Restoration evaluation system and evaluation method for alpine meadow ecosystem

Abstract

The invention relates to the technical field of ecological system restoration evaluation, and particularly discloses a restoration evaluation system and evaluation method for an alpine meadow ecological system, and the method comprises the steps: firstly obtaining infrared temperature images and temperature parameters of a to-be-evaluated meadow at different sampling times; respectively generating a recognition temperature threshold set corresponding to each infrared temperature image, and then respectively recognizing a first vegetation coverage area, a second vegetation coverage area and a third vegetation coverage area on each infrared temperature image according to each recognition temperature threshold set; generating a vegetation coverage parameter set of the to-be-evaluated meadow according to the areas of the first vegetation coverage area and the second vegetation coverage area, finally fitting a vegetation coverage change curve of the to-be-evaluated meadow according to the vegetation coverage parameter set and the sampling time, and outputting an evaluation result according to the vegetation coverage change curve. Through temperature detection, the identification program is simplified, and the evaluation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of grassland ecological management, and in particular to a restoration assessment system and assessment method for an alpine meadow ecosystem. Background Art

[0002] Alpine meadow is a type of grassland that develops under cold climate conditions and is mainly distributed in plateaus and high mountain areas. It is composed of cold-tolerant perennial mesophytic plants that can grow and thrive in cold and humid environments. Alpine meadow has important value in the ecosystem. It is not only a habitat for many animals and plants, but also plays a key role in maintaining ecological balance and protecting biodiversity.

[0003] However, due to factors such as overgrazing and climate change, alpine meadows are facing serious degradation and destruction. Ecological restoration is particularly important for the protection of alpine meadows. When repairing alpine meadows, it is necessary not only to repair vegetation, but also to observe the growth of vegetation regularly or irregularly to provide data support for subsequent restoration work and ensure the quality of meadow restoration.

[0004] Although the existing technology can improve the efficiency of vegetation assessment through satellite remote sensing technology, it is affected by factors such as weather and clouds, and its data collection efficiency is low, which in turn reduces the efficiency of grassland restoration effect assessment. Summary of the invention

[0005] The present application provides a restoration assessment system and assessment method for an alpine meadow ecosystem, aiming to solve the technical problem of low assessment efficiency existing in the prior art.

[0006] To solve the above technical problems, the present application provides: A restoration assessment system for alpine meadow ecosystems, comprising: An infrared temperature image acquisition module is used to respectively acquire infrared temperature images of the grassland to be evaluated at different sampling times; A temperature parameter acquisition module, used to respectively acquire the temperature parameters of the grassland to be evaluated at different sampling times, and to generate a corresponding identification temperature threshold set for each infrared temperature image; An image recognition module, used to recognize a first vegetation coverage area, a second vegetation coverage area, and a third vegetation coverage area on each of the infrared temperature images according to each of the recognition temperature threshold sets; A calculation module, used for generating a vegetation coverage parameter set of the grassland to be evaluated according to the areas of the first vegetation coverage area and the second vegetation coverage area; The evaluation module fits the vegetation coverage change curve of the grassland to be evaluated according to the vegetation coverage parameter set and the sampling time, and outputs the evaluation result according to the vegetation coverage change curve.

[0007] Accordingly, the present application also discloses an assessment method based on the above-mentioned restoration assessment system for alpine meadow ecosystem, comprising the following steps: Obtain infrared temperature images of the grassland to be evaluated at different sampling times; Acquire the temperature parameters of the grassland to be evaluated at different sampling times respectively, and generate a corresponding identification temperature threshold set for each infrared temperature image respectively; Respectively identifying a first vegetation covered area, a second vegetation covered area, and a third vegetation covered area on each of the infrared temperature images according to each of the identification temperature threshold sets; Generating a vegetation coverage parameter set of the grassland to be evaluated according to the areas of the first vegetation coverage area and the second vegetation coverage area; The vegetation coverage variation curve of the grassland to be evaluated is fitted according to the vegetation coverage parameter set and the sampling time, and the evaluation result is output according to the vegetation coverage variation curve.

[0008] Optionally, obtaining infrared temperature images of the grassland to be evaluated at different sampling times includes the following steps: Divide the grassland to be assessed into a number of assessment areas, and select sampling points in each of the assessment areas; Setting a sampling period, and selecting a sampling time according to the sampling period, wherein the time difference between any two adjacent sampling periods is not less than the sampling period; According to the sampling time, the UAV is controlled to collect infrared temperature images of each area to be evaluated at each sampling point; The infrared temperature images of each area to be evaluated obtained at the same sampling time are stitched together to obtain infrared temperature images of several grasslands to be evaluated.

[0009] Optionally, the temperature parameters of the grassland to be evaluated at different sampling times are obtained respectively, and a corresponding identification temperature threshold set is generated for each infrared temperature image respectively, including the following steps: Selecting a first vegetation-covered area, a second vegetation-covered area and a third vegetation-covered area in each area to be evaluated respectively; wherein the first vegetation-covered area represents a fully vegetation-covered area, the second vegetation-covered area represents a semi-vegetation-covered area and the third vegetation-covered area represents a completely bare area; At any sampling time, obtain the temperature t of the first vegetation coverage area in each area to be evaluated. 11 ,t 21 ,...,t n1 , the temperature of the second vegetation coverage area t 12 ,t 22 ,...,tn2 and the temperature of the third vegetation coverage area t 13 ,t 23 ,...,t n3 ; Where n represents the number of each area to be evaluated, 1, 2 and 3 represent the first vegetation coverage area, the second vegetation coverage area and the third vegetation coverage area respectively; According to the temperature t of the first vegetation coverage area 11 ,t 21 ,...,t n1 Generate a first identification temperature threshold, wherein the first identification temperature threshold satisfies T1≤max{t 11 ,t 21 ,...,t n1}; According to the temperature t of the second vegetation coverage area 12 ,t 22 ,...,t n2 Generate a second identification temperature threshold, wherein the second identification temperature threshold satisfies min{t 12 ,t 22 ,...,t n2}≤T2≤max{t 12 ,t 22 ,...,t n2} and T1<T2; According to the temperature t of the third vegetation coverage area 13 ,t 23 ,...,t n3 Generate a third identification temperature threshold, wherein the third identification temperature threshold satisfies T3≥min{t 13 ,t 23 ,...,t n3} and T2<T3; Repeat the steps of obtaining the temperature of the first vegetation coverage area, the temperature of the second vegetation coverage area and the temperature of the third vegetation coverage area in each to-be-evaluated area at any sampling time, and integrate and output each identification temperature threshold set {T1, T2, T3}1, {T1, T2, T3}2, ..., {T1, T2, T3} m , where m represents the number set according to the order of sampling time.

[0010] Optionally, identifying the first vegetation coverage area, the second vegetation coverage area, and the third vegetation coverage area on each of the infrared temperature images according to each of the identification temperature threshold sets includes the following steps: Grayscale values ​​are calibrated according to each set of identified temperature thresholds to generate a grayscale-temperature conversion function; Obtain any infrared temperature image and a corresponding identification temperature threshold set; Calculate an identification grayscale set according to the identification temperature threshold set and the grayscale-temperature conversion function; Converting the infrared temperature image into a grayscale image; Identifying a first vegetation-covered area, a second vegetation-covered area, and a third vegetation-covered area on the grayscale image according to the identification grayscale set; The steps of obtaining any infrared temperature image and the corresponding identification temperature threshold set are repeated to complete the identification of all infrared temperature images.

[0011] Optionally, grayscale value calibration is performed according to each identification temperature threshold set to generate a grayscale-temperature conversion function, including the following steps: Acquire each identification temperature threshold set, and determine the fitting temperature range according to the temperature value of each identification temperature threshold set; Randomly select a number of test temperatures within the fitting temperature range; Control the temperature of the adjustable black body furnace to any test temperature and take an infrared temperature image at the test temperature; Calculating a test grayscale value corresponding to the test temperature according to the infrared temperature image; Repeat the steps of controlling the temperature of the adjustable black body furnace to any test temperature, photographing the infrared temperature image at the test temperature, and obtaining all test gray values; Constructing a standard coordinate system, wherein the abscissa of the standard coordinate system represents the test temperature, and the ordinate represents the test grayscale value; Selecting a number of calibration points in the standard coordinate system according to each of the test temperatures and each of the test gray values; The grayscale-temperature conversion function is generated by fitting each calibration point.

[0012] Optionally, the expression of the grayscale-temperature conversion function is T=a•G+b, where a and b are fitting coefficients, T is temperature, and G is the grayscale value.

[0013] Optionally, identifying a first vegetation coverage area, a second vegetation coverage area, and a third vegetation coverage area on the grayscale image according to the identification grayscale set comprises the following steps: Acquire a recognition grayscale set and the grayscale image; Dividing the grayscale image into a number of standard cells, and obtaining the actual grayscale value of each standard cell respectively; Respectively comparing the identified grayscale set with each of the actual grayscale values, and dividing each of the standard cells into a first vegetation coverage area, a second vegetation coverage area, or a third vegetation coverage area; Count the number of standard cells Q contained in the first vegetation coverage area and the second vegetation coverage area respectively 1m and Q 2m, where m represents the infrared temperature image number, 1 and 2 represent the first vegetation coverage area and the second vegetation coverage area, respectively.

[0014] Optionally, generating a vegetation coverage parameter set of the grassland to be evaluated according to the areas of the first vegetation coverage area and the second vegetation coverage area comprises the following steps: The number Q of standard cells contained in the first vegetation coverage area and the second vegetation coverage area of ​​each infrared temperature image is obtained respectively. 11 , Q 12 , ..., Q 1m , Q 21 , Q 22 , ..., Q 2m ; Calculate the vegetation coverage parameters of each grassland to be evaluated and output the vegetation coverage parameter set {S1, S2, ..., S m}, where the expression of the vegetation coverage parameter is S m =k•Q 1m +j•Q 2m , k and j are constants.

[0015] Optionally, fitting a vegetation coverage change curve of the grassland to be evaluated according to the vegetation coverage parameter set and the sampling time, and outputting an evaluation result according to the vegetation coverage change curve, comprises the following steps: Get the vegetation coverage parameter set {S1, S2, ..., S m}; Constructing a fitting coordinate system, wherein the abscissa of the fitting coordinate system represents time, and the ordinate represents a vegetation coverage parameter; Get each sampling time t1, t2, ..., t m ; Selecting fitting points in the fitting coordinate system according to the vegetation coverage parameter set and each sampling time; Fit and connect the fitting points in series to generate the vegetation coverage change curve; The upper standard curve of vegetation coverage and the lower standard curve of vegetation coverage are retrieved. If the vegetation coverage change curve is between the upper standard curve and the lower standard curve of vegetation coverage, the assessment is qualified; otherwise, it is judged to be unqualified.

[0016] Compared with the prior art, this application has the following beneficial effects: The present application first obtains infrared temperature images of the grassland to be evaluated at different sampling times and temperature parameters of the grassland to be evaluated at different sampling times, and generates a corresponding identification temperature threshold set for each infrared temperature image, and then identifies the first vegetation coverage area, the second vegetation coverage area and the third vegetation coverage area on each infrared temperature image according to each identification temperature threshold set, and then generates a vegetation coverage parameter set of the grassland to be evaluated according to the areas of the first vegetation coverage area and the second vegetation coverage area, and finally fits the vegetation coverage change curve of the grassland to be evaluated according to the vegetation coverage parameter set and the sampling time, and outputs the evaluation result according to the vegetation coverage change curve; In the case of similar climate environments, due to vegetation coverage, the surface temperature will show large differences. The above differences are manifested in that the temperature in the fully vegetation-covered area is the lowest, the temperature in the semi-covered area will increase, and the temperature in the bare soil area is the highest. Based on the above temperature differences, the present application can accurately and quickly capture the above temperature differences through infrared temperature images, and then realize the rapid identification of different temperature areas of the image through the mapping relationship between temperature differences and image grayscale, that is, the rapid identification and separation of different vegetation coverage areas is realized, and then the area calculation of the vegetation coverage area is realized. By observing the changes in the vegetation coverage area at different time points, it is possible to quickly evaluate whether the vegetation restoration situation meets the requirements. Compared with the prior art, the present application realizes the observation of vegetation coverage area through temperature detection, and no longer needs to identify and monitor vegetation and vegetation types, which simplifies the identification procedure and improves the evaluation efficiency; Secondly, the vegetation coverage area is graded by temperature, and different levels of coverage areas correspond to different vegetation coverage coefficients, thereby completing a rapid estimation of the vegetation coverage area. It is no longer necessary to perform complex image processing and area calculations on irregular vegetation coverage areas. While ensuring the accuracy of the results, the image processing procedure is simplified as much as possible, thereby improving the efficiency of restoration assessment.

[0017] Finally, the vegetation coverage change curve can reflect the changes in grassland vegetation coverage in different time periods. In particular, the slope of the curve can reflect the vegetation growth rate, thereby reflecting whether the growth of vegetation is consistent with the time (season), and then predicting future vegetation changes and intervening in the adverse factors that affect vegetation growth in advance, thereby improving the restoration effect of grassland vegetation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation of the present application or the technical solution in the prior art, the following is a brief introduction to the drawings required for the specific implementation or the prior art description. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0019] Figure 1 This is a schematic diagram of the structure of a restoration assessment system for an alpine meadow ecosystem involved in this application; Figure 2 A flowchart of a restoration assessment system for an alpine meadow ecosystem involved in this application; Figure 3 Generate a schematic for the grayscale-to-temperature conversion function Figure 4 Partition schematics for standard cells; Figure 5 Generate schematic diagrams for vegetation cover change curves; Figure 6 This is the principle diagram of vegetation coverage comparison; The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] The precise feeding method for livestock and poultry based on image recognition of the present application, when judging the food intake and weight of individual livestock and poultry, is not simply judged by setting a threshold, but analyzed and judged by a deep learning model, which can better adapt to the differences between different livestock and poultry individuals, thereby improving the accuracy of judgment. In addition, the precise feeding method for livestock and poultry based on image recognition described in the present application can monitor the feeding situation and weight changes of livestock and poultry in real time. If a problem is found, an alarm message can be sent to the feeder in time, so that measures can be taken in time to ensure the healthy growth of livestock and poultry. It can be seen that the present application greatly improves the breeding efficiency, reduces labor costs, and improves economic benefits through automated monitoring and intelligent judgment.

[0022] It should be noted that all directional indications in the embodiments of the present application (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0023] In this application, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0024] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0025] Embodiment 1:

[0026] Reference Figure 1 This embodiment discloses a restoration and assessment system for an alpine meadow ecosystem, including an infrared temperature image acquisition module and a temperature parameter acquisition module, wherein the infrared temperature image is used to acquire an infrared temperature image of the grassland to be evaluated, and the temperature parameter acquisition module is used to acquire the temperature parameters of the grassland to be evaluated; the assessment system also includes an image recognition module, wherein the input end of the image recognition module is respectively connected to the infrared temperature image acquisition module and the temperature parameter acquisition module, and the output end of the image recognition module is connected to a calculation module, and the output end of the calculation module is connected to an assessment module.

[0027] Embodiment 2:

[0028] Reference Figure 2 This embodiment discloses a restoration assessment method for an alpine meadow ecosystem, comprising the following steps: S1, respectively obtaining infrared temperature images of the grassland to be evaluated at different sampling times; S11, dividing the grassland to be evaluated into a number of areas to be evaluated, and selecting sampling points in each of the areas to be evaluated; First obtain a topographic map of the grassland to be assessed; This application mainly uses an infrared camera mounted on a drone to obtain infrared temperature images. Therefore, when dividing the grassland to be evaluated, it is necessary to consider the flight altitude of the drone and the performance parameters of the infrared camera, that is, the area of ​​the divided area to be evaluated cannot exceed the maximum shooting range of the infrared camera; Based on the above principles, the grassland to be evaluated is divided into several areas to be evaluated, and each area to be evaluated is assigned a number n; After the segmentation is completed, an optimal shooting point is selected in each area to be evaluated, and its coordinates are obtained at the same time, that is, the sampling point is set.

[0029] In the actual shooting process, each photo sampling of the drone needs to be carried out at the optimal shooting point to ensure the consistency of the image and improve the accuracy of the assessment; When the area of ​​grassland to be evaluated is large, due to the flight altitude of the drone and the performance limitations of the infrared camera, it is impossible to obtain the infrared temperature image of the entire grassland to be evaluated at one time. Therefore, the above segmentation method can regularly complete the sampling work area by area, and at the same time, the accuracy of the splicing can be guaranteed when the images are stitched in the later stage, which is not only conducive to improving the accuracy of the evaluation results, but also can improve work efficiency; S12, setting a sampling period, and selecting a sampling time according to the sampling period, wherein the time difference between any two adjacent sampling periods is not less than the sampling period; First, the sampling period is set. It should be noted that the setting of the sampling period needs to follow the growth cycle of alpine meadow vegetation. If the time is too short, the vegetation changes are not obvious, the difficulty of data analysis increases, and the accuracy is reduced. The time process may lead to the omission of key data. The sampling period can be set from 15 days to 30 days; After the sampling period is set, the first sampling time is determined, and then all sampling times can be determined. It should be noted that, considering the impact of weather on shooting, the interval between two adjacent sampling times can be greater than the sampling period, that is, if the weather does not meet the shooting conditions, it can be postponed; to ensure that the weather conditions can meet the requirements each time sampling is taken, eliminate the impact of weather on infrared temperature images, and improve the accuracy of evaluation; S13, controlling the drone to collect infrared temperature images of each area to be evaluated at each sampling point according to the sampling time; Under the premise that the weather conditions meet the requirements, the drone is controlled to collect infrared temperature images of the area to be evaluated at the sampling point of each area to be evaluated at the sampling time; At the same time, each infrared temperature image is numbered according to the number of each area to be evaluated; S14, respectively splicing the infrared temperature images of each area to be evaluated obtained at the same sampling time to obtain infrared temperature images of several grasslands to be evaluated; All infrared temperature images taken are obtained and classified according to the area to be evaluated. That is, all infrared temperature images of the same area to be evaluated are grouped into the same category. The staff selects the best one from the above images for evaluation and numbers the infrared temperature image. It should be noted that each infrared temperature image has two numbers, namely the number of the area to be evaluated and the number assigned according to the chronological order; After the arrangement is completed, the infrared temperature images obtained at the same sampling time are grouped into the same set again, thereby obtaining an infrared temperature image; Repeating the above steps can obtain an infrared temperature image in each sampling period; then obtain several infrared temperature images, the expression of which is {A1, A2, ..., A n}1,{A1, A2, ..., A n}2, ..., {A1, A2, ..., A n} m ; Where n represents the number of each area to be evaluated, and m represents the infrared temperature image number determined according to the order of sampling time; Then call any infrared temperature image {A1, A2, ..., A n} m , stitching the infrared temperature images according to the numbers of the infrared temperature images and the actual positions of the areas to be evaluated, thereby obtaining the infrared temperature image of the grassland to be evaluated; Repeat the above operation to obtain the infrared temperature images B1, B2, ..., B of the grassland to be evaluated at all sampling times. m ; S2, respectively obtaining the temperature parameters of the grassland to be evaluated at different sampling times, and generating a corresponding identification temperature threshold set for each infrared temperature image; S21, respectively selecting a first vegetation-covered area, a second vegetation-covered area and a third vegetation-covered area in each area to be evaluated; wherein the first vegetation-covered area represents a fully vegetation-covered area, the second vegetation-covered area represents a semi-vegetation-covered area and the third vegetation-covered area represents a completely bare area; Firstly, the first vegetation coverage area, the second vegetation coverage area and the third vegetation coverage area are randomly selected in each area to be evaluated by means of artificial wetland survey, wherein the first vegetation coverage area represents a fully covered area, the second vegetation coverage area represents a semi-covered area and the third vegetation coverage area represents a completely bare area; It should be noted that the number of the first vegetation coverage area, the second vegetation coverage area and the third vegetation coverage area is at least one, and the first vegetation coverage area, the second vegetation coverage area and the third vegetation coverage area in different areas should be at a certain distance from each other. If there are multiple first vegetation coverage areas, second vegetation coverage areas and third vegetation coverage areas in the same area to be evaluated, they should be distributed as evenly as possible in the entire area to be evaluated to ensure the representativeness of the data.

[0030] Secondly, each sampling time needs to be selected once to avoid the influence of vegetation growth and ensure the accuracy and reliability of data detection; After the first vegetation coverage area, the second vegetation coverage area and the third vegetation coverage area are selected, a temperature sensor or a thermometer is arranged in each area to detect the temperature thereof.

[0031] S22, at any sampling time, respectively obtain the temperature t of the first vegetation coverage area in each to-be-assessed area 11 ,t 21 ,...,t n1 , the temperature of the second vegetation coverage area t 12 ,t 22 ,...,t n2 and the temperature of the third vegetation coverage area t 13 ,t 23 ,...,t n3 ; Where n represents the number of each area to be evaluated, 1, 2 and 3 represent the first vegetation coverage area, the second vegetation coverage area and the third vegetation coverage area respectively; At any sampling time, obtain the temperature t of the first vegetation coverage area in each area to be evaluated. 11 ,t 21 ,...,t n1 , the temperature of the second vegetation coverage area t 12 ,t 22 ,...,t n2 and the temperature of the third vegetation coverage area t 13 ,t 23 ,...,t n3 ; It should be noted that if multiple first vegetation coverage areas are set, the average value thereof is calculated and used as the temperature of the first vegetation coverage area in the area to be evaluated; S23, according to the temperature t of the first vegetation coverage area 11 ,t 21 ,...,t n1 Generate a first identification temperature threshold, wherein the first identification temperature threshold satisfies T1≤max{t 11 ,t 21 ,...,t n1}; Extract the temperature t of the first vegetation coverage area 11 ,t 21 ,...,t n1 , select the maximum value among the above data as the upper limit of the first identification temperature threshold, that is, the first identification temperature threshold satisfies T1≤max{t 11 ,t 21 ,...,t n1}; If the maximum value is 5°C, the first identification temperature threshold satisfies T1≤5°C.

[0032] S24, according to the temperature t of the second vegetation coverage area 12 ,t 22 ,...,t n2 Generate a second identification temperature threshold, wherein the second identification temperature threshold satisfies min{t 12 ,t 22 ,...,t n2}≤T2≤max{t 12 ,t 22 ,...,t n2} and T1<T2; Extract the temperature t of the second vegetation coverage area 12 ,t 22 ,...,t n2 , the minimum value of the above parameters is used as the lower limit of the second identification temperature threshold, and the maximum value is used as the upper limit, that is, the second identification temperature threshold satisfies min{t 12 ,t 22 ,...,t n2}≤T2≤max{t 12 ,t 22 ,...,t n2}; It should also be noted that the second identification temperature threshold also needs to satisfy T1<T2 to avoid overlap of identification temperatures; If the minimum value is 7℃ and the maximum value is 15℃, then 7℃≤T2≤15℃.

[0033] S25, according to the temperature t of the third vegetation coverage area 13 ,t 23 ,...,t n3 Generate a third identification temperature threshold, wherein the third identification temperature threshold satisfies T3≥min{t 13 ,t 23 ,...,t n3} and T2<T3; The third identification temperature threshold is obtained by the same method as steps S23 and S24. If the minimum value is 17°C, then T3 ≥ 17°C; At this time, integrating all the data can obtain the identification temperature threshold set of the sampling time; such as {T1≤5℃, 7℃≤T2≤15℃, T3≥17℃}.

[0034] S26, repeat the steps of obtaining the temperature of the first vegetation coverage area, the temperature of the second vegetation coverage area and the temperature of the third vegetation coverage area in each to-be-evaluated area at any sampling time, and integrate and output each identification temperature threshold set {T1, T2, T3}1, {T1, T2, T3}2, ..., {T1, T2, T3} m , where m represents the number set according to the order of sampling time.

[0035] Repeat steps S22-S25 to obtain the identification temperature threshold sets of all sampling time points, and then output the identification temperature threshold sets {T1, T2, T3}1, {T1, T2, T3}2, ..., {T1, T2, T3} m , where m represents the number set according to the order of sampling time.

[0036] It should be noted that the first vegetation coverage area, the second vegetation coverage area and the third vegetation coverage area need to be appropriately adjusted at each sampling time point to avoid the influence of vegetation growth and ensure the accuracy and reliability of data detection; S3, identifying a first vegetation covered area, a second vegetation covered area, and a third vegetation covered area on each of the infrared temperature images according to each of the identification temperature threshold sets; S31, calibrating the grayscale value according to each identification temperature threshold set to generate a grayscale-temperature conversion function; S311, obtaining each identification temperature threshold set, and determining a fitting temperature range according to the temperature value of each identification temperature threshold set; First, obtain all the identified temperature sets that have been obtained, obtain the minimum value as the lower limit value, and extract the maximum value as the upper limit value; Secondly, considering that data selection is performed when the identification temperature threshold set is generated, a certain degree of upward and downward floating is performed based on the upper and lower limits, such as 3°C. Specifically, if the upper limit value is 17°C, it is increased by 3°C and the value is 20°C. Similarly, if the lower limit value is 5°C, it is taken as 2°C.

[0037] S312, randomly selecting a number of test temperatures within the fitting temperature range; Generate a fitting temperature range according to the upper limit value and the lower limit value obtained in step S311, and randomly select several test temperatures within the fitting temperature range; If the fitting temperature range is 2°C-20°C, a series of test temperatures can be extracted at intervals of 1°C or 0.5°C.

[0038] S313, controlling the temperature of the adjustable black body furnace to any test temperature, and taking an infrared temperature image at the test temperature; A standard adjustable black body furnace is set, a first test temperature is extracted at the same time, the temperature of the adjustable black body furnace is adjusted to the test temperature, and then an infrared temperature image of the adjustable black body furnace is captured by an infrared camera; It should be noted that the infrared camera used in this step is the same as the infrared camera used to obtain the infrared temperature image of the grassland to be evaluated, or is the same model camera with the same performance parameters, so as to eliminate the interference of the infrared camera's own performance on the detection results; S314, calculating a test gray value corresponding to the test temperature according to the infrared temperature image; After the infrared temperature image is obtained, it is automatically processed by a computer and the corresponding test gray value is extracted; S315, repeating the steps of controlling the temperature of the adjustable black body furnace to any test temperature, photographing the infrared temperature image at the test temperature, and obtaining all test gray values; All test grayscale values ​​can be obtained by repeating step S313 to step S314, and at the same time, a one-to-one mapping relationship is established between the test temperature and the test grayscale value to achieve data binding and facilitate subsequent calculations.

[0039] S316, constructing a standard coordinate system, wherein the abscissa of the standard coordinate system represents the test temperature, and the ordinate represents the test gray value; S317, selecting a number of calibration points in the standard coordinate system according to each of the test temperatures and each of the test gray values; The left and right test temperatures and the test grayscale values ​​obtained in step S315 are extracted, and points are taken in the standard coordinate system according to the mapping relationship between the two to obtain a number of calibration points.

[0040] S318, generating a grayscale-temperature conversion function according to the fitting of each calibration point.

[0041] The grayscale-temperature conversion function can be obtained by computer fitting. The expression of the grayscale-temperature conversion function is T=a•G+b, where a and b are fitting coefficients, T is temperature, and G is grayscale value. For the specific principle, refer to Figure 3 ; That is, the specific values ​​of the fitting coefficients a and b can be determined by fitting.

[0042] S32, obtaining any infrared temperature image and a corresponding identification temperature threshold set; Retrieving any infrared temperature image obtained in step S1, and obtaining a set of identification temperature thresholds of the infrared temperature image obtained in step S2 according to the mapping relationship; S33, calculating an identification grayscale set according to the identification temperature threshold set and the grayscale-temperature conversion function; Substituting the recognition temperature threshold set into the grayscale-temperature conversion function to calculate the corresponding recognition grayscale; If the recognition temperature threshold set is {T1≤5℃, 7℃≤T2≤15℃, T3≥17℃}, then 5℃, 7℃, 15℃ and 17℃ are respectively substituted into the expression of the grayscale-temperature conversion function obtained in step S318, that is, T=a•G+b, and the corresponding recognition grayscale is calculated; finally, the recognition grayscale set is integrated, such as {G1≤13, 18≤G2≤38, G3≥44}; S34, converting the infrared temperature image into a grayscale image; S35, identifying a first vegetation covered area, a second vegetation covered area, and a third vegetation covered area on the grayscale image according to the identification grayscale set; S351, obtaining a recognition grayscale set and the grayscale image; S352, dividing the grayscale image into a number of standard cells, and obtaining the actual grayscale value of each standard cell respectively; Reference Figure 4 , dividing the grayscale image into a number of standard cells, such as dividing it into 10,000 standard cells, and the area of ​​each cell is exactly the same; It should be noted that the division of standard cells is determined according to the actual situation, as long as the shapes and areas of the standard cells are exactly the same; After division, the actual grayscale value of each standard cell is obtained, such as G1', G2', ..., G p ', where p is the number of the standard cell.

[0043] S353, respectively comparing the identified grayscale set with each of the actual grayscale values, and dividing each of the standard cells into a first vegetation coverage area, a second vegetation coverage area, or a third vegetation coverage area; First, three empty sets are established, and the three empty sets correspond to the first vegetation coverage area, the second vegetation coverage area, and the third vegetation coverage area respectively; At the same time, the actual grayscale values ​​G1', G2', ..., G p '; At the same time, obtain the recognition grayscale set calculated in step S33; Extracting the actual grayscale value G1', comparing it with the identification grayscale set, dividing it into the first vegetation coverage area, the second vegetation coverage area or the third vegetation coverage area according to the comparison result, and grouping it into the corresponding empty set; If G1'=6, the identified grayscale set is {G1≤13, 18≤G2≤38, G3≥44}, then it is classified into the first vegetation coverage area; Repeat the above steps to complete the division of all standard cells.

[0044] It should be noted that the divided areas can be further refined, such as the fourth vegetation coverage area and the fifth vegetation coverage area, where the second, third and fourth vegetation coverage areas correspond to different vegetation coverage standards, such as 30%, 60% and 90% coverage.

[0045] S354: Count the number of standard cells Q included in the first vegetation coverage area and the second vegetation coverage area respectively. 1m and Q 2m , where m represents the infrared temperature image number, 1 and 2 represent the first vegetation coverage area and the second vegetation coverage area, respectively.

[0046] Retrieve the sets corresponding to the first vegetation coverage area and the second vegetation coverage area obtained in step 353, and count the number of standard cells Q in each set respectively. 1m and Q 2m , where m represents the infrared temperature image number, 1 and 2 represent the first vegetation coverage area and the second vegetation coverage area respectively; S36, repeating the step of acquiring any infrared temperature image and the corresponding identification temperature threshold set to complete the identification of all infrared temperature images.

[0047] Repeat steps S32 to S35 to obtain the number of all standard cells, and then obtain the corresponding parameter set {Q 11 , Q 12 , ..., Q 1m , Q 21 , Q 22 , ..., Q 2m}, where m represents the infrared temperature image number, 1 and 2 represent the first vegetation coverage area and the second vegetation coverage area respectively; S4. Generate a vegetation coverage parameter set of the grassland to be evaluated according to the areas of the first vegetation coverage area and the second vegetation coverage area; S41, respectively obtaining the number Q of standard cells contained in the first vegetation coverage area and the second vegetation coverage area of ​​each infrared temperature image 11 , Q 12 , ..., Q 1m , Q 21 , Q 22 , ..., Q 2m ; S42, respectively calculate the vegetation coverage parameters of each grassland to be evaluated, and output the vegetation coverage parameter set {S1, S2, ..., Sm}, where the expression of the vegetation coverage parameter is S m =k•Q 1m +j•Q 2m , k and j are constants.

[0048] Get the number of standard cells Q 11 , Q 12 , ..., Q 1m , Q 21 , Q 22 , ..., Q 2m , group the infrared images according to their numbers, i.e. Q 11 , Q 12 Divide them into a group, and then obtain several groups of calculation parameters in turn; The expression of the vegetation coverage parameter is S m =k•Q 1m +j•Q 2m , k and j are constants. It should be noted that k and j need to be set by the staff. For example, if k corresponds to the full coverage area, it is set to 1, and j is set to 0.5, then S m =Q 1m +0.5•Q 2m The first set of parameters (Q 11 , Q 12 ) Substitute into S m =Q 1m +0.5•Q 2m Then you can get S1; Repeat the above steps to obtain the vegetation coverage parameter set {S1, S2, ..., S m}; The image processing process is simplified by the above-mentioned method of assigning values ​​and dividing cells. At the same time, different assignments reflect different vegetation coverage conditions, thereby objectively reflecting the vegetation coverage conditions, which is conducive to improving evaluation efficiency.

[0049] S5. Fitting a vegetation coverage change curve of the grassland to be evaluated according to the vegetation coverage parameter set and the sampling time, and outputting an evaluation result according to the vegetation coverage change curve.

[0050] S51, obtain the vegetation coverage parameter set {S1, S2, ..., S m}; S52, constructing a fitting coordinate system, wherein the abscissa of the fitting coordinate system represents time, and the ordinate represents a vegetation coverage parameter; S53, obtaining each sampling time t1, t2, ..., t m ; The time needs to be recorded each time a sample is taken, for example, the recorded time is March 2; S54, selecting fitting points in the fitting coordinate system according to the vegetation coverage parameter set and each sampling time; Get the vegetation coverage parameter set and sampling times t1, t2, ..., t m ; Since the vegetation coverage parameter has a time tag, the vegetation coverage parameter and the same time are matched based on the same number, such as (S1, t1); Several sets of coordinates can be obtained by pairing. The fitting points can be selected in the fitting coordinate system by using the above coordinates. Figure 5 ; S55, fitting and connecting the fitting points in series to generate a vegetation coverage change curve; S56, retrieve the upper standard curve of vegetation coverage and the lower standard curve of vegetation coverage, if the vegetation coverage change curve is between the upper standard curve and the lower standard curve of vegetation coverage, the evaluation is qualified, otherwise it is judged as unqualified.

[0051] According to the types of alpine meadow vegetation and annual climatic conditions, the staff can roughly evaluate the changing trend of grassland vegetation, such as the recovery of vegetation within half a month. Through the above parameters, a vegetation coverage standard curve can be manually drawn. Through the vegetation coverage standard curve, the changing trend of vegetation coverage of the grassland to be evaluated in a year can be intuitively seen; Then, the deviation rate is set according to the requirements, such as 5%. Under the condition of keeping the attachment unchanged, the upper standard curve of vegetation coverage can be obtained by moving up 5% of the standard curve of vegetation coverage, and the lower standard curve of vegetation coverage can be obtained by moving down in the same way. Reference Figure 6 , the vegetation cover change curve, the upper standard curve of vegetation cover and the lower standard curve of vegetation cover are integrated into the same coordinate system. If the vegetation cover change curve is between the upper standard curve and the lower standard curve of vegetation cover, the evaluation is qualified, otherwise it is judged as unqualified.

[0052] Compared with the prior art, the present application realizes the observation of vegetation coverage area through temperature detection, and no longer needs to identify and monitor vegetation and vegetation types, which simplifies the identification procedure and improves the evaluation efficiency; Secondly, the vegetation coverage area is graded by temperature, and different levels of coverage areas correspond to different vegetation coverage coefficients, thereby completing a rapid estimation of the vegetation coverage area. It is no longer necessary to perform complex image processing and area calculations on irregular vegetation coverage areas. While ensuring the accuracy of the results, the image processing procedure is simplified as much as possible, thereby improving the efficiency of restoration assessment.

[0053] Finally, the vegetation coverage change curve can reflect the changes in grassland vegetation coverage in different time periods. In particular, the slope of the curve can reflect the vegetation growth rate, thereby reflecting whether the growth of vegetation is consistent with the time (season), and then predicting future vegetation changes and intervening in the adverse factors that affect vegetation growth in advance, thereby improving the restoration effect of grassland vegetation.

[0054] The above descriptions are only optional embodiments of the present disclosure, and are not intended to limit the patent scope of the present disclosure. All equivalent structural transformations made using the contents of the present disclosure and the drawings under the inventive concept of the present disclosure, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present disclosure.

Claims

1. A restoration assessment system for alpine meadow ecosystem, characterized in that: include: An infrared temperature image acquisition module is used to respectively acquire infrared temperature images of the grassland to be evaluated at different sampling times; A temperature parameter acquisition module is used to respectively acquire the temperature parameters of the grassland to be evaluated at different sampling times, and to generate a corresponding identification temperature threshold set for each infrared temperature image; An image recognition module, used to recognize a first vegetation coverage area, a second vegetation coverage area, and a third vegetation coverage area on each of the infrared temperature images according to each of the recognition temperature threshold sets; A calculation module, used for generating a vegetation coverage parameter set of the grassland to be evaluated according to the areas of the first vegetation coverage area and the second vegetation coverage area; The evaluation module fits the vegetation coverage change curve of the grassland to be evaluated according to the vegetation coverage parameter set and the sampling time, and outputs the evaluation result according to the vegetation coverage change curve.

2. The evaluation method based on the restoration evaluation system for alpine meadow ecosystem according to claim 1, characterized in that: The following steps are involved: Obtain infrared temperature images of the grassland to be evaluated at different sampling times; Acquire the temperature parameters of the grassland to be evaluated at different sampling times respectively, and generate a corresponding identification temperature threshold set for each infrared temperature image respectively; Respectively identifying a first vegetation covered area, a second vegetation covered area, and a third vegetation covered area on each of the infrared temperature images according to each of the identification temperature threshold sets; Generating a vegetation coverage parameter set of the grassland to be evaluated according to the areas of the first vegetation coverage area and the second vegetation coverage area; The vegetation coverage variation curve of the grassland to be evaluated is fitted according to the vegetation coverage parameter set and the sampling time, and the evaluation result is output according to the vegetation coverage variation curve.

3. The evaluation method according to claim 2, characterized in that: The step of respectively acquiring infrared temperature images of the grassland to be evaluated at different sampling times comprises the following steps: Divide the grassland to be assessed into a number of assessment areas, and select sampling points in each of the assessment areas; Setting a sampling period, and selecting a sampling time according to the sampling period, wherein the time difference between any two adjacent sampling periods is not less than the sampling period; According to the sampling time, the UAV is controlled to collect infrared temperature images of each area to be evaluated at each sampling point; The infrared temperature images of each area to be evaluated obtained at the same sampling time are stitched together to obtain infrared temperature images of several grasslands to be evaluated.

4. The evaluation method according to claim 2, characterized in that: The step of respectively obtaining the temperature parameters of the grassland to be evaluated at different sampling times and respectively generating a corresponding identification temperature threshold set for each infrared temperature image comprises the following steps: A first vegetation-covered area, a second vegetation-covered area and a third vegetation-covered area are respectively selected in each area to be evaluated; wherein the first vegetation-covered area represents a fully vegetation-covered area, the second vegetation-covered area represents a semi-vegetation-covered area and the third vegetation-covered area represents a completely bare area; At any sampling time, obtain the temperature t of the first vegetation coverage area in each area to be evaluated. 11 ,t 21 ,...,t n1 , the temperature of the second vegetation coverage area t 12 ,t 22 ,...,t n2 and the temperature of the third vegetation coverage area t 13 ,t 23 ,...,t n3 ; Where n represents the number of each area to be evaluated, 1, 2 and 3 represent the first vegetation coverage area, the second vegetation coverage area and the third vegetation coverage area respectively; According to the temperature t of the first vegetation coverage area 11 ,t 21 ,...,t n1 Generate a first identification temperature threshold, wherein the first identification temperature threshold satisfies T1≤max{t 11 ,t 21 ,...,t n1 }; According to the temperature t of the second vegetation coverage area 12 ,t 22 ,...,t n2 Generate a second identification temperature threshold, wherein the second identification temperature threshold satisfies min{t 12 ,t 22 ,...,t n2 }≤T2≤max{t 12 ,t 22 ,...,t n2 } and T1<T2; According to the temperature t of the third vegetation coverage area 13 ,t 23 ,...,t n3 Generate a third identification temperature threshold, wherein the third identification temperature threshold satisfies T3≥min{t 13 ,t 23 ,...,t n3 } and T2<T3; Repeat the steps of obtaining the temperature of the first vegetation coverage area, the temperature of the second vegetation coverage area and the temperature of the third vegetation coverage area in each to-be-evaluated area at any sampling time, and integrate and output each identification temperature threshold set {T1, T2, T3}1, {T1, T2, T3}2, ..., {T1, T2, T3} m , where m represents the number set according to the order of sampling time.

5. The evaluation method according to claim 2, characterized in that: The step of identifying the first vegetation coverage area, the second vegetation coverage area and the third vegetation coverage area on each of the infrared temperature images according to each of the identification temperature threshold sets comprises the following steps: Grayscale values ​​are calibrated according to each set of identified temperature thresholds to generate a grayscale-temperature conversion function; Obtain any infrared temperature image and a corresponding identification temperature threshold set; Calculate an identification grayscale set according to the identification temperature threshold set and the grayscale-temperature conversion function; Converting the infrared temperature image into a grayscale image; Identifying a first vegetation-covered area, a second vegetation-covered area, and a third vegetation-covered area on the grayscale image according to the identification grayscale set; The steps of obtaining any infrared temperature image and the corresponding identification temperature threshold set are repeated to complete the identification of all infrared temperature images.

6. The evaluation method according to claim 5, characterized in that: The grayscale value calibration is performed according to each identification temperature threshold set to generate a grayscale-temperature conversion function, including the following steps: Acquire each identification temperature threshold set, and determine the fitting temperature range according to the temperature value of each identification temperature threshold set; Randomly select a number of test temperatures within the fitting temperature range; Control the temperature of the adjustable black body furnace to any test temperature and take an infrared temperature image at the test temperature; Calculating a test grayscale value corresponding to the test temperature according to the infrared temperature image; Repeat the steps of controlling the temperature of the adjustable black body furnace to any test temperature, photographing the infrared temperature image at the test temperature, and obtaining all test gray values; Constructing a standard coordinate system, wherein the abscissa of the standard coordinate system represents the test temperature, and the ordinate represents the test grayscale value; Selecting a number of calibration points in the standard coordinate system according to each of the test temperatures and each of the test gray values; The grayscale-temperature conversion function is generated by fitting each calibration point.

7. The evaluation method according to claim 6, characterized in that: The grayscale-temperature conversion function is expressed as T=a•G+b, where a and b are fitting coefficients, T is temperature, and G is the grayscale value.

8. The evaluation method according to claim 5, characterized in that: The step of identifying a first vegetation coverage area, a second vegetation coverage area, and a third vegetation coverage area on the grayscale image according to the identification grayscale set comprises the following steps: Acquire a recognition grayscale set and the grayscale image; Dividing the grayscale image into a number of standard cells, and obtaining the actual grayscale value of each standard cell respectively; Respectively comparing the identified grayscale set with each of the actual grayscale values, and dividing each of the standard cells into a first vegetation coverage area, a second vegetation coverage area, or a third vegetation coverage area; Count the number of standard cells Q contained in the first vegetation coverage area and the second vegetation coverage area respectively 1m and Q 2m , where m represents the infrared temperature image number, 1 and 2 represent the first vegetation coverage area and the second vegetation coverage area, respectively.

9. The evaluation method according to claim 2, characterized in that: The step of generating a vegetation coverage parameter set of the grassland to be evaluated according to the areas of the first vegetation coverage area and the second vegetation coverage area comprises the following steps: The number Q of standard cells contained in the first vegetation coverage area and the second vegetation coverage area of ​​each infrared temperature image is obtained respectively. 11 , Q 12 , ..., Q 1m , Q 21 , Q 22 , ..., Q 2m ; Calculate the vegetation coverage parameters of each grassland to be evaluated and output the vegetation coverage parameter set {S1, S2, ..., S m }, where the expression of the vegetation coverage parameter is S m =k•Q 1m +j•Q 2m , k and j are constants.

10. The evaluation method according to claim 2, characterized in that: The method of fitting the vegetation coverage change curve of the grassland to be evaluated according to the vegetation coverage parameter set and the sampling time, and outputting the evaluation result according to the vegetation coverage change curve, comprises the following steps: Get the vegetation coverage parameter set {S1, S2, ..., S m }; Constructing a fitting coordinate system, wherein the abscissa of the fitting coordinate system represents time, and the ordinate represents a vegetation coverage parameter; Get each sampling time t1, t2, ..., t m ; Selecting fitting points in the fitting coordinate system according to the vegetation coverage parameter set and each sampling time; Fit and connect the fitting points in series to generate the vegetation coverage change curve; The upper standard curve of vegetation coverage and the lower standard curve of vegetation coverage are retrieved. If the vegetation coverage change curve is between the upper standard curve and the lower standard curve of vegetation coverage, the assessment is qualified; otherwise, it is judged as unqualified.

Images