CN114359730B - Method for quickly identifying crop planting area under sample-free condition - Google Patents
Method for quickly identifying crop planting area under sample-free condition Download PDFInfo
- Publication number
- CN114359730B CN114359730B CN202210010622.7A CN202210010622A CN114359730B CN 114359730 B CN114359730 B CN 114359730B CN 202210010622 A CN202210010622 A CN 202210010622A CN 114359730 B CN114359730 B CN 114359730B
- Authority
- CN
- China
- Prior art keywords
- layer
- rice
- crop
- probability
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 21
- 239000000203 mixture Substances 0.000 claims abstract description 10
- 230000010354 integration Effects 0.000 claims abstract description 5
- 230000000873 masking effect Effects 0.000 claims abstract description 3
- 241000209094 Oryza Species 0.000 claims description 40
- 235000007164 Oryza sativa Nutrition 0.000 claims description 40
- 235000009566 rice Nutrition 0.000 claims description 40
- 240000008042 Zea mays Species 0.000 claims description 18
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 claims description 18
- 235000002017 Zea mays subsp mays Nutrition 0.000 claims description 18
- 235000005822 corn Nutrition 0.000 claims description 18
- 230000004927 fusion Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 238000000576 coating method Methods 0.000 claims description 7
- 238000000926 separation method Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000003973 irrigation Methods 0.000 claims description 4
- 230000002262 irrigation Effects 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000002194 synthesizing effect Effects 0.000 claims description 4
- 239000011248 coating agent Substances 0.000 claims description 3
- 238000002310 reflectometry Methods 0.000 claims 4
- 238000010276 construction Methods 0.000 abstract 1
- 239000010410 layer Substances 0.000 description 52
- 230000006872 improvement Effects 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 235000013339 cereals Nutrition 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 239000011247 coating layer Substances 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 235000017060 Arachis glabrata Nutrition 0.000 description 1
- 244000105624 Arachis hypogaea Species 0.000 description 1
- 235000010777 Arachis hypogaea Nutrition 0.000 description 1
- 235000018262 Arachis monticola Nutrition 0.000 description 1
- 244000068988 Glycine max Species 0.000 description 1
- 235000010469 Glycine max Nutrition 0.000 description 1
- 240000000111 Saccharum officinarum Species 0.000 description 1
- 235000007201 Saccharum officinarum Nutrition 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 244000098338 Triticum aestivum Species 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000020232 peanut Nutrition 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- 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
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method for quickly identifying a crop planting area under a sample-free condition, which comprises the five steps of image collection, crop layer masking in summer, construction and operation of a Gaussian mixture model, calculation of a crop probability layer and weighted average integration of multi-phase probability layers.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method for quickly identifying a crop planting area under a sample-free condition.
Background
The corn is the second largest crop in the world, the yield of the corn occupies 13% of the total yield of the crop in the world, which is only inferior to sugarcane (21%), the corn is the largest grain crop in the world, the yield of the corn is higher than that of rice (9%) and wheat (8%), the space distribution and the planting area of the corn are extracted in near real time by utilizing remote sensing data in the growing season of the corn before harvesting, which is called early corn monitoring, the early corn monitoring has important significance for early grain risk warning, agricultural disaster response, international grain trade prediction and the like, the existing crop classification technology depends on a large number of ground samples, the cost is high, the timeliness is poor, the migration is difficult, and the application is limited;
the existing crop classification algorithm depends on ground samples and has more defects, such as: 1) The cost is high: the large-area high-quality crop classification sample collection has the advantages of large workload and high cost, and the samples are difficult to collect in remote areas, disordered areas or epidemic areas; 2) Aging is poor: the classification often needs full-time images in the whole growing season, so the remote sensing classification can be performed after crops are harvested; 3) Difficult migration: the classification model obtained by supervision and classification has poor mobility, and the classification model trained in a certain year in a certain region is difficult to be applied to other regions or other years, so the invention provides a method for quickly identifying crop planting regions under the condition of no sample so as to solve the problems in the prior art.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a method for quickly identifying a crop planting area under the condition of no sample, and the method for quickly identifying the crop planting area under the condition of no sample is used for quickly identifying by getting rid of the limitation of ground samples and adopting a mode of referencing satellite remote sensing images, so that the workload of early monitoring of crops is reduced, the timeliness of monitoring is improved, and the problems in the prior art are solved.
In order to achieve the purpose of the invention, the invention is realized by the following technical scheme: a method for quickly identifying a crop planting area under a sample-free condition, comprising the following steps:
step one, image collection
Selecting a crop planting area to be identified, acquiring satellite remote sensing images of the selected crop planting area through a preset platform, then performing image processing on the acquired satellite remote sensing images, and then splicing and synthesizing the satellite remote sensing images under the same orbit and the same time, and calculating a red edge index REPI on the basis;
step two, summer crop layer mask
Masking the red index REPI image layer obtained in the first step by utilizing a plurality of groups of land use data fusion land coating layers, wherein the plurality of groups of land use data fusion land coating layers comprise a northeast mask image layer, a cultivated land mask image layer and a rice mask image layer;
step three: building and running a Gaussian mixture model
Aiming at the red index REPI layer after each mask in the second step, firstly, on a platform preset in the first step, obtaining the red index REPI of a plurality of pixels through random sampling, deriving, removing abnormal values by using a quartile syntax, constructing a Gaussian mixture model GMM by using a python scikit-learn module, and operating to obtain parameters;
step four: calculating probability layer and overlap index of crops
The parameters obtained in the third step are transmitted back to the platform preset in the first step, then the crop probability P of each red edge index REPI is calculated, and then the overlapping rate index OLR is calculated;
step five: weighted average integration of multi-temporal probability layers
And calculating the probability average value of crops by utilizing the multi-phase probability layer and the calculated corresponding overlap rate index OLR, and carrying out threshold separation on the average probability layer on the basis, and if the probability average value is larger than a preset value, identifying the crops as corresponding crops.
The further improvement is that: in the first step, the image processing is to perform noise reduction processing on the obtained satellite remote sensing image, so as to remove clouds, cloud shadows and snow in the satellite remote sensing image.
The further improvement is that: in the first step, the calculation of the red edge index REPI is performed by a formula, where the formula is as follows:
the further improvement is that: in the second step, the northeast mask layer is a set of reliable cultivated map layer formed by fusing a plurality of groups of cultivated land products, then rice pixels in the reliable cultivated map layer are extracted by using a rice climatic algorithm, and finally non-rice pixels in the reliable cultivated map layer are used as summer crop layer masks.
The further improvement is that: in the second step, the farmland mask layer uses four groups of data including FROM-GLC, GLC_FCS30, GFSAD and CLUDs to carry out farmland fusion, and more than two sets of data are regarded as farmland pixels to serve as a reliable farmland coating.
The further improvement is that: in the second step, the rice mask layer is used for acquiring remote sensing images of all rice in the irrigation period, identifying rice flooding signals by utilizing the relative sizes of LSWI and NDVI/EVI, calculating the occurrence frequency of the flooding signals, and taking a preset threshold value as a rice identification basis.
The further improvement is that: in the third step, the calculation formula of the acquired parameters is as follows:
wherein mu is 1 ,σ 1 ,π 1 ,μ 2 ,σ 2 And pi 2 The were represents the mean, standard deviation and ratio of component 1 and component 2, respectively.
The further improvement is that: in the fourth step, the calculation formula of the crop probability P of each red edge index REPI is as follows:
wherein mu is 1 ,σ 1 ,π 1 ,μ 2 ,σ 2 And pi 2 The were represents the mean, standard deviation and ratio of component 1 and component 2, respectively.
The further improvement is that: in the fourth step, the calculation formula of the overlap ratio index OLR is:
wherein OLR represents the overlap ratio, h int And h lp The probability density at the intersection of the two components and the probability density corresponding to the lower peak are represented, respectively.
The beneficial effects of the invention are as follows: the method for quickly identifying the crop planting area under the condition of no sample gets rid of the limitation of a ground sample, and adopts a mode of referencing satellite remote sensing images to quickly identify, thereby reducing the workload of early monitoring of crops, improving the timeliness and the accuracy of monitoring, having stronger mobility and being capable of migrating between different areas and years.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a schematic diagram of a first embodiment of the present invention.
Fig. 2 is a schematic overall flow chart of a second embodiment of the present invention.
FIG. 3 is a diagram of a red index composite layer of the same track and the same time according to a second embodiment of the present invention.
Fig. 4 is an enlarged schematic view of the square frame of fig. 3 according to the present invention.
Fig. 5 is a schematic diagram of a summer crop mask layer according to a second embodiment of the present invention.
Fig. 6 is a schematic diagram of solving an overlap ratio index of a gaussian mixture model according to a second embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
According to fig. 1, the embodiment provides a method for quickly identifying a crop planting area under a sample-free condition, which comprises the following steps:
step one, image collection
Selecting a crop planting area to be identified, acquiring satellite remote sensing images of the selected crop planting area through a preset platform, then performing image processing on the acquired satellite remote sensing images, splicing and synthesizing the satellite remote sensing images under the same orbit and the same time, and calculating a red edge index REPI on the basis, wherein the image processing is to perform noise reduction processing on the acquired satellite remote sensing images to remove clouds, cloud shadows and snow in the satellite remote sensing images, and the calculation of the red edge index REPI is performed through a formula, wherein the formula is as follows:
step two, summer crop layer mask
The red index REPI image layer mask obtained in the first step is reserved only by utilizing a plurality of groups of land utilization data fusion cultivated land coatings, wherein the plurality of groups of land utilization data fusion cultivated land coatings comprise a northeast mask image layer, a cultivated land mask image layer and a rice mask image layer, the northeast mask image layer is formed by utilizing a plurality of groups of cultivated land products to fuse, then the rice image in the reliable cultivated land image layer is extracted by utilizing a rice climate algorithm, finally non-rice image in the reliable cultivated land image layer is used as a summer crop image layer mask, cultivated land fusion is carried out by utilizing four groups of data including FROM-GLC, GLC_FCS30, GFSAD and CLUDs, more than two sets of data are used as cultivated land image elements to serve as the reliable cultivated land coatings, the rice mask image layer is obtained by utilizing the relative sizes of WI and NDVI/EVI to identify a flooding signal, the occurrence frequency of the flooding signal is calculated again, and a preset threshold value is adopted as a rice identification basis;
step three: building and running a Gaussian mixture model
Aiming at the red index REPI layer after each mask in the second step, firstly, on a platform preset in the first step, obtaining the red index REPI of a plurality of pixels through random sampling, deriving, removing abnormal values by using a quartile syntax, constructing a Gaussian mixture model GMM by using a python scikit-learn (machine learning python library) module, and operating to obtain parameters, wherein the calculation formula of the obtained parameters is as follows:
wherein mu is 1 ,σ 1 ,π 1 ,μ 2 ,σ 2 And pi 2 The were represents the mean, standard deviation and ratio of component 1 and component 2, respectively;
step four: calculating probability layer and overlap index of crops
The parameters obtained in the third step are transmitted back to the platform preset in the first step, the crop probability P of each red edge index REPI is calculated, the overlap rate index OLR is calculated, and the calculation formula of the crop probability P of each red edge index REPI is as follows:
wherein mu is 1 ,σ 1 ,π 1 ,μ 2 ,σ 2 And pi 2 The were represents the mean, standard deviation and proportion of component 1 and component 2, respectively, and the calculation formula of the overlap ratio index OLR is:
wherein OLR represents the overlap ratio, h int And h lp Respectively representing the probability density at the intersection point of the two components and the probability density corresponding to the lower peak;
step five: weighted average integration of multi-temporal probability layers
And calculating the probability average value of crops by utilizing the multi-phase probability layer and the calculated corresponding overlap rate index OLR, and carrying out threshold separation on the average probability layer on the basis, and if the probability average value is larger than a preset value, identifying the crops as corresponding crops.
Example two
According to fig. 2-6, in this embodiment, taking a corn planting area as an example, the method includes the following steps:
step one, image collection
Selecting a crop planting area to be identified, acquiring satellite remote sensing images of the selected corn planting area through a sentinel No. 2 in a classification window selected on a Google Earth Engine (GEE) platform, then performing image processing on the acquired satellite remote sensing images, and then splicing and synthesizing satellite remote sensing images under the same orbit (orbit) and the same time (DOY), wherein on the basis, red edge index REPI (Red edge position index) is calculated, the image processing is noise reduction processing on the acquired satellite remote sensing images, cloud shadow and snow in the satellite remote sensing images are removed, and red edge index REPI is calculated through a formula, wherein the formula is as follows:
step two, summer crop layer mask
The red index REPI image layer mask obtained in the first step is masked by utilizing a plurality of groups of land utilization data fusion, and only summer crop image elements such as corn, soybean, peanut and the like are reserved, wherein the plurality of groups of land utilization data fusion land coatings comprise a northeast mask image layer, a cultivated land mask image layer and a rice mask image layer, the northeast mask image layer is formed by utilizing four groups of cultivated land products to fuse, then the rice image elements in the reliable cultivated land layer are extracted by utilizing a rice climate algorithm, finally non-rice image elements in the reliable cultivated land layer are used as a crop image layer mask, the cultivated land fusion is carried out by utilizing four groups of data including FROM-GLC, GLC_FCS30, SAD and CLUDS in 2015, and at least two groups of data are regarded as image elements of cultivated land to be used as the reliable cultivated land coating, as shown in fig. 4, wherein the calculation formula is:
wherein SummerCrop represents the final summer Crop mask layer, crop i Represents the ith set of cultivated land data (1 is cultivated land, 0 is other), and the rice mask layerThe remote sensing images of all rice irrigation periods are obtained, the relative sizes of LSWI and NDVI/EVI are utilized to identify rice flooding signals, and the calculation formula is as follows:
wherein Flood represents a flooding signal, SOT and EOT represent the start (DOY: 120) and end time (DOY: 160) of the flooding period, and the frequency of occurrence of the flooding signal is calculated by the following formula:
wherein R is f Represents the flooding signal frequency, Σn flood ,∑N all Sum sigma N bad The number of times of water flooding signals in the water filling period, the total observation times and the ineffective observation times are represented, a 10% threshold is adopted as the basis of rice identification, and the formula is expressed as
In the formula, rice represents a Rice layer.
Step three: building and running a Gaussian mixture model
Aiming at the red index REPI layer after each mask in the second step, firstly, on a GEE platform in the first step, obtaining the red index REPI of five thousands of pixels through random sampling, deriving, removing abnormal values by using a quartile syntax, constructing a Gaussian mixture model GMM by using a python scikit-learn module, and operating to obtain parameters, wherein the calculation formula of the obtained parameters is as follows:
wherein mu 1 ,σ 1 ,π 1 ,μ 2 ,σ 2 And pi 2 were represents the mean, standard deviation and ratio of component 1 and component 2, respectively, and component 2 represents the corn fraction.
Step four: calculating probability layer and overlap index of crops
The parameters obtained in the third step are transmitted back to the platform preset in the first step, the crop probability P of each red edge index REPI is calculated, the overlap rate index OLR is calculated, and the calculation formula of the crop probability P of each red edge index REPI is as follows:
wherein mu 1 ,σ 1 ,π 1 ,μ 2 ,σ 2 And pi 2 The wee represents the mean, standard deviation and ratio of the component 1 and the component 2, respectively, and as shown in fig. 5, the calculation formula of the overlap index OLR is:
wherein OLR represents the overlap ratio, h int And h lp Respectively representing the probability density at the intersection point of the two components and the probability density corresponding to the lower peak;
step five: weighted average integration of multi-temporal probability layers
And calculating the probability average value of crops by using the multi-phase probability layer and the calculated corresponding overlap rate index OLR, wherein the calculation formula is as follows:
where T1 and T2 represent the start and stop times of the classification window (Heilongjiang: DOY 191-254, DOY 175-215, ixowa), for a certain phase T,
all p before time t i Weighted average of (2), weight w i ，w i And (3) jointly determining by the OLR at the time t and all the OLRs before t, and on the basis, carrying out threshold separation on the average probability layer, and if the average probability value is greater than 0.5, identifying the corn, wherein the formula is as follows:
where Corn represents the final Corn layer.
And on the basis, carrying out threshold separation on the average probability layers, and identifying the corresponding crops if the probability average value is larger than a preset value.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. A method for quickly identifying a crop planting area under a sample-free condition is characterized by comprising the following steps of: the method comprises the following steps:
step one, image collection
Selecting a crop planting area to be identified, acquiring satellite remote sensing images of the selected crop planting area through a preset platform, then performing image processing on the acquired satellite remote sensing images, splicing and synthesizing the satellite remote sensing images under the same orbit and the same time, and calculating a red index REPI of each pixel in the images based on the satellite remote sensing images synthesized by splicing to obtain a red index REPI image layer;
step two, summer crop layer mask
Masking the red index REPI image layer by utilizing a plurality of groups of land utilization data fusion plough map layers, removing non-ploughed land and rice pixels, and only reserving summer crop pixels, wherein the plurality of groups of land utilization data fusion plough map layers comprise a northeast mask image layer, a ploughing mask image layer and a rice mask image layer; the multiple groups of land utilization data fusion cultivation map layers comprise a northeast mask layer, a cultivated land mask layer and a rice mask layer, wherein the northeast mask layer is formed by fusing four groups of cultivated land products, then rice pixels in the reliable cultivation map layer are extracted by a rice climate algorithm, and finally non-rice pixels in the reliable cultivation map layer are used as a summer crop layer mask, and a calculation formula is as follows:
wherein SummerCrop represents the final summer Crop mask layer, crop i The ith set of cultivated land data is represented, and the rice mask layer is used for acquiring remote sensing images of all rice in the irrigation period;
step three: building and running a Gaussian mixture model
Aiming at the red index REPI layer of each mask in the second step, firstly, on a platform preset in the first step, obtaining red indexes REPI of a plurality of pixels through random sampling, deriving, removing abnormal values by using a four-bit-distance method, constructing a Gaussian mixture model GMM by using a python scikit-learn module, and operating to obtain parameters;
step four: calculating probability layer and overlap index of crops
The parameters obtained in the third step are transmitted back to the platform preset in the first step, the crop probability P of the red index REPI is calculated, and the overlapping rate index OLR is calculated;
step five: weighted average integration of multi-temporal probability layers
Calculating the probability average value of crops by utilizing the multi-phase probability layer and the calculated corresponding overlap rate index OLR thereof, and carrying out threshold separation on the average probability layer on the basis, and identifying the crops as corresponding crops if the probability average value is larger than a preset value; the average value calculation formula is as follows:
where T1 and T2 represent the start-stop times of the classification window, for a certain phase T,
all p before time t i Weighted average of (2), weight w i ，w i And (3) jointly determining by the OLR at the time t and all the OLRs before t, and on the basis, carrying out threshold separation on the average probability layer, and if the average probability value is greater than 0.5, identifying the corn, wherein the formula is as follows:
wherein Corn represents the final Corn layer;
and carrying out threshold separation on the average probability layers, and identifying the corresponding crops if the average probability value is larger than a preset value.
2. A method for rapid identification of crop planting areas without samples as defined in claim 1, wherein: in the first step, the image processing is to perform noise reduction processing on the obtained satellite remote sensing image, so as to remove clouds, cloud shadows and snow in the satellite remote sensing image.
3. A method for rapid identification of crop planting areas without samples as defined in claim 1, wherein: in the first step, the calculation of the red edge index REPI is performed by a formula, where the formula is as follows:
wherein ρ is re1 For the red-side band 1 reflectivity ρ re2 For red edge band 2 reflectivity ρ re3 For the red edge band 3 reflectivity ρ red Red band reflectivity.
4. A method for rapid identification of crop planting areas without samples as defined in claim 1, wherein: in the second step, the northeast mask layer is a set of reliable cultivated map layer formed by fusing a plurality of groups of cultivated land products, then rice pixels in the reliable cultivated map layer are extracted by using a rice climatic algorithm, and finally non-rice pixels in the reliable cultivated map layer are used as summer crop layer masks.
5. A method for rapid identification of crop planting areas without samples as defined in claim 1, wherein: in the second step, the farmland mask layer uses four groups of data including FROM-GLC, GLC_FCS30, GFSAD and CLUDs to carry out farmland fusion, and more than two sets of data are regarded as farmland pixels to serve as a reliable farmland coating.
6. A method for rapid identification of crop planting areas without samples as defined in claim 1, wherein: in the second step, the rice mask layer is used for acquiring remote sensing images of all rice in the irrigation period, identifying rice flooding signals by utilizing the relative sizes of LSWI and NDVI/EVI, calculating the occurrence frequency of the flooding signals, and taking a preset threshold value as a rice identification basis.
7. A method for rapid identification of crop planting areas without samples as defined in claim 1, wherein: in the third step, the calculation formula of the acquired parameters is as follows:
wherein mu is 1 ,σ 1 ,π 1 ,μ 2 ,σ 2 And pi 2 Representing the mean, standard deviation and ratio of component 1 and component 2, respectively.
8. A method for rapid identification of crop planting areas without samples as defined in claim 1, wherein: in the fourth step, the crop probability P of each red edge index REPI i The calculation formula of (2) is as follows:
wherein mu is 1 ,σ 1 ,π 1 ,μ 2 ,σ 2 And pi 2 Representing the mean, standard deviation and ratio of component 1 and component 2, respectively.
9. A method for rapid identification of crop planting areas without samples as defined in claim 1, wherein: in the fourth step, the calculation formula of the overlap ratio index OLR is:
wherein OLR represents the overlap ratio, h int And h lp The probability density at the intersection of the two components and the probability density corresponding to the lower peak are represented, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210010622.7A CN114359730B (en) | 2022-01-05 | 2022-01-05 | Method for quickly identifying crop planting area under sample-free condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210010622.7A CN114359730B (en) | 2022-01-05 | 2022-01-05 | Method for quickly identifying crop planting area under sample-free condition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114359730A CN114359730A (en) | 2022-04-15 |
| CN114359730B true CN114359730B (en) | 2023-06-09 |
Family
ID=81108015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210010622.7A Active CN114359730B (en) | 2022-01-05 | 2022-01-05 | Method for quickly identifying crop planting area under sample-free condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114359730B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118521969A (en) * | 2024-07-25 | 2024-08-20 | 广东省科学院广州地理研究所 | Monitoring method for rice seed withdrawal risk |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN113723291A (en) * | 2021-08-31 | 2021-11-30 | 西南大学 | Multispectral image-based sloping field ground feature refined classification method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3611733B1 (en) * | 2018-08-15 | 2024-09-25 | Siemens Healthineers AG | Searching a medical reference image |
| CN112435292B (en) * | 2020-12-18 | 2023-10-31 | 太原理工大学 | Remote sensing image-based rice planting area extraction method |
| CN113033670B (en) * | 2021-03-29 | 2023-06-23 | 华南农业大学 | Rice planting area extraction method based on Sentinel-2A/B data |
| CN113139683A (en) * | 2021-04-19 | 2021-07-20 | 浙江甲骨文超级码科技股份有限公司 | Crop cultivation method and device based on block chain and electronic device |
| CN113392759B (en) * | 2021-06-11 | 2022-02-01 | 河南大学 | Overwintering crop planting area identification method based on multi-source full-time-phase satellite image under cloud computing platform |
-
2022
- 2022-01-05 CN CN202210010622.7A patent/CN114359730B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN113723291A (en) * | 2021-08-31 | 2021-11-30 | 西南大学 | Multispectral image-based sloping field ground feature refined classification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114359730A (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108846832B (en) | Multi-temporal remote sensing image and GIS data based change detection method and system | |
| CN112164062A (en) | Wasteland information extraction method and device based on remote sensing time sequence analysis | |
| CN109767409B (en) | Landslide change detection method based on remote sensing image, storage medium and electronic equipment | |
| KR102496740B1 (en) | System and method for reservoir water body analysis using synthetic aperture radar data | |
| CN114387516B (en) | Single-season rice SAR (synthetic aperture radar) identification method for small and medium-sized fields in complex terrain environment | |
| CN109918449B (en) | Internet of things-based agricultural disaster information remote sensing extraction method and system | |
| CN115222296B (en) | Remote sensing monitoring method and system for dynamic change of mountain green coverage index | |
| CN114998728B (en) | Method and system for predicting cotton leaf area index by unmanned aerial vehicle multi-source remote sensing | |
| JP7450838B1 (en) | Method and device for calculating crop canopy coverage using small amount of data learning based on background filtering | |
| King et al. | Modelling and mapping damage to forests from an ice storm using remote sensing and environmental data | |
| CN113221806A (en) | Cloud platform fusion multi-source satellite image and tea tree phenological period based automatic tea garden identification method | |
| CN114359730B (en) | Method for quickly identifying crop planting area under sample-free condition | |
| CN117437538A (en) | Tropical rainforest ecosystem space-time pattern feature extraction and prediction method | |
| CN114548277B (en) | Method and system for ground point fitting and crop height extraction based on point cloud data | |
| CN117197668A (en) | Crop lodging level prediction method and system based on deep learning | |
| CN117690017B (en) | Single-season and double-season rice extraction method considering physical time sequence characteristics | |
| CN113534083B (en) | SAR-based corn stubble mode identification method, device and medium | |
| CN118153802A (en) | Remote sensing and multi-environment factor coupled wheat key waiting period prediction method and device | |
| Ayub et al. | Wheat Crop Field and Yield Prediction using Remote Sensing and Machine Learning | |
| CN112967308B (en) | Amphibious boundary extraction method and system for dual-polarized SAR image | |
| CN112418073B (en) | Wheat plant nitrogen content estimation method based on unmanned aerial vehicle image fusion characteristics | |
| CN117871550A (en) | Large-area farmland irrigation monitoring method, system and electronic equipment | |
| CN117523398A (en) | Remote sensing image land coverage evolution time-space diagram analysis method for self-adaptive migration training sample | |
| CN114782835B (en) | Crop lodging area proportion detection method and device | |
| CN116310864A (en) | Automatic identification method, system, electronic equipment and medium for crop lodging |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |