Forest risk control method and system based on optical fiber sensor

Abstract

The invention relates to the technical field of forest risk management and control, and particularly discloses a forest risk control method and system based on an optical fiber sensor, and the method comprises the steps: obtaining the zoning information of a forest, and determining the installation point location of the optical fiber sensor according to the zoning information; the optical fiber sensor is used for acquiring wind power parameters and temperature; determining a recording track of the unmanned aerial vehicle according to the installation point location of the optical fiber sensor; receiving feedback data of the optical fiber sensor and the unmanned aerial vehicle in real time, performing time domain normalization on the feedback data, and constructing a forest region three-dimensional model; and acquiring personnel information in the forest region in real time, determining a risk region according to the personnel information and the forest region three-dimensional model, and actually reporting the risk region. According to the method, the data of the forest region are collected in real time through the optical fiber sensor and the unmanned aerial vehicle, after time domain registration is carried out on the data, a dynamic forest region three-dimensional model is established according to the data, the risk region is marked according to the same frequency of the data, reference is provided for the risk control process of workers, and the risk control real-time performance is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of forest risk management and control, and in particular to a forest risk control method and system based on optical fiber sensors. Background Art

[0002] With the improvement of living standards, the tourism industry has gradually developed. Some scenic spots with natural landscapes will develop tourism based on the natural landscapes. The existing natural landscapes are mostly dominated by vegetation areas, such as forests and mountains. Roads are built in these vegetation areas to obtain natural scenic spots that are easy to travel.

[0003] For these natural scenic spots based in forest areas, there are many tourists and potential risks, so real-time risk control is needed. The existing risk control plan process is relatively simple and mainly relies on manual work. The amount of information obtained from the forest area is small and the real-time performance is not high. How to obtain a larger amount of forest area information in real time and improve the real-time performance and accuracy of risk control are the technical problems that the technical solution of the present invention aims to solve. Summary of the invention

[0004] The purpose of the present invention is to provide a forest wind control method and system based on optical fiber sensors to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A forest area wind control method based on optical fiber sensors, the method comprising:

[0007] Acquire the zoning information of the forest area, and determine the installation point of the optical fiber sensor according to the zoning information; the optical fiber sensor is used to obtain wind parameters and temperature;

[0008] Determining the recording track of the drone according to the installation point of the optical fiber sensor;

[0009] Receive feedback data from optical fiber sensors and drones in real time, regularize the feedback data in the time domain, and construct a three-dimensional model of the forest area;

[0010] Obtain personnel information in the forest area in real time, determine risk areas based on personnel information and the three-dimensional model of the forest area, and actually report risk areas.

[0011] As a further solution of the present invention: the step of obtaining the zoning information of the forest area and determining the installation point of the optical fiber sensor according to the zoning information includes:

[0012] The forest area is divided into vegetation area and traffic area according to the road construction data in the forest area;

[0013] Determine the installation density based on the area of ​​the vegetation area and the distance between the vegetation area and the traffic area;

[0014] Installing optical fiber sensors for detecting wind parameters at the border of the vegetation area based on the installation density;

[0015] installing optical fiber sensors for detecting temperature inside the vegetation area based on the installation density;

[0016] The installation density is a percentage. When applied on the boundary of a vegetation area, it means the distance corresponding to one optical fiber sensor. When applied inside a vegetation area, it means the area corresponding to one optical fiber sensor.

[0017] As a further solution of the present invention: the step of determining the recording track of the drone according to the installation point of the optical fiber sensor includes:

[0018] Querying a traffic zone, and constructing a reference trajectory according to the traffic zone; the reference trajectory includes all traffic zones;

[0019] Obtain the projection of each vegetation area on the reference track and mark it as a mapping segment of the vegetation area;

[0020] For any vegetation area, sub-areas were randomly selected in the vegetation area and the sub-areas were connected to obtain additional trajectories;

[0021] Before each recording of the drone, a mapping segment is randomly selected, and the baseline trajectory and additional trajectory are counted to obtain the recording trajectory of that recording;

[0022] The sub-area selection process is as follows:

[0023] (x i ,y i )=(Rand(1)*A i ,Rand(1)*B i );

[0024] A i =A i-1 -R; B i =B i-1 -R;

[0025] In the formula, (x i ,y i ) is the coordinate of the center point of the selected i-th sub-area, R is the preset sub-area radius; A i The initial value of is the length of the vegetation area when selected, B i The initial value of is the width of the vegetation area when selected; Rand(1) is used to randomly generate a value ranging from 0 to 1;

[0026] The mapping segment selection process is:

[0027]

[0028] Where Pj is the selection probability of the jth mapping segment, L j is the length of the jth mapping segment, and M is the total number of mapping segments.

[0029] As a further solution of the present invention, the steps of receiving feedback data from the optical fiber sensor and the drone in real time, regularizing the feedback data in the time domain, and constructing a three-dimensional model of the forest area include:

[0030] Receive temperature and wind parameters fed back by optical fiber sensors;

[0031] Receive images fed back by the drone; the temperature, wind parameters and images all contain timestamps;

[0032] Take the timestamp of the image as a reference, read the most recent temperature and the most recent wind parameters, and establish a matching relationship;

[0033] A three-dimensional model of the forest area is constructed based on the feedback data.

[0034] As a further solution of the present invention: the step of constructing a three-dimensional model of the forest area based on the feedback data includes:

[0035] Simulating an initial model based on a remote sensing image of a forest area; the remote sensing image is a 2.5D image;

[0036] The initial model is adjusted according to the image fed back by the drone to obtain a three-dimensional model of the forest area; the three-dimensional model of the forest area is indexed by the timestamp of the image;

[0037] Read the time and wind force parameters under the same matching relationship, and construct a temperature matrix according to the temperature;

[0038] The temperature matrix is ​​corrected according to the wind parameters, and a temperature layer is created based on the corrected temperature matrix and inserted into the three-dimensional model of the forest area.

[0039] As a further solution of the present invention: the step of obtaining the personnel information in the forest area in real time, determining the risk area according to the personnel information and the three-dimensional model of the forest area, and actually reporting the risk area includes:

[0040] Sort the three-dimensional models of the forest area according to their timestamps;

[0041] For any point in the three-dimensional model of the forest area, extract the temperature in the sorted three-dimensional model of the forest area, and determine the risk value according to the extracted temperature;

[0042] When the risk value reaches a preset threshold, the point is marked as a risk point;

[0043] Count the risk points to get the risk area, and simultaneously calculate the average of the risk values ​​of all risk points in the risk area as the risk value of the risk area;

[0044] Obtaining the location of a person with a time tag according to a person detection device built into the forest area; the person detection device includes at least a camera and an infrared detector;

[0045] Determine the number of people in each risk area according to the positions of the people, and correct the risk value according to the number of people;

[0046] Report the risk area and revised risk value.

[0047] The technical solution of the present invention also provides a forest wind control system based on optical fiber sensors, the system comprising:

[0048] A sensor installation module is used to obtain the zoning information of the forest area and determine the installation point of the optical fiber sensor according to the zoning information; the optical fiber sensor is used to obtain wind parameters and temperature;

[0049] A drone preprocessing module, used to determine the recording trajectory of the drone according to the installation point of the optical fiber sensor;

[0050] A data regularization module is used to receive feedback data from optical fiber sensors and drones in real time, perform time domain regularization on the feedback data, and construct a three-dimensional model of the forest area;

[0051] The risk area reporting module is used to obtain the personnel information in the forest area in real time, determine the risk area based on the personnel information and the three-dimensional model of the forest area, and actually report the risk area.

[0052] As a further solution of the present invention: the sensor installation module includes:

[0053] Area classification units, which are used to divide forest areas into vegetation areas and access areas based on road construction data in forest areas;

[0054] A density determination unit, used to determine the installation density according to the area of ​​the vegetation area and the distance between the vegetation area and the traffic area;

[0055] A wind force detection unit, used to install an optical fiber sensor for detecting wind force parameters at a boundary of the vegetation area based on the installation density;

[0056] A temperature detection unit, used to install an optical fiber sensor for detecting temperature inside the vegetation area based on the installation density;

[0057] The installation density is a percentage. When applied on the boundary of a vegetation area, it means the distance corresponding to one optical fiber sensor. When applied inside a vegetation area, it means the area corresponding to one optical fiber sensor.

[0058] As a further solution of the present invention: the drone preprocessing module includes:

[0059] A reference trajectory generating unit, used for querying a passage area and constructing a reference trajectory according to the passage area; the reference trajectory includes all passage areas;

[0060] A projection calculation unit, used for obtaining the projection of each vegetation area on the reference track, and marking it as a mapping segment of the vegetation area;

[0061] An additional trajectory generating unit is used for randomly selecting sub-areas in any vegetation area and connecting the sub-areas to obtain additional trajectories;

[0062] The random selection unit is used to randomly select the mapping segment before each recording of the drone, count the reference trajectory and the additional trajectory, and obtain the recording trajectory of the recording;

[0063] The sub-area selection process is as follows:

[0064] (x i ,y i )=(Rand(1)*A i ,Rand(1)*B i );

[0065] A i =A i-1 -R; B i =B i-1 -R;

[0066] In the formula, (x i ,y i ) is the coordinate of the center point of the selected i-th sub-area, R is the preset sub-area radius; A i The initial value of is the length of the vegetation area when selected, B i The initial value of is the width of the vegetation area when selected; Rand(1) is used to randomly generate a value ranging from 0 to 1;

[0067] The mapping segment selection process is:

[0068]

[0069] Where P j is the selection probability of the jth mapping segment, L j is the length of the jth mapping segment, and M is the total number of mapping segments.

[0070] As a further solution of the present invention: the data regularization module includes:

[0071] A sensor data receiving unit, used for receiving temperature and wind force parameters fed back by the optical fiber sensor;

[0072] An image receiving unit, used to receive images fed back by the drone; the temperature, wind parameters and images all contain timestamps;

[0073] The data registration unit is used to use the timestamp of the image as a reference, read the temperature and wind parameters of the most recent time, and establish a matching relationship;

[0074] A modeling execution unit is used to construct a three-dimensional model of the forest area based on the feedback data.

[0075] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention collects data of the forest area in real time through optical fiber sensors and drones, and after time domain registration of the data, establishes a dynamic three-dimensional model of the forest area based on the data, and marks the risk areas according to the same frequency of the data, providing a reference for the risk control process of the staff, thereby greatly improving the real-time performance of risk control. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0077] Figure 1 This is a flowchart of the forest area wind control method based on optical fiber sensors.

[0078] Figure 2 This is the first sub-process flowchart of the forest area wind control method based on optical fiber sensors.

[0079] Figure 3 This is the second sub-process flowchart of the forest area wind control method based on optical fiber sensors.

[0080] Figure 4 This is the third sub-process flowchart of the forest area wind control method based on optical fiber sensors.

[0081] Figure 5 This is the fourth sub-process flowchart of the forest area wind control method based on optical fiber sensors.

[0082] Figure 6 This is a structural block diagram of the forest wind control system based on optical fiber sensors. DETAILED DESCRIPTION

[0083] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0084] Figure 1 The flowchart of the forest area wind control method based on the optical fiber sensor is as follows. In an embodiment of the present invention, a forest area wind control method based on the optical fiber sensor includes:

[0085] Step S100: obtaining zoning information of the forest area, and determining the installation point of the optical fiber sensor according to the zoning information; the optical fiber sensor is used to obtain wind parameters and temperature;

[0086] The forest area in the present application refers to an area with large areas of plants planted, generally referring to a forest area. Some wheat fields can also be applied to the technical solution of the present invention, but wheat fields are generally managed by dedicated personnel. Under the current circumstances, there will not be large areas of wheat fields, and there is no need to apply the risk control method provided by the present application.

[0087] The zoning information of the forest area is obtained, where the zoning information is mainly used to distinguish between vegetation areas and traffic areas. The vegetation area is an area for growing plants, and the traffic area is an area for people to walk.

[0088] By analyzing the zoning information, the installation point of the fiber optic sensor can be determined. The fiber optic sensor is a sensor that uses optical fiber as a sensing element to measure physical quantities such as light, temperature, pressure, and deformation. Its working principle is based on the optical properties of the optical fiber. When the measured physical quantity changes, it will affect the optical signal in the optical fiber. By detecting these changes, the corresponding measurement results can be obtained. Fiber optic sensors have many advantages, such as high sensitivity, anti-electromagnetic interference, and easy remote monitoring. This application uses fiber optic sensors to obtain wind parameters and temperature.

[0089] Step S200: determining the recording track of the drone according to the installation point of the optical fiber sensor;

[0090] The recording track of the drone is determined according to the installation point of the optical fiber sensor. The drone is used to collect images of the forest area, assist the wind control process in the forest area, and improve the comprehensiveness and accuracy of the wind control process.

[0091] Step S300: receiving feedback data from the optical fiber sensor and the drone in real time, regularizing the feedback data in the time domain, and constructing a three-dimensional model of the forest area;

[0092] During the wind control process, fiber optic sensors and drones will continuously acquire data according to a preset time period, which is called feedback data. The feedback data with the same time correspondence is classified into one category and used to construct a three-dimensional model of the forest area. The same time correspondence means that the time difference is less than the preset threshold. Due to the different transmission distances of the feedback data, there will be a certain time difference when the data collected at the same time is fed back. In addition, the data collection time of the fiber optic sensor and the drone may also be different. Therefore, time domain regularization is to classify the most similar feedback data into one category.

[0093] Step S400: obtaining personnel information in the forest area in real time, determining risk areas based on the personnel information and the three-dimensional model of the forest area, and actually reporting the risk areas;

[0094] With the help of existing equipment (such as surveillance cameras installed in the traffic area), personnel information can be obtained, and the risk area can be jointly determined based on the personnel information and the three-dimensional model of the forest area containing feedback data, and then reported.

[0095] The essence of this process is to first identify the three-dimensional model of the forest area containing feedback data, determine some risk areas, and then make adjustments based on personnel information. The resulting risk areas are determined by both environmental and personnel factors. The determination process is no longer single, with higher accuracy and a higher degree of fit with actual conditions.

[0096] Figure 2 The first sub-flow chart of the forest area wind control method based on optical fiber sensors is as follows: the steps of obtaining the zoning information of the forest area and determining the installation point of the optical fiber sensor according to the zoning information include:

[0097] Step S101: dividing the forest area into a vegetation area and a traffic area according to the road construction data of the forest area;

[0098] Step S102: determining the installation density according to the area of ​​the vegetation area and the distance between the vegetation area and the traffic area;

[0099] Step S103: installing optical fiber sensors for detecting wind parameters at the boundary of the vegetation area based on the installation density;

[0100] Step S104: installing optical fiber sensors for detecting temperature inside the vegetation area based on the installation density;

[0101] The installation density is a percentage. When applied on the boundary of a vegetation area, it means the distance corresponding to one optical fiber sensor. When applied inside a vegetation area, it means the area corresponding to one optical fiber sensor.

[0102] In an example of the technical solution of the present invention, the installation process of the fiber optic sensor is specifically limited. First, the forest area is divided into a passage area and a vegetation area according to the road construction data of the forest area. For the convenience of operation, this application generally determines the passage area according to the road construction data, and directly regards other areas as vegetation areas. In actual applications, the passage area itself can be used as the boundary of the vegetation area, thereby dividing the vegetation area into multiple blocks.

[0103] Then, for each vegetation area, the installation density can be determined based on the distance between the vegetation area and the traffic area and the area of ​​the vegetation area itself. The greater the installation density, the more fiber optic sensors are installed in the vegetation area. Specifically, the farther the distance between the vegetation area and the traffic area, the farther the vegetation area is from the staff. At this time, a greater installation density is required. When the area of ​​the vegetation area itself is larger, it means that the vegetation area is more difficult to detect. At this time, a greater installation density is required.

[0104] Finally, based on the installation density, optical fiber sensors for detecting wind parameters are installed at the boundary of the vegetation area; based on the installation density, optical fiber sensors for detecting temperature are installed inside the vegetation area; wherein the installation density is a percentage, and when applied to the boundary of the vegetation area, it means the distance corresponding to one optical fiber sensor, that is, how far apart a optical fiber sensor is installed, and when applied inside the vegetation area, it means the area corresponding to one optical fiber sensor, that is, how large an area is installed with one optical fiber sensor.

[0105] Figure 3 The second sub-flow chart of the forest area wind control method based on the optical fiber sensor is as follows: the step of determining the recording track of the drone according to the installation point of the optical fiber sensor comprises:

[0106] Step S201: querying a traffic zone, and constructing a reference trajectory according to the traffic zone; the reference trajectory includes all traffic zones;

[0107] Step S202: obtaining the projection of each vegetation area on the reference track and marking it as a mapping segment of the vegetation area;

[0108] Step S203: for any vegetation area, randomly select sub-areas in the vegetation area, and connect the sub-areas to obtain additional trajectories;

[0109] Step S204: before each recording of the drone, randomly select a mapping segment, count the reference trajectory and the additional trajectory, and obtain the recording trajectory of the recording;

[0110] The sub-area selection process is as follows:

[0111] (x i ,y i )=(Rand(1)*A i ,Rand(1)*B i );

[0112] A i =A i-1 -R; B i =B i-1 -R;

[0113] In the formula, (x i ,y i ) is the coordinate of the center point of the selected i-th sub-area, R is the preset sub-area radius; A i The initial value of is the length of the vegetation area when selected, B i The initial value of is the width of the vegetation area when selected; Rand(1) is used to randomly generate a value ranging from 0 to 1;

[0114] The mapping segment selection process is:

[0115]

[0116] Where P j is the selection probability of the jth mapping segment, L j is the length of the jth mapping segment, and M is the total number of mapping segments.

[0117] After the fiber optic sensor is arranged, the UAV needs to be calibrated, specifically, to determine the trajectory of the UAV to collect images; in the technical solution of the present application, the trajectory of the UAV includes two parts, one is a reference trajectory, which is established according to the passage area, that is, the reference movement of the UAV is along the passage area; on this basis, the projection of each vegetation area on the reference trajectory is obtained, and the segment corresponding to the vegetation area can be obtained on the reference trajectory.

[0118] For each vegetation area, some sub-areas are randomly selected as the detection targets of the drone. Before each mission, the drone needs to perform a selection process. The selected sub-areas can create some collection tracks inside the vegetation area, which are called additional tracks.

[0119] Based on the above content, for each operation of the drone, sub-areas are first selected in each vegetation area to create multiple additional trajectories. Then, some segments are randomly selected on the baseline trajectory. When the drone moves to the segment, the additional trajectory is read and connected to the baseline trajectory to obtain the collection trajectory of this operation, which is called the recorded trajectory.

[0120] Figure 4 The third sub-flow chart of the forest area wind control method based on optical fiber sensors, wherein the steps of receiving feedback data from optical fiber sensors and drones in real time, regularizing the feedback data in the time domain, and constructing a three-dimensional model of the forest area include:

[0121] Step S301: receiving temperature and wind force parameters fed back by the optical fiber sensor;

[0122] Step S302: receiving an image fed back by the drone; the temperature, wind parameters and image all contain a timestamp;

[0123] Step S303: taking the timestamp of the image as a reference, reading the temperature and wind parameters at the most recent time, and establishing a matching relationship;

[0124] Step S304: constructing a three-dimensional model of the forest area based on the feedback data.

[0125] Fiber optic sensors are used to obtain temperature and wind parameters, and drones are used to obtain images. Both of these data contain time. The temperature and wind parameters fed back by the fiber optic sensors and the images fed back by the drones are received and aligned according to time. Data with similar time periods are taken as a group, called feedback data, to establish a three-dimensional model of the forest area at that moment.

[0126] Furthermore, the step of constructing a three-dimensional model of the forest area based on the feedback data includes:

[0127] Simulating an initial model based on a remote sensing image of a forest area; the remote sensing image is a 2.5D image;

[0128] The initial model is adjusted according to the image fed back by the drone to obtain a three-dimensional model of the forest area; the three-dimensional model of the forest area is indexed by the timestamp of the image;

[0129] Read the time and wind force parameters under the same matching relationship, and construct a temperature matrix according to the temperature;

[0130] The temperature matrix is ​​corrected according to the wind parameters, and a temperature layer is created based on the corrected temperature matrix and inserted into the three-dimensional model of the forest area.

[0131] The above content provides a specific solution for building a three-dimensional model of a forest area. The 2.5D image of the forest area is read according to the map service as the initial model. The initial model is adjusted according to the image feedback from the drone. The adjusted initial model is called the three-dimensional model of the forest area. The adjustment process is the refinement process of the initial model. The simplest way is to directly replace the corresponding area of ​​the initial model with the image and then blur the edges.

[0132] Read the time and wind parameters under the same matching relationship, and construct a temperature matrix according to the temperature. The temperature matrix represents the temperature of each position. Combined with the wind parameters, the temperature matrix is ​​adjusted. The specific adjustment plan is to read the closest wind parameters (including wind direction and wind speed, represented by vectors) for the temperature at any position, and adjust the temperature according to the wind parameters. If the temperature at the previous position on the wind parameter is higher, add a value to the temperature at the current position. On the contrary, if the temperature at the previous position on the wind parameter is lower, subtract a value from the temperature at the current position.

[0133] Insert the temperature matrix as a layer into the 3D model of the forest area.

[0134] Figure 5 This is a fourth sub-flow chart of the forest area risk control method based on optical fiber sensors. The steps of obtaining personnel information in the forest area in real time, determining the risk area according to the personnel information and the three-dimensional model of the forest area, and actually reporting the risk area include:

[0135] Step S401: sorting the three-dimensional forest area models according to their timestamps;

[0136] Step S402: for any point in the three-dimensional model of the forest area, extract the temperature in the sorted three-dimensional model of the forest area, and determine the risk value according to the extracted temperature;

[0137] Step S403: When the risk value reaches a preset threshold, the point is marked as a risk point;

[0138] Step S404: Count the risk points to obtain a risk area, and simultaneously calculate the average of the risk values ​​of all risk points in the risk area as the risk value of the risk area;

[0139] Step S405: obtaining the personnel position with the time tag according to the personnel detection equipment built into the forest area; the personnel detection equipment at least includes a camera and an infrared detector;

[0140] Step S406: determining the number of people in each risk area according to the positions of the people, and correcting the risk value according to the number of people;

[0141] Step S407: Report the risk area and the corrected risk value.

[0142] The above content describes in detail the process of determining the risk zone. The three-dimensional model of the forest area is sorted according to the timestamp of the three-dimensional model of the forest area. For any point in the three-dimensional model of the forest area, the temperature is extracted in the sorted three-dimensional model of the forest area. The risk value is determined according to the extracted temperature. The temperature is proportional to the risk value. The higher the temperature, the greater the risk value. When the risk value is large enough, the point is marked as a risk point, and the adjacent risk points are counted and connected to obtain an area, called the risk area; the average risk value of all risk points in the risk area is calculated as the risk value of the risk area.

[0143] On this basis, the risk value is corrected according to the personnel situation obtained by the cameras installed in the forest area, and the personnel position is used to correct the risk value. Generally speaking, the more people there are in a risk area, the more serious the consequences will be once a risk occurs. In other words, the more people there are, the larger the risk value must be adjusted. The risk area and the corrected risk value can be reported.

[0144] Figure 6 The structure block diagram of the forest wind control system based on optical fiber sensors is shown in the following figure. In an embodiment of the present invention, a forest wind control system based on optical fiber sensors is provided. The system 10 includes:

[0145] The sensor installation module 11 is used to obtain the zoning information of the forest area and determine the installation point of the optical fiber sensor according to the zoning information; the optical fiber sensor is used to obtain wind parameters and temperature;

[0146] The drone preprocessing module 12 is used to determine the recording track of the drone according to the installation point of the optical fiber sensor;

[0147] The data regularization module 13 is used to receive the feedback data from the optical fiber sensor and the drone in real time, perform time domain regularization on the feedback data, and construct a three-dimensional model of the forest area;

[0148] The risk area reporting module 14 is used to obtain the personnel information in the forest area in real time, determine the risk area based on the personnel information and the three-dimensional model of the forest area, and actually report the risk area.

[0149] Furthermore, the sensor installation module 11 includes:

[0150] Area classification units, which are used to divide forest areas into vegetation areas and access areas based on road construction data in forest areas;

[0151] A density determination unit, used to determine the installation density according to the area of ​​the vegetation area and the distance between the vegetation area and the traffic area;

[0152] A wind force detection unit, used to install an optical fiber sensor for detecting wind force parameters at a boundary of the vegetation area based on the installation density;

[0153] A temperature detection unit, used to install an optical fiber sensor for detecting temperature inside the vegetation area based on the installation density;

[0154] The installation density is a percentage. When applied on the boundary of a vegetation area, it means the distance corresponding to one optical fiber sensor. When applied inside a vegetation area, it means the area corresponding to one optical fiber sensor.

[0155] Specifically, the drone preprocessing module 12 includes:

[0156] A reference trajectory generating unit, used for querying a passage area and constructing a reference trajectory according to the passage area; the reference trajectory includes all passage areas;

[0157] A projection calculation unit, used for obtaining the projection of each vegetation area on the reference track, and marking it as a mapping segment of the vegetation area;

[0158] An additional trajectory generating unit is used for randomly selecting sub-areas in any vegetation area and connecting the sub-areas to obtain additional trajectories;

[0159] The random selection unit is used to randomly select the mapping segment before each recording of the drone, count the reference trajectory and the additional trajectory, and obtain the recording trajectory of the recording;

[0160] The sub-area selection process is as follows:

[0161] (x i ,y i )=(Rand(1)*A i ,Rand(1)*B i );

[0162] A i =A i-1 -R; B i =B i-1 -R;

[0163] In the formula, (x i ,y i ) is the coordinate of the center point of the selected i-th sub-area, R is the preset sub-area radius; A i The initial value of is the length of the vegetation area when selected, B i The initial value of is the width of the vegetation area when selected; Rand(1) is used to randomly generate a value ranging from 0 to 1;

[0164] The mapping segment selection process is:

[0165]

[0166] Where P j is the selection probability of the jth mapping segment, L j is the length of the jth mapping segment, and M is the total number of mapping segments.

[0167] In addition, the data regularization module 13 includes:

[0168] A sensor data receiving unit, used for receiving temperature and wind force parameters fed back by the optical fiber sensor;

[0169] An image receiving unit, used to receive images fed back by the drone; the temperature, wind parameters and images all contain timestamps;

[0170] The data registration unit is used to use the timestamp of the image as a reference, read the temperature and wind parameters of the most recent time, and establish a matching relationship;

[0171] A modeling execution unit is used to construct a three-dimensional model of the forest area based on the feedback data.

[0172] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A forest wind control method based on optical fiber sensors, characterized in that: The method comprises: Acquire the zoning information of the forest area, and determine the installation point of the optical fiber sensor according to the zoning information; the optical fiber sensor is used to obtain wind parameters and temperature; Determining the recording track of the drone according to the installation point of the optical fiber sensor; Receive feedback data from optical fiber sensors and drones in real time, regularize the feedback data in the time domain, and construct a three-dimensional model of the forest area; Obtain personnel information in the forest area in real time, determine risk areas based on personnel information and the three-dimensional model of the forest area, and actually report risk areas.

2. The forest area wind control method based on optical fiber sensor according to claim 1 is characterized in that: The step of obtaining the zoning information of the forest area and determining the installation point of the optical fiber sensor according to the zoning information includes: The forest area is divided into vegetation area and traffic area according to the road construction data in the forest area; Determine the installation density based on the area of ​​the vegetation area and the distance between the vegetation area and the traffic area; Installing optical fiber sensors for detecting wind parameters at the border of the vegetation area based on the installation density; installing optical fiber sensors for detecting temperature inside the vegetation area based on the installation density; The installation density is a percentage. When applied on the boundary of a vegetation area, it means the distance corresponding to one optical fiber sensor. When applied inside a vegetation area, it means the area corresponding to one optical fiber sensor.

3. The forest area wind control method based on optical fiber sensor according to claim 1 is characterized in that: The step of determining the recording track of the drone according to the installation point of the optical fiber sensor comprises: Querying a traffic zone, and constructing a reference trajectory according to the traffic zone; the reference trajectory includes all traffic zones; Obtain the projection of each vegetation area on the reference track and mark it as a mapping segment of the vegetation area; For any vegetation area, sub-areas were randomly selected in the vegetation area and the sub-areas were connected to obtain additional trajectories; Before each recording of the drone, a mapping segment is randomly selected, and the baseline trajectory and additional trajectory are counted to obtain the recording trajectory of that recording; The sub-area selection process is as follows: (x i ,y i )=(Rand(1)*A i ,Rand(1)*B i ); A i =A i-1 -R;B i =B i-1 -R; In the formula, (x i ,y i ) is the coordinate of the center point of the selected i-th sub-area, R is the preset sub-area radius; A i The initial value of is the length of the vegetation area when selected, B i The initial value of is the width of the vegetation area when selected; Rand(1) is used to randomly generate a value ranging from 0 to 1; The mapping segment selection process is: Where P j is the selection probability of the jth mapping segment, L j is the length of the jth mapping segment, and M is the total number of mapping segments.

4. The forest area wind control method based on optical fiber sensor according to claim 1 is characterized in that: The steps of receiving feedback data from the optical fiber sensor and the drone in real time, regularizing the feedback data in the time domain, and constructing a three-dimensional model of the forest area include: Receive temperature and wind parameters fed back by optical fiber sensors; Receive images fed back by the drone; the temperature, wind parameters and images all contain timestamps; Take the timestamp of the image as a reference, read the most recent temperature and the most recent wind parameters, and establish a matching relationship; A three-dimensional model of the forest area is constructed based on the feedback data.

5. The forest area wind control method based on optical fiber sensor according to claim 4 is characterized in that: The step of constructing a three-dimensional model of the forest area based on the feedback data comprises: Simulating an initial model based on a remote sensing image of a forest area; the remote sensing image is a 2.5D image; The initial model is adjusted according to the image fed back by the drone to obtain a three-dimensional model of the forest area; the three-dimensional model of the forest area is indexed by the timestamp of the image; Read the time and wind force parameters under the same matching relationship, and construct a temperature matrix according to the temperature; The temperature matrix is ​​corrected according to the wind parameters, and a temperature layer is created based on the corrected temperature matrix and inserted into the three-dimensional model of the forest area.

6. The forest area wind control method based on optical fiber sensor according to claim 1 is characterized in that: The steps of obtaining personnel information in the forest area in real time, determining the risk area according to the personnel information and the three-dimensional model of the forest area, and actually reporting the risk area include: Sort the three-dimensional models of the forest area according to their timestamps; For any point in the three-dimensional model of the forest area, extract the temperature in the sorted three-dimensional model of the forest area, and determine the risk value according to the extracted temperature; When the risk value reaches a preset threshold, the point is marked as a risk point; Count the risk points to get the risk area, and simultaneously calculate the average of the risk values ​​of all risk points in the risk area as the risk value of the risk area; Obtaining the location of a person with a time tag according to a person detection device built into the forest area; the person detection device includes at least a camera and an infrared detector; Determine the number of people in each risk area according to the positions of the people, and correct the risk value according to the number of people; Report the risk area and revised risk value.

7. A forest wind control system based on optical fiber sensors, characterized in that: The system comprises: A sensor installation module is used to obtain the zoning information of the forest area and determine the installation point of the optical fiber sensor according to the zoning information; the optical fiber sensor is used to obtain wind parameters and temperature; A drone preprocessing module, used to determine the recording trajectory of the drone according to the installation point of the optical fiber sensor; A data regularization module is used to receive feedback data from optical fiber sensors and drones in real time, perform time domain regularization on the feedback data, and construct a three-dimensional model of the forest area; The risk area reporting module is used to obtain the personnel information in the forest area in real time, determine the risk area based on the personnel information and the three-dimensional model of the forest area, and actually report the risk area.

8. The forest wind control system based on optical fiber sensor according to claim 7 is characterized in that: The sensor installation module comprises: Area classification units, which are used to divide forest areas into vegetation areas and access areas based on road construction data in forest areas; A density determination unit, used to determine the installation density according to the area of ​​the vegetation area and the distance between the vegetation area and the traffic area; A wind force detection unit, used to install an optical fiber sensor for detecting wind force parameters at a boundary of the vegetation area based on the installation density; A temperature detection unit, used to install an optical fiber sensor for detecting temperature inside the vegetation area based on the installation density; The installation density is a percentage. When applied on the boundary of a vegetation area, it means the distance corresponding to one optical fiber sensor. When applied inside a vegetation area, it means the area corresponding to one optical fiber sensor.

9. The forest wind control system based on optical fiber sensor according to claim 7 is characterized in that: The UAV preprocessing module includes: A reference trajectory generating unit, used for querying a passage area and constructing a reference trajectory according to the passage area; the reference trajectory includes all passage areas; A projection calculation unit, used for obtaining the projection of each vegetation area on the reference track, and marking it as a mapping segment of the vegetation area; An additional trajectory generating unit is used for randomly selecting sub-areas in any vegetation area and connecting the sub-areas to obtain additional trajectories; The random selection unit is used to randomly select the mapping segment before each recording of the drone, count the reference trajectory and the additional trajectory, and obtain the recording trajectory of the recording; The sub-area selection process is as follows: (x i ,y i )=(Rand(1)*A i ,Rand(1)*B i ); A i =A i-1 -R;B i =B i-1 -R; In the formula, (x i ,y i ) is the coordinate of the center point of the selected i-th sub-area, R is the preset sub-area radius; A i The initial value of is the length of the vegetation area when selected, B i The initial value of is the width of the vegetation area when selected; Rand(1) is used to randomly generate a value ranging from 0 to 1; The mapping segment selection process is: Where P j is the selection probability of the jth mapping segment, L j is the length of the jth mapping segment, and M is the total number of mapping segments.

10. The forest wind control system based on optical fiber sensor according to claim 7, characterized in that: The data regularization module includes: A sensor data receiving unit, used for receiving temperature and wind force parameters fed back by the optical fiber sensor; An image receiving unit, used to receive images fed back by the drone; the temperature, wind parameters and images all contain timestamps; The data registration unit is used to use the timestamp of the image as a reference, read the temperature and wind parameters of the most recent time, and establish a matching relationship; A modeling execution unit is used to construct a three-dimensional model of the forest area based on the feedback data.

Images