Robinia pseudoacacia forest intermediate cutting monitoring system and method based on distributed sensing

Abstract

The invention discloses a robinia pseudoacacia forest intermediate cutting monitoring system and method based on distributed sensing. The system comprises distributed sensors, an unmanned aerial vehicle, an edge server and a cloud platform. The distributed sensors are distributed in a target robinia pseudoacacia forest and are used for measuring illumination intensity; the edge server is used for acquiring measurement data sent by the distributed sensors in the edge area, generating an edge area sensor position distribution diagram and analyzing whether the distributed sensors are abnormal or not; the cloud platform is used for acquiring a target robinia pseudoacacia forest image acquired by the unmanned aerial vehicle and dividing a target robinia pseudoacacia forest area into a crown area and a ground area based on an image recognition algorithm, and is also used for calculating the canopy density of each edge area and correcting and calculating the canopy density of each edge area to obtain intermediate cutting parameters. According to the invention, distributed sensors are arranged in a robinia pseudoacacia forest, images shot by an unmanned aerial vehicle are combined, multi-source data are fused to identify the growth condition and environment of robinia pseudoacacia, and the intermediate cutting opportunity can be accurately and reliably judged.

Description

Technical Field

[0001] The present invention relates to the technical field of thinning, and in particular to a Robinia pseudoacacia forest thinning monitoring system and method based on distributed sensing. Background Art

[0002] Thinning is an important technical measure in forest management, which refers to regularly cutting down some trees in immature forests to adjust the stand density and create better growth space and environmental conditions for the remaining trees. Thinning can optimize the forest structure, improve the wood quality, and promote the health of the ecosystem. As a pioneer tree species with fast growth, drought tolerance, and strong sprouting ability, scientific thinning is crucial for the healthy management of its plantations.

[0003] The initial thinning technology had problems such as relying on manpower, low automation level, and low efficiency. With the development of technology, some intelligent means have been applied in thinning technology, but there are still problems with low accuracy in judging the timing of thinning. In the prior art, the canopy projection area is mostly used to calculate the canopy density, and whether to conduct thinning is judged based on whether the canopy density reaches a threshold. Although the canopy density is an important indicator reflecting the growth of Robinia pseudoacacia, the accuracy of drones in identifying the canopy is not high enough, and the sparsity of each canopy is different, and the canopy is not completely static but in a state of being blown by the wind. Therefore, it is difficult for drones to accurately identify the sparsity and gaps of the canopy, which leads to inaccurate calculation of the canopy projection area, and the calculated canopy density cannot accurately reflect the growth environment of Robinia pseudoacacia, which brings difficulties to the determination of the thinning timing.

[0004] In the prior art, the patent application for invention CN116958813A proposes a method for designing artificial forest thinning operations based on drone images. This patent application for invention first collects drone images of the target area and reconstructs the images to generate DOM and DSM data, then uses computer image processing methods for single-tree recognition and canopy information extraction, then calculates the forest attributes of the unit grid and conducts cold and hot spot analysis, and finally determines the thinning area and thinning intensity. Using this method for designing artificial forest thinning operations makes up for the deficiencies of traditional ground surveys in the single-tree coordinates and stand spatial information in the whole area; subdivides the whole forest into grids, fully considers the spatial heterogeneity within the stand, and improves the refinement level of thinning design; provides a scheme for determining the priority order of forest thinning, reduces the subjectivity in the thinning process, and improves the scientificity of object tree selection. However, the method in this patent application for invention is judged based on the threshold of canopy density, and the calculation of canopy density is only a simple calculation based on the canopy projection area, which highly depends on the accuracy of image recognition. However, the objects captured by drones are moving leaves, so it is difficult to accurately identify the moving canopies with different sparsity degrees, and thus it cannot accurately reflect the actual growth environment of the trees and is difficult to accurately grasp the thinning timing. Summary of the Invention

[0005] Objective of the Invention: Aiming at the above problems, the present invention proposes a Robinia pseudoacacia forest thinning monitoring system and method based on distributed sensing.

[0006] Technical Solution:

[0007] In a first aspect, the present invention provides a Robinia pseudoacacia forest thinning monitoring system based on distributed sensing, including distributed sensors, unmanned aerial vehicles (UAVs), edge servers, and cloud platforms;

[0008] The distributed sensors are distributed in the target Robinia pseudoacacia forest for measuring the light intensity;

[0009] The UAVs are used to collect images of the target Robinia pseudoacacia forest and send them to the cloud platform;

[0010] The edge servers include a distribution map generation module and an anomaly analysis module;

[0011] The distribution map generation module is used to obtain the measurement data sent by the distributed sensors within the edge area and generate a distribution map of the sensor positions in the edge area;

[0012] The anomaly analysis module is used to analyze whether the distributed sensors are abnormal;

[0013] The cloud platforms include a region division module, a canopy density calculation module, and a thinning parameter analysis module;

[0014] The region division module is used to obtain the images of the target Robinia pseudoacacia forest collected by the UAVs and divide the target Robinia pseudoacacia forest area into a canopy area and a ground area based on an image recognition algorithm;

[0015] The canopy density calculation module is used to calculate the canopy density of each edge area;

[0016] The thinning parameter analysis module is used to perform a correction calculation on the canopy density of the edge area to obtain the thinning parameters.

[0017] Preferably, the anomaly analysis module for analyzing whether the distributed sensors are abnormal includes:

[0018] Obtaining the generation time of the region division map, set as the first time;

[0019] Querying the light weather information of the target Robinia pseudoacacia forest area at the first time;

[0020] Obtaining a first reference range and a second reference range based on the light weather information;

[0021] The edge server receives the first reference range and the second reference range, queries the measurement data corresponding to the time stamp and the first time, determines whether the light intensity data of a certain type of sensor is within the first reference range, and determines whether the light intensity data of another type of sensor is within the second reference range. If so, there is no anomaly; otherwise, it is determined as an abnormal sensor.

[0022] Preferably, the cloud platform obtains the total number M of distributed sensors in the edge area and the number m of abnormal sensors in the edge area;

[0023] Calculate the correction weight based on the abnormal ratio m / M of the distributed sensors;

[0024] Based on the correction weight and the measurement data, correct the canopy density of each edge area to obtain the thinning parameters.

[0025] In a second aspect, the present invention also provides a method for monitoring the thinning of black locust forests based on distributed sensing, the method comprising:

[0026] S2. Each edge server generates a distribution map of sensor positions in an edge area based on the measurement data; where the area where the distributed sensors under the jurisdiction of each edge server are located is an edge area;

[0027] S3. Use a drone to collect images of the target black locust forest area and send the collected images to the cloud platform;

[0028] S4. The cloud platform extracts the tree crowns in the images based on an image recognition algorithm, divides the target black locust forest area into a tree crown area and a ground area, and obtains a target area division map;

[0029] S5. The cloud platform fuses the distribution map of sensor positions in the edge area with the target area division map and classifies the distributed sensors;

[0030] S6. Determine whether there are monitoring abnormalities in the first-class sensors and the second-class sensors;

[0031] S7. The cloud platform calculates the canopy density C0 of each edge area based on the images of the drone;

[0032] S8. Based on the measurement data of the distributed sensors, correct the canopy density of the edge area to obtain the thinning parameters.

[0033] Preferably, S5 includes:

[0034] S51. The cloud platform obtains the distribution map of sensor positions in the edge area generated by each edge server and synthesizes the distribution map of sensor positions in the target black locust forest area;

[0035] S52. Fuse the distribution map of sensor positions in the target black locust forest area with the target area division map, and divide the distributed sensors into first-class sensors and second-class sensors according to the type of area where the sensors are located; the first-class sensors are located within the tree crown area, and the second-class sensors are located within the ground area.

[0036] Preferably, S6 includes:

[0037] S61. Obtain the generation time of the area division map and set it as the first time;

[0038] S62. Query the lighting weather information of the target locust forest area at the first time;

[0039] S63. The cloud platform obtains the first reference range and the second reference range based on the lighting weather information. The first reference range is the reference range of the light intensity under the shadow, and the second shadow range is the reference range of the light intensity without the shadow;

[0040] S64. The edge server receives the first reference range and the second reference range, queries the measurement data corresponding to the time stamp and the first time, judges whether the light intensity data of the first type of sensor is within the first reference range, and judges whether the light intensity data of the second type of sensor is within the second reference range. If so, there is no abnormality, otherwise it is judged as an abnormal sensor.

[0041] Preferably, S8 includes:

[0042] S81. Obtain the total number M of distributed sensors in the edge area and the number m of abnormal sensors in the edge area;

[0043] S82. Calculate the correction weight α based on the abnormal ratio m / M of the distributed sensors;

[0044] S83. Correct the canopy density of each edge area based on the correction weight and the measurement data to obtain the thinning parameter D.

[0045] Preferably, before the step S2, there is also a preliminary layout step S1, and after the step S8, there is also a thinning execution step S9;

[0046] S1 includes: arranging a number of distributed sensors among the locust trees; the distributed sensors are used to measure the light intensity and send the measurement data to the edge server; the measurement data includes the sensor number, the sensor position, the light intensity data, and the time stamp;

[0047] S9 includes: when the thinning parameter is greater than or equal to the preset limit value, execute the thinning strategy; when the thinning parameter is less than the threshold value, continuously monitor the target locust forest.

[0048] In a third aspect, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor. When the processor executes the computer program, it implements the steps in the locust tree thinning monitoring method based on distributed sensing.

[0049] Fourthly, the present invention also provides a computer-readable storage medium, on which a computer program is stored. Preferably, when the computer program is executed by a processor, the steps in the method for monitoring the thinning of Robinia pseudoacacia forests based on distributed sensing are implemented.

[0050] The present invention has the following beneficial effects compared with the prior art:

[0051] 1. In the present invention, distributed sensors are set in Robinia pseudoacacia forests to collect light intensity data, and combined with the image data captured by drones, multi-source data are fused to identify and judge the growth status and environment of Robinia pseudoacacia, which is more accurate and reliable than the prior art. Moreover, considering that Robinia pseudoacacia forests are often unattended and distributed sensors are easily damaged due to animal damage, pest gnawing, etc., in order to improve the reliability of data, the present invention extracts the tree crowns in the images based on an image recognition algorithm, divides the target Robinia pseudoacacia forest area into a tree crown area and a ground area, obtains a target area division map, and classifies the distributed sensors, which can further judge whether the distributed sensors are abnormal, and the data analysis is more reliable and accurate.

[0052] 2. In the present invention, an edge server is set at the Robinia pseudoacacia forest, which cooperates with the remote cloud platform to form a cloud-edge collaborative monitoring system. The edge server is responsible for determining the distribution positions of sensors and judging sensor abnormalities, and the cloud platform is responsible for calculations such as canopy density identification and weight correction. The allocation of computing resources is more reasonable, and it is applicable to large-area and large-range Robinia pseudoacacia forests and other forest species.

[0053] 3. The present invention can first classify the distributed sensors, and then judge whether the sensors are abnormal based on the classification results. Determine the correction weight according to the overall abnormal proportion of the sensors in the edge area, and correct the canopy density according to the gap between the light intensity and the middle value of the reference range, so as to obtain the final thinning parameters, which more truly reflect the growth state and growth environment of Robinia pseudoacacia, and can accurately grasp the thinning timing. Description of the Drawings

[0054] Figure 1 It is a schematic structural diagram of a monitoring system for thinning Robinia pseudoacacia forests based on distributed sensing provided by an embodiment of the present invention;

[0055] Figure 2 It is a flowchart of a method for monitoring the thinning of Robinia pseudoacacia forests based on distributed sensing provided by an embodiment of the present invention;

[0056] Figure 3 It is a flowchart of a method for judging whether a distributed sensor is abnormal provided by an embodiment of the present invention;

[0057] Figure 4 It is a flowchart of a method for correcting the canopy density to obtain thinning parameters provided by an embodiment of the present invention;

[0058] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Specific embodiments

[0059] Obviously, many modifications and variations made by those skilled in the art based on the purpose of the present invention fall within the protection scope of the present invention.

[0060] Those skilled in the art of the present technology can understand that unless specifically stated otherwise, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the description of the present invention means the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups. It should be understood that when an element or component is referred to as being "connected" to another element or component, it can be directly connected to other elements or components, or there may also be intermediate elements or components. The phrase "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0061] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0062] Embodiment 1:

[0063] An embodiment of the present invention provides a Robinia pseudoacacia forest thinning monitoring system based on distributed sensing. For details, please refer to Figure 1 , Figure 1 A schematic diagram of the structure of a Robinia pseudoacacia forest thinning monitoring system based on distributed sensing provided by an embodiment of the present invention. The system includes: distributed sensors, unmanned aerial vehicles (UAVs), edge servers, and cloud platforms;

[0064] The distributed sensors are distributed in the target Robinia pseudoacacia forest for measuring the light intensity;

[0065] The UAVs are used to collect images of the target Robinia pseudoacacia forest and send them to the cloud platform;

[0066] The edge server includes a distribution map generation module and an anomaly analysis module;

[0067] The distribution map generation module is used to obtain the measurement data sent by the distributed sensors within the edge area and generate a distribution map of the positions of the sensors in the edge area;

[0068] The anomaly analysis module is used to analyze whether the distributed sensors are abnormal;

[0069] The cloud platform includes a regional division module, a canopy density calculation module, and a thinning parameter analysis module;

[0070] The regional division module is used to obtain the target locust forest image collected by the drone and divide the target locust forest area into a canopy area and a ground area based on an image recognition algorithm;

[0071] The canopy density calculation module is used to calculate the canopy density of each edge area;

[0072] The thinning parameter analysis module is used to perform a correction calculation on the canopy density of the edge area to obtain the thinning parameter.

[0073] Preferably, the anomaly analysis module for analyzing whether the distributed sensors are abnormal includes:

[0074] Obtain the generation time of the regional division map and set it as the first time;

[0075] Query the lighting weather information of the target locust forest area at the first time;

[0076] Obtain the first reference range and the second reference range based on the lighting weather information;

[0077] The edge server receives the first reference range and the second reference range, queries the measurement data corresponding to the time stamp and the first time, determines whether the light intensity data of the first type of sensors is within the first reference range, and determines whether the light intensity data of the second type of sensors is within the second reference range. If so, there is no anomaly; if not, it is determined as an abnormal sensor.

[0078] Preferably, the regional division module of the cloud platform is used to:

[0079] Obtain the distribution map of the sensor positions in the edge area generated by each edge server and synthesize the distribution map of the sensor positions in the target locust forest area;

[0080] Fuse the distribution map of the sensor positions in the target locust forest area with the target regional division map, and divide the distributed sensors into the first type of sensors and the second type of sensors according to the type of the area where the sensors are located; the first type of sensors are located within the canopy area, and the second type of sensors are located within the ground area.

[0081] Preferably, the cloud platform corrects the canopy density of the edge area based on the measurement data of the distributed sensors to obtain the thinning parameter, including:

[0082] Obtain the total number M of the distributed sensors in the edge area and the number m of the abnormal sensors in the edge area;

[0083] Calculate the correction weight α based on the abnormal ratio m / M of the distributed sensors;

[0084] When m / M is greater than or equal to the first threshold, α = 0;

[0085] When m / M is greater than or equal to the second threshold and less than the first threshold, α = the first weight;

[0086] When m / M is greater than or equal to the third threshold and less than the second threshold, α = the second weight;

[0087] Based on the correction weight and the measurement data, correct the canopy density of each edge area to obtain the thinning parameter D;

[0088] Eliminate the data of abnormal sensors in a type of sensors in the edge area, and obtain the light intensity data L of normal sensors;

[0089] Let the difference between the light intensity data L and the middle value L0 of the first reference range be L c ;

[0090] Calculate L of all normal sensors c And take the average to obtain the mean value L q ;

[0091] Correct the canopy density C0 of the edge area to obtain the thinning parameter D = C0 - (L q / L0) × α.

[0092] Example 2:

[0093] This embodiment of the present invention also provides a method for monitoring the thinning of Robinia pseudoacacia forests based on distributed sensing. For details, please refer to Figure 2 , Figure 2 which is a flowchart of a method for monitoring the thinning of Robinia pseudoacacia forests based on distributed sensing provided by this embodiment of the present invention. The method includes the steps:

[0094] S1. Arrange a number of distributed sensors in the Robinia pseudoacacia forest;

[0095] The distributed sensors are used to measure the light intensity and send the measurement data to the edge server;

[0096] The measurement data includes the sensor number, sensor position, light intensity data, and timestamp;

[0097] S2. Each edge server generates a distribution map of sensor positions in an edge area based on the measurement data;

[0098] Wherein the area where the distributed sensors under the jurisdiction of each edge server are located is an edge area;

[0099] Before step S1, it further includes establishing a mapping relationship between the edge server and the distributed sensors, and enabling the distributed sensors to send data to the corresponding edge servers;

[0100] Optionally, each distributed sensor only sends measurement data to one edge server, thereby forming a many-to-one distributed sensing architecture. In this way, each edge server independently collects and controls the distributed sensors in an edge area, which can improve the control efficiency.

[0101] Optionally, each distributed sensor can send measurement data to at least two edge servers, so as to improve the redundancy of edge computing and the reliability of control.

[0102] S3. Use a drone to collect images of the target locust forest area, and send the collected images to the cloud platform;

[0103] The target locust forest area is the locust forest area to be analyzed for whether thinning needs to be carried out.

[0104] S4. The cloud platform extracts the tree crowns in the images based on an image recognition algorithm, divides the target locust forest area into a tree crown area and a ground area, and obtains a target area division map; there are currently various recognition algorithms for the recognition of the tree crown area, which is not the focus of the present invention. In order to ensure the integrity of the technical solution of the present invention, the methods in the prior art are used here for recognition.

[0105] S4 includes:

[0106] S41. Perform preprocessing operations on the images to remove noise in the images to reduce interference;

[0107] S42. Perform grayscale processing on the images and obtain a gradient image;

[0108] S43. Perform preliminary segmentation into foreground and background;

[0109] S44. Take the maximum value of the foreground area as the internal marker, and perform a watershed transformation on the background area to extract adjacent areas as the external marker.

[0110] S45. Modify the gradient image so that the image has a minimum value at the internal marker and the external marker, and make the image flat;

[0111] S46. Perform a watershed transformation on the modified gradient image;

[0112] S47. Merge the segmented images in the connected areas, and finally obtain the segmented foreground tree crown image.

[0113] S5. The cloud platform fuses the sensor position distribution map of the edge area and the target area division map, and classifies the distributed sensors;

[0114] S51. The cloud platform obtains the distribution maps of the positions of sensors in the edge areas generated by each edge server and synthesizes the distribution map of the positions of sensors in the target locust forest area.

[0115] S52. The cloud platform fuses the distribution map of the positions of sensors in the target locust forest area with the target area division map, and divides the distributed sensors into type-I sensors and type-II sensors according to the types of the areas where the sensors are located; the type-I sensors are located within the canopy area, and the type-II sensors are located within the ground area.

[0116] It should be particularly noted that the acquisition time of the area division map is very crucial and should be consistent with the time stamps of the measurement data of the distributed sensors so that comparative analysis can be carried out.

[0117] S6. Determine whether there are monitoring anomalies for the type-I sensors and the type-II sensors; for details, please refer to Figure 3 , Figure 3 which is a flowchart of a method for determining whether a distributed sensor is abnormal provided by an embodiment of the present invention, including:

[0118] S61. Obtain the generation time of the area division map, which is set as the first time.

[0119] S62. Query the illumination weather information of the target locust forest area at the first time.

[0120] S63. Based on the illumination weather information, obtain a first reference range and a second reference range. The first reference range is the reference range of the illumination intensity under the shadow, and the second reference range is the reference range of the illumination intensity without the shadow.

[0121] S64. The edge server receives the first reference range and the second reference range, queries the measurement data corresponding to the first time by time stamp, determines whether the light intensity data of the type-I sensors are within the first reference range, and determines whether the light intensity data of the type-II sensors are within the second reference range. If so, there is no anomaly; if not, they are determined as abnormal sensors.

[0122] Since the images collected by the UAV are multiple images collected during a continuous period of time, it is difficult to select the generation time points of the images. The present invention adopts the generation time of the area division map because the total time consumed by the period during which the UAV collects images and the cloud platform generates the area division map is relatively short, and it can be basically considered that the weather has not changed and the illumination intensity has not changed during this time.

[0123] Based on the images collected by the drone, through the recognition algorithm, the location of the tree canopy area can be obtained. However, the obtained tree canopy area is not strictly accurate because the tree canopy is not static but moves with the wind, and it is difficult for the drone's shooting and image analysis to accurately determine the exact tree canopy area. Moreover, the tree canopy area is sparse or dense, and the reference range under different sparse conditions is an interval. Therefore, the present invention uses the first reference range and the second reference range to determine whether there are serious data anomaly errors in the distributed light intensity sensors.

[0124] Furthermore, data at multiple first times can be collected for analysis and comparison to improve the accuracy of the judgment.

[0125] S7. The cloud platform calculates the canopy density based on the images of the drone, and calculates the canopy density C0 of each edge area;

[0126] For each edge area, calculate the area of the tree canopy area divided by the total area of the edge area to obtain the canopy density C0 of the edge area.

[0127] S8. Modify the canopy density of the edge area based on the measurement data of the distributed sensors to obtain the thinning parameters; specifically, please refer to Figure 4 , Figure 4 which is a flowchart of a method for modifying the canopy density to obtain the thinning parameters provided by an embodiment of the present invention, including:

[0128] S81. Obtain the total number M of distributed sensors in the edge area and the number m of abnormal sensors in the edge area;

[0129] S82. Calculate the correction weight α based on the abnormal ratio m / M of the distributed sensors;

[0130] When m / M is greater than or equal to the first threshold, α = 0;

[0131] When m / M is greater than or equal to the second threshold and less than the first threshold, α = the first weight;

[0132] When m / M is greater than or equal to the third threshold and less than the second threshold, α = the second weight;

[0133] S83. Modify the canopy density of each edge area based on the correction weight and the measurement data to obtain the thinning parameter D;

[0134] Eliminate the data of abnormal sensors in a type of sensors in the edge area, and obtain the light intensity data L of normal sensors;

[0135] Let the difference between the light intensity data L and the median value L0 of the first reference range be the difference value L c ;

[0136] Calculate the L of all normal sensorsc And calculate the average to obtain the mean value L q ;

[0137] Correct the canopy density C0 of the edge area to obtain the thinning parameter D = C0 - (L q / L0) × α.

[0138] The present invention corrects the canopy density based on the calculation at the edge end. Since there are sparse differences in the tree crowns identified by the image, it is necessary to combine the light intensity to more realistically reflect the plant growth state, which is the core index of thinning; it should be noted that the value finally obtained in S8 of the present invention is not the canopy density, but the index after correcting the canopy density, which is a physical parameter that can better reflect the thinning timing.

[0139] It should be noted that if there are many abnormal sensors in an edge area, it indicates that the environment in this area is relatively poor, the failure rate is high, and the data credibility is low. Therefore, the correction weight is reduced; otherwise, the data credibility is high, and the correction weight is increased.

[0140] The specific values of the above-mentioned first threshold, second threshold, third threshold, first weight, and second weight should be determined according to the specific environment and tree species. Through experiments, the present invention exemplarily takes the first threshold as 0.8, the second threshold as 0.5, the third threshold as 0.2, the first weight as 0.4, and the second weight as 0.7.

[0141] In addition, it should be noted that the present invention uses a type of sensor for correction in the correction stage and does not use a type II sensor. This does not mean that the analysis and judgment of the type II sensor in the previous steps are useless, because the division between type I and type II is dynamically changing. Since the trees are in a cycle of growth, felling, and growth, a type II at that time may be classified as a type I at this time.

[0142] In addition, the main content of the present invention is to grasp the thinning timing according to the thinning parameter calculated in S8. For the characteristics of Robinia pseudoacacia forests, other thinning strategies should be specifically implemented. Considering multiple strategies comprehensively can be more beneficial to the growth of Robinia pseudoacacia.

[0143] Robinia pseudoacacia young forests grow rapidly. If the initial planting density is too high (e.g., > 2000 plants / hm²), a high canopy density (> 0.8) can be formed within 3 to 5 years, resulting in the polarization of forest trees into "dominant trees" (superior trees) and "suppressed trees" competing for light and nutrients. Practices in the sandy areas of the eastern Henan Plain have shown that Robinia pseudoacacia forests at the age of 5 to 7 years need to be thinned for the first time to relieve the competition pressure. Research in the Loess Plateau has shown that when the reserved density is 1110 plants / hm² (thinning intensity is about 50%), the light in the forest is significantly improved, the soil moisture increases by 40%, and the biomass of understory vegetation and the productivity of forest trees reach the optimal level. If the density after thinning < 800 plants / hm², although the light is sufficient, it may lead to an increased risk of soil erosion (especially on slopes), and the competition of understory weeds intensifies.

[0144] In addition, the thinning of Robinia pseudoacacia forests also needs to adopt the understory thinning method, preferably removing the suppressed trees, diseased and weak trees first, and retaining the healthy and dominant trees to promote the growth of the main trunk.

[0145] Example 3:

[0146] The embodiment of the present invention also provides an electronic device. For details, please refer to Figure 5 , Figure 5 which is a schematic structural diagram of an electronic device provided by the embodiment of the present invention, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor. When the processor executes the computer program, the steps in the Robinia pseudoacacia forest thinning monitoring method based on distributed sensing are implemented.

[0147] Example 4:

[0148] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. Preferably, when the computer program is executed by a processor, the steps in the Robinia pseudoacacia forest thinning monitoring method based on distributed sensing are implemented.

[0149] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, please refer to the description in the method section.

[0150] Those skilled in the art may further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in the form of hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0151] Finally, it should also be noted that in this text, relationships such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not explicitly listed, or elements inherent to such process, method, article or device.

Claims

1. A Robinia pseudoacacia forest thinning monitoring system based on distributed sensing, comprising a distributed sensor, a drone, an edge server, and a cloud platform; the distributed sensors are distributed in the target Robinia pseudoacacia forest for measuring the light intensity; the drone is used to collect images of the target Robinia pseudoacacia forest and send them to the cloud platform; characterized in that, The edge server includes a distribution map generation module and an anomaly analysis module; the distribution map generation module is used to obtain the measurement data sent by the distributed sensors in the edge area and generate a distribution map of the sensor positions in the edge area; the anomaly analysis module is used to analyze whether the distributed sensors are abnormal; the cloud platform includes a region division module, a canopy density calculation module, and a thinning parameter analysis module; the region division module is used to obtain the images of the target Robinia pseudoacacia forest collected by the drone and divide the target Robinia pseudoacacia forest area into a canopy area and a ground area based on an image recognition algorithm; the canopy density calculation module is used to calculate the canopy density of each edge area; the thinning parameter analysis module is used to perform a correction calculation on the canopy density of the edge area to obtain the thinning parameter.

2. The robinia pseudoacacia intermediate cutting monitoring system based on distributed sensing according to claim 1, wherein The anomaly analysis module is used to analyze whether the distributed sensors are abnormal, including: obtaining the generation time of the region division map, set as the first time; querying the light weather information of the target Robinia pseudoacacia forest area at the first time; obtaining the first reference range and the second reference range based on the light weather information; the edge server receives the first reference range and the second reference range, queries the measurement data corresponding to the time stamp and the first time, judges whether the light intensity data of a certain type of sensor is within the first reference range, and judges whether the light intensity data of another type of sensor is within the second reference range. If so, there is no anomaly, otherwise it is judged as an abnormal sensor.

3. The distributed sensing-based black locust thinning monitoring system according to claim 2, wherein, The cloud platform obtains the total number M of distributed sensors in the edge area and the number m of abnormal sensors in the edge area; calculates a correction weight based on the anomaly ratio m / M of the distributed sensors; Corrects the canopy density of each edge area based on the correction weight and the measurement data to obtain the thinning parameter.

4. A method for monitoring the thinning of black locust forests based on distributed sensing, which is applied to the distributed sensing-based black locust forest thinning monitoring system described in any one of claims 1-3, and is characterized in that, The method includes: S2. Each edge server generates a distribution map of the sensor positions in an edge area based on the measurement data; where the area where the distributed sensors under the jurisdiction of each edge server are located is an edge area; S3. The drone collects images of the target Robinia pseudoacacia forest area and sends the collected images to the cloud platform; S4. The cloud platform extracts the canopy in the image based on the image recognition algorithm, divides the target Robinia pseudoacacia forest area into a canopy area and a ground area, and obtains a target area division map; S5. The cloud platform fuses the distribution map of the sensor positions in the edge area and the target area division map, and classifies the distributed sensors; S6. Judges whether there are monitoring anomalies in a certain type of sensor and another type of sensor; S7. The cloud platform calculates the canopy density C0 of each edge area based on the images of the drone; S8. Corrects the canopy density of the edge area based on the measurement data of the distributed sensors to obtain the thinning parameter.

5. The method for monitoring the thinning of black locust forests based on distributed sensing according to claim 4, characterized in that S5 Includes: S51. The cloud platform obtains the distribution map of the sensor positions in the edge area generated by each edge server and synthesizes the distribution map of the sensor positions in the target Robinia pseudoacacia forest area; S52. Integrate the distribution map of sensor positions in the target locust forest area with the target area division map, and divide the distributed sensors into type-I sensors and type-II sensors according to the type of the area where the sensors are located; type-I sensors are located within the tree crown area, and type-II sensors are located within the ground area.

6. The method for monitoring the thinning of black locust forests based on distributed sensing according to claim 5, characterized in that S6 Including: S61. Obtain the generation time of the area division map, and set it as the first time; S62. Query the illumination weather information of the target locust forest area at the first time; S63. The cloud platform obtains a first reference range and a second reference range based on the illumination weather information. The first reference range is the reference range of illumination intensity under shade, and the second reference range is the reference range of illumination intensity without shade; S64. The edge server receives the first reference range and the second reference range, queries the measurement data corresponding to the time stamp and the first time, determines whether the light intensity data of type-I sensors is within the first reference range, and determines whether the light intensity data of type-II sensors is within the second reference range. If so, there is no abnormality; otherwise, it is determined as an abnormal sensor.

7. The method for monitoring the thinning of Robinia pseudoacacia forests based on distributed sensing according to claim 6, wherein S8 includes: S81. Obtain the total number M of distributed sensors in the edge area and the number m of abnormal sensors in the edge area; S82. Calculate the correction weight α based on the abnormal ratio m / M of the distributed sensors; S83. Correct the canopy density of each edge area based on the correction weight and the measurement data to obtain the thinning parameter D.

8. The method for monitoring the thinning of black locust forests based on distributed sensing according to claim 7, wherein Before the step S2, there is also a preliminary layout step S1, and after the step S8, there is also a thinning execution step S9; S1 includes: arranging a number of distributed sensors among the locust trees; the distributed sensors are used to measure the illumination intensity and send the measurement data to the edge server; the measurement data includes the sensor number, the sensor position, the light intensity data, and the time stamp; S9 includes: when the thinning parameter is greater than or equal to the preset limit value, execute the thinning strategy; when the thinning parameter is less than the threshold value, continuously monitor the target locust forest.

9. An electronic device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor. When the processor executes the computer program, it implements the steps in the method for monitoring locust tree thinning based on distributed sensing according to any one of claims 4-8.

10. A 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 steps in the method for monitoring locust tree thinning based on distributed sensing according to any one of claims 4-8.

Images