CN116524225A - Crop classification method and system based on multi-source remote sensing data - Google Patents
Crop classification method and system based on multi-source remote sensing data Download PDFInfo
- Publication number
- CN116524225A CN116524225A CN202211663023.1A CN202211663023A CN116524225A CN 116524225 A CN116524225 A CN 116524225A CN 202211663023 A CN202211663023 A CN 202211663023A CN 116524225 A CN116524225 A CN 116524225A
- Authority
- CN
- China
- Prior art keywords
- crop
- remote sensing
- classification
- sensing data
- source remote
- 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 45
- 238000011160 research Methods 0.000 claims abstract description 16
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 238000003306 harvesting Methods 0.000 claims abstract description 8
- 238000004590 computer program Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000005855 radiation Effects 0.000 claims description 4
- 238000003967 crop rotation Methods 0.000 abstract description 8
- 240000008042 Zea mays Species 0.000 description 29
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 29
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 29
- 235000005822 corn Nutrition 0.000 description 29
- 241000209140 Triticum Species 0.000 description 17
- 235000021307 Triticum Nutrition 0.000 description 17
- 244000105624 Arachis hypogaea Species 0.000 description 12
- 235000020232 peanut Nutrition 0.000 description 12
- 235000017060 Arachis glabrata Nutrition 0.000 description 9
- 235000010777 Arachis hypogaea Nutrition 0.000 description 9
- 235000018262 Arachis monticola Nutrition 0.000 description 9
- 208000003643 Callosities Diseases 0.000 description 6
- 206010020649 Hyperkeratosis Diseases 0.000 description 6
- 238000011835 investigation Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000035558 fertility Effects 0.000 description 3
- 230000006651 lactation Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000007637 random forest analysis Methods 0.000 description 3
- 238000009331 sowing Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 235000013339 cereals Nutrition 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- 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
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- 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
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Animal Husbandry (AREA)
- Economics (AREA)
- Agronomy & Crop Science (AREA)
- Remote Sensing (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Astronomy & Astrophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of crop classification, and provides a crop classification method and system based on multi-source remote sensing data, wherein the method comprises the following steps: acquiring multisource remote sensing data in a physical period of a research area; based on the multi-source remote sensing data, calculating optimal indexes of crop classification at a plurality of time points in a climatic period; extracting a woodland mask based on crop classification optimal indexes of harvest time of all crops; determining two key time points for each crop based on the climatic period of each crop; for each crop, based on the woodland mask, the crop extraction is performed in combination with the difference in crop classification optimum index for the two key time points. The influence of different data sources on the crop classification precision is eliminated, and the classification precision of large-range crop rotation is improved.
Description
Technical Field
The invention belongs to the technical field of crop classification, and particularly relates to a crop classification method and system based on multi-source remote sensing data.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The spatial distribution information of crops plays a vital role in grain yield prediction, national agricultural policy formulation and economic development. The worldwide emphasis on agriculture has led to an increasing emphasis on the distribution and variation of crops. The remote sensing data has important significance for agricultural monitoring, so that the dependence of people on field investigation is greatly reduced, the field investigation method is high in cost and can cause crop damage to a certain extent, and the growth conditions in the climatic period are also different to a certain extent due to different growth periods of different crops, so that the requirements of people on acquisition of crop space information and distribution can be met to a certain extent by classifying the crops in the climatic period through the time sequence of the remote sensing image. Remote sensing provides a investigation means with high timeliness, high precision and no damage.
In recent years, many scholars use optical remote sensing images to conduct classification, identification and research on various crops in different time-space scales and develop the crops to be mature. However, coastal cities are often subjected to weather effects such as clouds and fog in the critical weather period of crops, so that the application of the coastal cities in practical research is greatly limited due to the fact that some image data are lost, and therefore the problem of data loss caused by weather and other reasons can be solved by utilizing multi-source data. The extraction of the frame structure of the crops mainly utilizes the spectrum, time and space characteristics of the crops.
At present, the research on crop classification by using remote sensing technology means mainly has the following main problems:
1. most researches on crop classification firstly extract cultivated land, but if the cultivated land is extracted inaccurately, the subsequent precision problem is seriously influenced, and the mountain land block distribution is smaller than the scattered planting area, so that the problems of too small pixels, larger errors and the like can occur on the images;
2. the number of the features extracted from the images has great influence on the precision result, fewer features can not reflect the difference between different crops, redundancy occurs if more features are available, the precision of the crops is reduced, and reasonable decision is needed for the category and the number of the features;
3. the defects that the classification precision of the traditional single remote sensing image is low, the crop characteristics are not obvious, the classification precision of different data sources is different and the like are overcome;
4. when the key-period remote sensing data is generally utilized for classification, the classification accuracy difference is larger due to the fact that different resolutions of data sources are selected, so that the important problems of inconsistent resolutions, data loss and the like can be effectively solved by establishing a classification method based on multi-source remote sensing data;
5. the traditional time sequence classification is easier to distinguish mutant crops, but the crop growth is usually gradual, and particularly, for crop rotation, the traditional method has low universality and takes a long time, namely, the traditional time sequence classification method has good identification capability on the mutant development of crops, but the crop growth is gradual, and the small change of the crops needs to be quantified.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a crop classification method and a crop classification system based on multi-source remote sensing data, which are used for rapidly classifying based on the difference value of the weather information of the multi-source remote sensing data, can quantify the difference information of different crop types, eliminate the influence of different data sources on the crop classification precision, and further improve the classification accuracy of large-scale crop rotation.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a first aspect of the present invention provides a crop classification method based on multisource remote sensing data, comprising:
acquiring multisource remote sensing data in a physical period of a research area;
based on the multi-source remote sensing data, calculating optimal indexes of crop classification at a plurality of time points in a climatic period;
extracting a woodland mask based on crop classification optimal indexes of harvest time of all crops;
determining two key time points for each crop based on the climatic period of each crop;
for each crop, based on the woodland mask, the crop extraction is performed in combination with the difference in crop classification optimum index for the two key time points.
Further, after radiation correction, orthographic correction, cloud removal and image stitching are sequentially carried out on the multi-source remote sensing data, crop classification optimal indexes of a plurality of time points in a physical weather period are calculated.
Further, the crop classification optimal index is selected from NDVI, EVI and RVI according to characteristic index timing diagrams of a plurality of crops.
Further, for a certain crop, after the forest land mask is adopted to process the multi-source remote sensing data, if the difference value of the crop classification optimal indexes of two key time points is larger than a threshold value, the crop is extracted from the multi-source remote sensing data.
Further, the threshold value corresponding to a certain crop is the average value of the differences of the crop classification optimal indexes of two key time points of the training samples corresponding to the crop in the training set.
Further, the multi-source remote sensing data comprises Sentille-2A data or Landsat8 remote sensing image data.
A second aspect of the present invention provides a crop classification system based on multi-source remote sensing data, comprising:
a data acquisition module configured to: acquiring multisource remote sensing data in a physical period of a research area;
a classification index calculation module configured to: based on the multi-source remote sensing data, calculating optimal indexes of crop classification at a plurality of time points in a climatic period;
a mask extraction module configured to: extracting a woodland mask based on crop classification optimal indexes of harvest time of all crops;
a point in time determination module configured to: determining two key time points for each crop based on the climatic period of each crop;
a classification module configured to: for each crop, based on the woodland mask, the crop extraction is performed in combination with the difference in crop classification optimum index for the two key time points.
A third aspect of the invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a method of classifying crops based on multi-source remote sensing data as described above.
A fourth aspect of the invention provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in a method of classifying crops based on multi-source telemetry data as described above when the program is executed.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a crop classification method based on multi-source remote sensing data, which is used for quickly classifying based on the difference value of the weather information of the multi-source remote sensing data, can quantify the difference information of different crop types, and eliminates the influence of different data sources on the crop classification precision, thereby improving the classification accuracy of large-scale crop rotation.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flow chart of a crop classification method based on multi-source remote sensing data according to a first embodiment of the invention;
FIG. 2 is a timing diagram of an enhanced vegetation index EVI according to a first embodiment of the present invention;
FIG. 3 is a timing diagram of a normalized vegetation index NDVI according to a first embodiment of the present invention;
FIG. 4 is a timing chart of a ratio vegetation index according to a first embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
Example 1
The embodiment provides a crop classification method based on multi-source remote sensing data, which constructs a high-frequency vegetation characteristic time sequence based on the multi-source remote sensing data, determines different crop classification thresholds by using vegetation index mean value difference values, and improves the classification precision of large-range crop rotation.
Because Sentille-2A is greatly affected by weather, a vegetation characteristic sequence with high spatial resolution is constructed by combining two remote sensing images by utilizing the characteristic of Landsat8 with high temporal resolution. In this example, a coastal region was used as a study area, and according to the field investigation data, the physical periods of different crops (such as table 1, table 2, table 3 and table 4) were investigated by dividing the field investigation data into a training sample 407 and a verification sample 425, and according to the physical periods, images of 3.24, 4.18, 5.08, 5.22, 6.23, 7.25, 8.11, 9.30 and 10.25 days 9 were selected.
The two data of Sentille-2A and Landsat8 are not overlapped, and are complementary, for example, the rainfall of 6.7.8 months is large, and the cloud content of the data of the Sentinel satellite in the passing day is large and can not be used, so Landsat data can be used as a replacement.
TABLE 1 winter wheat climatic period
Table 2, spring corn waiting period (ten days)
| Period of fertility | Date of day |
| Sowing time | 4 months below-5 above |
| Seedling stage | In 5 months |
| Period of jointing | On-7 in 6 months |
| Male stage of drawing | On-8 in 7 months |
| Period of lactation | On-9 in 8 months |
| Maturity stage | In 9 months-9% |
Table 3, summer corn waiting period (ten days)
| Period of fertility | Date of day |
| Sowing time | In 6 months-under 6 months |
| Seedling stage | 7 months above-7 months |
| Period of jointing | 7 months below-8 months above |
| Male stage of drawing | 8 months under 8 months |
| Period of lactation | 9 months up to 9 months |
| Maturity stage | 9 months below-10 days above |
Table 4, flower life waiting period (ten days)
| Period of fertility | Date of day |
| Sowing time | Last 6 months-during 6 months |
| Seedling stage | In 7 months |
| Under floweringStage of needle | 7 months of |
| Pod bearing period | 8 months of |
| Period of lactation | 9 months up |
The crop classification method based on the multi-source remote sensing data provided in this embodiment, as shown in fig. 1, specifically includes the following steps:
(1) Acquiring multisource remote sensing data in a physical period of a research area;
(2) Based on the multi-source remote sensing data, after preprocessing the multi-source remote sensing data, calculating crop classification optimal indexes at a plurality of time points in a physical weather period;
(3) Extracting a woodland mask based on crop classification optimal indexes of harvest time (10 months and 25 days) of all crops;
(4) Determining two key time points for each crop based on the climatic period of each crop;
(5) For each crop, based on the woodland mask, the crop extraction is performed in combination with the difference in crop classification optimum index for the two key time points.
For a certain crop, after the multisource remote sensing data is processed by adopting a woodland mask, if the difference value of the crop classification optimal indexes of two key time points is larger than a threshold value, the crop is extracted from the multisource remote sensing data.
The threshold value corresponding to a certain crop is the average value of the difference value of the crop classification optimal indexes of two key time points of the training sample corresponding to the crop in the training set.
The method comprises the following steps of determining the optimal index of crop classification and obtaining a threshold value of a difference value in the process of extracting crops:
step 1, collecting multi-source remote sensing data in a physical weather period of a research area, discarding data with a cloud coverage rate of the research area exceeding 10%, performing space-time optimization on a multi-element image of the research area, preprocessing the optimized multi-source remote sensing data, and performing radiation correction, orthographic correction, cloud removal and image stitching on the multi-source remote sensing data in the selected research area in a preprocessing process.
Step 2, calculating a vegetation characteristic index of the preprocessed multi-source remote sensing image, wherein the specific characteristic index comprises NDVI (normalized vegetation index), EVI (enhanced vegetation index) and RVI (ratio vegetation index), and the specific expression formula is as follows:
wherein ρ is R 、ρ B 、ρ NIR Respectively representing reflection values of red wave band, blue wave band and near infrared wave band; l is a background (soil) adjustment coefficient; c (C) 1 、C 2 For fitting coefficients, in the EVI algorithm, l=1, C is taken 1 ＝6、C 2 ＝7.5。
According to training samples, various vegetation characteristic index time sequence diagrams are drawn, as shown in fig. 2, as can be seen from the EVI index time sequence diagram, winter wheat and other crops can be well distinguished before 5.22 days, but the EVI time sequence curves of spring corn and peanut after 6.23 days are relatively close, so that the distinction of the spring corn and the peanut is not facilitated; as shown in fig. 3, from the NDVI timing curves, the winter wheat and summer corn curves were found to be closer together because most of the area was wheat and corn rotation, and thus the two crop timing curves were more similar. In the period of 5.22-6.23, the spring corns and the peanuts are in an ascending trend, the wheat NDVI is in a descending trend, and the spring corns are obtained by subtracting the 5.9 day images from the 6.23 day images, wherein the difference is larger and positive. The spring corns after 6.23 grow slowly after jointing, the NDVI time sequence curve changes slowly, and the peanuts grow quickly after 6.23, and the time sequence curve changes obviously, so that the method is beneficial to the district spring corns and the peanuts. The NDVI value of the summer corns is larger about 9.30 days, which is favorable for distinguishing the summer corns; as shown in figure 4, the ratio vegetation index RVI time sequence chart shows that the change trend is more similar to the NDVI change trend, but the RVI values of the spring corn and the wheat at 5.22 days are more similar, and the RVI curve change is not obvious in the period of 5.22-8.11, because the RVI is sensitive to the atmospheric influence, and the resolution capability is weaker when the vegetation coverage is not dense enough. Therefore, the normalized vegetation index NDVI is selected for classifying crops, namely, the NDVI is used as the optimal index for classifying the crops.
Step 3, according to the crop weather period table, wheat can be found to be mature in the middle of 6 months, spring corn is sowed in the middle of 4 months, seedlings emerge in the early 5 months, summer corn and peanut are sowed in the middle of and the last of 6 months, peanut is harvested in the early 9 months, summer corn is harvested in the early 10 months at the end of 9 months, so that various crops in the early 10 months and 25 days are harvested, and according to the training sample NDVI average value, as shown in Table 5, the NDVI is obtained 10/25 >0.565 is a woodland (forest, blocky woodland and grass-filled land), so that the woodland can be extracted as a forest mask.
TABLE 5 NDVI mean value table for various ground object samples
Step 4, combining the images of the two stages 3/24 and 4/18 with a forest mask (removing forest lands in the images according to the forest mask, wherein only wheat is remained after removing the forest lands, so that wheat is conveniently extracted), and obtaining the NDVI by taking the average value of the winter wheat training samples as the difference 4/18-3/24 >0.289 is winter wheat.
Step 5, according to the comparison of the images of the two stages of 6/29 and 5/11 and the forest mask, the spring corn can be extracted, because the spring corn is sowed in the middle and the last ten days of 4 months and the seedlings emerge in the middle and the last ten days of 5 months, the NDVI values of the wheat and the spring corn are relatively close, the wheat is in the node joint in the middle and the last ten days of 6 months, the wheat is mature, so the NDVI value of the wheat is smaller,difference is carried out on the two-stage NDVI images, and NDVI is obtained 6/23-5/09 >And 0.571 is spring corn, spring corn is extracted according to the decision tree, and a spring corn mask is made.
Step 6, performing mask processing on the 8/11 and 9/30 two-stage images according to the forest and spring corn mask files, wherein the rest crop areas are peanut and summer corn, and the difference value is performed on the two-stage NDVI images because peanut harvesting is earlier than 9 months 8/11-9/30 >0.217 is summer corn, and then 8/11 of the period of image is processed by using a summer corn mask file, and NDVI is obtained 8/11 >0.880 is the peanut.
Step 7, according to the field collected samples, the precision evaluation adopts an evaluation method of a confusion matrix, the evaluation result is shown in a table 6, the overall precision is as high as 95.8432%, the crop area is counted in an ArcGIS, and the wheat area is 830.432km 2 The corn planting area is 832.3857km 2 The peanut planting area is 3.3259km 2 。
TABLE 6 precision assessment of different crop classification results
| Ground object category | Training sample | Verification of samples | PA | UA |
| Winter wheat | 103 | 108 | 94.50 | 95.37 |
| Spring corn | 94 | 101 | 95.92 | 93.07 |
| Summer corn | 106 | 109 | 95.50 | 97.25 |
| Peanut | 104 | 107 | 96.30 | 97.20 |
According to the crop classification method based on the multi-source remote sensing data, a set of rapid and accurate crop rotation classification method suitable for large-scale multi-source remote sensing data is established according to the defects of the existing crop classification method, firstly, a field sample and a crop waiting period are inspected, satellite remote sensing image data in a key waiting period are screened, and a vegetation index time sequence curve is constructed by utilizing the random-2A data with the spatial resolution of 10 m in 2021 9 and the Landsat8 remote sensing image data with the resolution of 30 m. And secondly, screening out vegetation indexes favorable for crop classification, differencing the obtained time series indexes, quantifying the fine change among crops, and determining the segmentation time and sequence threshold value of each type of crops. And finally, feature selection and classification are carried out based on random forests, verification is carried out on the random forests and the field investigation samples, and the total classification accuracy is up to 95.8342%. In the embodiment, the time sequence covers the whole growth period of 2021-year crops, so that the vegetation index threshold values of different crops can be distinguished, and the problem that satellite images are lost due to weather and the like is solved by utilizing multi-source data.
According to the crop classification method based on the multi-source remote sensing data, provided by the embodiment, not only can the high spatial resolution of the image data be reserved, but also the time sequence of the two types of data can be used simultaneously, so that the observation period of a research area is improved, and the problems of low crop identification precision and different data source resolution differences caused by weather influence are effectively solved. In addition, the characteristic category of crops can be determined according to the vegetation characteristic index time sequence diagram, so that the method has the characteristic of accurately and quickly extracting the spatial distribution of the crops, and is beneficial to the management and planning of agriculture.
According to the crop classification method based on the multi-source remote sensing data, the Sentinel-2A and Landsat8 data are utilized to construct a vegetation characteristic time sequence with high time-space resolution, the time sequence covers the growth period of crops, the high space-time characteristics of two images are fully utilized, and high precision is achieved through characteristic selection and classification based on random forests. The classification algorithm can solve the problem of rapid and high-precision classification of a large-scale and various typical crop rotation types.
According to the crop classification method based on the multi-source remote sensing data, rapid classification is performed based on the difference value of the multi-source remote sensing data weather information, the difference information of different crop types can be quantized, the influence of different data sources on crop classification accuracy is eliminated, and therefore the classification accuracy of large-scale crop rotation is improved.
Example two
The embodiment provides a crop classification system based on multisource remote sensing data, which specifically comprises:
a data acquisition module configured to: acquiring multisource remote sensing data in a physical period of a research area;
a classification index calculation module configured to: based on the multi-source remote sensing data, calculating optimal indexes of crop classification at a plurality of time points in a climatic period;
a mask extraction module configured to: extracting a woodland mask based on crop classification optimal indexes of harvest time of all crops;
a point in time determination module configured to: determining two key time points for each crop based on the climatic period of each crop;
a classification module configured to: for each crop, based on the woodland mask, the crop extraction is performed in combination with the difference in crop classification optimum index for the two key time points.
It should be noted that, each module in the embodiment corresponds to each step in the first embodiment one to one, and the implementation process is the same, which is not described here.
Example III
The present embodiment provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a crop classification method based on multi-source remote sensing data as described in the above embodiment.
Example IV
The present embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps in a crop classification method based on multi-source telemetry data according to the above embodiment when the processor executes the program.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random access Memory (Random AccessMemory, RAM), or the like.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A crop classification method based on multi-source remote sensing data, comprising:
acquiring multisource remote sensing data in a physical period of a research area;
based on the multi-source remote sensing data, calculating optimal indexes of crop classification at a plurality of time points in a climatic period;
extracting a woodland mask based on crop classification optimal indexes of harvest time of all crops;
determining two key time points for each crop based on the climatic period of each crop;
for each crop, based on the woodland mask, the crop extraction is performed in combination with the difference in crop classification optimum index for the two key time points.
2. The method for classifying crops based on multi-source remote sensing data according to claim 1, wherein after radiation correction, orthographic correction, cloud removal and image stitching are sequentially performed on the multi-source remote sensing data, an optimal index of crop classification at a plurality of time points in a weathered period is calculated.
3. The method of claim 1, wherein the optimal index for classifying the crop is selected from NDVI, EVI, and RVI according to a characteristic index timing diagram of a plurality of crops.
4. The method for classifying crops based on multi-source remote sensing data according to claim 1, wherein for a certain crop, after the multi-source remote sensing data is processed by using a woodland mask, if the difference between the optimal indices of crop classifications at two key time points is greater than a threshold value, the crop is extracted from the multi-source remote sensing data.
5. The method of claim 4, wherein the threshold value for a crop is a mean value of differences between optimal indices of crop classifications at two key time points of the training sample for the crop in the training set.
6. The method of claim 1, wherein the multi-source remote sensing data comprises sentille-2A data or Landsat8 remote sensing image data.
7. A crop classification system based on multi-source remote sensing data, comprising:
a data acquisition module configured to: acquiring multisource remote sensing data in a physical period of a research area;
a classification index calculation module configured to: based on the multi-source remote sensing data, calculating optimal indexes of crop classification at a plurality of time points in a climatic period;
a mask extraction module configured to: extracting a woodland mask based on crop classification optimal indexes of harvest time of all crops;
a point in time determination module configured to: determining two key time points for each crop based on the climatic period of each crop;
a classification module configured to: for each crop, based on the woodland mask, the crop extraction is performed in combination with the difference in crop classification optimum index for the two key time points.
8. The crop classification system based on multi-source remote sensing data of claim 7, wherein the classification index calculation module is specifically configured to: and (3) after radiation correction, orthographic correction, cloud removal and image splicing are sequentially carried out on the multi-source remote sensing data, calculating crop classification optimal indexes at a plurality of time points in a physical weather period.
9. A computer readable storage medium having stored thereon a computer program, which when executed by a processor performs the steps of a method of classifying crops based on multi-source remote sensing data as claimed in any of claims 1 to 6.
10. A computer 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 a method of classifying crops based on multi-source telemetry data as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211663023.1A CN116524225A (en) | 2022-12-23 | 2022-12-23 | Crop classification method and system based on multi-source remote sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211663023.1A CN116524225A (en) | 2022-12-23 | 2022-12-23 | Crop classification method and system based on multi-source remote sensing data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116524225A true CN116524225A (en) | 2023-08-01 |
Family
ID=87405285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211663023.1A Pending CN116524225A (en) | 2022-12-23 | 2022-12-23 | Crop classification method and system based on multi-source remote sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116524225A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117151477A (en) * | 2023-10-31 | 2023-12-01 | 中化现代农业有限公司 | Crop anomaly identification method, device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103033150A (en) * | 2011-10-09 | 2013-04-10 | 黄青 | Method for quickly extracting main crop planting area through utilization of moderate resolution imaging spectroradiometer (MODIS) data |
| CN111507303A (en) * | 2020-04-28 | 2020-08-07 | 同济大学 | Wetland plant species detection method |
| CN113392759A (en) * | 2021-06-11 | 2021-09-14 | 河南大学 | Overwintering crop planting area identification method based on multi-source full-time-phase satellite image under cloud computing platform |
| CN113963275A (en) * | 2021-10-12 | 2022-01-21 | 中科禾信遥感科技（苏州）有限公司 | Remote sensing identification method and remote sensing identification system for winter wheat and land crops |
| CN113963260A (en) * | 2021-10-20 | 2022-01-21 | 中科三清科技有限公司 | Extraction method and device for winter wheat planting area and computer equipment |
| CN114255395A (en) * | 2021-07-06 | 2022-03-29 | 中国农业大学 | Crop classification method, system, equipment and medium with multi-source remote sensing data fusion |
| EP3997546A1 (en) * | 2019-07-08 | 2022-05-18 | Indigo AG, Inc. | Crop yield forecasting models |
| US20220210987A1 (en) * | 2019-09-27 | 2022-07-07 | Indigo Ag, Inc. | Modeling field irrigation with remote sensing imagery |
-
2022
- 2022-12-23 CN CN202211663023.1A patent/CN116524225A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103033150A (en) * | 2011-10-09 | 2013-04-10 | 黄青 | Method for quickly extracting main crop planting area through utilization of moderate resolution imaging spectroradiometer (MODIS) data |
| EP3997546A1 (en) * | 2019-07-08 | 2022-05-18 | Indigo AG, Inc. | Crop yield forecasting models |
| US20220210987A1 (en) * | 2019-09-27 | 2022-07-07 | Indigo Ag, Inc. | Modeling field irrigation with remote sensing imagery |
| CN111507303A (en) * | 2020-04-28 | 2020-08-07 | 同济大学 | Wetland plant species detection method |
| CN113392759A (en) * | 2021-06-11 | 2021-09-14 | 河南大学 | Overwintering crop planting area identification method based on multi-source full-time-phase satellite image under cloud computing platform |
| CN114255395A (en) * | 2021-07-06 | 2022-03-29 | 中国农业大学 | Crop classification method, system, equipment and medium with multi-source remote sensing data fusion |
| CN113963275A (en) * | 2021-10-12 | 2022-01-21 | 中科禾信遥感科技（苏州）有限公司 | Remote sensing identification method and remote sensing identification system for winter wheat and land crops |
| CN113963260A (en) * | 2021-10-20 | 2022-01-21 | 中科三清科技有限公司 | Extraction method and device for winter wheat planting area and computer equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117151477A (en) * | 2023-10-31 | 2023-12-01 | 中化现代农业有限公司 | Crop anomaly identification method, device, electronic equipment and storage medium |
| CN117151477B (en) * | 2023-10-31 | 2024-01-23 | 中化现代农业有限公司 | Crop anomaly identification method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109948596B (en) | Method for identifying rice and extracting planting area based on vegetation index model | |
| CN113009485A (en) | Remote sensing tobacco field identification method based on improved vegetation index | |
| CN111345214A (en) | Xinjiang cotton region identification method and system based on satellite image data | |
| Sun et al. | Monitoring maize lodging grades via unmanned aerial vehicle multispectral image | |
| CN114821362B (en) | Multi-source data-based rice planting area extraction method | |
| CN116524225A (en) | Crop classification method and system based on multi-source remote sensing data | |
| CN114581768A (en) | Crop lodging unmanned aerial vehicle monitoring method and device | |
| CN111950361B (en) | Beet identification method, system, device, medium and terminal based on single-time-sequence NDVI | |
| CN112240869A (en) | Grassland plot information extraction method based on high-resolution remote sensing image | |
| CN115861844A (en) | Rice early-stage remote sensing identification method based on planting probability | |
| CN115165773A (en) | Rice area extraction method based on Google Earth Engine | |
| CN116124774A (en) | Method for predicting nitrogen content of canopy based on unmanned aerial vehicle spectrum multi-source data | |
| Cui et al. | Phenotypic characteristics of ramie (Boehmeria nivea L) germplasm resources based on UAV remote sensing | |
| CN114663780A (en) | Method and system for identifying river-crossing irrigation area planting structure based on GEE and machine learning | |
| Wang et al. | Classification of medicinal plants astragalus mongholicus bunge and sophora flavescens aiton using GaoFen-6 and multitemporal Sentinel-2 data | |
| CN113743370A (en) | Citrus identification method based on multi-temporal remote sensing vegetation index | |
| Pluto-Kossakowska et al. | Automatic detection of dominant crop types in Poland based on satellite images | |
| Ye et al. | Inter-relationships between canopy features and fruit yield in citrus as detected by airborne multispectral imagery | |
| Zhang et al. | Detection of wheat lodging plots using indices derived from multi-spectral and visible images | |
| Parreiras et al. | Exploring the Harmonized Landsat Sentinel (hls) Datacube to Map AN Agricultural Landscape in the Brazilian Savanna | |
| El Hajj et al. | Multi-source information fusion: Monitoring sugarcane harvest using multi-temporal images, crop growth modelling, and expert knowledge | |
| CN114332628B (en) | Ginger rapid remote sensing extraction method based on typical physical condition and film network characteristics | |
| Song et al. | Crop Classification Using Multitemporal Landsat 8 Images | |
| CN112712038B (en) | Method and system for monitoring wheat lodging condition based on multispectral satellite image | |
| Chen et al. | Coupling optical and SAR imagery for automatic garlic mapping |
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 |