Bamboo forest growth monitoring method and device based on multispectral image

Abstract

The invention provides a bamboo forest growth monitoring method and device based on a multispectral image, and relates to the technical field of remote sensing monitoring, and the method comprises the steps: obtaining a multispectral image of a to-be-detected bamboo forest through a multispectral camera, and enabling the multispectral camera to be carried on an unmanned aerial vehicle; based on the multispectral image, growth indexes of the bamboo forest to be detected are obtained, and the growth indexes comprise the height of bamboo plants, the number of the bamboo plants, chlorophyll content indication values of the bamboo plants and biomass of the bamboo plants; based on the growth indexes, determining the bamboo forest growth vigor. According to the bamboo forest growth vigor monitoring method based on the multispectral image, the growth vigor of the bamboo forest is comprehensively analyzed through all growth indexes, and accurate and efficient growth vigor monitoring of the large-area regional bamboo forest is achieved.

Description

Technical Field

[0001] This invention relates to the field of remote sensing monitoring technology, and in particular to a method and device for monitoring bamboo forest growth based on multispectral images. Background Technology

[0002] Bamboo forests are single-dominant species communities composed of bamboo plants, widely distributed and with numerous species. In recent years, the bamboo industry has developed rapidly, and the planting area of ​​bamboo forests has increased rapidly. As the bamboo industry's demands for bamboo growth rate and quality continue to rise, the need for regional bamboo forest growth monitoring is becoming increasingly urgent.

[0003] Existing methods for monitoring bamboo forest growth mainly include empirical judgment and testing methods. Empirical judgment relies heavily on subjective human experience, making it difficult to establish unified standards, severely impacting accuracy, and resulting in low efficiency. Testing methods, on the other hand, obtain information on bamboo forest growth characteristics through extensive field measurements and tests. Compared to empirical judgment, these methods offer higher reliability, but require significant manpower and resources, leading to high costs and low efficiency. Therefore, existing bamboo forest growth monitoring methods cannot simultaneously achieve both accuracy and efficiency when monitoring the growth of regional bamboo forests. Summary of the Invention

[0004] This invention provides a method and device for monitoring bamboo forest growth based on multispectral images, which solves the technical problem that existing technologies cannot accurately and efficiently monitor the growth of large-area regional bamboo forests.

[0005] This invention provides a method for monitoring bamboo forest growth based on multispectral images, comprising the following steps: Multispectral images of the bamboo forest under test are acquired using a multispectral camera mounted on a drone. Based on the multispectral images, growth indicators of the bamboo forest to be tested are obtained; the growth indicators include bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass. The growth status of the bamboo forest is determined based on the aforementioned growth indicators.

[0006] According to the present invention, a method for monitoring bamboo forest growth based on multispectral images is provided, wherein obtaining growth indicators of the bamboo forest under test based on the multispectral images includes: Based on the multispectral images, a digital land surface model is generated; Threshold segmentation is performed on the multispectral image to obtain a point image of the soil area of ​​the bamboo forest to be tested; Using the height data of the center point of the patch in the soil area point image as sample points, interpolation is performed on the soil area point image to obtain the soil area surface data. Based on the soil area areal data, a soil height layer is simulated for the bamboo forest to be tested; The bamboo plant height is obtained by performing a difference operation between the digital surface model and the soil height layer.

[0007] According to the present invention, a method for monitoring bamboo forest growth based on multispectral images is provided, wherein generating a digital land surface model based on the multispectral images includes: Atmospheric correction and radiometric calibration are performed on the multispectral images to obtain surface reflectance data; Feature extraction is performed on the surface reflectance data to obtain surface feature points; The surface features are converted into a three-dimensional coordinate point cloud to generate a digital surface model.

[0008] According to the present invention, a method for monitoring bamboo forest growth based on multispectral images is provided, wherein obtaining growth indicators of the bamboo forest under test based on the multispectral images includes: The multispectral image is input into the first model to obtain the number of bamboo plants output by the first model. The first model is trained using the first historical multispectral image as feature data and the corresponding measured number of bamboo plants as label data.

[0009] According to the present invention, a method for monitoring bamboo forest growth based on multispectral images is provided, wherein obtaining growth indicators of the bamboo forest under test based on the multispectral images includes: The multispectral image is input into the second model to obtain the chlorophyll content indicator value of the bamboo plant output by the second model; The second model is trained using the second historical multispectral image as feature data and the corresponding measured chlorophyll content of bamboo plants as label data.

[0010] According to the present invention, a method for monitoring bamboo forest growth based on multispectral images is provided, wherein obtaining growth indicators of the bamboo forest under test based on the multispectral images includes: The multispectral image is input into the third model to obtain the bamboo biomass output by the third model; The third model is trained using the third historical multispectral image as feature data and the corresponding measured bamboo biomass as label data.

[0011] According to the present invention, a method for monitoring bamboo forest growth based on multispectral images is provided, wherein determining the bamboo forest growth based on the growth indicators includes: When all growth indicators are greater than or equal to the corresponding preset thresholds, the bamboo forest is considered to be growing well. If any of the growth indicators is less than the corresponding preset threshold, the bamboo forest is considered to be in poor condition.

[0012] The present invention also provides a bamboo forest growth monitoring device based on multispectral images, comprising the following modules: The acquisition module is used to acquire multispectral images of the bamboo forest under test using a multispectral camera; the multispectral camera is mounted on a drone. The quantization module is used to obtain the growth indicators of the bamboo forest to be tested based on the multispectral image; the growth indicators include bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass. The monitoring module is used to determine the growth status of the bamboo forest based on the growth indicators.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the bamboo forest growth monitoring method based on multispectral images as described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the bamboo forest growth monitoring method based on multispectral images as described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the bamboo forest growth monitoring method based on multispectral images as described above.

[0016] This invention provides a method and apparatus for monitoring bamboo forest growth based on multispectral images. It acquires multispectral images of the bamboo forest under test using a multispectral camera mounted on a drone, allowing for efficient data collection over large areas of bamboo forest regardless of terrain. The high-resolution images acquired by the multispectral camera improve data accuracy. Based on the multispectral images, growth indicators of the bamboo forest under test are obtained, including bamboo height, number of bamboo plants, chlorophyll content, and biomass. This multi-dimensional growth indicator allows for detailed quantitative analysis of bamboo forest growth, improving the accuracy and interpretability of the analysis results. Based on these growth indicators, the bamboo forest growth is determined. By comprehensively analyzing all growth indicators, errors are reduced, achieving accurate and efficient monitoring of bamboo forest growth over large areas. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a method for monitoring bamboo forest growth based on multispectral images provided by the present invention.

[0019] Figure 2 This is a schematic diagram of the structure of a bamboo forest growth monitoring device based on multispectral images provided by the present invention.

[0020] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0022] The main methods for monitoring bamboo forest growth currently include: (1) Experience-based judgment method: Forest farmers and bamboo forest managers judge the growth of bamboo forests based on their years of management experience, such as leaf color, plant height, diameter at breast height, and stand condition. This method mainly relies on subjective human experience, which makes it difficult to form a unified standard, seriously affects the accuracy of judgment, makes it impossible to quantify the judgment results, and has low judgment efficiency; (2) Testing and determination method: A large number of researchers conducted on-site measurements and physicochemical tests to determine the growth of bamboo forest communities. By measuring the height, diameter at breast height, biomass, and stand density of bamboo trees on-site, bamboo samples were collected for instrumental testing of the content of chlorophyll and other internal components of bamboo trees. This method requires a lot of manpower and resources, is costly, and has low efficiency, and cannot achieve real-time, large-area, and rapid monitoring.

[0023] To address this, this invention proposes a method for monitoring bamboo forest growth based on multispectral images. It utilizes a drone equipped with a multispectral camera to collect images of bamboo forests. Based on drone-scale multispectral remote sensing monitoring information, an inversion model is constructed between the spectral characteristics of regional bamboo forest populations and the measured data. This method obtains measured data by conducting tests on regional bamboo forest plots, while simultaneously using drone multispectral remote sensing monitoring of the plot areas. This achieves a certain degree of standardization in detection and enables large-scale, rapid, and real-time accurate monitoring. Consequently, it provides real-time, large-area information feedback for regional bamboo forest management, assisting farmers in optimizing cultivation, tending bamboo forests, and rationally planning bamboo harvesting. Furthermore, the bamboo forest growth monitoring method based on multispectral images proposed in this invention, combined with the rapidly developing drone industry, can avoid the shortcomings of low efficiency and high cost of experience-based judgment and testing methods. It provides a more efficient, convenient, and real-time regional intelligent monitoring platform for bamboo forest management and provides important monitoring technology for the development of the bamboo industry, the improvement of bamboo quality, the enhancement of bamboo forest tending effect, and the production of bamboo shoots.

[0024] The following is combined Figures 1 to 3 This invention describes a method and apparatus for monitoring bamboo forest growth based on multispectral images.

[0025] Figure 1 This is a flowchart illustrating a method for monitoring bamboo forest growth based on multispectral images provided by the present invention, as shown below. Figure 1 As shown, the method includes the following: Step 101: Acquire multispectral images of the bamboo forest to be tested using a multispectral camera; the multispectral camera is mounted on a drone.

[0026] Specifically, in this embodiment of the invention, a multispectral camera mounted on a drone is used for data collection. By leveraging the flight advantages of the drone, the complex terrain and area limitations of the bamboo forest are overcome, improving data collection efficiency and reducing manpower and time costs. At the same time, the multispectral camera is used to collect high-resolution images, thereby improving data accuracy.

[0027] For example, the DJI M300 RTK drone with a gimbal was selected. This drone platform has good flight performance, and its payload capacity and endurance can meet the needs of multispectral data acquisition. At the same time, the MS600 V2 multispectral camera was selected to acquire multispectral images of the bamboo forest. This camera has the characteristics of high resolution, multi-band, lightweight and easy portability, and can acquire high-quality multispectral image data.

[0028] In some embodiments, to further improve data quality, data collection can be conducted under clear, cloudless weather conditions between 10:00 AM and 2:00 PM to ensure consistent lighting conditions. Simultaneously, based on the area and terrain shape of the bamboo forest sample plot to be measured, various flight parameters for the UAV are set, such as a flight altitude of 80 meters, a flight speed of 6 m / s, a forward overlap of 80%, and a lateral overlap of 75%, to ensure the acquisition of complete bamboo forest images and minimize data redundancy.

[0029] Step 102: Based on the multispectral image, obtain the growth indicators of the bamboo forest to be tested; the growth indicators include bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass.

[0030] Specifically, in order to conduct a detailed and reliable quantitative assessment of the growth of bamboo forests from multiple dimensions, this embodiment of the invention designs multiple growth indicators, including bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass.

[0031] The aforementioned growth indicators can be obtained by processing multispectral images.

[0032] For example, Pix 4d software is used to stitch together multispectral images to obtain a Digital Surface Model (DSM). Then, Kriging interpolation is performed on the DSM to simulate a soil height layer. The difference between the DSM and the soil height layer is calculated to obtain a bamboo height monitoring layer, thereby determining the bamboo height. Using the YOLO series of small target detection algorithms (such as YOLOv5, YOLOv8, etc.), target detection can be performed on multispectral images to obtain the number of bamboo plants contained in the image; An initial model is constructed using classification algorithms (such as decision trees, partial least squares, or XGBoost), and then supervised training is performed on the initial model. For example, if historical multispectral images are used as feature data and the corresponding measured bamboo plant chlorophyll content indicators are used as labels for training, the initial model can fully learn the chlorophyll features in historical multispectral images of bamboo forests, thus obtaining a bamboo forest nitrogen estimation model. This model can then be used to detect multispectral images and obtain chlorophyll content indicators. Similarly, if historical multispectral images are used as feature data and the corresponding measured bamboo plant biomass is used as label data for training, the initial model can fully learn the bamboo plant biomass features in historical multispectral images of bamboo forests, thus obtaining a bamboo forest biomass estimation model. This model can then be used to detect multispectral images and obtain bamboo plant biomass.

[0033] This invention employs four growth indicators—bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass—to conduct precise quantitative analysis of bamboo forest growth. Furthermore, by using deep learning or machine learning models to detect multispectral images, the growth indicators of the bamboo forest are obtained, thereby improving the scientific rigor, accuracy, and reliability of bamboo forest growth analysis.

[0034] Step 103: Determine the growth status of the bamboo forest based on the growth indicators.

[0035] Furthermore, determining the bamboo forest growth status based on the growth indicators includes: When all growth indicators are greater than or equal to the corresponding preset thresholds, the bamboo forest is considered to be growing well. If any of the growth indicators is less than the corresponding preset threshold, the bamboo forest is considered to be in poor condition.

[0036] Specifically, based on growth index data from multiple dimensions, including morphological indicators (such as bamboo height and number of bamboo plants) and physiological indicators (including chlorophyll content and biomass of bamboo plants), the growth of bamboo forests can be comprehensively and accurately detected.

[0037] Based on the bamboo species, corresponding thresholds or threshold ranges are set for each growth indicator in each dimension. Then, the measured growth indicator data are compared with the corresponding thresholds or threshold ranges to scientifically classify the growth. When all growth indicators are greater than or equal to the corresponding preset thresholds, the bamboo forest is judged to be growing well. When any of the growth indicators is less than the corresponding preset threshold, the bamboo forest is judged to be growing poorly. This allows for accurate and efficient detection of bamboo forest growth.

[0038] For example, the threshold for bamboo stalk height can be 3 meters, the threshold for bamboo stalk quantity can be 1200 stalks per acre, the threshold for chlorophyll content indicative value per stalk can be 35, and the threshold for bamboo stalk biomass per stalk can be 2 kg / m². By comparing the measured data with the thresholds, the growth of bamboo stalks can be directly judged as good or poor.

[0039] This invention utilizes multispectral images from unmanned aerial vehicles (UAVs) for bamboo forest growth monitoring, significantly improving the efficiency and accuracy of monitoring and quantification. It avoids the low efficiency and high cost of empirical judgment and testing methods, facilitating widespread application. Furthermore, using UAV multispectral images as the data source overcomes the limitations of satellite imagery, such as its inability to be acquired, difficulty in acquisition, inability to meet requirements, or excessive cost. In addition, the theory proposed in this invention, which uses four dimensions of growth indicators—bamboo height, number of bamboo plants, chlorophyll content, and biomass—to characterize bamboo forest growth, not only provides multi-level characterization of growth and enhances the accuracy and interpretability of results, but also efficiently obtains bamboo height data without the need for high-cost and technically complex lidar sensors, reducing costs and enabling more precise quantification of bamboo growth. Ultimately, this achieves low-cost, high-precision, high-efficiency, and scientifically objective regional bamboo forest growth monitoring, providing crucial technical support for refined bamboo forest planting and management.

[0040] This invention provides a method for monitoring bamboo forest growth based on multispectral images. It acquires multispectral images of the bamboo forest under test using a multispectral camera mounted on a drone, allowing for efficient data collection over large areas of bamboo forest regardless of terrain. Furthermore, the high-resolution images acquired by the multispectral camera improve data accuracy. Based on the multispectral images, growth indicators of the bamboo forest under test are obtained, including bamboo height, number of bamboo plants, chlorophyll content, and biomass. This multi-dimensional quantitative analysis of bamboo forest growth improves the accuracy and interpretability of the results. Based on these growth indicators, the bamboo forest growth is determined. By comprehensively analyzing all growth indicators, errors are reduced, enabling accurate and efficient monitoring of bamboo forest growth over large areas.

[0041] Furthermore, obtaining the growth indicators of the bamboo forest to be tested based on the multispectral image includes: Based on the multispectral images, a digital land surface model is generated; Threshold segmentation is performed on the multispectral image to obtain a point image of the soil area of ​​the bamboo forest to be tested; Using the height data of the center point of the patch in the soil area point image as sample points, interpolation is performed on the soil area point image to obtain the soil area surface data. Based on the soil area areal data, a soil height layer is simulated for the bamboo forest to be tested; The bamboo plant height is obtained by performing a difference operation between the digital surface model and the soil height layer.

[0042] Furthermore, generating a digital land surface model based on the multispectral image includes: Atmospheric correction and radiometric calibration are performed on the multispectral images to obtain surface reflectance data; Feature extraction is performed on the surface reflectance data to obtain surface feature points; The surface features are converted into a three-dimensional coordinate point cloud to generate a digital surface model.

[0043] Specifically, firstly, atmospheric correction and radiometric calibration are used to eliminate the influence of geometric distortion and sensor differences to obtain accurate surface reflectance data; then, the scale-invariant feature transform (SIFT) algorithm is used to extract stable feature points, transform the two-dimensional features into a three-dimensional point cloud, and establish a high-precision digital surface model.

[0044] For example, using ENVI software for FLAASH atmospheric correction, the SIFT algorithm is used to extract no less than 500 feature points from each multispectral image, and the Structure from Motion (SFM) algorithm is used to generate a dense point cloud (density > 50 points / m²). Finally, Poisson reconstruction is used to generate a DSM.

[0045] Soil area point images are extracted from multispectral images by threshold segmentation, and soil height area data are constructed using Kriging interpolation. The bamboo plant height can be obtained by subtracting it from the DSM.

[0046] For example, the Maximum Class Interval Variance Method (MCIVM) is used to perform threshold segmentation on the multispectral image to obtain point images of the soil area. Then, the elevation of the center point of the patch is selected as the sampling point. Kriging interpolation is used in ArcGIS software to generate a soil height raster with a resolution of 5cm (i.e., a soil height layer). Finally, the difference between the raster and DSM is performed to obtain the plant height distribution map, thereby determining the height of the bamboo plant.

[0047] This invention addresses the complex canopy environment of bamboo forests by processing multispectral images to accurately measure bamboo height. This avoids the inefficiencies and inaccuracies of manual measurement and the high costs of lidar scanning, achieving efficient, low-cost, and accurate bamboo height measurement.

[0048] Furthermore, obtaining the growth indicators of the bamboo forest to be tested based on the multispectral image includes: The multispectral image is input into the first model to obtain the number of bamboo plants output by the first model. The first model is trained using the first historical multispectral image as feature data and the corresponding measured number of bamboo plants as label data.

[0049] Furthermore, obtaining the growth indicators of the bamboo forest to be tested based on the multispectral image includes: The multispectral image is input into the second model to obtain the chlorophyll content indicator value of the bamboo plant output by the second model; The second model is trained using the second historical multispectral image as feature data and the corresponding measured chlorophyll content of bamboo plants as label data.

[0050] Furthermore, obtaining the growth indicators of the bamboo forest to be tested based on the multispectral image includes: The multispectral image is input into the third model to obtain the bamboo biomass output by the third model; The third model is trained using the third historical multispectral image as feature data and the corresponding measured bamboo biomass as label data.

[0051] Specifically, an initial model is constructed using small object detection algorithms from the YOLO series (such as YOLOv5 and YOLOv8). Then, the initial model is trained under supervision using the first historical multispectral image as feature data and the corresponding measured number of bamboo plants as label data, resulting in the first model. Using the first model, object detection can be performed on the multispectral image to obtain the number of bamboo plants contained in the image.

[0052] An initial model is constructed using classification algorithms (such as decision trees, partial least squares, or XGBoost). Then, different supervised training methods are applied to this initial model to obtain a second and a third model. Specifically, the second model is trained using the second historical multispectral image as feature data and the corresponding measured bamboo plant chlorophyll content indicator as label data. This second model can then be used to detect multispectral images and obtain chlorophyll content indicators. Similarly, the third model is trained using the third historical multispectral image as feature data and the corresponding measured bamboo plant biomass as label data. This third model can then be used to detect multispectral images and obtain bamboo plant biomass.

[0053] The first, second, and third historical multispectral images can be multispectral images collected in the same bamboo forest area or in different bamboo forest areas.

[0054] For example, select any bamboo forest sample plot and manually count the number of bamboo plants within the plot area; measure the chlorophyll content indicator value of the bamboo canopy, taking 5 measurements in each sampling area and using the average value as the chlorophyll content indicator value for that area; measure the sum of the heights of the bamboo plants using a measuring tape, again measuring 5 plants in each sampling area and using the average value as the sum of the plant heights for that area; randomly harvest the above-ground parts of 5 bamboo plants in each sampling area using a harvesting method, weighing the bamboo leaves, branches, culms, and stalks respectively, and combine this with the plant height to measure the bamboo biomass. Use the above-mentioned manually measured data as label data for model training, and use a drone equipped with a multispectral camera to fly over the bamboo forest sample plot to collect multispectral images as feature data for supervised training of the model, thus obtaining the first model, the second model, and the third model respectively.

[0055] This invention employs a multi-model collaborative inversion system to establish dedicated prediction models for different growth indicators, forming a complementary advantage between deep learning and traditional machine learning. The overall performance is superior to any single model, improving the accuracy and efficiency of quantifying various growth indicators of bamboo forests. This enables accurate and efficient monitoring of the growth of large-scale regional bamboo forests.

[0056] The following describes the bamboo forest growth monitoring device based on multispectral images provided by the present invention. The bamboo forest growth monitoring device based on multispectral images described below and the bamboo forest growth monitoring method based on multispectral images described above can be referred to in correspondence.

[0057] Based on any of the above embodiments Figure 2 This is a schematic diagram of the structure of a bamboo forest growth monitoring device based on multispectral images provided by the present invention, as shown below. Figure 2 As shown. This embodiment of the invention provides a bamboo forest growth monitoring device based on multispectral images, including a data acquisition module 201, a quantization module 202, and a monitoring module 203, wherein: The acquisition module 201 is used to acquire multispectral images of the bamboo forest to be tested using a multispectral camera; the multispectral camera is mounted on a drone; the quantization module 202 is used to obtain growth indicators of the bamboo forest to be tested based on the multispectral images; the growth indicators include bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass; the monitoring module 203 is used to determine the growth status of the bamboo forest based on the growth indicators.

[0058] The bamboo forest growth monitoring device based on multispectral images provided by this invention acquires multispectral images of the bamboo forest under test through a multispectral camera mounted on a drone, thus enabling efficient data collection of large areas of bamboo forests regardless of terrain limitations. Simultaneously, the acquisition of high-resolution images by the multispectral camera improves data accuracy. Based on the multispectral images, growth indicators of the bamboo forest under test are obtained, including bamboo height, number of bamboo plants, chlorophyll content, and biomass. This allows for detailed quantitative analysis of bamboo forest growth through multiple dimensions of growth indicators, improving the accuracy and interpretability of the analysis results. Based on these growth indicators, the bamboo forest growth is determined. By comprehensively analyzing all growth indicators, errors are reduced, achieving accurate and efficient monitoring of the growth of large-area regional bamboo forests.

[0059] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a bamboo forest growth monitoring method based on multispectral images, the method including: Multispectral images of the bamboo forest under test are acquired using a multispectral camera mounted on a drone. Based on the multispectral images, growth indicators of the bamboo forest to be tested are obtained; the growth indicators include bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass. The growth status of the bamboo forest is determined based on the aforementioned growth indicators.

[0060] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0061] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the bamboo forest growth monitoring method based on multispectral images provided by the above methods, the method comprising: Multispectral images of the bamboo forest under test are acquired using a multispectral camera mounted on a drone. Based on the multispectral images, growth indicators of the bamboo forest to be tested are obtained; the growth indicators include bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass. The growth status of the bamboo forest is determined based on the aforementioned growth indicators.

[0062] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the bamboo forest growth monitoring method based on multispectral images provided by the above methods, the method comprising: Multispectral images of the bamboo forest under test are acquired using a multispectral camera mounted on a drone. Based on the multispectral images, growth indicators of the bamboo forest to be tested are obtained; the growth indicators include bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass. The growth status of the bamboo forest is determined based on the aforementioned growth indicators.

[0063] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0064] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0065] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0066] In this application's embodiments, "determine B based on A" means that factor A must be considered when determining B. It is not limited to "B can be determined based solely on A," but should also include: "determine B based on A and C," "determine B based on A, C, and E," "determine C based on A, and further determine B based on C," etc. Additionally, it can include using A as a condition for determining B, for example, "when A meets the first condition, determine B using the first method"; another example, "when A meets the second condition, determine B," etc.; another example, "when A meets the third condition, determine B based on the first parameter," etc. Of course, it can also be a condition where A is a factor in determining B, for example, "when A meets the first condition, determine C using the first method, and further determine B based on C," etc.

[0067] In this invention, the term "multiple" refers to two or more, and other quantifiers are similar.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring bamboo forest growth based on multispectral images, characterized in that, include: Multispectral images of the bamboo forest under test are acquired using a multispectral camera mounted on a drone. Based on the multispectral images, growth indicators of the bamboo forest to be tested are obtained; the growth indicators include bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass. The growth status of the bamboo forest is determined based on the aforementioned growth indicators.

2. The bamboo forest growth monitoring method based on multispectral images according to claim 1, characterized in that, The process of obtaining the growth indicators of the bamboo forest under test based on the multispectral image includes: Based on the multispectral images, a digital land surface model is generated; Threshold segmentation is performed on the multispectral image to obtain a point image of the soil area of ​​the bamboo forest to be tested; Using the height data of the center point of the patch in the soil area point image as sample points, interpolation is performed on the soil area point image to obtain the soil area surface data. Based on the soil area areal data, a soil height layer is simulated for the bamboo forest to be tested; The bamboo plant height is obtained by performing a difference operation between the digital surface model and the soil height layer.

3. The bamboo forest growth monitoring method based on multispectral images according to claim 2, characterized in that, The process of generating a digital land surface model based on the multispectral image includes: Atmospheric correction and radiometric calibration are performed on the multispectral images to obtain surface reflectance data; Feature extraction is performed on the surface reflectance data to obtain surface feature points; The surface features are converted into a three-dimensional coordinate point cloud to generate a digital surface model.

4. The bamboo forest growth monitoring method based on multispectral images according to claim 1, characterized in that, The process of obtaining the growth indicators of the bamboo forest under test based on the multispectral image includes: The multispectral image is input into the first model to obtain the number of bamboo plants output by the first model. The first model is trained using the first historical multispectral image as feature data and the corresponding measured number of bamboo plants as label data.

5. The bamboo forest growth monitoring method based on multispectral images according to claim 1, characterized in that, The process of obtaining the growth indicators of the bamboo forest under test based on the multispectral image includes: The multispectral image is input into the second model to obtain the chlorophyll content indicator value of the bamboo plant output by the second model; The second model is trained using the second historical multispectral image as feature data and the corresponding measured chlorophyll content of bamboo plants as label data.

6. The bamboo forest growth monitoring method based on multispectral images according to claim 1, characterized in that, The process of obtaining the growth indicators of the bamboo forest under test based on the multispectral image includes: The multispectral image is input into the third model to obtain the bamboo biomass output by the third model; The third model is trained using the third historical multispectral image as feature data and the corresponding measured bamboo biomass as label data.

7. The bamboo forest growth monitoring method based on multispectral images according to claim 1, characterized in that, The determination of the bamboo forest growth status based on the growth indicators includes: When all growth indicators are greater than or equal to the corresponding preset thresholds, the bamboo forest is considered to be growing well. If any of the growth indicators is less than the corresponding preset threshold, the bamboo forest is considered to be in poor condition.

8. A bamboo forest growth monitoring device based on multispectral images, characterized in that, include: The acquisition module is used to acquire multispectral images of the bamboo forest to be tested using a multispectral camera; the multispectral camera is mounted on a drone. The quantization module is used to obtain the growth indicators of the bamboo forest to be tested based on the multispectral image; the growth indicators include bamboo height, number of bamboo plants, chlorophyll content of bamboo plants, and bamboo biomass. The monitoring module is used to determine the growth status of the bamboo forest based on the growth indicators.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the bamboo forest growth monitoring method based on multispectral images as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the bamboo forest growth monitoring method based on multispectral images as described in any one of claims 1 to 6.

Images