CN112084926A - Screening method for ecological restoration plants of abandoned mine - Google Patents

Screening method for ecological restoration plants of abandoned mine Download PDF

Info

Publication number
CN112084926A
CN112084926A CN202010916797.5A CN202010916797A CN112084926A CN 112084926 A CN112084926 A CN 112084926A CN 202010916797 A CN202010916797 A CN 202010916797A CN 112084926 A CN112084926 A CN 112084926A
Authority
CN
China
Prior art keywords
information
abandoned mine
vegetation
image
soil
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
CN202010916797.5A
Other languages
Chinese (zh)
Inventor
朱建琴
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changde Furong Xin Environmental Protection Co ltd
Original Assignee
Changde Furong Xin Environmental Protection Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Changde Furong Xin Environmental Protection Co ltd filed Critical Changde Furong Xin Environmental Protection Co ltd
Priority to CN202010916797.5A priority Critical patent/CN112084926A/en
Publication of CN112084926A publication Critical patent/CN112084926A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/188—Vegetation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
    • G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
    • G01C11/025—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures by scanning the object
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0098—Plants or trees
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/24—Earth materials
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/05—Geographic models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/40—Analysis of texture
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

The invention provides a method for screening ecological restoration plants of abandoned mines, which obtains vegetation growth climate environment information and vegetation growth soil environment information of the abandoned mines in different altitude areas by carrying out multi-angle aerial image shooting and soil sampling analysis on the abandoned mines, thus being capable of carrying out targeted analysis on the different altitude areas of the abandoned mines, providing scientific and reliable basis for selecting proper plant planting for the different altitude areas and realizing sustainable ecological restoration of the abandoned mines.

Description

Screening method for ecological restoration plants of abandoned mine
Technical Field
The invention relates to the technical field of mine greening, in particular to a screening method of ecological restoration plants of abandoned mines.
Background
The mine requires excavation of soil during mining, and the mine is gradually abandoned after mining of the mineral materials in the mine is completed. The mountain structure and the soil structure of the abandoned mine are damaged in different degrees and become very fragile, if under the long-term action of rainwater, the soil ecosystem of the abandoned mine can be seriously damaged, so that the mountain structure stability of the abandoned mine is endangered, but the prior art only has a repairing mode of temporarily reinforcing the soil of the abandoned mine, and the prior art can not select proper plants for greening and planting according to the climatic conditions and the soil conditions of different areas of the abandoned mine, so that the sustainable ecological restoration of the abandoned mine is realized.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method for screening ecological restoration plants of abandoned mines, which comprises the steps of aerial photography of the abandoned mine to obtain a corresponding multi-angle aerial image of the abandoned mine, analyzing and processing the multi-angle aerial image of the abandoned mine, thereby determining the geographic environmental information and the vegetation existence information of the abandoned mine, determining the vegetation growth climate environmental information corresponding to the abandoned mine in different areas according to the geographic environmental information and the vegetation existence information, then collecting soil samples of the abandoned mine in different areas, analyzing the soil samples, determining vegetation growth soil environment information corresponding to the abandoned mine in different areas, and finally determining the plant types suitable for planting in the different areas of the abandoned mine according to the vegetation growth climate environment information and the vegetation growth soil environment information; therefore, the method for screening the ecological restoration plants of the abandoned mine obtains the vegetation growth climate environment information and the vegetation growth soil environment information of the abandoned mine in the areas with different altitudes by carrying out multi-angle aerial image shooting and soil sampling analysis on the abandoned mine, and can carry out targeted analysis on the areas with different altitudes of the abandoned mine, thereby providing scientific and reliable basis for selecting proper plant planting for the areas with different altitudes and realizing sustainable ecological restoration of the abandoned mine.
The invention provides a screening method of ecological restoration plants of abandoned mines, which is characterized by comprising the following steps:
step S1, aerial photography is carried out on the abandoned mine, so that a corresponding multi-angle aerial photography image of the abandoned mine is obtained, and the multi-angle aerial photography image of the abandoned mine is analyzed and processed, so that geographic environment information and vegetation existence information of the abandoned mine are determined;
step S2, determining vegetation growth climate environment information corresponding to the abandoned mine in different areas according to the geographic environment information and the vegetation existence information;
step S3, collecting soil samples of different areas of the abandoned mine, and analyzing the soil samples, thereby determining vegetation growth soil environment information corresponding to the abandoned mine in the different areas;
step S4, determining the plant species suitable for planting in different areas of the abandoned mine according to the vegetation growth climate environment information and the vegetation growth soil environment information;
further, in the step S1, the abandoned mine is aerial-photographed to obtain a corresponding abandoned mine multi-angle aerial-photographed image, and the abandoned mine multi-angle aerial-photographed image is analyzed and processed to determine that the geographic environment information and vegetation existence information of the abandoned mine specifically include,
step S101, performing circumferential scanning shooting on the abandoned mine according to the direction from low altitude to high altitude so as to obtain a plurality of multi-angle aerial images corresponding to different altitude areas of the abandoned mine;
step S102, constructing a three-dimensional image of the abandoned mine according to a plurality of multi-angle aerial images, and simulating to form an external natural environment where the abandoned mine is currently located by adopting the three-dimensional image, so as to determine geographical environment information of the abandoned mine;
step S103, constructing a three-dimensional image of the abandoned mine according to the multi-angle aerial images, extracting corresponding image chromaticity characteristic information and image texture characteristic information from the three-dimensional image, and determining vegetation existence information of the abandoned mine according to the image chromaticity characteristic information and the image texture characteristic information;
further, in the step S101, the step of performing circumferential scanning shooting on the abandoned mine according to the direction from low altitude to high altitude to obtain a plurality of multi-angle aerial images corresponding to different altitude areas of the abandoned mine specifically includes,
step S1011, dividing the abandoned mine into a plurality of areas with different altitudes from low to high according to a preset altitude difference, wherein the preset altitude difference is not less than 3.5 m;
step S1012, sequentially performing clockwise or counterclockwise circumferential scanning shooting on each altitude area according to the direction from low altitude to high altitude, thereby obtaining a multi-angle aerial image corresponding to the altitude area;
further, in the step S102, a three-dimensional image of the abandoned mine is constructed according to the plurality of multi-angle aerial images, and the three-dimensional image is used to simulate and form an external natural environment in which the abandoned mine is currently located, so as to determine that the geographic environment information of the abandoned mine specifically includes,
step S1021, calculating image parallax between the multi-angle aerial images of every two adjacent altitude areas in the different altitude areas so as to form a corresponding image parallax sequence;
step S1022, constructing and obtaining a three-dimensional image of the abandoned mine according to the image parallax sequence;
step S1023, the three-dimensional image is adopted to simulate and form the illumination, wind direction and precipitation environment of the abandoned mine, so that the sunny distribution area information, the shady distribution area information, the windward slope distribution information, the leeward slope distribution information and the wind and watershed distribution information of the abandoned mine are determined and used as the geographic environment information;
further, in the step S103, a three-dimensional image of the abandoned mine is constructed according to the plurality of multi-angle aerial images, corresponding image chromaticity characteristic information and image texture characteristic information are extracted from the three-dimensional image, and vegetation existence information of the abandoned mine is determined to specifically include,
step S1031, calculating image parallax between the multi-angle aerial images of every two adjacent altitude areas in the different altitude areas so as to form corresponding image parallax sequences;
step S1032, constructing and obtaining a three-dimensional image of the abandoned mine according to the image parallax sequence, and extracting corresponding image chromaticity characteristic information and image texture characteristic information from the three-dimensional image;
step S1033, a vegetation existence state evaluation neural network model is constructed, and the image chromaticity characteristic information and the image texture characteristic information are input into the vegetation existence state evaluation neural network model, so that vegetation coverage area distribution information and vegetation coverage density information of the abandoned mine are obtained and serve as the vegetation existence information;
further, in the step S2, it is determined that the vegetation growth climate environment information corresponding to the abandoned mine in different areas specifically includes, according to the geographic environment information and the vegetation existence information,
constructing a mine plant growth climate environment evaluation neural network model, and inputting sun distribution area information, shade distribution area information, windward slope distribution information, leeward slope distribution information and watershed distribution information in the geographic environment information, and vegetation coverage area distribution information and vegetation coverage density information in the vegetation existence information into the mine plant growth climate environment evaluation neural network model, so as to determine vegetation production climate environment information corresponding to the abandoned mine in different altitude areas;
further, in step S3, the step of collecting soil samples of different areas of the abandoned mine and analyzing the soil samples to determine that the vegetation growth soil environment information of the abandoned mine in different areas specifically includes,
step S301, respectively collecting soil samples with preset depths in different altitude areas of the abandoned mine, wherein the altitude difference between two adjacent altitude areas in the different altitude areas is not less than 3.5m, and the preset depth is not less than 1 m;
step S302, analyzing and processing soil components, soil organic matter components, soil trace element components and soil pH values of each collected soil sample, so as to obtain soil component information, soil organic matter component information, soil trace element component information and soil pH value information corresponding to the abandoned mine in different altitude areas, and taking the soil component information, the soil organic matter component information, the soil trace element component information and the soil pH value information as vegetation growth soil environment information;
further, in the step S4, the determining the plant types suitable for planting in different areas of the abandoned mine according to the vegetation growth climate environment information and the vegetation growth soil environment information specifically includes,
step S401, determining the temperature, illumination duration, rainfall, soil nutrient value and soil hydrophobicity of the abandoned mine in different altitude areas according to the vegetation growth climate environment information and the vegetation growth soil environment information;
step S402, determining the plant species suitable for planting in the abandoned mine in different altitude areas according to the temperature, the illumination time, the rainfall, the soil nutrient value and the soil hydrophobicity;
further, in the step S1033, a vegetation presence state evaluation neural network model is constructed, and the image chromaticity characteristic information and the image texture characteristic information are input to the vegetation presence state evaluation neural network model, so that vegetation coverage area distribution information and vegetation coverage density information of the abandoned mine are obtained, which specifically includes, as the vegetation presence information,
firstly, according to the following formula (1), determining the membership between the sample corresponding to the image chrominance characteristic information and the image texture characteristic information and the divided category
Figure BDA0002665308160000051
In the above-mentioned formula (1),
Figure BDA0002665308160000052
representing the membership between the a-th sample matrix and the i-th class matrix corresponding to the image chrominance characteristic information and the image texture characteristic information, DaA-th sample matrix, Z, representing the image chrominance characteristic information and the image texture characteristic informationiAnd ZjRespectively representing the clustering center of the ith class matrix and the clustering center of the jth class matrix, wherein i is not equal to j, n represents the total number of divided classes, m represents a preset weighting index, the value of the preset weighting index is 2, and T represents the transposition of the matrix;
secondly, establishing a relational expression of the membership and the minimum clustering center in each of the class matrixes by using the following formula (2)
Figure BDA0002665308160000053
In the above formula (2), min (Z)i) A minimum cluster center of the ith class matrix is represented, S represents the total number of sample matrixes of the image chromaticity characteristic information and the image texture characteristic information, wherein min (Z) in the formula (2) is definedi) Substituting Z into the above formula (1)iAnd simultaneously solving in the formula (2) to obtain the minimum clustering center min (Z) corresponding to each class matrixi) A value of (d);
thirdly, the minimum clustering center min (Z) obtained by the above stepsi) Substituting the value of (a) into the input-output equation of the vegetation existence state evaluation neural network model corresponding to the following formula (3)
Figure BDA0002665308160000061
In the above formula (3), C represents output information of the vegetation presence state evaluation neural network model, R represents input information of the vegetation presence state evaluation neural network model, and μiRepresenting the weight, μ, of the hidden node and the output node joining the ith class matrix0Represents a preset deviation value and takes the value of (0, 1)]；
And inputting the image chromaticity characteristic information and the image texture characteristic information into the formula (3) as the R value so as to obtain output information of the vegetation existence state evaluation neural network model, and taking the output information as vegetation existence information.
Compared with the prior art, the method for screening the ecological restoration plants of the abandoned mine comprises the steps of aerial photographing the abandoned mine to obtain a corresponding multi-angle aerial photographing image of the abandoned mine, analyzing and processing the multi-angle aerial photographing image of the abandoned mine to determine geographical environment information and vegetation existence information of the abandoned mine, determining vegetation growth climate environment information of the abandoned mine in different areas according to the geographical environment information and the vegetation existence information, collecting soil samples of the abandoned mine in different areas, analyzing the soil samples to determine vegetation growth soil environment information of the abandoned mine in different areas, and finally determining the plant types suitable for planting in different areas of the abandoned mine according to the vegetation growth climate environment information and the vegetation growth soil environment information; therefore, the method for screening the ecological restoration plants of the abandoned mine obtains the vegetation growth climate environment information and the vegetation growth soil environment information of the abandoned mine in the areas with different altitudes by carrying out multi-angle aerial image shooting and soil sampling analysis on the abandoned mine, and can carry out targeted analysis on the areas with different altitudes of the abandoned mine, thereby providing scientific and reliable basis for selecting proper plant planting for the areas with different altitudes and realizing sustainable ecological restoration of the abandoned mine.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of the method for screening the ecological restoration plants of the abandoned mine provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a method for screening plants for ecological restoration of a waste mine according to an embodiment of the present invention. The method for screening the ecological restoration plants of the abandoned mine comprises the following steps:
step S1, aerial photography is carried out on the abandoned mine, so that a corresponding multi-angle aerial photography image of the abandoned mine is obtained, and the multi-angle aerial photography image of the abandoned mine is analyzed and processed, so that geographic environment information and vegetation existence information of the abandoned mine are determined;
step S2, determining vegetation growth climate environment information corresponding to the abandoned mine in different areas according to the geographic environment information and the vegetation existence information;
step S3, collecting soil samples of different areas of the abandoned mine, and analyzing the soil samples, thereby determining vegetation growth soil environment information corresponding to the abandoned mine in different areas;
and step S4, determining the plant types suitable for planting in different areas of the abandoned mine according to the vegetation growth climate environment information and the vegetation growth soil environment information.
The mining degrees of different areas of the abandoned mine are different in the process of mining, so that the climatic environment and the soil environment of the different areas are correspondingly different, the abandoned mine ecological restoration plant screening method can comprehensively and accurately analyze the climatic environment and the soil environment of the abandoned mine by carrying out multi-angle aerial photography and soil sampling analysis on the abandoned mine so as to determine which plant is suitable for growing in the different areas on the abandoned mine, and therefore the effectiveness and the efficiency of greening ecological restoration of the abandoned mine are guaranteed to the maximum extent.
Preferably, in step S1, the abandoned mine is aerial-photographed to obtain a corresponding abandoned mine multi-angle aerial-photographed image, and the abandoned mine multi-angle aerial-photographed image is analyzed and processed to determine that the geographic environmental information and vegetation existence information of the abandoned mine specifically include,
step S101, according to the direction from low altitude to high altitude of the elevation, circumferential scanning shooting is carried out on the abandoned mine, and therefore a plurality of multi-angle aerial shooting images corresponding to different elevation areas of the abandoned mine are obtained;
step S102, constructing a three-dimensional image of the abandoned mine according to a plurality of multi-angle aerial images, and simulating to form the external natural environment of the abandoned mine by adopting the three-dimensional image, so as to determine the geographic environment information of the abandoned mine;
and S103, constructing a three-dimensional image of the abandoned mine according to the multi-angle aerial images, extracting corresponding image chromaticity characteristic information and image texture characteristic information from the three-dimensional image, and determining vegetation existence information of the abandoned mine according to the image chromaticity characteristic information and the image texture characteristic information.
Because the mining degrees of mines in different altitude areas are different in the mining process and the mines are influenced by vertical change of climatic factors, the abandoned mines inevitably have different geographic environment information and vegetation existence information in the different altitude areas, and the geographic environment information and the vegetation existence information can be accurately and comprehensively determined by constructing three-dimensional images of the abandoned mines through multi-angle aerial images.
Preferably, in the step S101, the step of performing circumferential scanning shooting on the abandoned mine according to the direction from low to high in altitude, so as to obtain a plurality of multi-angle aerial images corresponding to different altitude areas of the abandoned mine specifically includes,
step S1011, dividing the abandoned mine into a plurality of areas with different altitudes from low to high according to a preset altitude difference, wherein the preset altitude difference is not less than 3.5 m;
step S1012, sequentially performing clockwise or counterclockwise circumferential scanning and shooting on each altitude area according to the direction from low altitude to high altitude, so as to obtain a multi-angle aerial image corresponding to the altitude area.
According to the division of different altitude height areas of the abandoned mine according to the preset altitude difference, the repeated aerial photography of the abandoned mine can be effectively avoided, so that the workload of aerial photography is reduced, and the effectiveness of aerial photography images is guaranteed.
Preferably, in step S102, a three-dimensional image of the abandoned mine is constructed according to a plurality of the multi-angle aerial images, and the three-dimensional image is used to simulate and form the external natural environment of the abandoned mine, so as to determine that the geographic environment information of the abandoned mine specifically includes,
step S1021, calculating image parallax between the multi-angle aerial images of every two adjacent altitude areas in the different altitude areas so as to form a corresponding image parallax sequence;
step S1022, constructing and obtaining a three-dimensional image of the abandoned mine according to the image parallax sequence;
and S1023, simulating and forming the current illumination, wind direction and precipitation environment of the abandoned mine by adopting the three-dimensional image, so as to determine the sunny distribution area information, the shady distribution area information, the windward slope distribution information, the leeward slope distribution information and the wind and watershed distribution information of the abandoned mine, and taking the sunny distribution area information, the shady distribution area information, the windward slope distribution information, the leeward slope distribution information and the watershed distribution information as the geographic environment information.
Corresponding image parallax sequences are formed through image parallaxes between the multi-angle aerial images of the two adjacent altitude areas, and therefore the accuracy and reliability of the determined geographic environment information can be guaranteed by constructing the three-dimensional images of the abandoned mine.
Preferably, in step S103, a three-dimensional image of the abandoned mine is constructed according to a plurality of the multi-angle aerial images, corresponding image chromaticity characteristic information and image texture characteristic information are extracted from the three-dimensional image, and vegetation existence information of the abandoned mine is determined to specifically include,
step S1031, calculating image parallax between the multi-angle aerial images of two adjacent altitude areas in the different altitude areas so as to form corresponding image parallax sequences;
step S1032, constructing and obtaining a three-dimensional image of the abandoned mine according to the image parallax sequence, and extracting corresponding image chromaticity characteristic information and image texture characteristic information from the three-dimensional image;
step S1033, a vegetation presence state evaluation neural network model is constructed, and the image chromaticity characteristic information and the image texture characteristic information are input to the vegetation presence state evaluation neural network model, so that vegetation coverage area distribution information and vegetation coverage density information of the abandoned mine are obtained as the vegetation presence information.
The vegetation existence information can be quickly and accurately obtained by constructing the vegetation existence state evaluation neural network model, so that the reliability of subsequent plant type selection is improved.
Preferably, in the step S2, it is determined that the vegetation growth climate environment information corresponding to the abandoned mine in different areas specifically includes,
and constructing a mine plant growth climate environment evaluation neural network model, and inputting the sunny distribution area information, the shady distribution area information, the windward slope distribution information, the leeward slope distribution information and the watershed distribution information in the geographic environment information, as well as the vegetation coverage area distribution information and the vegetation coverage density information in the vegetation existence information into the mine plant growth climate environment evaluation neural network model, so as to determine the vegetation production climate environment information corresponding to the abandoned mine in different altitude areas.
By constructing the mine plant growth climate environment evaluation neural network model, the vegetation production climate environment information can be quickly and accurately obtained, so that the reliability of subsequent plant type selection is improved.
Preferably, in step S3, the acquiring of soil samples of different areas of the abandoned mine and the analyzing of the soil samples are performed to determine that the vegetation growth soil environment information of the abandoned mine in different areas specifically includes,
step S301, respectively collecting soil samples with preset depth in different altitude areas of the abandoned mine, wherein the altitude difference between two adjacent altitude areas in the different altitude areas is not less than 3.5m, and the preset depth is not less than 1 m;
step S302, each collected soil sample is analyzed and processed about soil composition, soil organic matter composition, soil microelement composition and soil pH value, so that soil composition information, soil organic matter composition information, soil microelement composition information and soil pH value information corresponding to the abandoned mine in different altitude areas are obtained and serve as the vegetation growth soil environment information.
Because the mine can inevitably excavate the process and the mine soil also can receive the weathering effect of different degrees at the exploitation in-process, this can make the abandoned mine can be corresponding different at the regional soil property of different altitudes, can judge the soil property of abandoned mine fast and accurately through carrying out soil sampling to the soil horizon of predetermineeing the degree of depth to in the follow-up suitable plant type of pertinence selection.
Preferably, in the step S4, the determining the plant species suitable for planting in the different areas of the abandoned mine according to the vegetation growth climate environment information and the vegetation growth soil environment information includes,
step S401, determining the temperature, illumination duration, rainfall, soil nutrient value and soil hydrophobicity of the abandoned mine in different altitude areas according to the vegetation growth climate environment information and the vegetation growth soil environment information;
step S402, determining the plant species suitable for planting in the abandoned mine in different altitude areas according to the temperature, the illumination time, the rainfall, the soil nutrient value and the soil hydrophobicity.
Because the growth state of the plants is influenced by the weather conditions and the soil conditions, the selected and determined plant type can be ensured to be matched with the corresponding altitude area direction by determining the temperature, the illumination duration, the rainfall, the soil nutrient value and the soil hydrophobicity of the abandoned mine corresponding to different altitude areas, so that the survival rate of the vegetation is improved to the maximum extent.
Preferably, in the step S1033, a vegetation presence state evaluation neural network model is constructed, and the image chromaticity characteristic information and the image texture characteristic information are input to the vegetation presence state evaluation neural network model, so that vegetation coverage area distribution information and vegetation coverage density information of the abandoned mine are obtained, which are specifically included as the vegetation presence information,
firstly, according to the following formula (1), determining the membership between the sample corresponding to the image chrominance characteristic information and the image texture characteristic information and the classified category
Figure BDA0002665308160000111
In the above-mentioned formula (1),
Figure BDA0002665308160000112
representing the membership between the a-th sample matrix and the i-th class matrix corresponding to the image chrominance characteristic information and the image texture characteristic information, DaA-th sample matrix, Z, representing the image chrominance characteristic information and the image texture characteristic informationiAnd ZjRespectively representing the clustering center of the ith class matrix and the clustering center of the jth class matrix, wherein i is not equal to j, n represents the total number of divided classes, m represents a preset weighting index, the value of the preset weighting index is 2, and T represents the transposition of the matrix;
secondly, by using the following formula (2), a relational expression of the membership and the minimum cluster center in each category matrix is established
Figure BDA0002665308160000121
In the above formula (2), min (Z)i) The minimum cluster center of the ith class matrix is shown, S represents the total number of sample matrixes of the image chromaticity characteristic information and the image texture characteristic information, wherein min (Z) in the formula (2) is definedi) Substituting Z into the above formula (1)iAnd simultaneously solving in the formula (2) to obtain the minimum clustering center min (Z) corresponding to each category matrixi) A value of (d);
thirdly, the minimum clustering center min (Z) obtained by the above stepsi) Substituting the value of (a) into the input-output equation of the vegetation existence state evaluation neural network model corresponding to the following formula (3)
Figure BDA0002665308160000122
In the above formula (3), C represents output information of the vegetation presence state evaluation neural network model, R represents input information of the vegetation presence state evaluation neural network model, and μiRepresenting the weight, μ, of the hidden node and the output node joining the ith class matrix0Represents a preset deviation value and takes the value of (0, 1)]；
The image chromaticity characteristic information and the image texture characteristic information are input as the R value to the formula (3) to obtain output information of the vegetation presence state evaluation neural network model, and the output information is used as vegetation presence information.
Obtaining the membership between the samples of the image chromaticity characteristic information and the image texture characteristic information and the divided classes by using a formula (1) in order to divide each sample into each class by using a dynamic clustering method; then, obtaining a relational expression of the membership relationship and the minimum clustering center in each class matrix by using a formula (2) so as to minimize the sum of squares of errors of each sample and the mean value of the class in which the sample is located; and then, an input and output equation of the vegetation existence state evaluation neural network model is obtained by using the formula (3), so that the vegetation existence state evaluation neural network model is established, the vegetation existence information can be obtained by inputting the image chromaticity characteristic information and the image texture characteristic information, and the model can be automatically updated and iterated, so that the efficiency of the whole process is higher, and the automation degree is higher.
From the content of the above embodiment, the method for screening the plants for ecological restoration of the abandoned mine comprises the steps of taking aerial photographs of the abandoned mine, so as to obtain a corresponding multi-angle aerial image of the abandoned mine, and analyze and process the multi-angle aerial image of the abandoned mine, thereby determining the geographic environmental information and the vegetation existence information of the abandoned mine, determining the vegetation growth climate environmental information corresponding to the abandoned mine in different areas according to the geographic environmental information and the vegetation existence information, then collecting soil samples of the abandoned mine in different areas, analyzing the soil samples, determining vegetation growth soil environment information corresponding to the abandoned mine in different areas, and finally determining the plant types suitable for planting in the different areas of the abandoned mine according to the vegetation growth climate environment information and the vegetation growth soil environment information; therefore, the method for screening the ecological restoration plants of the abandoned mine obtains the vegetation growth climate environment information and the vegetation growth soil environment information of the abandoned mine in the areas with different altitudes by carrying out multi-angle aerial image shooting and soil sampling analysis on the abandoned mine, and can carry out targeted analysis on the areas with different altitudes of the abandoned mine, thereby providing scientific and reliable basis for selecting proper plant planting for the areas with different altitudes and realizing sustainable ecological restoration of the abandoned mine.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (9)

1. The screening method of the ecological restoration plants of the abandoned mine is characterized by comprising the following steps:
step S1, aerial photography is carried out on the abandoned mine, so that a corresponding multi-angle aerial photography image of the abandoned mine is obtained, and the multi-angle aerial photography image of the abandoned mine is analyzed and processed, so that geographic environment information and vegetation existence information of the abandoned mine are determined;
step S2, determining vegetation growth climate environment information corresponding to the abandoned mine in different areas according to the geographic environment information and the vegetation existence information;
step S3, collecting soil samples of different areas of the abandoned mine, and analyzing the soil samples, thereby determining vegetation growth soil environment information corresponding to the abandoned mine in the different areas;
and step S4, determining the plant types suitable for planting in different areas of the abandoned mine according to the vegetation growth climate environment information and the vegetation growth soil environment information.
2. The method for screening the ecological restoration plants for the abandoned mine according to claim 1, wherein the method comprises the following steps:
in step S1, the abandoned mine is aerial-photographed to obtain a corresponding multi-angle aerial-photographed image of the abandoned mine, and the multi-angle aerial-photographed image of the abandoned mine is analyzed to determine that the geographic environmental information and the vegetation existence information of the abandoned mine specifically include,
step S101, performing circumferential scanning shooting on the abandoned mine according to the direction from low altitude to high altitude so as to obtain a plurality of multi-angle aerial images corresponding to different altitude areas of the abandoned mine;
step S102, constructing a three-dimensional image of the abandoned mine according to a plurality of multi-angle aerial images, and simulating to form an external natural environment where the abandoned mine is currently located by adopting the three-dimensional image, so as to determine geographical environment information of the abandoned mine;
and S103, constructing a three-dimensional image of the abandoned mine according to the multi-angle aerial images, extracting corresponding image chromaticity characteristic information and image texture characteristic information from the three-dimensional image, and determining vegetation existence information of the abandoned mine according to the image chromaticity characteristic information and the image texture characteristic information.
3. The method for screening the ecological restoration plants for the abandoned mine according to claim 2, wherein:
in the step S101, the step of performing circumferential scanning shooting on the abandoned mine according to the direction from low altitude to high altitude to obtain a plurality of multi-angle aerial images corresponding to different altitude areas of the abandoned mine specifically includes,
step S1011, dividing the abandoned mine into a plurality of areas with different altitudes from low to high according to a preset altitude difference, wherein the preset altitude difference is not less than 3.5 m;
step S1012, sequentially performing clockwise or counterclockwise circumferential scanning shooting on each altitude area according to the direction from low altitude to high altitude, so as to obtain a multi-angle aerial image corresponding to the altitude area.
4. The method for screening the ecological restoration plants for the abandoned mine according to claim 2, wherein:
in the step S102, a three-dimensional image of the abandoned mine is constructed according to a plurality of the multi-angle aerial images, and the three-dimensional image is used to simulate and form an external natural environment where the abandoned mine is currently located, so as to determine that the geographic environment information of the abandoned mine specifically includes,
step S1021, calculating image parallax between the multi-angle aerial images of every two adjacent altitude areas in the different altitude areas so as to form a corresponding image parallax sequence;
step S1022, constructing and obtaining a three-dimensional image of the abandoned mine according to the image parallax sequence;
and S1023, simulating and forming the current illumination, wind direction and precipitation environment of the abandoned mine by adopting the three-dimensional image, so as to determine the sunny distribution area information, the shady distribution area information, the windward slope distribution information, the leeward slope distribution information and the wind and watershed distribution information of the abandoned mine, and taking the sunny distribution area information, the shady distribution area information, the windward slope distribution information, the leeward slope distribution information and the watershed distribution information as the geographic environment information.
5. The method for screening the ecological restoration plants for the abandoned mine according to claim 2, wherein:
in the step S103, a three-dimensional image of the abandoned mine is constructed according to the plurality of multi-angle aerial images, corresponding image chromaticity feature information and image texture feature information are extracted from the three-dimensional image, and vegetation existence information of the abandoned mine is determined to specifically include,
step S1031, calculating image parallax between the multi-angle aerial images of every two adjacent altitude areas in the different altitude areas so as to form corresponding image parallax sequences;
step S1032, constructing and obtaining a three-dimensional image of the abandoned mine according to the image parallax sequence, and extracting corresponding image chromaticity characteristic information and image texture characteristic information from the three-dimensional image;
step S1033, a vegetation existence state evaluation neural network model is constructed, and the image chromaticity characteristic information and the image texture characteristic information are input into the vegetation existence state evaluation neural network model, so that vegetation coverage area distribution information and vegetation coverage density information of the abandoned mine are obtained and serve as the vegetation existence information.
6. The method for screening the ecological restoration plants for the abandoned mine according to claim 1, wherein the method comprises the following steps:
in the step S2, it is determined that the vegetation growth climate environment information corresponding to the abandoned mine in different areas specifically includes, according to the geographic environment information and the vegetation existence information,
and constructing a mine plant growth climate environment evaluation neural network model, inputting the sun distribution area information, the shade distribution area information, the windward slope distribution information, the leeward slope distribution information and the wind and watershed distribution information in the geographic environment information, and the vegetation coverage area distribution information and the vegetation coverage density information in the vegetation existence information into the mine plant growth climate environment evaluation neural network model, thereby determining the vegetation production climate environment information corresponding to the abandoned mine in different altitude areas.
7. The method for screening the ecological restoration plants for the abandoned mine according to claim 1, wherein the method comprises the following steps:
in step S3, the method includes the steps of collecting soil samples of different areas of the abandoned mine, analyzing the soil samples, and determining that the vegetation growth soil environment information of the abandoned mine in different areas specifically includes,
step S301, respectively collecting soil samples with preset depths in different altitude areas of the abandoned mine, wherein the altitude difference between two adjacent altitude areas in the different altitude areas is not less than 3.5m, and the preset depth is not less than 1 m;
step S302, each collected soil sample is analyzed and processed about soil composition, soil organic matter composition, soil microelement composition and soil pH value, so that soil composition information, soil organic matter composition information, soil microelement composition information and soil pH value information corresponding to the abandoned mine in different altitude areas are obtained and serve as vegetation growth soil environment information.
8. The method for screening the ecological restoration plants for the abandoned mine according to claim 1, wherein the method comprises the following steps:
in the step S4, the determining the plant species suitable for planting in different areas of the abandoned mine according to the vegetation growth climate environment information and the vegetation growth soil environment information specifically includes,
step S401, determining the temperature, illumination duration, rainfall, soil nutrient value and soil hydrophobicity of the abandoned mine in different altitude areas according to the vegetation growth climate environment information and the vegetation growth soil environment information;
and S402, determining the plant species suitable for planting in the abandoned mine in different altitude areas according to the temperature, the illumination time, the rainfall, the soil nutrient value and the soil hydrophobicity.
9. The method for screening ecological restoration plants for abandoned mines according to claim 5, which comprises the following steps:
in the step S1033, a vegetation presence state evaluation neural network model is constructed, and the image chromaticity characteristic information and the image texture characteristic information are input to the vegetation presence state evaluation neural network model, so that vegetation coverage area distribution information and vegetation coverage density information of the abandoned mine are obtained, which specifically include, as the vegetation presence information,
firstly, according to the following formula (1), determining the membership between the sample corresponding to the image chrominance characteristic information and the image texture characteristic information and the divided category
Figure FDA0002665308150000051
In the above-mentioned formula (1),
Figure FDA0002665308150000052
representing the membership between the a-th sample matrix and the i-th class matrix corresponding to the image chrominance characteristic information and the image texture characteristic information, DaA-th sample matrix, Z, representing the image chrominance characteristic information and the image texture characteristic informationiAnd ZjRespectively representing the clustering center of the ith class matrix and the clustering center of the jth class matrix, wherein i is not equal to j, n represents the total number of divided classes, m represents a preset weighting index, the value of the preset weighting index is 2, and T represents the transposition of the matrix;
secondly, establishing a relational expression of the membership and the minimum clustering center in each of the class matrixes by using the following formula (2)
Figure FDA0002665308150000053
In the above formula (2), min (Z)i) A minimum cluster center of the ith class matrix is represented, S represents the total number of sample matrixes of the image chromaticity characteristic information and the image texture characteristic information, wherein min (Z) in the formula (2) is definedi) Substituting Z into the above formula (1)iAnd simultaneously solving in the formula (2) to obtain the minimum clustering center min (Z) corresponding to each class matrixi) A value of (d);
thirdly, the minimum clustering center min (Z) obtained by the above stepsi) Substituting the value of (a) into the input-output equation of the vegetation existence state evaluation neural network model corresponding to the following formula (3)
Figure FDA0002665308150000054
In the above formula (3), C represents output information of the vegetation presence state evaluation neural network model, R represents input information of the vegetation presence state evaluation neural network model, and μiRepresenting the weight, μ, of the hidden node and the output node joining the ith class matrix0Represents a preset deviation value and takes the value of (0, 1)]；
And inputting the image chromaticity characteristic information and the image texture characteristic information into the formula (3) as the R value so as to obtain output information of the vegetation existence state evaluation neural network model, and taking the output information as vegetation existence information.
CN202010916797.5A 2020-09-03 2020-09-03 Screening method for ecological restoration plants of abandoned mine Withdrawn CN112084926A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010916797.5A CN112084926A (en) 2020-09-03 2020-09-03 Screening method for ecological restoration plants of abandoned mine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010916797.5A CN112084926A (en) 2020-09-03 2020-09-03 Screening method for ecological restoration plants of abandoned mine

Publications (1)

Publication Number Publication Date
CN112084926A true CN112084926A (en) 2020-12-15

Family

ID=73731842

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010916797.5A Withdrawn CN112084926A (en) 2020-09-03 2020-09-03 Screening method for ecological restoration plants of abandoned mine

Country Status (1)

Country Link
CN (1) CN112084926A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113516083A (en) * 2021-07-19 2021-10-19 中国农业科学院草原研究所 Ecological restoration modeling method for vegetation in abandoned farmland in grassland area
CN113868963A (en) * 2021-10-20 2021-12-31 中国水利水电科学研究院 Method, system and equipment for constructing nature-imitated ecological vegetation based on machine learning

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113516083A (en) * 2021-07-19 2021-10-19 中国农业科学院草原研究所 Ecological restoration modeling method for vegetation in abandoned farmland in grassland area
CN113868963A (en) * 2021-10-20 2021-12-31 中国水利水电科学研究院 Method, system and equipment for constructing nature-imitated ecological vegetation based on machine learning
CN113868963B (en) * 2021-10-20 2022-06-28 中国水利水电科学研究院 Method, system and equipment for constructing nature-imitated ecological vegetation based on machine learning
US11694005B2 (en) 2021-10-20 2023-07-04 China Institute Of Water Resources And Hydropower Research Method, system and equipment for vegetation restoration or rehabilitation based on machine learning

Similar Documents

Publication Publication Date Title
US9430499B2 (en) Automated feature extraction from imagery
CN111062351B (en) Method for identifying site features of coal mining area by means of satellite/airborne image data fusion
CN108195767B (en) Estuary wetland foreign species monitoring method
CN113221765B (en) Vegetation phenological period extraction method based on digital camera image effective pixels
Yeboah et al. Assessing the land use and land cover changes due to urban growth in Accra, Ghana
Bastarrika et al. Automatic burned land mapping from MODIS time series images: Assessment in Mediterranean ecosystems
Körner et al. Introducing Gradient Boosting as a universal gap filling tool for meteorological time series
CN112084926A (en) Screening method for ecological restoration plants of abandoned mine
Singer et al. STORM 1.0: a simple, flexible, and parsimonious stochastic rainfall generator for simulating climate and climate change
CN109145885B (en) Remote sensing classification method and system for large-scale crops
CN111937016B (en) City internal poverty-poor space measuring method and system based on street view picture and machine learning
CN114758252A (en) Image-based distributed photovoltaic roof resource segmentation and extraction method and system
CN112580982A (en) Ecological protection red line implementation assessment based on multi-temporal remote sensing and CASA model
CN115630567A (en) Coastal zone soil organic carbon reserve simulation and prediction method
CN112800827A (en) Hyperspectral image classification experimental method
Zhang et al. A 250 m annual alpine grassland AGB dataset over the Qinghai–Tibet Plateau (2000–2019) in China based on in situ measurements, UAV photos, and MODIS data
CN117408495A (en) Data analysis method and system based on comprehensive management of land resources
CN111854851A (en) Method for monitoring change of ecological environment in karst depression
KR102487904B1 (en) A system for automatic detection and restoration of damaged topsoil
CN113327032B (en) Land-sea overall planning-based dual-evaluation man-machine interaction adjustment method for territorial space planning
CN113780175B (en) Remote sensing identification method for typhoon and storm landslide in high vegetation coverage area
Brigante et al. USE OF MULTISPECTRAL SENSORS WITH HIGH SPATIAL RESOLUTION FOR TERRITORIAL AND ENVIRONMENTAL ANALYSIS.
Musy et al. Automated forest area estimation using iterative guided spectral class rejection
Dong et al. Spatial decision analysis on wetlands restoration in the lower reaches of Songhua River (LRSR), Northeast China, based on remote sensing and GIS
Gatzouras Assessment of trampling impact in Icelandic natural areas in experimental plots with focus on image analysis of digital photographs

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication

Application publication date: 20201215

WW01 Invention patent application withdrawn after publication