Leaf area statistics method, device and storage medium based on ultra-low altitude remote sensing

Abstract

The present invention relates to the technical field of crop growth monitoring, and specifically to a leaf area statistics method, device and storage medium based on ultra-low altitude remote sensing. The method includes acquiring ultra-low altitude remote sensing image data of a target area; solving the ultra-low altitude remote sensing image data of the target area to construct a corresponding three-dimensional point cloud model; performing point cloud simplification editing on the three-dimensional point cloud model, removing redundant point clouds, and obtaining a branch and leaf point cloud model of a target crop in the target area; performing rasterization processing on the branch and leaf point cloud model, and converting the branch and leaf point cloud in the branch and leaf point cloud model into raster pixels; determining the branch and leaf area of ​​a single target crop according to the size of the raster pixels, and calculating the total branch and leaf area of ​​the target crop in the target area according to the number of branch and leaf point clouds and the size of the raster pixels in the branch and leaf point cloud model. The present invention can realize the accurate segmentation of a single crop by using point cloud segmentation, and the calculation amount for statistically obtaining leaf area information is smaller and more efficient.

Description

Technical Field

[0001] The present invention relates to the technical field of crop growth monitoring, and in particular to a leaf area statistics method, device and storage medium based on ultra-low altitude remote sensing. Background Art

[0002] Leaf area index refers to the ratio of crop leaf area to crop land area, and is an important parameter for measuring vegetation growth. It is also a basic parameter for many mathematical models in agricultural science, ecological science, and remote sensing science. Leaf area index controls many biological and physical processes in water, nutrient, and carbon cycles. These parameters are often used to assess crop health, nutrient supply, and the impact of agricultural management practices.

[0003] Accurate estimation of canopy biophysical parameters during crop growth and development is of great significance for optimizing crop field management measures. As a commonly used crop canopy indicator, leaf area index is often used to monitor the development and changes of crop canopy structure and estimate crop yield. Accurate estimation of leaf area index can provide theoretical support for crop fertilization, irrigation, pest and disease control, and food productivity. Traditional field fixed-point observation is not only time-consuming and labor-intensive, but can only obtain the leaf area index value of a single point, and cannot obtain the leaf area index situation on the surface. Remote sensing technology is an indispensable tool for obtaining agricultural information. With the development of remote sensing technology, ultra-low altitude remote sensing monitoring using drones and other means has made it possible to accurately estimate the leaf area index at a regional scale.

[0004] At present, the statistics of crop leaf area can be directly extracted from the ultra-low-altitude images of drones, or extracted through segmentation of orthophotos. These two methods are based on image recognition technology to obtain leaf area index, which has a large amount of calculation and relatively poor segmentation effect, and is not efficient enough. Therefore, the existing methods for obtaining leaf area information statistics need to be improved. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a leaf area statistics method, device and storage medium based on ultra-low altitude remote sensing. When applied, the method, device and storage medium can replace the existing image recognition and segmentation technology. Point cloud segmentation can achieve accurate segmentation of individual crops, which is not affected by surface cover and image color changes. It has good replicability and scalability, and the calculation amount for statistically obtaining leaf area information is smaller and the efficiency is higher.

[0006] In a first aspect, the present invention provides a leaf area statistics method based on ultra-low altitude remote sensing, comprising:

[0007] Acquire ultra-low altitude remote sensing image data of the target area;

[0008] Solve the ultra-low altitude remote sensing image data of the target area and construct the corresponding three-dimensional point cloud model;

[0009] Perform point cloud simplification editing on the 3D point cloud model, remove redundant point clouds, and obtain the branch and leaf point cloud model of the target crop in the target area;

[0010] The branch and leaf point cloud model is rasterized to convert the branch and leaf point cloud in the branch and leaf point cloud model into raster pixels;

[0011] The branch and leaf area of ​​a single target crop is determined according to the size of the grid pixels, and the total branch and leaf area of ​​the target crop in the target area is calculated according to the number of branch and leaf point clouds in the branch and leaf point cloud model and the size of the grid pixels.

[0012] Based on the above invention, by performing corresponding calculations on the ultra-low altitude remote sensing image data, a three-dimensional point cloud model of the target area is constructed, and then the three-dimensional point cloud model is simplified, and irrelevant point clouds are removed, leaving only the branch and leaf point clouds of the target crop, and then the branch and leaf point clouds are rasterized and converted into corresponding raster pixels, so that the branch and leaf area of ​​a single target crop and the total branch and leaf area of ​​the target crop in the target area can be calculated, which is convenient for determining the growth of the target crop based on the branch and leaf area of ​​a single target crop and the total branch and leaf area of ​​the target crop in the target area. This method can replace the existing image recognition and segmentation technology, and the use of point cloud segmentation can achieve accurate segmentation of a single crop, which is not affected by surface coverage and image color changes, has good reproducibility and scalability, and the calculation amount for statistically obtaining leaf area information is smaller and more efficient.

[0013] In a possible design, the simplification and editing of the three-dimensional point cloud model to remove redundant point clouds to obtain a branch and leaf point cloud model of the target crop in the target area includes:

[0014] Construct a curve function y=f(z) about frequency y and height z for the three-dimensional point cloud model, where the first-order derivative of the peak point is 0 and the second-order derivative is negative, and the first-order derivative of the trough point is 0 and the second-order derivative is positive;

[0015] Solve and obtain the peak and trough points of the curve function value in the set direction x;

[0016] The z value is determined by the adjacent peak points and trough points;

[0017] The point cloud is divided according to the z value, and some point clouds with z values ​​less than the set threshold are deleted to obtain the branch and leaf point cloud model of the target crop in the target area.

[0018] In one possible design, the method further includes:

[0019] Get the plot area of ​​the target area;

[0020] The leaf area index of the target crop is calculated based on the total branch and leaf area of ​​the target crop in the target area and the plot area of ​​the target area.

[0021] In a possible design, the branch and leaf point cloud model is rasterized to convert the branch and leaf point clouds in the branch and leaf point cloud model into raster pixels, including: importing the branch and leaf point cloud model into the ArcGIS platform, rasterizing the branch and leaf point clouds through ArcGIS's spatial conversion tools, and converting each branch and leaf point cloud into a raster pixel of a certain size.

[0022] In a possible design, the grid pixel size is determined according to the ground resolution of the ultra-low altitude remote sensing image data, and the total branch and leaf area of ​​the target crop in the target area is calculated according to the number of branch and leaf point clouds and the size of the grid pixels in the branch and leaf point cloud model, including: multiplying the number of branch and leaf point clouds by the pixel area of ​​the grid pixel to obtain the total branch and leaf area of ​​the target crop.

[0023] In a possible design, the position and attitude system data of ultra-low altitude remote sensing image data are imported and read, image matching is performed, and the coordinates of aerial triangulation are submitted for solution. The coordinates of the set ground phased points are combined for solution to obtain the absolute three-dimensional coordinate system of the target area and construct the initial three-dimensional point cloud model;

[0024] The initial 3D point cloud model is cut and screened to generate a 3D point cloud model of the target area.

[0025] In a second aspect, the present invention provides a leaf area counting device based on ultra-low altitude remote sensing, the device comprising:

[0026] An acquisition unit, used to acquire ultra-low altitude remote sensing image data of a target area;

[0027] A construction unit is used to solve the ultra-low altitude remote sensing image data of the target area and construct a corresponding three-dimensional point cloud model;

[0028] The simplification unit is used to simplify and edit the three-dimensional point cloud model, remove redundant point clouds, and obtain the branch and leaf point cloud model of the target crop in the target area;

[0029] A conversion unit, used for rasterizing the branch and leaf point cloud model, and converting the branch and leaf point cloud in the branch and leaf point cloud model into raster pixels;

[0030] The calculation unit is used to determine the branch and leaf area of ​​a single target crop according to the size of the grid pixel, and calculate the total branch and leaf area of ​​the target crop in the target area according to the number of branch and leaf point clouds in the branch and leaf point cloud model and the size of the grid pixel.

[0031] In a possible design, the acquisition unit is further used to acquire the plot area of ​​the target area; the calculation unit is further used to calculate the leaf area index of the target crop based on the total branch and leaf area of ​​the target crop in the target area and the plot area of ​​the target area.

[0032] In a third aspect, the present invention provides a leaf area counting device based on ultra-low altitude remote sensing, the device comprising:

[0033] A memory for storing instructions;

[0034] A processor is used to read the instructions stored in the memory and execute any one of the methods described in the first aspect according to the instructions.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon, and when the instructions are executed on a computer, the computer is enabled to execute any one of the methods described in the first aspect.

[0036] In a fifth aspect, the present invention provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute any one of the methods described in the first aspect.

[0037] The beneficial effects of the present invention are:

[0038] The present invention solves the ultra-low altitude remote sensing image data accordingly, constructs a three-dimensional point cloud model of the target area, and then performs point cloud simplification processing on the three-dimensional point cloud model, removes irrelevant point clouds, and only leaves the branch and leaf point clouds of the target crop, and then performs rasterization processing on the branch and leaf point clouds, converting them into corresponding raster pixels, so as to calculate the branch and leaf area of ​​a single target crop and the total branch and leaf area of ​​the target crop in the target area, so as to determine the growth of the target crop according to the branch and leaf area of ​​a single target crop and the total branch and leaf area of ​​the target crop in the target area. This method can replace the existing image recognition and segmentation technology, and can realize the accurate segmentation of a single crop by using point cloud segmentation, which is not affected by the changes in surface coverage and image color, has good reproducibility and generalizability, and the calculation amount of statistically obtaining leaf area information is smaller and more efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only 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.

[0040] Figure 1It is a schematic diagram of the method steps of the present invention;

[0041] Figure 2 It is a schematic diagram of the peaks and troughs of the curve function;

[0042] Figure 3 The figure is a schematic diagram of the process of obtaining the area of ​​branches and leaves on the shelf of a single plant;

[0043] Figure 4 It is a schematic diagram of the first device structure of the present invention;

[0044] Figure 5 It is a schematic diagram of the second device structure of the present invention. DETAILED DESCRIPTION

[0045] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. The specific structures and functional details disclosed herein are only used to describe the exemplary embodiments of the present invention. However, the present invention can be embodied in many alternative forms, and it should not be understood that the present invention is limited to the embodiments set forth herein.

[0046] It should be understood that the terms first, second, etc. are only used to distinguish descriptions and should not be understood as indicating or suggesting relative importance. Although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, the first unit may be referred to as the second unit, and similarly, the second unit may be referred to as the first unit without departing from the scope of the exemplary embodiments of the present invention.

[0047] In the following description, certain details are provided to facilitate a complete understanding of the example embodiments. However, it will be appreciated by those of ordinary skill in the art that the example embodiments may be implemented without these certain details. For example, the system may be shown in a block diagram to avoid obscuring the example with unnecessary details. In other embodiments, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the example embodiments.

[0048] Embodiment 1:

[0049] This embodiment provides a leaf area statistics method based on ultra-low altitude remote sensing, which can be applied to the monitoring of branch and leaf area of ​​various crops, such as Figure 1 As shown, the following steps are included:

[0050] S101. Acquire ultra-low altitude remote sensing image data of the target area.

[0051] In the specific implementation, taking kiwifruit plants as an example, based on field surveys, the boundaries of kiwifruit plots are obtained, and different photographic scales are selected according to the different growth stages of kiwifruit branches and leaves (germination, flowering, and fruiting) for UAV ultra-low altitude remote sensing photography; the UAV route mission is delineated, and according to the requirements of aerial photogrammetry, in order to build a relatively accurate three-dimensional field model, the actual route needs to be expanded to ensure the accuracy of later modeling; in order to ensure the accuracy of later plot and leaf area calculations, ground control points are set to perform absolute coordinate control of remote sensing images, and RTK (Real-time kinematic) is used to accurately measure the ground control points and collect and store ground points.

[0052] This embodiment uses photos to obtain the absolute coordinates of the ground point cloud based on the principle of photogrammetry; therefore, when the camera's internal orientation elements are known, the ground control points need to be known, and the collinear equation is used to solve the external orientation elements to obtain the absolute coordinates of the ground points. Based on this principle, a low-cost low-altitude UAV remote sensing platform is used to perform mission planning, data collection operations, ground coordinate measurement, etc. on the target area to complete the acquisition of low-altitude remote sensing images of the target detection area and obtain real-time ultra-low-altitude remote sensing image data.

[0053] In the field of ultra-low altitude remote sensing, the UAV remote sensing system composed of the UAV flight system, effective mission payload and ground support system has the characteristics of high timeliness, imaging under clouds and high mobility; the UAV flight system includes aircraft, navigation and control, data transmission and link, etc.; carrying different mission payloads can obtain rich ground information, such as high-resolution aerial cameras, hyperspectral cameras, infrared cameras, etc.; the ground support system implements the acquisition of the status information of the UAV remote sensing system to ensure real-time ground monitoring of the UAV.

[0054] S102. Calculate the ultra-low altitude remote sensing image data of the target area and construct a corresponding three-dimensional point cloud model.

[0055] In the specific implementation, the ultra-low altitude remote sensing image data collected by the drone is preprocessed, image matched and solved by aerial triangulation. Usually, image processing requires the use of third-party image stitching processing software, which imports and reads the high-precision position and attitude system data (POS, position and orientation system) of the image, performs image matching, and submits the coordinates for aerial triangulation solution. Commonly used stitching processing software includes Pix4D Mapper, Agisoft PhotoScan, Smart3D, etc. In the solution process, it is necessary to absolutely position the image system after the relative positioning is completed, and re-solve the coordinates of the ground phased points measured in the above steps to obtain the absolute three-dimensional coordinate system of the kiwifruit plot; finally, the software generates a three-dimensional point cloud model (Point Cloud) and digital orthophoto (DOM, Digital Orthophoto Map), digital surface model (DSM, Digital Surface Model) products.

[0056] S103. Simplify and edit the three-dimensional point cloud model, remove redundant point clouds, and obtain a branch and leaf point cloud model of the target crop in the target area.

[0057] In the specific implementation, the 3D point cloud model at this time is massive, including the entire point cloud data of the surface entity. It is necessary to remove the redundant point clouds to obtain the point cloud of the kiwi fruit branches and leaves on the shelf. The process includes:

[0058] For the three-dimensional point cloud model, a curve function y=f(z) about frequency y and height z is constructed, where the peak point satisfies the first-order derivative of 0 and the second-order derivative is negative, and the trough point satisfies the first-order derivative of 0 and the second-order derivative is positive; then the peak point and trough point of the curve function value in the set direction x are solved according to the first-order derivative and the second-order derivative, as shown in Figure 2 As shown;

[0059] First-order derivative:

[0060] Second order derivative:

[0061] The z value is determined by adjacent peak points and trough points; the point cloud is divided according to the z value, and the part of the point cloud with a z value less than the set threshold is deleted to obtain the branch and leaf point cloud model of the target crop in the target area. The amount of point cloud data after elimination is compressed, and the kiwi fruit branch and leaf point cloud is obtained after slight pruning, and the branch and leaf point cloud on the shelf can be directly statistically analyzed later.

[0062] S104. Rasterize the branch and leaf point cloud model, and convert the branch and leaf point cloud in the branch and leaf point cloud model into raster pixels.

[0063] In the specific implementation, the point cloud is classified and simplified after the simplified editing process in the above steps. Because the area of ​​branches and leaves on the shelf is to be obtained, the obtained branch and leaf point cloud cannot be used to count the area, so the point cloud needs to be rasterized. The software needed here is the ArcGIS series software, which can perform planar rasterization on spatial point clouds. The branch and leaf point cloud is rasterized using ArcGIS's spatial conversion tool. After rasterization, the point cloud of kiwifruit branches and leaves on the shelf is converted into raster pixels of a certain size, and the size of the raster pixels is determined by the ground resolution of the corresponding remote sensing image.

[0064] S105. Determine the branch and leaf area of ​​a single target crop according to the size of the grid pixel, and calculate the total branch and leaf area of ​​the target crop in the target area according to the number of branch and leaf point clouds in the branch and leaf point cloud model and the size of the grid pixel.

[0065] In specific implementation, the simple calculation method of kiwifruit branch and leaf area can be obtained by multiplying the number of branch and leaf point clouds and the pixel area of ​​the rasterized grid pixel to obtain the final area of ​​kiwifruit branches and leaves. Finally, the ratio of the kiwifruit branch and leaf area to the obtained plot area is the final branch and leaf coverage of the kiwifruit plot, that is, the leaf area index. According to the above steps, the process of obtaining the branch and leaf area of ​​a single plant is as follows: Figure 3 As shown, the dense point cloud of the three-dimensional point cloud model is cropped to obtain the point cloud of the target plant area, and then the point cloud of the single plant area is extracted for simplified processing and GIS analysis and screening to obtain the branch and leaf area of ​​the single plant.

[0066] Through this method flow, the branch and leaf area of ​​specific crop plants can be segmented, extracted, and converted in a simpler, faster, more efficient, and less expensive manner, and the branch and leaf area of ​​plants in a small area can be quickly obtained, which can provide the necessary basic data support for quantitative monitoring of crops, determination of pests and diseases, and yield estimation. Obviously, in addition to the same data results that can be obtained in each of the above steps, technicians can expand and extend the present invention (for example, using different photogrammetry tools to acquire ground data, using different modeling software to build corresponding point cloud models, and using different point cloud editing software to extract the area of ​​kiwi branches and leaves on the shelves, etc.), aiming at the process of using different tools to acquire images, and different software to edit and extract the area of ​​kiwi branches and leaves on the shelves without departing from the spirit and scope of the present invention. In this way, if these modifications and variations of the present invention belong to the scope of the claims of the present invention and their equivalent technologies, the present invention also includes these modifications and variations.

[0067] Embodiment 2:

[0068] This embodiment provides a leaf area counting device based on ultra-low altitude remote sensing, such as Figure 4 As shown, including:

[0069] An acquisition unit, used to acquire ultra-low altitude remote sensing image data of a target area;

[0070] A construction unit is used to solve the ultra-low altitude remote sensing image data of the target area and construct a corresponding three-dimensional point cloud model;

[0071] The simplification unit is used to simplify and edit the three-dimensional point cloud model, remove redundant point clouds, and obtain the branch and leaf point cloud model of the target crop in the target area;

[0072] A conversion unit, used for rasterizing the branch and leaf point cloud model, and converting the branch and leaf point cloud in the branch and leaf point cloud model into raster pixels;

[0073] The calculation unit is used to determine the branch and leaf area of ​​a single target crop according to the size of the grid pixel, and calculate the total branch and leaf area of ​​the target crop in the target area according to the number of branch and leaf point clouds in the branch and leaf point cloud model and the size of the grid pixel.

[0074] In a possible design, the acquisition unit is further used to acquire the plot area of ​​the target area; the calculation unit is further used to calculate the leaf area index of the target crop based on the total branch and leaf area of ​​the target crop in the target area and the plot area of ​​the target area.

[0075] Embodiment 3:

[0076] This embodiment provides another leaf area counting device based on ultra-low altitude remote sensing, such as Figure 5 As shown, at the hardware level, it includes:

[0077] A memory for storing instructions;

[0078] The processor is used to read the instructions stored in the memory and execute the Chinese herbal medicine quality inspection method described in Example 1 according to the instructions.

[0079] Optionally, the computer device further comprises an internal bus and a communication interface. The processor, the memory and the communication interface may be interconnected via the internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc.

[0080] The memory may include, but is not limited to, random access memory (RAM), read only memory (ROM), flash memory, first input first output (FIFO) and / or first in last out (FILO) memory, etc. The processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0081] Embodiment 4:

[0082] This embodiment provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed on a computer, the computer executes the leaf area statistics method based on ultra-low altitude remote sensing described in Embodiment 1. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0083] Embodiment 5:

[0084] This embodiment provides a computer program product including instructions, which, when executed on a computer, enables the computer to execute the leaf area statistics method based on ultra-low altitude remote sensing described in Embodiment 1. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0085] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The leaf area statistical method based on ultra-low altitude remote sensing is characterized by: include: Acquire ultra-low altitude remote sensing image data of the target area; Solve the ultra-low altitude remote sensing image data of the target area and construct the corresponding three-dimensional point cloud model; The three-dimensional point cloud model is simplified and edited, and redundant point clouds are removed to obtain a branch and leaf point cloud model of a target crop in a target area, including: constructing a curve function y=f(z) about frequency y and height z for the three-dimensional point cloud model, wherein the peak point satisfies that the first-order derivative is 0 and the second-order derivative is negative, and the trough point satisfies that the first-order derivative is 0 and the second-order derivative is positive; solving and obtaining the peak point and trough point of the curve function value in a set direction x; determining the z value through adjacent peak points and trough points; dividing the point cloud according to the z value, deleting part of the point cloud with a z value less than a set threshold, and obtaining a branch and leaf point cloud model of the target crop in the target area; The branch and leaf point cloud model is rasterized to convert the branch and leaf point cloud in the branch and leaf point cloud model into raster pixels; The branch and leaf area of ​​a single target crop is determined according to the size of the grid pixels, and the total branch and leaf area of ​​the target crop in the target area is calculated according to the number of branch and leaf point clouds in the branch and leaf point cloud model and the size of the grid pixels.

2. The leaf area statistics method based on ultra-low altitude remote sensing according to claim 1, characterized in that: The method further comprises: Get the plot area of ​​the target area; The leaf area index of the target crop is calculated based on the total branch and leaf area of ​​the target crop in the target area and the plot area of ​​the target area.

3. The leaf area statistics method based on ultra-low altitude remote sensing according to claim 1, characterized in that: The rasterization processing of the branch and leaf point cloud model converts the branch and leaf point cloud in the branch and leaf point cloud model into raster pixels, including: importing the branch and leaf point cloud model into the ArcGIS platform, rasterizing the branch and leaf point cloud through the ArcGIS spatial conversion tool, and converting each branch and leaf point cloud into a raster pixel of a certain size.

4. The leaf area statistics method based on ultra-low altitude remote sensing according to claim 3 is characterized in that: The grid pixel size is determined according to the ground resolution of the ultra-low altitude remote sensing image data, and the total branch and leaf area of ​​the target crop in the target area is calculated according to the number of branch and leaf point clouds in the branch and leaf point cloud model and the size of the grid pixels, including: multiplying the number of branch and leaf point clouds by the pixel area of ​​the grid pixel to obtain the total branch and leaf area of ​​the target crop.

5. The leaf area statistics method based on ultra-low altitude remote sensing according to claim 1, characterized in that: The ultra-low altitude remote sensing image data of the target area is solved to construct a corresponding three-dimensional point cloud model, including: Import and read the position and attitude system data of ultra-low altitude remote sensing image data, perform image matching, and submit the coordinates solved by aerial triangulation. Combined with the coordinates of the set ground phased points, solve the absolute three-dimensional coordinate system of the target area and construct the initial three-dimensional point cloud model. The initial 3D point cloud model is cut and screened to generate a 3D point cloud model of the target area.

6. A leaf area counting device based on ultra-low altitude remote sensing, characterized in that: The device comprises: An acquisition unit, used to acquire ultra-low altitude remote sensing image data of a target area; A construction unit is used to solve the ultra-low altitude remote sensing image data of the target area and construct a corresponding three-dimensional point cloud model; The simplification unit is used to simplify and edit the three-dimensional point cloud model, remove redundant point clouds, and obtain the branch and leaf point cloud model of the target crop in the target area, including: constructing a curve function y=f(z) about frequency y and height z for the three-dimensional point cloud model, wherein the peak point satisfies the first-order derivative of 0 and the second-order derivative is negative, and the trough point satisfies the first-order derivative of 0 and the second-order derivative is positive; solving and obtaining the peak point and trough point of the curve function value in the set direction x; determining the z value through adjacent peak points and trough points; dividing the point cloud according to the z value, deleting some point clouds with z values ​​less than the set threshold, and obtaining the branch and leaf point cloud model of the target crop in the target area; A conversion unit, used for rasterizing the branch and leaf point cloud model, and converting the branch and leaf point cloud in the branch and leaf point cloud model into raster pixels; The calculation unit is used to determine the branch and leaf area of ​​a single target crop according to the size of the grid pixel, and calculate the total branch and leaf area of ​​the target crop in the target area according to the number of branch and leaf point clouds in the branch and leaf point cloud model and the size of the grid pixel.

7. The leaf area counting device based on ultra-low altitude remote sensing according to claim 6, characterized in that: The acquisition unit is further used to acquire the plot area of ​​the target region; the calculation unit is further used to calculate the leaf area index of the target crop according to the total branch and leaf area of ​​the target crop in the target region and the plot area of ​​the target region.

8. A leaf area counting device based on ultra-low altitude remote sensing, characterized in that: The device comprises: A memory for storing instructions; A processor, configured to read the instructions stored in the memory and execute the method according to any one of claims 1 to 5 according to the instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the computer is enabled to execute the method according to any one of claims 1 to 5.

Images