Crop remote sensing extraction and above-ground biomass remote sensing estimation method, device and equipment

Abstract

The invention provides a crop remote sensing extraction and above-ground biomass remote sensing estimation method, device and equipment, and belongs to the technical field of data processing, and the method comprises the steps: obtaining a microwave remote sensing image sequence and an optical remote sensing image sequence of a crop planting region; based on the microwave remote sensing image sequence, establishing a vegetation mutation point identification model, and determining mutation times of mutation pixels; determining a crop identification index type of the abrupt change pixel based on a judgment result of whether the abrupt change frequency meets a preset frequency condition or not; determining crop identification indexes of the mutation pixels based on the optical remote sensing image sequence and crop identification index types; and determining the aboveground biomass of the crop planting area based on the crop identification index. By combining the difference between optical remote sensing and microwave remote sensing, the crop identification index type is determined by using the microwave remote sensing image sequence, and the above-ground biomass is estimated by using the optical remote sensing image sequence according to the crop identification index type and the crop identification index, so that the above-ground biomass rapid estimation method with high precision and low cost is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method, device and equipment for crop remote sensing extraction and aboveground biomass remote sensing estimation. Background Art

[0002] In the agricultural field, the use of remote sensing technology to estimate aboveground biomass helps agricultural managers quickly obtain relevant information about crop-growing areas.

[0003] At present, the main method of using remote sensing technology to estimate aboveground biomass is to classify or visually interpret the crops grown on farmland through the spectral information or texture information of optical remote sensing images, thereby estimating the aboveground biomass of various crops.

[0004] However, the representation of crops in optical remote sensing images easily leads to the "same object, different spectrum" and "same spectrum, different object" phenomena, making it difficult to distinguish differences in crop planting areas. There is a large accuracy uncertainty in the rapid extraction of aboveground biomass. In addition, when it is cloudy and rainy in some areas, it is difficult to obtain optical image data, or the optical image data obtained cannot accurately reflect the situation of crops on the ground. Summary of the invention

[0005] The present invention provides a crop remote sensing extraction and aboveground biomass remote sensing estimation method, device and equipment, which are used to solve the defect of the prior art that there is an accuracy uncertainty problem when estimating aboveground biomass using optical remote sensing, and realize aboveground biomass estimation combining microwave remote sensing and optical remote sensing.

[0006] The present invention provides a crop remote sensing extraction and aboveground biomass remote sensing estimation method, comprising: Acquire microwave remote sensing image sequences and optical remote sensing image sequences of crop planting areas; Based on the microwave remote sensing image sequence, a vegetation mutation point recognition model is established, and the mutation times of the mutation pixels are determined; Determining the crop identification index type of the mutation pixel based on a judgment result of whether the number of mutations meets a preset number condition; Determining the crop identification index of the sudden pixel based on the optical remote sensing image sequence and the crop identification index type; Based on the crop identification index, the aboveground biomass of the crop planting area is determined.

[0007] According to a crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention, for any image pixel, a vegetation mutation point recognition model is established based on the microwave remote sensing image sequence, and the mutation number of the mutation pixel is determined, including: Determining a vegetation mutation index of the image pixel based on a vegetation change index of the image pixel in the microwave remote sensing image of the microwave remote sensing image sequence; Based on the comparison result between the vegetation mutation index and the first preset threshold, determining whether the pixel is a mutation pixel; All microwave remote sensing images of the microwave remote sensing image sequence are traversed, and the number of times the judgment result is that the image pixel is a mutation pixel is used as the mutation number of the mutation pixel.

[0008] According to a crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention, the vegetation mutation index of the image pixel is determined based on the vegetation change index of the image pixel in the microwave remote sensing image of the microwave remote sensing image sequence, including: Determining a first vegetation change index and a second vegetation change index of the image pixel based on the polarization mode of the microwave remote sensing image; the first vegetation change index is the vegetation change index of the previous microwave remote sensing image in the microwave remote sensing image; the second vegetation change index is the vegetation change index of the next microwave remote sensing image in the microwave remote sensing image; The vegetation mutation index is determined based on a difference between the first vegetation change index and the second vegetation change index.

[0009] According to a crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention, the crop identification index type of the mutation pixel is determined based on the judgment result of whether the number of mutations meets the preset number condition, including: When the number of mutations meets the first number condition, determining that the crop identification index type of the mutation pixel includes a first crop identification index; When the number of mutations meets the second number condition, determining that the crop identification index type of the mutation pixel includes a first crop identification index and a second crop identification index; The first crop identification index is a crop identification index of a main crop in the crop planting area; and the second crop identification index is a crop identification index of a rotation crop in the crop planting area.

[0010] According to a crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention, for each mutation pixel, determining the crop identification index of the mutation pixel based on the optical remote sensing image sequence and the crop identification index type includes: When the crop identification index type includes a first crop identification index, determining a first vegetation cover index sequence and a second vegetation cover index sequence based on the optical remote sensing image sequence; Determining a first crop identification index of the mutation pixel based on a maximum vegetation coverage index in the first vegetation coverage index sequence and a minimum vegetation coverage index in the second vegetation coverage index sequence; When the crop identification index type includes a second crop identification index, determining a third vegetation cover index sequence and a fourth vegetation cover index sequence based on the optical remote sensing image sequence; Based on the maximum vegetation coverage index in the third vegetation coverage index sequence and the minimum vegetation coverage index in the fourth vegetation coverage index sequence, a second crop recognition index of the sudden change pixel is determined.

[0011] According to a crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention, the aboveground biomass of the crop planting area is determined based on the crop identification index, including: Determine the number of first mutation pixels and the number of second mutation pixels; the first mutation pixel is a mutation pixel whose first crop recognition index is greater than a second preset threshold; the second mutation pixel is a mutation pixel whose second crop recognition index is greater than a third preset threshold; Determining the aboveground biomass of the main crop in the crop planting area based on the number of the first mutation pixels and the first unit biomass; Based on the number of the second mutation pixels and the second unit biomass, the aboveground biomass of the rotation crop in the crop planting area is determined.

[0012] The present invention also provides a crop remote sensing extraction and aboveground biomass remote sensing estimation device, comprising: An image sequence acquisition module is used to acquire microwave remote sensing image sequences and optical remote sensing image sequences of crop planting areas; A mutation number determination module is used to establish a vegetation mutation point recognition model based on the microwave remote sensing image sequence and determine the mutation number of the mutation pixel; An index type determination unit, configured to determine the crop identification index type of the mutation pixel based on a judgment result of whether the number of mutations meets a preset number condition; an identification index determining unit, configured to determine the crop identification index of the sudden change pixel based on the optical remote sensing image sequence and the crop identification index type; The aboveground biomass determination unit is used to determine the aboveground biomass of the crop planting area based on the crop identification index.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned crop remote sensing extraction and aboveground biomass remote sensing estimation methods is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for crop remote sensing extraction and aboveground biomass remote sensing estimation as described above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned crop remote sensing extraction and aboveground biomass remote sensing estimation methods.

[0016] The crop remote sensing extraction and aboveground biomass remote sensing estimation method, device and equipment provided by the present invention combine the differences between optical remote sensing and microwave remote sensing, use microwave remote sensing image sequences to determine the mutation times of mutation pixels, thereby predetermining the crop identification index type for calculating aboveground biomass, so as to distinguish the main crops and rotation crops planted on the mutation pixels, and then use the optical remote sensing image sequence to calculate the crop identification index of the mutation pixel according to the crop identification index type, and then calculate the aboveground biomass of the crop planting area, thereby improving the accuracy of estimating aboveground biomass, and there is no need to predetermine the spatiotemporal distribution information of different crop mixtures, thereby reducing the estimation cost; at the same time, when it is difficult to obtain optical remote sensing images in some areas due to cloudy and rainy weather, or the obtained optical remote sensing image data cannot accurately reflect the ground conditions, the microwave remote sensing image sequence is used to assist in estimating the aboveground biomass, which can improve the applicability and application range of estimating aboveground biomass using remote sensing technology, and the aboveground biomass can be estimated even in bad weather. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of the crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention.

[0019] Figure 2 It is a structural schematic diagram of the crop remote sensing extraction and aboveground biomass remote sensing estimation device provided by the present invention.

[0020] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] It should be noted that, in the description of the present invention, the term "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0023] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0024] Combine the following Figure 1-Figure 3 The invention describes the crop remote sensing extraction and aboveground biomass remote sensing estimation method, device and equipment.

[0025] Remote sensing technology has the characteristics of multi-time, multi-space and multi-spectral, and can effectively obtain relevant information on surface cover and its changes. It has been applied to the agricultural field to estimate the aboveground biomass of crops grown on farmland.

[0026] At present, the main method of using remote sensing technology to estimate the aboveground biomass of crops grown on farmland is to classify or visually interpret the crops grown on farmland through the spectral information or texture information of optical remote sensing images, thereby estimating the aboveground biomass of various crops.

[0027] Take silage corn as an example. Silage corn is a very common main source of feed in northern pastoral areas. The above-ground part of the corn plant is harvested, chopped, processed, and fermented into silage for feeding cattle, sheep and other livestock in winter.

[0028] When applying remote sensing technology to estimate the aboveground biomass of silage corn, the vegetation structure of silage corn, such as leaf area index and vegetation cover, can be inverted through optical remote sensing.

[0029] However, this approach of estimating the aboveground biomass of silage corn through optical remote sensing has the following problems: First, the representation of silage corn in optical remote sensing images easily leads to the phenomenon of "same object, different spectrum" and "same spectrum, different object", making it difficult to distinguish information such as the growth time and harvesting of silage corn, a major crop, from other non-major crops, and there is great uncertainty in the results of extracting information such as the growth time of silage corn; second, for many silage corn growing areas, due to the similarity with other crop types, natural vegetation, etc., the spectrum of silage corn and other non-major crops is similar, resulting in uncertainty in the information of silage corn, soybeans, wheat, forests, grasses and their mixtures. At this time, if the spatiotemporal distribution information of a large number of different crop mixtures is not determined in advance, the accuracy of estimating aboveground biomass through remote sensing technology will be low, and pre-determining the spatiotemporal distribution information of different crop mixtures will lead to increased estimation costs; third, due to problems such as cloudy and rainy weather in some areas, it is difficult to obtain optical image data.

[0030] In view of this, the present invention provides a method, device, electronic device and storage medium for crop remote sensing extraction and aboveground biomass remote sensing estimation to solve at least one of the above-mentioned technical problems.

[0031] Figure 1 FIG. 1 is a flow chart of the crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention, such as Figure 1 As shown, the crop remote sensing extraction and aboveground biomass remote sensing estimation method includes but is not limited to steps 101 to 105.

[0032] It should be noted that the executor of the crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention is the corresponding crop remote sensing extraction and aboveground biomass remote sensing estimation device, which can specifically be a server, computer equipment, such as a mobile phone, tablet computer, laptop computer, PDA, vehicle-mounted electronic equipment, wearable device, Ultra-Mobile Personal Computer (UMPC), netbook or Personal Digital Assistant (PDA), etc.

[0033] Step 101: Acquire a microwave remote sensing image sequence and an optical remote sensing image sequence of a crop planting area.

[0034] The crop planting area is the key area and spatial scope for estimating the aboveground biomass of the planted crops, which is determined according to the arrangement of planting tasks or biomass estimation tasks.

[0035] Optical remote sensing images are images obtained after inverting the vegetation structure of crops (such as leaf area index, vegetation cover, etc.); microwave remote sensing is an image that comprehensively reflects the surface undulation, soil moisture, and geometric information through backscattering coefficients, and can identify the geometric information of crops.

[0036] Specifically, multiple microwave remote sensing images and multiple optical remote sensing images collected by the remote sensing satellite when passing through the crop planting area multiple times within a preset time period are obtained. The multiple microwave remote sensing images constitute a microwave remote sensing image sequence, and the multiple optical remote sensing images constitute an optical remote sensing image sequence.

[0037] For example, obtain or collect medium-to-high resolution microwave remote sensing data (such as Sentinel data, high-resolution series data, etc.) and optical remote sensing data (such as Landsat, Sentinel data, high-resolution series data, etc.) of the crop-growing area in the current year or the current year and previous years, so as to obtain time series microwave remote sensing image sequences and optical remote sensing image sequences.

[0038] Step 102: Based on the microwave remote sensing image sequence, a vegetation mutation point recognition model is established, and the mutation times of the mutation pixels are determined.

[0039] Specifically, the microwave remote sensing image sequence is a collection of multiple time-series microwave remote sensing images of the same crop planting area, so each image pixel located at the same position in each microwave remote sensing image corresponds to a fixed area in the crop planting area. For an image pixel at a certain position in the microwave remote sensing image sequence, by comparing the degree of change of the image pixel of the microwave remote sensing image, it can be determined whether the image pixel is a sudden change pixel.

[0040] Sudden pixel, i.e., the pixel at a certain position of the microwave remote sensing image changes more than a preset degree, represents that the crop planting situation in the corresponding area of ​​the crop planting area has changed.

[0041] By traversing all image pixels in the microwave remote sensing image sequence, multiple mutation pixels can be determined and the number of multiple mutation pixels can be counted; by comparing the degree of change of image pixels in the microwave remote sensing image in the sequence one by one, the number of mutations of each mutation pixel can be determined.

[0042] For example, if a region A changes from a period of vigorous crop growth to a period of crop harvest, then in the microwave remote sensing image sequence acquired by the remote sensing satellite, there must be two adjacent microwave remote sensing images with significant changes in the pixel a at the pixel position corresponding to the region A, and the image pixel a is the mutation pixel. If the image acquisition time span of the acquired microwave remote sensing image sequence covers more than two crop growth periods and harvest periods, then the mutation number of the mutation pixel is more than two times.

[0043] Step 103: Based on the judgment result of whether the number of mutations meets the preset number condition, the crop identification index type of the mutation pixel is determined.

[0044] Among them, the crop identification index types include the crop identification index of the main crops planted in the crop planting area and the crop identification index of the rotation crops.

[0045] Specifically, after obtaining the mutation pixels and the number of mutations of each mutation pixel on the microwave remote sensing image of the crop planting area, it is judged whether the number of mutations of each mutation pixel meets the preset number conditions, and the crop identification index type of the mutation pixel is determined according to the judgment result, so as to further determine whether the crop planted in the crop planting area corresponding to the mutation pixel is the main crop, the rotation crop, or the crop other than the main crop and the rotation crop, that is, to determine whether the crop planting area is a rotation planting area or a single crop planting area.

[0046] It can be understood that the preset number of conditions may include only one preset condition or more than two preset conditions.

[0047] For example, the mutation number of mutation pixel b is 2, and the preset number conditions include "the mutation number is equal to 1" and "the mutation number is equal to 2". At this time, the mutation number of mutation pixel b is consistent with the preset number condition "the mutation number is equal to 2", then it can be determined that the crop planting area corresponding to the mutation pixel b is a rotation planting area, and the corresponding crop identification index types include the crop identification index of the main crop and the crop identification index of the rotation crop.

[0048] Step 104: Determine the crop identification index of the sudden change pixel based on the optical remote sensing image sequence and the crop identification index type.

[0049] Specifically, after the crop identification index type of the mutation pixel is determined, the crop identification index of the crop identification index type corresponding to the mutation pixel is calculated by using the characteristics of the optical remote sensing image sequence that can characterize the vegetation structure.

[0050] For example, after determining that the crop identification index type of the mutation pixel c is the crop identification index of the main crop, the crop identification index of the mutation pixel c as the main crop is calculated using the optical remote sensing image sequence.

[0051] Step 105: Determine the aboveground biomass of the crop planting area based on the crop identification index.

[0052] Specifically, based on the crop identification index of all mutation pixels in the crop planting area and the unit biomass of the main crop or rotation crop corresponding to each mutation pixel, the aboveground biomass of the main crop and / or rotation crop in the crop planting area can be calculated.

[0053] The crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention combines the differences between optical remote sensing and microwave remote sensing, uses microwave remote sensing image sequences to determine the mutation times of mutation pixels, thereby predetermining the crop identification index type for calculating aboveground biomass, so as to distinguish the main crops and rotation crops planted on the mutation pixels, and then uses the optical remote sensing image sequence to calculate the crop identification index of the mutation pixels according to the crop identification index type, and then calculates the aboveground biomass of the crop planting area, thereby improving the accuracy of estimating aboveground biomass, and there is no need to predetermine the spatiotemporal distribution information of different crop mixtures, thereby reducing the estimation cost; at the same time, when it is difficult to obtain optical remote sensing images due to cloudy and rainy weather in some areas, or the obtained optical remote sensing image data cannot accurately reflect the ground conditions, the microwave remote sensing image sequence is used to assist in estimating the aboveground biomass, which can improve the scope of application and application of estimating aboveground biomass using remote sensing technology, and the aboveground biomass can be estimated even in bad weather.

[0054] Based on the above embodiment, as an optional embodiment, for any image pixel, the vegetation mutation point recognition model is established based on the microwave remote sensing image sequence, and the mutation number of the mutation pixel is determined, including: Determining a vegetation mutation index of the image pixel based on a vegetation change index of the image pixel in the microwave remote sensing image of the microwave remote sensing image sequence; Based on the comparison result between the vegetation mutation index and the first preset threshold, determining whether the pixel is a mutation pixel; All microwave remote sensing images of the microwave remote sensing image sequence are traversed, and the number of times the judgment result is that the image pixel is a mutation pixel is used as the mutation number of the mutation pixel.

[0055] Specifically, for each image pixel corresponding to the crop planting area in the microwave remote sensing image, two vegetation change indexes of each image pixel in two adjacent microwave remote sensing images in the microwave remote sensing image sequence are calculated, and the vegetation mutation index of each image pixel is determined according to the difference between the two vegetation change indexes. The vegetation mutation index of each image pixel is compared with the first preset threshold a1. If the vegetation mutation index is greater than the first preset threshold a1, the image pixel is determined to be a mutation pixel. For each image pixel, all two adjacent microwave remote sensing images in the microwave remote sensing image sequence are traversed, and the number of times the vegetation mutation index of the image pixel is greater than the first preset threshold a1 is counted to obtain the number of mutations of each mutation pixel.

[0056] Optionally, the expression for determining the vegetation mutation index of the image pixel based on the vegetation change index of the image pixel in the microwave remote sensing image of the microwave remote sensing image sequence is as follows: ; in, is the vegetation mutation index; The time point when the remote sensing satellite passes by; It is the vegetation change index of the previous microwave remote sensing image in the microwave remote sensing image; It is the vegetation change index of the next microwave remote sensing image in the microwave remote sensing image.

[0057] Furthermore, for all image pixels, the steps of determining the vegetation mutation index and comparing the vegetation mutation index with the first preset threshold are repeated to obtain a mutation pixel set.

[0058] The crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention determines the vegetation mutation index by traversing and calculating the changes of the vegetation change index of the image pixels in the microwave remote sensing image, and compares the vegetation mutation index with a preset threshold value, thereby using the microwave remote sensing image sequence to accurately identify the mutation pixels in the image pixels and the number of mutations of each mutation pixel, which is beneficial to improving the accuracy of estimating the aboveground biomass at different times.

[0059] Based on the above embodiment, as an optional embodiment, determining the vegetation mutation index of the image pixel based on the vegetation change index of the image pixel in the microwave remote sensing image of the microwave remote sensing image sequence includes: Determining a first vegetation change index and a second vegetation change index of the image pixel based on the polarization mode of the microwave remote sensing image; the first vegetation change index is the vegetation change index of the previous microwave remote sensing image in the microwave remote sensing image; the second vegetation change index is the vegetation change index of the next microwave remote sensing image in the microwave remote sensing image; The vegetation mutation index is determined based on a difference between the first vegetation change index and the second vegetation change index.

[0060] The calculation method of the first vegetation change index is the same as the calculation method of the second vegetation change index.

[0061] Among them, the polarization modes of microwave remote sensing images include but are not limited to VV polarization (vertical polarization), HH polarization (horizontal polarization) and VH polarization (polarization transmitted in the vertical direction and received in the horizontal direction), etc.

[0062] Specifically, when calculating the vegetation mutation index of any image pixel, based on the different polarization modes when collecting microwave remote sensing images, the first vegetation change index of the image pixel in the previous microwave remote sensing image in the microwave remote sensing image is calculated, and the second vegetation change index of the image pixel in the next microwave remote sensing image in the microwave remote sensing image is calculated. The difference between the first vegetation change index and the second vegetation change index is used as the vegetation mutation index of the image pixel at the time of collecting the microwave remote sensing image.

[0063] As an optional embodiment, the vegetation change index is determined based on the following expression: ; in, is the vegetation change index; is the pixel number of the image pixel; The pixel number is VV polarization data of image pixels; The pixel number is VH polarization data of image pixels.

[0064] The crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention calculates the vegetation change index of image pixels of adjacent microwave remote sensing images according to the different polarization modes adopted by the microwave remote sensing images, makes full use of the image features of microwave remote sensing, more accurately identifies the image pixels in the microwave remote sensing images, and thus more accurately determines the degree of change in the crop planting area, which is conducive to improving the accuracy of estimating the aboveground biomass at different times.

[0065] Based on the above embodiment, as an optional embodiment, the determining of the crop identification index type of the mutation pixel based on the judgment result of whether the number of mutations meets the preset number condition includes: When the number of mutations meets the first number condition, determining that the crop identification index type of the mutation pixel includes a first crop identification index; When the number of mutations meets the second number condition, determining that the crop identification index type of the mutation pixel includes a first crop identification index and a second crop identification index; The first crop identification index is a crop identification index of a main crop in the crop planting area; and the second crop identification index is a crop identification index of a rotation crop in the crop planting area.

[0066] The preset number of times condition includes a first number of times condition and a second number of times condition.

[0067] Among them, the main crop and rotation crop are the classification of crops planted in the crop planting area; when only one crop is planted in the crop planting area, this crop is the main crop; when two crops are planted in rotation in the crop planting area, one of the crops is the main crop and the other is the rotation crop.

[0068] Specifically, for a mutation pixel, after obtaining the number of mutations of the mutation pixel, it is determined whether the number of mutations of the mutation pixel meets the preset number conditions; if the number of mutations of the mutation pixel meets the first number condition in the preset number conditions, it is determined that the crop identification index type for calculating the crop identification index of the mutation pixel includes the first crop identification index, and at the same time represents that the crop planting area corresponding to the image pixel is the main crop planting area; if the number of mutations of the mutation pixel meets the second number condition in the preset number conditions, it is determined that the crop identification index type for calculating the crop identification index of the mutation pixel includes the first crop identification index and the second crop identification index, and at the same time represents that the crop planting area corresponding to the image pixel is the main crop-rotation crop planting area.

[0069] For example, assume that the first number condition in the preset number condition is "the number of mutations is 1", and the second number condition is "the number of mutations is 2". If the number of mutations of the mutation pixel d is 1, it means that the crop planting area corresponding to the mutation pixel d is a silage corn planting area, and the crop identification index type for calculating the crop identification index of the mutation pixel d is the silage corn identification index (first crop identification index). If the number of mutations of the mutation pixel d is 2, it means that the crop planting area corresponding to the mutation pixel d is a silage corn-winter wheat rotation planting area, and the crop identification index types for calculating the crop identification index of the mutation pixel d include the silage corn identification index (first crop identification index) and the winter wheat identification index (second crop identification index).

[0070] The crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention determines in advance the type and quantity of crop identification indexes for calculating mutation pixels by judging whether the mutation times of the mutation pixels meet a certain number condition in preset number conditions, and can also determine whether the crop planting area corresponding to the mutation pixels belongs to a single planting area or a rotation planting area, which is beneficial to improving the accuracy of estimating different types of aboveground biomass.

[0071] Based on the above embodiment, as an optional embodiment, for each sudden change pixel, determining the crop identification index of the sudden change pixel based on the optical remote sensing image sequence and the crop identification index type includes: When the crop identification index type includes a first crop identification index, determining a first vegetation cover index sequence and a second vegetation cover index sequence based on the optical remote sensing image sequence; Determining a first crop identification index of the mutation pixel based on a maximum vegetation coverage index in the first vegetation coverage index sequence and a minimum vegetation coverage index in the second vegetation coverage index sequence; When the crop identification index type includes a second crop identification index, determining a third vegetation cover index sequence and a fourth vegetation cover index sequence based on the optical remote sensing image sequence; Based on the maximum vegetation coverage index in the third vegetation coverage index sequence and the minimum vegetation coverage index in the fourth vegetation coverage index sequence, a second crop recognition index of the sudden change pixel is determined.

[0072] Specifically, for each mutation pixel, when the crop identification index type including the first crop identification index is determined according to the mutation number of the mutation pixel, the optical remote sensing image sequence is used to determine the first vegetation coverage index sequence and the second vegetation coverage index sequence, and then the maximum vegetation coverage index in the first vegetation coverage index sequence is used as the first crop identification index. and the minimum vegetation cover index in the second vegetation cover index sequence The difference between them is used as the first crop identification index of the mutation pixel .

[0073] When the crop identification index type is determined according to the mutation times of the mutation pixel, including the second crop identification index, the third vegetation coverage index sequence and the fourth vegetation coverage index sequence are determined by using the optical remote sensing image sequence; then the maximum vegetation coverage index of the third vegetation coverage index sequence is and the minimum vegetation cover index in the fourth vegetation cover index sequence The difference between them is used as the second crop identification index of the mutation pixel .

[0074] Among them, each first vegetation cover index in the first vegetation cover index sequence is determined based on the normalized vegetation index of the mutation pixel in the first optical remote sensing image; the first optical remote sensing image is an optical remote sensing image acquired in the optical remote sensing image sequence with a first time range; the first time range is the time range of the vigorous growth period of the main crops (such as silage corn).

[0075] Each second vegetation cover index in the second vegetation cover index sequence is determined based on the normalized vegetation index of the mutation pixel in the second optical remote sensing image; the second optical remote sensing image is an optical remote sensing image in the optical remote sensing image sequence with an acquisition time of a second time range; the second time range is the time range from the vigorous growth period to the harvest period of the main crops.

[0076] Each third vegetation cover index in the third vegetation cover index sequence is determined based on the normalized vegetation index of the mutation pixel in the third optical remote sensing image; the third optical remote sensing image is an optical remote sensing image acquired in the optical remote sensing image sequence within a third time range; the third time range is the time range of the vigorous growth period of rotation crops (such as winter wheat).

[0077] Each fourth vegetation cover index in the fourth vegetation cover index sequence is determined based on the normalized vegetation index of the mutation pixel in the fourth optical remote sensing image; the fourth optical remote sensing image is an optical remote sensing image in the optical remote sensing image sequence with an acquisition time of a fourth time range; the fourth time range is the time range from the vigorous growth period to the harvest period of the rotation crops.

[0078] Optionally, the maximum vegetation coverage index in the first vegetation coverage index sequence is , the minimum vegetation cover index in the second vegetation cover index sequence The expression is as follows: ; ; in, is the maximum vegetation cover index in the first vegetation cover index sequence; The first time range is the period of vigorous growth of major crops; , , …, is the first vegetation cover index; , , …, A time node for acquiring a first optical remote sensing image within a first time range; is the minimum vegetation cover index in the second vegetation cover index sequence; The second time range is from the peak growth period to the harvest period of the main crops; , , …, is the second vegetation cover index; , ,,…, A time node for acquiring a second optical remote sensing image within a second time range; is the Normalized Difference Vegetation Index.

[0079] Optionally, the maximum vegetation cover index of the third vegetation cover index sequence is , the minimum vegetation cover index in the fourth vegetation cover index sequence The expression is as follows: ; ; in, is the maximum vegetation cover index of the third vegetation cover index sequence; The third time range is the vigorous growth period of the rotation crops; , , …, is the third vegetation cover index; , , …, A time node for acquiring a third optical remote sensing image within a third time range; is the minimum vegetation cover index in the fourth vegetation cover index sequence; The fourth time range is from the vigorous growth period to the harvest period of the rotation crops; , , …, It is the fourth vegetation cover index; , , …, A time node for acquiring a fourth optical remote sensing image within a fourth time range; is the Normalized Difference Vegetation Index.

[0080] In one embodiment, the normalized vegetation index is determined based on the following expression: ; in, is the normalized difference vegetation index; is the reflectivity of the mutation pixel in the near-infrared band of the optical remote sensing image; is the red band reflectivity of the mutation pixel in the optical remote sensing image.

[0081] If the normalized difference vegetation index is greater than the preset normalized difference vegetation index threshold, the crop planting area corresponding to the mutation pixel can be determined as a vegetation coverage area.

[0082] The crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention obtains the vegetation cover index sequence of different crops in different growth periods from the optical remote sensing image sequence according to the different types of crop identification index and in combination with the growth periods of different crops, and determines the crop identification index of the mutation pixel according to the difference between the maximum value and the minimum value in the vegetation cover index sequence of the same crop in different growth periods, thereby more accurately calculating the crop identification index of the mutation pixel, which is beneficial to improving the accuracy of estimating the aboveground biomass of different types.

[0083] Based on the above embodiment, as an optional embodiment, determining the aboveground biomass of the crop planting area based on the crop identification index includes: Determine the number of first mutation pixels and the number of second mutation pixels; the first mutation pixel is a mutation pixel whose first crop recognition index is greater than a second preset threshold; the second mutation pixel is a mutation pixel whose second crop recognition index is greater than a third preset threshold; Determining the aboveground biomass of the main crop in the crop planting area based on the number of the first mutation pixels and the first unit biomass; Based on the number of the second mutation pixels and the second unit biomass, the aboveground biomass of the rotation crop in the crop planting area is determined.

[0084] The first unit biomass is the biomass of the crop planting area per unit area corresponding to the unit mutation pixel when the main crop is planted; the second unit biomass is the biomass of the crop planting area per unit area corresponding to the unit mutation pixel when the rotation crop is planted. The first unit biomass and the second unit biomass can be obtained through the results of ground survey.

[0085] The second preset threshold is a preset threshold for determining that the crop planted in the crop planting area corresponding to the mutation pixel is the main crop; the third preset threshold is a preset threshold for determining that the crop planted in the crop planting area corresponding to the mutation pixel is a rotation crop.

[0086] Specifically, all mutation pixels are traversed to calculate the first crop identification index of each mutation pixel, or the first crop identification index and the second crop identification index of each mutation pixel are calculated. For the mutation pixels with the first crop identification index calculated, it is determined whether the first crop identification index of each mutation pixel is greater than the second preset threshold, so as to obtain the number of first mutation pixels with the first crop identification index greater than the second preset threshold. For the mutation pixels with the second crop identification index calculated, it is determined whether the second crop identification index of each mutation pixel is greater than the third preset threshold, so as to obtain the number of second mutation pixels with the second crop identification index greater than the third preset threshold.

[0087] Further using the number of the first mutation pixel and the first unit biomass Optionally, the expression for determining the aboveground biomass of the main crop in the crop planting area based on the number of the first mutation pixels and the first unit biomass is as follows: ; in, is the aboveground biomass of the main crop; is the unit area corresponding to the unit mutation pixel; is the first unit biomass; is the number of the first mutation pixels.

[0088] Optionally, the expression for determining the aboveground biomass of the rotation crop in the crop planting area based on the number of the second mutation pixels and the second unit biomass is as follows: ; in, is the above-ground biomass of the rotation crops; is the unit area corresponding to the unit mutation pixel; is the second unit biomass; is the number of the second mutation pixels.

[0089] The crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by the present invention estimates the aboveground biomass by utilizing medium- and high-resolution microwave remote sensing image sequences and optical remote sensing image sequences that are easily accessible and capable of characterizing ground crops, and combining the differences in different growth peaks and harvest periods of main crops and rotation crops in the crop planting area. The aboveground biomass is estimated, thereby overcoming the problems of unstable accuracy and high cost when using a single optical remote sensing to quickly identify the aboveground biomass and growth duration of crops, and effectively applying optical remote sensing data and microwave remote sensing data to establish relevant model methods. The method has the advantage of high accuracy in quickly identifying crops and extracting information such as aboveground biomass and growth duration of crops, thereby better serving forage management.

[0090] Figure 2 Schematic diagram of the structure of the crop remote sensing extraction and aboveground biomass remote sensing estimation device provided by the present invention. Figure 2 As shown, the crop remote sensing extraction and aboveground biomass remote sensing estimation device includes but is not limited to an image sequence acquisition module 201, a mutation number determination module 202, an index type determination unit 203, an identification index determination unit 204 and an aboveground biomass determination unit 205.

[0091] The image sequence acquisition module 201 is used to acquire a microwave remote sensing image sequence and an optical remote sensing image sequence of a crop planting area.

[0092] The mutation number determination module 202 is used to establish a vegetation mutation point recognition model based on the microwave remote sensing image sequence and determine the mutation number of the mutation pixel.

[0093] The index type determination unit 203 is used to determine the crop identification index type of the mutation pixel based on the judgment result of whether the number of mutations meets the preset number condition.

[0094] The identification index determining unit 204 is used to determine the crop identification index of the sudden change pixel based on the optical remote sensing image sequence and the crop identification index type.

[0095] The aboveground biomass determination unit 205 is used to determine the aboveground biomass of the crop planting area based on the crop identification index.

[0096] It should be noted that the crop remote sensing extraction and aboveground biomass remote sensing estimation device provided by the present invention can execute the crop remote sensing extraction and aboveground biomass remote sensing estimation method described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0097] The crop remote sensing extraction and aboveground biomass remote sensing estimation device provided by the present invention combines the differences between optical remote sensing and microwave remote sensing, uses microwave remote sensing image sequences to determine the mutation times of mutation pixels, thereby predetermining the crop identification index type for calculating aboveground biomass, so as to distinguish the main crops and rotation crops planted on the mutation pixels, and then uses the optical remote sensing image sequence to calculate the crop identification index of the mutation pixel according to the crop identification index type, and then calculates the aboveground biomass of the crop planting area, thereby improving the accuracy of estimating aboveground biomass, and there is no need to predetermine the spatiotemporal distribution information of different crop mixtures, thereby reducing the estimation cost; at the same time, when it is difficult to obtain optical remote sensing images due to cloudy and rainy weather in some areas, or the obtained optical remote sensing image data cannot accurately reflect the ground conditions, the microwave remote sensing image sequence is used to assist in estimating the aboveground biomass, which can improve the scope of application and application of estimating aboveground biomass using remote sensing technology, and the aboveground biomass can be estimated even in bad weather.

[0098] Figure 3 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 3As shown, the electronic device may include: a processor (Processor) 310, a communication interface (Communications 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 through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by any of the above-mentioned embodiments, and the crop remote sensing extraction and aboveground biomass remote sensing estimation method includes but is not limited to the following steps: obtaining a microwave remote sensing image sequence and an optical remote sensing image sequence of a crop planting area; establishing a vegetation mutation point recognition model based on the microwave remote sensing image sequence, and determining the mutation number of the mutation pixel; determining the crop identification index type of the mutation pixel based on the judgment result of whether the mutation number meets the preset number condition; determining the crop identification index of the mutation pixel based on the optical remote sensing image sequence and the crop identification index type; determining the aboveground biomass of the crop planting area based on the crop identification index.

[0099] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0100] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the crop remote sensing extraction and aboveground biomass remote sensing estimation method provided by any of the above-mentioned embodiments, and the crop remote sensing extraction and aboveground biomass remote sensing estimation method includes but is not limited to the following steps: obtaining a microwave remote sensing image sequence and an optical remote sensing image sequence of a crop planting area; based on the microwave remote sensing image sequence, establishing a vegetation mutation point recognition model, and determining the mutation number of the mutation pixel; based on the judgment result of whether the mutation number meets the preset number condition, determining the crop identification index type of the mutation pixel; based on the optical remote sensing image sequence and the crop identification index type, determining the crop identification index of the mutation pixel; based on the crop identification index, determining the aboveground biomass of the crop planting area.

[0101] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the crop remote sensing extraction and aboveground biomass remote sensing estimation method provided in any of the above-mentioned embodiments is implemented. The crop remote sensing extraction and aboveground biomass remote sensing estimation method includes but is not limited to the following steps: obtaining a microwave remote sensing image sequence and an optical remote sensing image sequence of a crop planting area; establishing a vegetation mutation point recognition model based on the microwave remote sensing image sequence, and determining the mutation number of the mutation pixel; determining the crop identification index type of the mutation pixel based on a judgment result of whether the mutation number meets a preset number condition; determining the crop identification index of the mutation pixel based on the optical remote sensing image sequence and the crop identification index type; and determining the aboveground biomass of the crop planting area based on the crop identification index.

[0102] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0103] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for crop remote sensing extraction and aboveground biomass remote sensing estimation, characterized in that: include: Acquire a microwave remote sensing image sequence and an optical remote sensing image sequence of a crop planting area; establish a vegetation mutation point recognition model based on the microwave remote sensing image sequence, and determine the mutation number of the mutation pixel; Determining the crop identification index type of the mutation pixel based on a judgment result of whether the number of mutations meets a preset number condition; Determining the crop identification index of the sudden pixel based on the optical remote sensing image sequence and the crop identification index type; Based on the crop identification index, the aboveground biomass of the crop planting area is determined.

2. The method for crop remote sensing extraction and aboveground biomass remote sensing estimation according to claim 1, characterized in that: For any image pixel, the vegetation mutation point recognition model is established based on the microwave remote sensing image sequence, and the mutation number of the mutation pixel is determined, including: Determining a vegetation mutation index of the image pixel based on a vegetation change index of the image pixel in the microwave remote sensing image of the microwave remote sensing image sequence; Based on the comparison result between the vegetation mutation index and the first preset threshold, determining whether the pixel is a mutation pixel; All microwave remote sensing images of the microwave remote sensing image sequence are traversed, and the number of times the judgment result is that the image pixel is a mutation pixel is used as the mutation number of the mutation pixel.

3. The method for crop remote sensing extraction and aboveground biomass remote sensing estimation according to claim 2, characterized in that: The determining of the vegetation mutation index of the image pixel based on the vegetation change index of the image pixel in the microwave remote sensing image of the microwave remote sensing image sequence comprises: Determining a first vegetation change index and a second vegetation change index of the image pixel based on the polarization mode of the microwave remote sensing image; the first vegetation change index is the vegetation change index of the previous microwave remote sensing image in the microwave remote sensing image; the second vegetation change index is the vegetation change index of the next microwave remote sensing image in the microwave remote sensing image; The vegetation mutation index is determined based on a difference between the first vegetation change index and the second vegetation change index.

4. The method for crop remote sensing extraction and aboveground biomass remote sensing estimation according to claim 1, characterized in that: The determining of the crop identification index type of the mutation pixel based on the judgment result of whether the number of mutations meets the preset number condition includes: When the number of mutations meets the first number condition, determining that the crop identification index type of the mutation pixel includes a first crop identification index; When the number of mutations meets the second number condition, determining that the crop identification index type of the mutation pixel includes a first crop identification index and a second crop identification index; The first crop identification index is a crop identification index of a main crop in the crop planting area; and the second crop identification index is a crop identification index of a rotation crop in the crop planting area.

5. The method for crop remote sensing extraction and aboveground biomass remote sensing estimation according to claim 4, characterized in that: For each sudden pixel, determining the crop identification index of the sudden pixel based on the optical remote sensing image sequence and the crop identification index type includes: When the crop identification index type includes a first crop identification index, determining a first vegetation cover index sequence and a second vegetation cover index sequence based on the optical remote sensing image sequence; Determining a first crop identification index of the mutation pixel based on a maximum vegetation coverage index in the first vegetation coverage index sequence and a minimum vegetation coverage index in the second vegetation coverage index sequence; When the crop identification index type includes a second crop identification index, determining a third vegetation cover index sequence and a fourth vegetation cover index sequence based on the optical remote sensing image sequence; Based on the maximum vegetation coverage index in the third vegetation coverage index sequence and the minimum vegetation coverage index in the fourth vegetation coverage index sequence, a second crop recognition index of the sudden change pixel is determined.

6. The method for crop remote sensing extraction and aboveground biomass remote sensing estimation according to claim 5, characterized in that: The step of determining the aboveground biomass of the crop planting area based on the crop identification index comprises: Determine the number of first mutation pixels and the number of second mutation pixels; the first mutation pixel is a mutation pixel whose first crop recognition index is greater than a second preset threshold; the second mutation pixel is a mutation pixel whose second crop recognition index is greater than a third preset threshold; Determining the aboveground biomass of the main crop in the crop planting area based on the number of the first mutation pixels and the first unit biomass; Based on the number of the second mutation pixels and the second unit biomass, the aboveground biomass of the rotation crop in the crop planting area is determined.

7. A crop remote sensing extraction and aboveground biomass remote sensing estimation device, characterized in that: include: An image sequence acquisition module is used to acquire microwave remote sensing image sequences and optical remote sensing image sequences of crop planting areas; A mutation number determination module is used to establish a vegetation mutation point recognition model based on the microwave remote sensing image sequence and determine the mutation number of the mutation pixel; An index type determination unit, configured to determine the crop identification index type of the mutation pixel based on a judgment result of whether the number of mutations meets a preset number condition; an identification index determining unit, configured to determine the crop identification index of the sudden change pixel based on the optical remote sensing image sequence and the crop identification index type; The aboveground biomass determination unit is used to determine the aboveground biomass of the crop planting area based on the crop identification index.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for crop remote sensing extraction and aboveground biomass remote sensing estimation as claimed in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for crop remote sensing extraction and aboveground biomass remote sensing estimation as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for crop remote sensing extraction and aboveground biomass remote sensing estimation as claimed in any one of claims 1 to 6 is implemented.

Images