processing, and the automatic classification of crops is facilitated.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of a multi-source remote sensing data fused crop classification method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a crop classification device with multi-source remote sensing data fusion according to an embodiment of the present invention; and
fig. 3 is a schematic diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The various terms or phrases used herein have the ordinary meaning as is known to those skilled in the art, and even then, it is intended that the present invention not be limited to the specific terms or phrases set forth herein. To the extent that the terms and phrases referred to herein have a meaning inconsistent with the known meaning, the meaning ascribed to the present invention controls; and have the meaning commonly understood by a person of ordinary skill in the art if not defined herein.
The remote sensing technical means adopted in the prior art has the following problems: (1) the image time sequence is not high, and the spatial resolution and the time resolution of the remote sensing sensor are difficult to be considered due to the design of the image sensor; (2) because the optical sensor of the remote sensing satellite is greatly influenced by weather, high-quality remote sensing data are difficult to obtain continuously in a phenological period; (3) the number of the features extracted from the image has great influence on the precision result, the fewer features have no way of reflecting the difference between different crops, the more features have redundancy, the precision of the crops is reduced, and the type and the number of the features need to be reasonably decided.
In order to solve the above problems, some researchers have proposed that image data with high spatial resolution and data with high temporal resolution are fused by using a spatio-temporal data model method to construct image data satisfying both high spatial resolution and high temporal resolution, but data generated by a model is greatly affected by spatial heterogeneity, the simulated reflectivity is far away from the actual ground object, and errors generated in the fusion process are further transmitted to a time sequence for generating images.
In view of the above, it is desirable to provide a solution that can realize accurate crop extraction and provide a scientific decision basis for agricultural decision-making departments.
In view of the above, in a first aspect, an embodiment of the present invention provides a method for classifying crops through multi-source remote sensing data fusion, which organizes and manages data based on grid subdivision, and can improve an observation period for a research area by retaining high spatial resolution of image data and using time sequences of two types of data simultaneously, thereby effectively solving a problem of low crop identification precision caused by weather influence, and well retaining real reflectivity of ground objects. In addition, the characteristic category and the number of the classification characteristics can be automatically determined, so that the method has the characteristic of accurately and quickly extracting the spatial distribution of crops, and is favorable for agricultural management and planning. The method utilizes GF-1WFV and Sentinel-2 data to construct a vegetation characteristic time sequence with high time-space resolution, the time sequence covers the growth cycle of crops, and the high space-time characteristics of two images are fully utilized, so that higher precision is achieved through random forest-based characteristic selection and classification; meanwhile, the whole process does not need manual participation and automatic processing, and the automatic classification of crops is facilitated.
The method selects Heilongjiang province as a research area, the terrain of the area is mainly plain and mountain land, the cultivated land occupies more than 30% of the total area, the area belongs to temperate continental monsoon climate, and the method is one of the main grain producing areas in China and is used for producing crops such as rice, corn, wheat and the like. In addition, the data time is acquired from 5 months to 9 months in 2017 in consideration of the crop phenological period in the region.
The multi-source remote sensing data fused crop classification method of the invention is described below with reference to fig. 1.
Fig. 1 is a flowchart of a multi-source remote sensing data fused crop classification method according to an embodiment of the present invention.
In this embodiment, it should be noted that the crop classification method based on multi-source remote sensing data fusion may include the following steps:
s1: collecting multi-source remote sensing data in a phenological period of a preset area, and preprocessing and meshing the multi-source remote sensing data;
s2: image space-time optimization is respectively carried out on multi-source remote sensing data in the grid;
s3: calculating vegetation index features of the optimized images, and determining features participating in crop classification according to an automatic feature selection result;
s4: extracting features from multi-source remote sensing data in the grid, and merging the extracted feature sample data into a feature total set;
s5: extracting corresponding features from the feature total set one by one according to the data condition in the grids to form feature subsets, and training a crop classification model based on the feature subsets;
s6: inputting the multi-source remote sensing data of the target area into the trained crop classification model to obtain a crop classification result of each grid of the target area output by the crop classification model;
s7: and splicing the crop classification results of all grids of the target area to generate a crop distribution map of the target area.
In this embodiment, it should be noted that the crop classification method based on multi-source remote sensing data fusion may further include: the preprocessing and gridding subdivision S1 of the remote sensing data further comprises: carrying out radiation correction, orthographic correction, cloud detection and projection transformation on multi-source remote sensing data in a predetermined area; and cutting the image into a grid with a preset size according to the distribution requirement of crops, and performing data organization management based on the grid.
Specifically, the predetermined size may include, but is not limited to, 10 KM. It is obvious that those skilled in the art can set different predetermined sizes according to actual working requirements without departing from the spirit and scope of the present invention.
In this embodiment, it should be noted that the crop classification method based on multi-source remote sensing data fusion may further include: performing image spatiotemporal optimization on the remote sensing data in the grid respectively S2 further comprises: discarding data with cloud coverage rate exceeding 20% in the grid; comparing multi-scene data of the same time phase and the same sensor in the grid, and then using the data with larger actual coverage area as the use data of the use time phase; and for the data with lower actual coverage rate in the grid, splicing the two pieces of scene data of the same sensor in adjacent time phases to generate the data with larger coverage area.
In this embodiment, it should be noted that the crop classification method based on multi-source remote sensing data fusion may further include: calculating vegetation index features for the preferred images, and determining features involved in crop classification according to the automated feature selection result S3 further comprises: respectively calculating vegetation characteristic indexes of multi-source remote sensing data in the grid; and selecting the features by using a random forest algorithm, and determining the optimal features participating in crop classification.
Specifically, the vegetation characteristic index is, in addition to red, green, blue and near infrared, GNDVI, NDWI, EVI, DVI, TVI, RVI, SAVI and NDVI, which are expressed by the following specific formulas:
DVI＝ρNIR- ρRed (3)
where ρ isRed,ρGreen,ρBlue,ρNRIRespectively representing the reflection values of a red wave band, a green wave band, a blue wave band and a near infrared wave band; and L represents that soil is sparsely regulated and has a value range of 0-1.
Specifically, features are selected using a random forest algorithm, and the optimal features participating in crop classification are determined to ensure that the acquired features can be effectively applied to crop extraction.
More specifically, each decision number t (specifically, t is a positive integer) is constructed by training a subset of data, the data that is not selected is the out-of-bag data, the error occurring in the out-of-bag data is divided into the out-of-bag error errOOB, on the basis of which random noise is added to the features in the out-of-bag data, and the out-of-bag error errOOB is re-evaluated′The importance of each feature can be calculated by interpolation of two errors, in order to guarantee the accuracy of the evaluation, the ordering of all features is ordered by the average importance of 50 rounds, unimportant features are removed from the minimum value according to the importance of the classification tree (CART), and finally m features are reserved, specifically, m is a positive integer. The feature importance calculation formula is as follows:
wherein, XiDenotes the ith feature, ntreeRepresenting the number of trees in the random forest.
Assuming that all features result in the smallest out-of-bag error, a threshold may be set to reject features with a higher error rate, which is set to the mean plus the standard deviation of all out-of-bag errors. The evaluation method is to sort the importance of the features in a descending order, establish a random forest from the most important feature to the last feature, when the out-of-bag error reaches the threshold, select the feature with the lowest error rate, and reserve k features, specifically, k is a positive integer.
The high correlation feature is mainly by looking at whether the out-of-bag error is meaningfully reduced. The threshold used to evaluate the significance of the reduction is determined by the average out-of-bag error of the features rejected from the previous step. The calculation formula is as follows:
if the average value of the error outside the bag of the former characteristic and the average value of the error outside the bag of the latter characteristic are larger than the threshold value, the error outside the bag is kept.
In this embodiment, it should be noted that the crop classification method based on multi-source remote sensing data fusion may further include: extracting features from the remote sensing data in the grid with the samples, and merging the extracted feature sample data into a feature total set S4 further comprises: the time sequence images of the multi-source remote sensing data of all grids containing the samples are filled up by adopting a linear interpolation algorithm; and aiming at the grids containing the samples, sequentially extracting the characteristic values of the sample positions in the characteristic data of each time phase according to the characteristic data in the grids, and combining the extracted characteristic results to generate a characteristic total set.
Specifically, all grids containing samples are found, time sequences of GF-1WFV and Sentinel-2 data are extracted, a union is obtained, a complete time sequence of a research area is obtained, and then time sequence images of GF-1WFV and Sentinel-2 of all grids containing samples are filled by adopting a linear interpolation algorithm.
In particular, the feature collection is used for subsequent classification for each mesh.
In this embodiment, it should be noted that the crop classification method based on multi-source remote sensing data fusion may further include: the linear interpolation method is to obtain the average value of each wave band pixel in two similar images before and after the time phase of the image to be interpolated.
Further, the splicing of the crop classification results of all grids in the target area to generate a crop distribution map S5 in the target area specifically includes: according to the actual time phase containing GF-1WFV and Sentinel-2 data in each grid, sample characteristic values of the corresponding time phase in the sample characteristic total set extraction form a characteristic subset of the grid, a random forest model is used for training and predicting the grid, crop classification results in each grid are obtained, all the results are spliced, and a crop distribution map is generated.
In this embodiment, it should be noted that the crop classification method based on multi-source remote sensing data fusion may further include: the multi-source remote sensing data comprises GF-1WFV data and Sentinel-2 data.
Based on the same inventive concept, on the other hand, an embodiment of the invention provides a crop classification system with multi-source remote sensing data fusion.
The multi-source remote sensing data fused crop classification system provided by the invention is described below with reference to fig. 2, and the multi-source remote sensing data fused crop classification system described below and the multi-source remote sensing data fused crop classification method described above can be referred to correspondingly.
Fig. 2 is a schematic structural diagram of a crop classification system with multi-source remote sensing data fusion according to an embodiment of the present invention.
In this embodiment, it should be noted that the crop classification system 1 with multi-source remote sensing data fused includes: the preprocessing and gridding subdivision module 10 is used for collecting multi-source remote sensing data in a phenological period of a preset area and preprocessing and gridding subdivision is carried out on the multi-source remote sensing data; the image space-time optimization module 20 is used for respectively performing image space-time optimization on the multi-source remote sensing data in the grid; a crop classification feature determination module 30, configured to calculate a vegetation index feature for the optimized image, and determine features participating in crop classification according to an automated feature selection result; the feature extraction and combination module 40 is used for extracting features from the multi-source remote sensing data in the grid and combining the extracted feature sample data into a feature total set; the model training module 50 is used for extracting corresponding features from the feature total set one by one according to the data condition in the grids to form feature subsets, and training a crop classification model based on the feature subsets; a result output module 60, configured to input the multi-source remote sensing data of the target area into the trained crop classification model, and obtain a crop classification result of each grid of the target area output by the crop classification model; and a distribution diagram generating module 70, configured to splice the crop classification results of all grids in the target area, so as to generate a crop distribution diagram in the target area.
The crop classification system with multi-source remote sensing data fusion provided by the embodiment of the invention can be used for executing the crop classification method with multi-source remote sensing data fusion described in the embodiment, and the working principle and the beneficial effect are similar, so detailed description is omitted here, and specific contents can be referred to the introduction of the embodiment.
In this embodiment, it should be noted that each module in the system according to the embodiment of the present invention may be integrated into a whole or may be separately deployed. The modules can be combined into one module, and can also be further split into a plurality of sub-modules.
In another aspect, a further embodiment of the present invention provides an electronic device based on the same inventive concept.
Fig. 3 is a schematic diagram of an electronic device according to an embodiment of the invention.
In this embodiment, it should be noted that the electronic device may include: a processor (processor)310, a communication Interface (communication Interface)320, a memory (memory)330 and a communication bus 340, wherein the processor 310, the communication Interface 320 and the memory 330 communicate with each other via the communication bus 340. Processor 310 may invoke logic instructions in memory 330 to perform a method for crop classification for multi-source remote sensing data fusion, the method comprising: collecting multi-source remote sensing data in a phenological period of a preset area, and preprocessing and meshing the multi-source remote sensing data; image space-time optimization is respectively carried out on multi-source remote sensing data in the grid; calculating vegetation index features of the optimized images, and determining features participating in crop classification according to an automatic feature selection result; extracting features from multi-source remote sensing data in the grid, and merging the extracted feature sample data into a feature total set; extracting corresponding features from the feature total set one by one according to the data condition in the grids to form feature subsets, and training a crop classification model based on the feature subsets; inputting the multi-source remote sensing data of the target area into the trained crop classification model to obtain a crop classification result of each grid of the target area output by the crop classification model; and splicing the crop classification results of all grids of the target area to generate a crop distribution map of the target area.
In addition, the logic instructions in the memory 330 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program that when executed by a processor performs a method of crop classification for multi-source remote sensing data fusion, the method comprising: collecting multi-source remote sensing data in a phenological period of a preset area, and preprocessing and meshing the multi-source remote sensing data; image space-time optimization is respectively carried out on multi-source remote sensing data in the grid; calculating vegetation index features of the optimized images, and determining features participating in crop classification according to an automatic feature selection result; extracting features from multi-source remote sensing data in the grid, and merging the extracted feature sample data into a feature total set; extracting corresponding features from the feature total set one by one according to the data condition in the grids to form feature subsets, and training a crop classification model based on the feature subsets; inputting the multi-source remote sensing data of the target area into the trained crop classification model to obtain a crop classification result of each grid of the target area output by the crop classification model; and splicing the crop classification results of all grids of the target area to generate a crop distribution map of the target area.
The above-described system embodiments are merely illustrative, wherein the modules described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Moreover, in the present invention, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Furthermore, in the present disclosure, reference to the description of the terms "embodiment," "this embodiment," "yet another embodiment," or the like, means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A crop classification method based on multi-source remote sensing data fusion is characterized by comprising the following steps:
collecting multi-source remote sensing data in a phenological period of a preset area, and preprocessing and meshing the multi-source remote sensing data;
performing image space-time optimization on the multi-source remote sensing data in the grid respectively;
calculating vegetation index features of the optimized images, and determining features participating in crop classification according to an automatic feature selection result;
extracting features from the multi-source remote sensing data in the grid, and merging the extracted feature sample data into a feature total set;
extracting corresponding features from the feature total set one by one according to the data condition in the grids to form feature subsets, and training a crop classification model based on the feature subsets;
inputting the multi-source remote sensing data of a target area into a trained crop classification model to obtain a crop classification result of each grid of the target area output by the crop classification model;
and splicing the crop classification results of all grids of the target area to generate a crop distribution map of the target area.
2. The method for crop classification based on multi-source remote sensing data fusion of claim 1, wherein the preprocessing and gridding subdivision of the remote sensing data comprises:
performing radiation correction, orthorectification, cloud detection and projection transformation on the multi-source remote sensing data in the predetermined region;
and cutting the image into a grid with a preset size according to the distribution requirement of crops, and performing data organization management based on the grid.
3. The crop classification method based on multi-source remote sensing data fusion of claim 1, wherein the image space-time optimization of the remote sensing data in the grid respectively comprises:
discarding data with cloud coverage exceeding 20% in the grid;
comparing multi-scene data of the same time phase and the same sensor in the grid, and then using data with larger actual coverage area as use data using the time phase;
and for the data with lower actual coverage rate in the grid, splicing the two pieces of scene data of the same sensor in adjacent time phases to generate the data with larger coverage area.
4. The crop classification method based on multi-source remote sensing data fusion of claim 1, wherein calculating vegetation index features for the preferred images and determining the features participating in crop classification according to automated feature selection results comprises:
respectively calculating vegetation characteristic indexes of the multi-source remote sensing data in the grid;
and selecting the features by using a random forest algorithm, and determining the optimal features participating in crop classification.
5. The crop classification method based on multi-source remote sensing data fusion of claim 1, wherein the extracting features from the remote sensing data in a grid with samples and merging the extracted feature sample data into a feature total set comprises:
filling time series images of the multi-source remote sensing data of the grid containing the samples by adopting a linear interpolation algorithm;
and sequentially extracting the characteristic value of the sample position in the characteristic data of each time phase according to the characteristic data in the grid containing the samples, and combining the extracted characteristic results to generate a characteristic total set.
6. The crop classification method based on multi-source remote sensing data fusion of claim 5, wherein the linear interpolation method comprises: and solving the average value of each wave band pixel in two similar images before and after the time phase of the image to be interpolated.
7. The crop classification method based on multi-source remote sensing data fusion of any one of claims 1-6, wherein the multi-source remote sensing data comprises GF-1WFV data and Sentinel-2 data.
8. A crop classification system with multi-source remote sensing data fusion is characterized in that,
the system comprises a preprocessing and gridding subdivision module, a data acquisition module, a data processing module and a data processing module, wherein the preprocessing and gridding subdivision module is used for collecting multi-source remote sensing data in a phenological period of a preset area and preprocessing and gridding subdivision is carried out on the multi-source remote sensing data;
the image space-time optimization module is used for respectively carrying out image space-time optimization on the multi-source remote sensing data in the grid;
the crop classification characteristic determination module is used for calculating vegetation index characteristics of the optimized images and determining the characteristics participating in crop classification according to an automatic characteristic selection result;
the characteristic extraction and combination module is used for extracting characteristics from the multi-source remote sensing data in the grid and combining extracted characteristic sample data into a characteristic total set;
the model training module is used for extracting corresponding features from the feature total set one by one according to the data condition in the grids to form a feature subset, and training a crop classification model based on the feature subset;
the result output module is used for inputting the multi-source remote sensing data of the target area into the trained crop classification model to obtain the crop classification result of each grid of the target area output by the crop classification model;
and the distribution map generation module is used for splicing the crop classification results of all grids of the target area to generate a crop distribution map of the target area.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the multi-source remote sensing data fused crop classification method according to any one of claims 1-7.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the electrical impedance imaging method of corn moisture distribution of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110762786.0A CN114255395A (en) | 2021-07-06 | 2021-07-06 | Crop classification method, system, equipment and medium with multi-source remote sensing data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110762786.0A CN114255395A (en) | 2021-07-06 | 2021-07-06 | Crop classification method, system, equipment and medium with multi-source remote sensing data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114255395A true CN114255395A (en) | 2022-03-29 |
Family
ID=80791148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110762786.0A Pending CN114255395A (en) | 2021-07-06 | 2021-07-06 | Crop classification method, system, equipment and medium with multi-source remote sensing data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114255395A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116524225A (en) * | 2022-12-23 | 2023-08-01 | 山东大学 | Crop classification method and system based on multi-source remote sensing data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678281A (en) * | 2016-02-04 | 2016-06-15 | 中国农业科学院农业资源与农业区划研究所 | Plastic film mulching farmland remote sensing monitoring method based on spectrum and texture features |
| CN110163303A (en) * | 2019-06-03 | 2019-08-23 | 中国农业大学 | A kind of remote sensing image parallel sorting method and system based on grid |
| CN112183209A (en) * | 2020-08-27 | 2021-01-05 | 中国农业大学 | Regional crop classification method and system based on multi-dimensional feature fusion |
| CN112304902A (en) * | 2020-11-02 | 2021-02-02 | 航天宏图信息技术股份有限公司 | Real-time monitoring method and device for crop phenology |
-
2021
- 2021-07-06 CN CN202110762786.0A patent/CN114255395A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678281A (en) * | 2016-02-04 | 2016-06-15 | 中国农业科学院农业资源与农业区划研究所 | Plastic film mulching farmland remote sensing monitoring method based on spectrum and texture features |
| CN110163303A (en) * | 2019-06-03 | 2019-08-23 | 中国农业大学 | A kind of remote sensing image parallel sorting method and system based on grid |
| CN112183209A (en) * | 2020-08-27 | 2021-01-05 | 中国农业大学 | Regional crop classification method and system based on multi-dimensional feature fusion |
| CN112304902A (en) * | 2020-11-02 | 2021-02-02 | 航天宏图信息技术股份有限公司 | Real-time monitoring method and device for crop phenology |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116524225A (en) * | 2022-12-23 | 2023-08-01 | 山东大学 | Crop classification method and system based on multi-source remote sensing data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10838936B2 (en) | Computer-implemented methods, computer readable medium and systems for generating an orchard data model for a precision agriculture platform | |
| US11100264B2 (en) | Computer-implemented methods, computer readable medium and systems for a precision agriculture platform that integrates a satellite date model and an orchard data model | |
| US10748081B2 (en) | Computer-implemented methods, computer readable medium and systems for a precision agriculture platform that identifies generic anomalies in crops | |
| US10395355B2 (en) | Computer-implemented methods, computer readable medium and systems for a precision agriculture platform | |
| US20180330487A1 (en) | Computer-implemented methods, computer readable medium and systems for a precision agriculture platform with a satellite data model | |
| Gao et al. | Object-based classification with features extracted by a semi-automatic feature extraction algorithm–SEaTH | |
| Röder et al. | Application of optical unmanned aerial vehicle-based imagery for the inventory of natural regeneration and standing deadwood in post-disturbed spruce forests | |
| US10943173B2 (en) | Computer-implemented methods, computer readable medium and systems for generating a satellite data model for a precision agriculture platform | |
| CN114926748A (en) | Soybean remote sensing identification method combining Sentinel-1/2 microwave and optical multispectral images | |
| Račič et al. | Application of temporal convolutional neural network for the classification of crops on sentinel-2 time series | |
| CN116543316B (en) | Method for identifying turf in paddy field by utilizing multi-time-phase high-resolution satellite image | |
| CN112364681A (en) | Vegetation coverage estimation method and device based on two-dimensional table | |
| Shahrin et al. | Agricultural analysis and crop yield prediction of habiganj using multispectral bands of satellite imagery with machine learning | |
| Gao et al. | LAI estimation across California vineyards using sUAS multi-seasonal multi-spectral, thermal, and elevation information and machine learning | |
| CN114255395A (en) | Crop classification method, system, equipment and medium with multi-source remote sensing data fusion | |
| Liu et al. | Evaluating how lodging affects maize yield estimation based on UAV observations | |
| Tesfamichael et al. | Retrieval of narrow-range LAI of at multiple lidar point densities: Application on Eucalyptus grandis plantation | |
| CN114782835A (en) | Crop lodging area proportion detection method and device | |
| CN115526927A (en) | Rice planting method integrating phenological data and remote sensing big data and area estimation method thereof | |
| CN115496999A (en) | Method and device for estimating field straw yield | |
| CN114611699A (en) | Soil moisture downscaling method and device, electronic equipment and storage medium | |
| Pluto-Kossakowska et al. | Automatic detection of dominant crop types in Poland based on satellite images | |
| van Niekerk et al. | THE APPLICATION OF NATIONAL SCALE REMOTELY SENSED EVAPOTRANSPIRATION (ET) ESTIMATES TO QUANTIFY WATER USE AND DIFFERENCES BETWEEN PLANTATIONS IN COMMERCIAL FORESTRY REGIONS OF SOUTH AFRICA | |
| Huong et al. | Estimating tropical forest stand volume using Sentinel-2A imagery | |
| CN115272860B (en) | Determination method and system for rice planting area, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |