A vegetation leaf area index inversion method and system based on a laser point cloud

Abstract

Embodiments of the present disclosure provide a vegetation leaf area index inversion method and system based on laser point cloud. Applied to the field of agricultural meteorological observation technology, the method comprises: acquiring laser point cloud data of the whole growth cycle of vegetation; wherein the laser point cloud data comprises vegetation canopy echo point cloud and ground echo point cloud; performing probability density statistics on height data in the laser point cloud data at a preset time interval and determining the height of the gradient maximum point; performing cloth simulation random filtering on the laser point cloud data according to the height of the gradient maximum point to remove ground points; and performing inversion on the laser point cloud data after removing the ground points based on the Beer-Lambert principle to obtain the vegetation leaf area index. In this way, the automatic calculation of the vegetation leaf area index LAI can be realized, and the spatiotemporal coverage and accuracy of the monitoring can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of agricultural meteorological observation, and in particular to a method and system for inverting vegetation leaf area index based on laser point clouds. Background Technology

[0002] Leaf area index (LAI) is a crucial parameter describing vegetation canopy structure, playing a vital role in monitoring crop growth, assessing ecological and environmental changes, and studying global climate change. Traditional LAI measurement methods, such as direct measurement and image analysis, typically require significant time and manpower and can be destructive to vegetation during measurement, hindering continuous crop monitoring. To address these issues, remote sensing technology has been widely applied to the quantitative estimation of crop growth parameters.

[0003] In recent years, LiDAR (Light Detection and Ranging) technology has shown great potential in acquiring vegetation structure parameters due to its high precision, high efficiency, and non-destructive measurement capabilities. Three-dimensional point cloud data acquired through LiDAR technology can provide a detailed description of vegetation canopy structure, which can then be used for LAI (Local Area Inversion) retrieval. For example, using ground-based laser scanning (TLS) to acquire vegetation structure parameters and segmenting the leaf echo point cloud using voxelization significantly improves the accuracy of LAI retrieval. However, existing LiDAR-based LAI retrieval methods still have some shortcomings. For instance, some methods suffer from algorithmic complexity and high computational cost during data processing, limiting their widespread application in practice. Furthermore, the canopy structure characteristics differ for different growth stages and vegetation varieties; how to further improve the accuracy and applicability of LAI retrieval remains a key research focus.

[0004] In summary, this invention aims to provide a method for inverting the leaf area index (LAI) of vegetation based on laser point clouds. This method can fully utilize the advantages of lidar technology in acquiring vegetation structure parameters, and combined with optimized algorithms and models, it can achieve accurate, rapid, and non-destructive measurement of vegetation LAI, providing strong technical support for precise vegetation growth monitoring and agricultural development. Summary of the Invention

[0005] This disclosure provides a method and system for inverting vegetation leaf area index based on laser point cloud, which solves the technical problem of untimely and inaccurate vegetation growth monitoring.

[0006] According to a first aspect of this disclosure, a method for inverting vegetation leaf area index based on laser point clouds is provided. The method includes:

[0007] Acquire laser point cloud data for the entire vegetation growth cycle; the laser point cloud data includes vegetation canopy echo point cloud and ground echo point cloud.

[0008] The height data in the laser point cloud data is statistically analyzed at preset time intervals to determine the height of the point with the maximum gradient.

[0009] Based on the height of the point with the maximum gradient, the laser point cloud data is subjected to cloth simulation random filtering to remove ground echo point clouds;

[0010] Based on Beer-Lambert's principle, the vegetation leaf area index is obtained by inverting the laser point cloud data after removing the ground echo point cloud.

[0011] As described above and in any possible implementation, a further implementation is provided in which the acquisition of laser point cloud data throughout the vegetation growth cycle further includes:

[0012] After rotating and correcting the laser point cloud data, outliers are removed.

[0013] As described above and in any possible implementation, a further implementation is provided, wherein the step of performing cloth simulation random filtering to remove ground points from the laser point cloud data based on the height of the maximum gradient point includes:

[0014] The ground echo point cloud is removed by cyclic fabric simulation random filtering. If the height of the removed ground echo point cloud exceeds the height of the maximum gradient point, the laser point cloud data after removing the ground echo point cloud is inverted based on the Beer-Lambert principle; otherwise, the ground echo point cloud is removed by fabric simulation random filtering.

[0015] As described above and in any possible implementation, a further implementation is provided, in which random filtering of the laser point cloud data based on the height of the point with the maximum gradient to remove ground points further includes:

[0016] The probability density is statistically analyzed at preset time intervals, and the height of the first gradient descent that is fastest is determined as the highest height for segmenting the ground echo point cloud, thereby limiting the number of loops for fabric simulation of random filtering.

[0017] In addition to the aspects and any possible implementations described above, a further implementation is provided, in which the leaf area index is calculated based on Beer-Lambert's principle and expressed by the formula:

[0018]

[0019]

[0020] Among them, f coverLet P(θ) represent the vegetation canopy coverage, μ represent the porosity, μ represent the cosine of the solar zenith angle (cosθ), θ represent the lidar scanning angle / solar zenith angle, G represent the average projection of all vegetation leaves per unit area onto the plane perpendicular to the solar incidence, taken as an empirical value of 0.5, λ0 represent the Nilsson parameter, taken as an empirical value of -1, and n represent the vegetation canopy coverage. crop For vegetation canopy echo point clouds, n cropland This is the general point cloud.

[0021] According to a second aspect of this disclosure, a vegetation leaf area index inversion system based on laser point clouds is provided. The system includes:

[0022] The acquisition module is used to acquire laser point cloud data throughout the entire growth cycle of vegetation; the laser point cloud data includes vegetation canopy echo point cloud and ground echo point cloud.

[0023] The processing module is used to perform probability density statistics on the height data in the laser point cloud data at preset time intervals and determine the height of the point with the maximum gradient.

[0024] The processing module is used to perform cloth simulation random filtering on the laser point cloud data to remove ground echo point clouds based on the height of the maximum gradient point.

[0025] The inversion module is used to invert laser point cloud data after removing ground echo point clouds based on the Beer-Lambert principle to obtain the vegetation leaf area index.

[0026] According to a third aspect of this disclosure, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described above.

[0027] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the methods according to the first and / or second aspects of this disclosure.

[0028] First, laser point cloud observation data throughout the entire vegetation growth cycle is acquired. Point cloud data with obvious missing or erroneous data are removed. The point cloud data is preprocessed, and then ground echo point clouds are filtered out using probability density statistics and fabric simulation random filtering methods. Finally, the laser point cloud data after removing ground echo point clouds is inverted based on the Beer-Lambert principle to obtain the vegetation leaf area index.

[0029] The beneficial effects of this disclosure include: (1) improved production efficiency: automated vegetation leaf area index (LAI) monitoring can help to accurately monitor and determine the development of vegetation, take appropriate measures, and improve the quality of vegetation.

[0030] (2) Reduce vegetation monitoring costs: Traditional observation methods rely on manual observation and recording. Using algorithms to automatically monitor the leaf area index (LAI) can greatly reduce the burden of manpower and labor costs.

[0031] (3) Promote intelligent development: Observing the leaf area index (LAI) of vegetation based on physical simulation methods is conducive to improving the modernization level and technological content of production, thereby promoting sustainable development;

[0032] (4) Provide data analysis and research: By collecting a large amount of vegetation leaf area index (LAI), we can discover the scientific basis for the laws of vegetation growth and development, which is conducive to improving planting techniques and management.

[0033] It should be understood that the description in the Summary of the Invention section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0034] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0035] Figure 1 A flowchart of a vegetation leaf area index inversion method based on laser point cloud according to an embodiment of the present disclosure is shown;

[0036] Figure 2 A schematic diagram illustrating a data missing condition according to an embodiment of the present disclosure is shown;

[0037] Figure 3 A schematic diagram showing data before and after rotation correction according to an embodiment of the present disclosure is shown;

[0038] Figure 4 A schematic diagram illustrating a data anomaly according to an embodiment of the present disclosure is shown;

[0039] Figure 5 A schematic diagram of the distribution of maize leaf area index according to an embodiment of the present disclosure is shown;

[0040] Figure 6 A block diagram of a vegetation leaf area index inversion system based on laser point clouds according to an embodiment of the present disclosure is shown.

[0041] Figure 7 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0043] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0044] This disclosure first acquires laser point cloud observation data throughout the entire vegetation growth cycle. Point cloud data with significant missing or erroneous data are then removed. The point cloud data undergoes preprocessing, followed by filtering out ground echo point clouds using probability density statistics and fabric simulation random filtering methods. Finally, based on the Beer-Lambert principle, the laser point cloud data after removing ground echo point clouds is inverted to obtain the vegetation leaf area index. This enables automated calculation of leaf area index during vegetation development, improving the spatiotemporal coverage and accuracy of monitoring.

[0045] Figure 1 A flowchart illustrating a vegetation leaf area index inversion method based on laser point clouds according to an embodiment of this disclosure is shown. Figure 1 As shown, a method for inverting vegetation leaf area index based on laser point clouds includes:

[0046] S101, acquire laser point cloud data for the entire growth cycle of vegetation; the laser point cloud data includes vegetation canopy echo point cloud and ground echo point cloud.

[0047] The acquisition of laser point cloud data for the entire vegetation growth cycle described in S101 also includes removing outliers after rotating and correcting the laser point cloud data.

[0048] In some embodiments, Figure 2 The diagram illustrates a data missing problem according to an embodiment of the present disclosure. For point cloud data with missing data, the present disclosure uses manual screening to perform quality control on the point cloud data, deleting data from historical data that has problems such as missing data, obvious data errors, or data corruption.

[0049] In some embodiments, after removing data with issues such as file corruption or data corruption, a specific day is selected from the remaining data for 3D drawing. Images are saved at the initial viewpoints of 0°, 30°, 60°, and 90° horizontally, as well as images in each direction at the same viewpoints. Rotation parameters are then set based on these images to ensure that the underlying surface of the final point cloud data is parallel to the xoy axis. Figure 3 The diagram illustrates data before and after rotation correction according to an embodiment of the present disclosure, wherein the specific calculation method for rotation correction is shown in the following formula:

[0050] (1) Rotate around the z-axis by an angle α:

[0051]

[0052] x′=cosα·x-sinα·y

[0053] y′=sinα·x+cosα·y

[0054] z′=z

[0055] (2) Rotate around the y-axis by an angle β:

[0056]

[0057] x′=cosβ·x+sinβ·z

[0058] y′=y

[0059] z′=-sinβ·x+cosβ·z

[0060] (3) Rotate around the x-axis by an angle θ:

[0061]

[0062] x′=x

[0063] y′=cosθ·y-sinθ·z

[0064] z′=sinθ·y+cosθ·z

[0065] In some embodiments, Figure 4 A schematic diagram of data anomalies according to an embodiment of the present disclosure is shown, in which outliers are removed from the rotated point cloud data by means of box plots, threshold monitoring, noise filtering, etc.

[0066] Specifically, a box plot structure is constructed based on the distribution pattern of vegetation point cloud data in each dimension. For the spatial coordinate dimension, the x, y, and z coordinate values ​​are used as variables to draw the box plot. The box covers the middle 50% of the data, the box line represents the upper and lower quartile range, and the whiskers extend to a certain multiple of the interquartile range. Data points outside the whiskers are initially identified as outliers.

[0067] Specifically, threshold monitoring mainly involves setting reasonable threshold ranges for specific attributes of vegetation point cloud data. Regarding reflectance intensity, upper and lower thresholds are determined based on the common reflectance intensity ranges of vegetation leaves and stems, as well as the performance parameters of the measuring equipment. When the reflectance intensity of the point cloud data exceeds this range, it is marked as an outlier.

[0068] Specifically, noise filtering mainly eliminates noise interference introduced by measuring equipment, environmental factors, etc.

[0069] S102, perform probability density statistics on the height data in the laser point cloud data at preset time intervals and determine the height of the point with the maximum gradient.

[0070] In some embodiments, probability density statistics are performed on the height point cloud data of the vegetation growth cycle and a probability density map is plotted for each day to determine the height of the point with the maximum gradient.

[0071] S103, perform cloth simulation random filtering on the laser point cloud data to remove ground echo point clouds based on the height of the maximum gradient point.

[0072] In some embodiments, Cloth Simulation Filtering (CSF) is used to remove ground echo point clouds. If the height of the removed ground echo point cloud exceeds the height of the maximum gradient point, the laser point cloud data after removing the ground echo point cloud is inverted based on the Beer-Lambert principle; otherwise, Cloth Simulation Filtering is continued to remove ground echo point clouds.

[0073] Specifically, the soil is imagined as multiple layers of fabric. The random filtering (CSF) algorithm is used to remove soil points through multiple iterations of fabric application. During each removal of ground echo point clouds, the height of the highest point in the removed ground echo point cloud set is continuously monitored and compared in real time with the height of the previously determined maximum gradient point. If the height of the highest point is less than the height of the maximum gradient point, it indicates that there may still be ground echo point clouds that have not been completely removed. The fabric application simulation CSF filtering operation needs to be performed again to ensure that ground points are removed as thoroughly as possible while avoiding the accidental deletion of vegetation points.

[0074] In some embodiments, probability density statistics are performed at preset time intervals, and the height of the first gradient descent with the fastest speed is determined as the highest height of the segmented ground point, thereby limiting the number of loops for fabric simulation random filtering.

[0075] Specifically, the number of cycles is limited by probability density statistics. As the vegetation grows and becomes denser, the number of points hitting the vegetation gradually exceeds the number of points on the ground, and the probability of ground points appearing decreases rapidly. Taking the point cloud of one observation as a sample, a probability density distribution map is drawn for each day. The height of the first gradient descent with the fastest speed is taken as the highest height of the segmented ground echo point cloud, which is used to limit the number of cycles of cloth simulation random filtering.

[0076] S104, based on Beer-Lambert's principle, inverts the laser point cloud data after removing ground echo point clouds to obtain the vegetation leaf area index.

[0077] In some embodiments, after multiple iterations of filtering, if the height of the highest point of the removed ground echo point cloud is found to be greater than or equal to the height of the maximum gradient point, the point cloud data of ground points and non-ground points are statistically analyzed, and the leaf area index of vegetation is calculated based on Beer Lambert's law.

[0078] In some embodiments, the leaf area index calculated based on Beer-Lambert's principle is expressed by the following formula:

[0079]

[0080]

[0081] Among them, f cover Let P(θ) represent the vegetation canopy coverage, μ represent the porosity, μ represent the cosine of the solar zenith angle (cosθ), θ represent the lidar scanning angle / solar zenith angle, G represent the average projection of all vegetation leaves per unit area onto the plane perpendicular to the solar incidence, taken as an empirical value of 0.5, λ0 represent the Nilsson parameter, taken as an empirical value of -1, and n represent the vegetation canopy coverage. crop For vegetation canopy echo point clouds, n cropland This is the general point cloud.

[0082] In some embodiments, various parameters need to be adjusted and improved to enhance the accuracy of vegetation leaf area index calculation.

[0083] Specifically, since the ground in the original data has a certain angle with the z-axis, the original data needs to be rotated and corrected before the ground points and crop points are separated. However, since the rotation correction is done manually, the setting of the rotation angle is somewhat subjective. Therefore, after obtaining the final result, the LiDAR scanning angle and rotation angle will be adjusted according to the result.

[0084] Specifically, since the threshold obtained using probability density is a relatively small range, the number of iterations of the fabric simulation random filtering CSF algorithm will be adjusted based on the results to make the results more reasonable.

[0085] The following detailed description, with reference to a specific embodiment, illustrates a vegetation leaf area index inversion method 100 based on laser point clouds provided in this disclosure, as shown below:

[0086] First, we obtained laser point cloud data of the entire corn growth cycle in 2023 from an agricultural website, including echo point clouds of the corn canopy and echo point clouds of the ground.

[0087] After rotating and correcting the corn laser point cloud data, outlier removal was performed. First, data with obvious errors or corruption were manually filtered out. Then, the remaining data was rotated and corrected so that the underlying surface of the final point cloud data was parallel to the xoy axis. Finally, outlier removal was performed on the rotated and corrected point cloud data using methods such as box plots, threshold monitoring, and noise filtering.

[0088] The height data in the corn laser point cloud data is statistically analyzed for probability density and a probability density map is plotted daily to determine the height of the maximum gradient point. Based on the determined maximum height, the corn laser point cloud data is subjected to cloth simulation random filtering to remove ground echo point clouds. If the height of the removed ground echo point cloud exceeds the height of the maximum gradient point, the corn laser point cloud data after removing the ground echo point cloud is inverted based on the Beer-Lambert principle; otherwise, cloth simulation random filtering is continued to remove ground echo point clouds.

[0089] Finally, based on Beer-Lambert's principle, the maize laser point cloud data after removing ground echo point clouds was inverted to obtain the maize leaf area index. Figure 5 A schematic diagram of the distribution of maize leaf area index according to an embodiment of the present disclosure is shown.

[0090] According to the embodiments of this disclosure, the following technical effects are achieved:

[0091] (1) Improve production efficiency: Automated vegetation leaf area index (LAI) monitoring can help accurately monitor and determine the development of vegetation, and take appropriate measures to improve the quality of vegetation.

[0092] (2) Reduce vegetation monitoring costs: Traditional observation methods rely on manual observation and recording. Using algorithms to automatically monitor the leaf area index (LAI) can greatly reduce the burden of manpower and labor costs.

[0093] (3) Promote intelligent development: Observing the leaf area index (LAI) of vegetation based on physical simulation methods is conducive to improving the modernization level and technological content of production, thereby promoting sustainable development;

[0094] (4) Provide data analysis and research: By collecting a large amount of vegetation leaf area index (LAI), we can discover the scientific basis for the laws of vegetation growth and development, which is conducive to improving planting techniques and management.

[0095] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0096] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0097] Figure 6 A block diagram of a vegetation leaf area index inversion system 600 based on laser point clouds according to an embodiment of the present disclosure is shown. Figure 6 As shown, system 600 includes:

[0098] The acquisition module is used to acquire laser point cloud data throughout the entire growth cycle of vegetation; the laser point cloud data includes vegetation canopy echo point cloud and ground echo point cloud.

[0099] The processing module is used to perform probability density statistics on the height data in the laser point cloud data at preset time intervals and determine the height of the point with the maximum gradient.

[0100] The processing module is used to perform cloth simulation random filtering on the laser point cloud data to remove ground echo point clouds based on the height of the maximum gradient point.

[0101] The inversion module is used to invert laser point cloud data after removing ground echo point clouds based on the Beer-Lambert principle to obtain the vegetation leaf area index.

[0102] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0103] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0104] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0105] Figure 7 A schematic block diagram of an electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0106] Electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in ROM 702 or a computer program loaded into RAM 703 from storage unit 708. RAM 703 can also store various programs and data required for the operation of electronic device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. I / O interface 705 is also connected to bus 704.

[0107] Multiple components in electronic device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of displays, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows electronic device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0108] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform method 100 by any other suitable means (e.g., by means of firmware).

[0109] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0112] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including voice input, speech input, or tactile input).

[0113] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0114] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0115] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0116] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for inverting vegetation leaf area index based on laser point clouds, comprising: Acquire laser point cloud data for the entire vegetation growth cycle; the laser point cloud data includes vegetation canopy echo point cloud and ground echo point cloud. The height data in the laser point cloud data is statistically analyzed at preset time intervals to determine the height of the point with the maximum gradient. Based on the height of the point with the maximum gradient, the laser point cloud data is subjected to cloth simulation random filtering to remove ground echo point clouds; wherein, it includes: The ground echo point cloud is removed by cyclic fabric simulation random filtering. If the height of the removed ground echo point cloud exceeds the height of the maximum gradient point, the laser point cloud data after removing the ground echo point cloud is inverted based on the Beer-Lambert principle; otherwise, the ground echo point cloud is removed by fabric simulation random filtering. Based on Beer-Lambert's principle, the vegetation leaf area index is obtained by inverting the laser point cloud data after removing the ground echo point cloud.

2. The method according to claim 1, characterized in that, The acquisition of laser point cloud data for the entire vegetation growth cycle also includes: After rotating and correcting the laser point cloud data, outliers are removed.

3. The method according to claim 1, characterized in that, The step of performing cloth simulation random filtering on the laser point cloud data to remove ground echo point clouds based on the height of the maximum gradient point also includes: The probability density is statistically analyzed at preset time intervals, and the height of the first gradient descent that is fastest is determined as the highest height for segmenting the ground echo point cloud, thereby limiting the number of loops for fabric simulation of random filtering.

4. The method according to claim 1, characterized in that, The leaf area index calculated based on Beer-Lambert's principle is expressed by the following formula: in, For vegetation canopy coverage, Porosity The cosine of the solar zenith angle , Where is the lidar scanning angle / solar zenith angle, and G is the average projection of all vegetation leaves per unit area onto the plane perpendicular to the solar incidence, taken as an empirical value of 0.

5. For the Nelson parameter, take the empirical value -1. Echo point clouds of vegetation canopy, For the general point cloud, This is a ground echo point cloud.

5. A vegetation leaf area index inversion system based on laser point clouds, comprising: The acquisition module is used to acquire laser point cloud data throughout the entire growth cycle of vegetation; the laser point cloud data includes vegetation canopy echo point cloud and ground echo point cloud. The processing module is used to perform probability density statistics on the height data in the laser point cloud data at preset time intervals and determine the height of the point with the maximum gradient. The processing module is used to perform cloth simulation random filtering on the laser point cloud data based on the height of the maximum gradient point to remove ground echo point clouds; wherein, it includes: The ground echo point cloud is removed by cyclic fabric simulation random filtering. If the height of the removed ground echo point cloud exceeds the height of the maximum gradient point, the laser point cloud data after removing the ground echo point cloud is inverted based on the Beer-Lambert principle; otherwise, the ground echo point cloud is removed by fabric simulation random filtering. The inversion module is used to invert laser point cloud data after removing ground echo point clouds based on the Beer-Lambert principle to obtain the vegetation leaf area index.

6. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in any one of claims 1-4.

7. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-4.

Images