Hyperspectral remote sensing mineralization alteration information extraction method, device, equipment and medium

Abstract

The invention discloses a hyperspectral remote sensing mineralization alteration information extraction method, device and equipment and a medium, and is applied to the technical field of remote sensing geological survey, the hyperspectral remote sensing mineralization alteration information extraction method comprises the following steps: obtaining sample laboratory spectral data and sample hyperspectral satellite remote sensing data of a rock and soil sample; calculating the sample laboratory spectral data and the sample hyperspectral satellite remote sensing data by adopting a direct standardization algorithm, and determining a transfer matrix required for converting the sample hyperspectral satellite remote sensing data into the sample laboratory spectral data; based on the transfer matrix, converting hyperspectral satellite remote sensing data of a research area to obtain laboratory-like spectral data of the research area; and performing similarity analysis on the laboratory-like spectral data and the standard spectral data of the altered mineral, and determining mineralization alteration information in the laboratory-like spectral data.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing geological survey, and in particular to a method, device, equipment and medium for extracting hyperspectral remote sensing mineralization alteration information. Background Art

[0002] Compared with multispectral satellites, hyperspectral satellite remote sensing data has excellent spectral resolution, and numerous spectral bands can fully reflect the unique spectral characteristics of different mineral types, providing sufficient support for mineral identification. Rich spectral information makes hyperspectral satellite remote sensing data show significant advantages in geological mapping, mineral type identification, altered mineral anomaly information extraction research, etc., and has made outstanding contributions to the field of remote sensing geological survey technology.

[0003] Due to the diversity and complexity of the surface environment, and the influence of uncertain factors such as atmosphere, topography, and soil moisture, the phenomenon of "same object with different spectra" and "different objects with the same spectrum" is common. Therefore, the spectral information obtained by hyperspectral satellites cannot fully reflect the true spectral characteristics of the objects, and it is difficult to accurately extract mineralization and alteration information from hyperspectral satellite remote sensing data. Summary of the invention

[0004] In view of the above-mentioned technical status, the present invention provides a method, device, equipment and medium for extracting hyperspectral remote sensing mineralization alteration information.

[0005] In order to achieve the above object, the present invention provides the following technical solutions: A method for extracting mineralization alteration information using hyperspectral remote sensing, comprising: Obtain sample laboratory spectral data and sample hyperspectral satellite remote sensing data of geotechnical samples; Using a direct standardization algorithm, the sample laboratory spectral data and the sample hyperspectral satellite remote sensing data are calculated to determine a transfer matrix required for transforming the sample hyperspectral satellite remote sensing data into the sample laboratory spectral data; Based on the transfer matrix, the hyperspectral satellite remote sensing data of the study area is transformed to obtain the laboratory-like spectral data of the study area; A similarity analysis is performed on the laboratory-like spectral data and the standard spectral data of altered minerals to determine the mineralization alteration information in the laboratory-like spectral data.

[0006] In an optional implementation manner of the present application, the obtaining of sample laboratory spectral data of the rock and soil sample includes: Acquire first laboratory spectral data of each of the rock and soil samples in the rock and soil sample set, and determine a mean vector of each of the first laboratory spectral data and a covariance matrix of the first laboratory spectral data; Determine the Mahalanobis distance between each of the first laboratory spectral data and the mean vector according to the mean vector and the covariance matrix; Based on the Mahalanobis distance between each of the first laboratory spectral data and the mean vector, outliers are removed from the first laboratory spectral data to obtain the sample laboratory spectral data.

[0007] In an optional implementation manner of the present application, determining the Mahalanobis distance between each of the first laboratory spectral data and the mean vector according to the mean vector and the covariance matrix includes: The Mahalanobis distance between each of the first laboratory spectral data and the mean vector is determined by the following formula: ; in, represents the Mahalanobis distance between the first laboratory spectral data of the i-th rock and soil sample and the mean vector; represents the first laboratory spectrum data of the i-th rock and soil sample; represents the mean vector; Denotes the covariance matrix.

[0008] In an optional implementation of the present application, the direct standardization algorithm is used to calculate the sample laboratory spectral data and the sample hyperspectral satellite remote sensing data to determine the transfer matrix required for transforming the sample hyperspectral satellite remote sensing data to the sample laboratory spectral data, including: Using a spatial clustering algorithm to cluster the spectrum data of each sample laboratory to obtain each cluster of the spectrum data of the sample laboratory, and determining the spectrum data of the sample laboratory corresponding to the core point of each cluster as the laboratory conversion set sample data; The direct standardization algorithm is used to calculate the laboratory conversion set sample data and the sample hyperspectral satellite remote sensing data to determine the transfer matrix required for transforming the sample hyperspectral satellite remote sensing data into the laboratory conversion set sample data.

[0009] In an optional implementation manner of the present application, the transfer matrix is ​​determined by the following formula: ; in, A matrix form representing the sample laboratory spectral data; A matrix form representing the sample hyperspectral satellite remote sensing data; and The dimension is m×n, where m is the number of the sample laboratory spectral data, and n is the number of bands of each of the sample laboratory spectral data; B represents the transfer matrix; and E represents the error term.

[0010] In an optional implementation of the present application, the similarity analysis is performed on the laboratory-like spectral data and the standard spectral data of the altered minerals to determine the mineralization alteration information in the laboratory-like spectral data, including: respectively calculating the spectral information divergence and spectral angle between the standard spectral data of the altered mineral and the quasi-laboratory spectral data of each pixel; Determining the similarity between the standard spectral data of the altered mineral and the quasi-laboratory spectral data of each pixel according to the spectral information divergence and the spectral angle; According to the similarity between the standard spectrum data of the altered mineral and the quasi-laboratory spectrum data of each pixel, abnormal pixels of the altered mineral are determined from the quasi-laboratory spectrum data of each pixel.

[0011] In an optional implementation manner of the present application, the spectral information divergence and spectral angle of the pixel are determined by the following formula: ; ; ; ; The similarity is represented by the SID_SAM index, which is represented by the following formula: ; in, The SID_SAM index represents the difference between the laboratory-like spectral data and the standard spectral data of the altered minerals; represents the spectral information divergence; represents the relative entropy of the standard spectrum data y relative to the quasi-laboratory spectrum data x; represents the relative entropy of the quasi-laboratory spectrum data x relative to the standard spectrum data y; represents the probability of the i-th wavelength point in the laboratory-like spectrum data x; represents the probability of the i-th wavelength point in the standard spectrum data y; represents the spectral angle; represents the i-th wavelength point in the laboratory-like spectrum data x; represents the i-th wavelength point in the standard spectrum data y.

[0012] For the laboratory-like spectral data of each pixel and the standard spectral data of the altered mineral, the smaller the value of the SID_SAM index is, the higher the similarity between the two spectra is. In practical applications, by setting a suitable threshold, the pixels in the laboratory-like spectral data that are greater than the threshold can be determined as abnormal pixels of altered minerals, thereby determining the mineralization alteration information in the laboratory-like spectral data.

[0013] Compared with the prior art, the hyperspectral remote sensing mineralization and alteration information extraction method provided by the present invention constructs a transfer matrix between laboratory spectral data and hyperspectral satellite remote sensing data through sample laboratory spectral data and sample hyperspectral satellite remote sensing data, and then converts the hyperspectral satellite remote sensing data collected in the study area into quasi-laboratory spectral data close to the laboratory spectral data through the transfer matrix, which is beneficial to eliminating the distortion in the hyperspectral satellite remote sensing data, and then completes the mineralization and alteration information extraction for the hyperspectral satellite remote sensing data based on the quasi-laboratory spectral data.

[0014] The present invention also provides a hyperspectral remote sensing mineralization alteration information extraction device, comprising: A data acquisition unit, used for acquiring sample laboratory spectral data and sample hyperspectral satellite remote sensing data of rock and soil samples; A matrix calculation unit, used for calculating the sample laboratory spectral data and the sample hyperspectral satellite remote sensing data by using a direct standardization algorithm, and determining a transfer matrix required for transforming the sample hyperspectral satellite remote sensing data into the sample laboratory spectral data; A data transfer unit, used for converting the hyperspectral satellite remote sensing data of the study area based on the transfer matrix to obtain laboratory-like spectral data of the study area; The alteration determination unit is used to perform similarity analysis on the laboratory-like spectral data and the standard spectral data of altered minerals to determine the mineralization alteration information in the laboratory-like spectral data.

[0015] Compared with the prior art, the beneficial effects of the hyperspectral remote sensing mineralization alteration information extraction device provided by the present invention are the same as the beneficial effects of the hyperspectral remote sensing mineralization alteration information extraction method described in the above technical solution, which will not be repeated here.

[0016] The present invention also provides an electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is used to execute the above-mentioned hyperspectral remote sensing mineralization alteration information extraction method by running the instructions in the memory.

[0017] Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the hyperspectral remote sensing mineralization alteration information extraction method described in the above technical solution, and will not be described in detail here.

[0018] The present invention also provides a computer storage medium, in which instructions are stored. When the instructions are executed, the above-mentioned method for extracting hyperspectral remote sensing mineralization alteration information is implemented.

[0019] Compared with the prior art, the beneficial effects of the computer storage medium provided by the present invention are the same as the beneficial effects of the hyperspectral remote sensing mineralization alteration information extraction method described in the above technical solution, and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 Flow chart of the hyperspectral remote sensing mineralization alteration information extraction method provided in the embodiment of the present application.

[0021] Figure 2 This is a structural diagram of the hyperspectral remote sensing mineralization and alteration information extraction device provided in an embodiment of the present application.

[0022] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. For example, the first threshold and the second threshold are only used to distinguish different thresholds, and their order is not limited. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0024] It should be noted that, in the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0025] In the present invention, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or multiple.

[0026] Compared with multispectral satellites, hyperspectral satellite remote sensing data has excellent spectral resolution, and numerous spectral bands can fully reflect the unique spectral characteristics of different mineral types, providing sufficient support for mineral identification. Rich spectral information makes hyperspectral satellite remote sensing data show significant advantages in geological mapping, mineral type identification, altered mineral anomaly information extraction research, etc., and has made outstanding contributions to the field of remote sensing geological survey technology.

[0027] Due to the diversity and complexity of the surface environment, and the influence of uncertain factors such as atmosphere, topography, and soil moisture, the phenomenon of "same object with different spectra" and "different objects with the same spectrum" is common. Therefore, the spectral information obtained by hyperspectral satellites cannot fully reflect the true spectral characteristics of the objects, and it is difficult to accurately extract mineralization and alteration information from hyperspectral satellite remote sensing data.

[0028] In view of the above-mentioned technical status, the present application provides a method, device, equipment and medium for extracting hyperspectral remote sensing mineralization and alteration information, which are described in detail one by one in the following embodiments.

[0029] Please refer to Figure 1 , Figure 1 Flow chart of the hyperspectral remote sensing mineralization alteration information extraction method provided in the embodiment of the present application.

[0030] like Figure 1 As shown, the hyperspectral remote sensing mineralization alteration information extraction method includes the following S101 to S104: S101, obtaining sample laboratory spectral data and sample hyperspectral satellite remote sensing data of rock and soil samples.

[0031] The rock and soil samples can be understood as different types of rock or soil samples collected at representative locations selected in the study area. After obtaining the rock and soil samples, they are ground, dried, and processed according to laboratory standards to process the rock or soil samples into a uniform state to reduce the impact of the internal heterogeneity of the samples on the reflectivity of the spectral curve.

[0032] After obtaining the rock and soil samples, a full-spectrum spectrometer (such as CSD350A) is used to scan the rock and soil samples to obtain sample laboratory spectrum data of the rock and soil samples.

[0033] In an optional implementation of the present application, in order to reduce the impact of the instrument noise of the full-spectrum spectrometer, the sample laboratory spectral data can be obtained by averaging multiple measurements.

[0034] The sample hyperspectral satellite remote sensing data can be understood as spectral information obtained from a satellite platform through hyperspectral imaging technology. In an embodiment of the present application, the sample hyperspectral satellite remote sensing data refers to hyperspectral satellite remote sensing data corresponding to the rock or soil type of the rock and soil sample.

[0035] In an optional implementation of the present application, considering that erroneous sampling may occur during the sample collection process, it is necessary to perform an abnormality removal process on the collected rock and soil samples.

[0036] Specifically, the sample laboratory spectral data of the rock and soil sample obtained in S101 above includes: Acquire first laboratory spectral data of each of the rock and soil samples in the rock and soil sample set, and determine a mean vector of each of the first laboratory spectral data and a covariance matrix of the first laboratory spectral data; Determine the Mahalanobis distance between each of the first laboratory spectral data and the mean vector according to the mean vector and the covariance matrix; Based on the Mahalanobis distance between each of the first laboratory spectral data and the mean vector, outliers are removed from the first laboratory spectral data to obtain the sample laboratory spectral data.

[0037] Among them, the mean vector of the first laboratory spectral data can be understood as the average value of each spectral band of the laboratory spectral data of the collected rock and soil samples; the covariance matrix is ​​used to describe the change characteristics of each band of the first laboratory spectral data and the correlation between them.

[0038] Furthermore, the Mahalanobis distance can be calculated by the following formula (1): (1); in, represents the Mahalanobis distance between the first laboratory spectral data of the i-th rock and soil sample and the mean vector; represents the first laboratory spectrum data of the i-th rock and soil sample; represents the mean vector; Denotes the covariance matrix.

[0039] S102, using a direct standardization algorithm to calculate the sample laboratory spectral data and the sample hyperspectral satellite remote sensing data, and determine a transfer matrix required for transforming the sample hyperspectral satellite remote sensing data into the sample laboratory spectral data.

[0040] The purpose of the hyperspectral remote sensing mineralization alteration information extraction method provided in the embodiment of the present application is to avoid the extraction of mineralization alteration information being affected by problems such as spectral information distortion caused by uncertain factors such as atmosphere, topography, soil, and moisture.

[0041] Therefore, before extracting mineralization alteration information from hyperspectral satellite remote sensing data, first of all, it is necessary to convert the hyperspectral satellite remote sensing data into laboratory spectral data as much as possible, so as to eliminate the distortion caused by uncertain factors such as atmosphere, topography, soil, and moisture.

[0042] Specifically, the above S102 includes: Using a spatial clustering algorithm to cluster the spectrum data of each sample laboratory to obtain each cluster of the spectrum data of the sample laboratory, and determining the spectrum data of the sample laboratory corresponding to the core point of each cluster as the laboratory conversion set sample data; The direct standardization algorithm is used to calculate the laboratory conversion set sample data and the sample hyperspectral satellite remote sensing data to determine the transfer matrix required for transforming the sample hyperspectral satellite remote sensing data into the laboratory conversion set sample data.

[0043] The purpose of the spatial clustering algorithm is to group data points into clusters so that objects within the same cluster are similar to each other, while objects in different clusters are quite different. In actual application, the spatial clustering algorithm can be a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm or an OPTICS (Ordering Points To Identify the Clustering Structure) algorithm, and this application does not impose any restrictions on this.

[0044] Taking the DBSCAN algorithm as an example, in the actual application process, the algorithm can set a suitable neighborhood ( ) and the minimum number of points (MinPts) parameters, randomly select an unprocessed point. If the point is a core point, expand the cluster with the point as the center and classify all points in its neighborhood (including core points and boundary points) into the same cluster. If the point is a boundary point, check whether it can join an existing cluster. If the point is a noise point, it is marked as noise and does not belong to any cluster. Repeat the above steps until all points are marked as core points, boundary points or noise points.

[0045] Further, the core point (ie, density center point) of each cluster is selected as the laboratory transformation set sample data, so as to participate in the calculation of the transfer matrix through the laboratory transformation set sample data as a representative.

[0046] Direct standardization (DS) is a spectral model transfer algorithm used to match high-quality spectral data from laboratories or ground measurements with satellite or aerial hyperspectral data to improve the spectral quality of satellite data.

[0047] Specifically, the laboratory conversion set sample data and the sample hyperspectral satellite remote sensing data, specifically the spectral curve, the transfer matrix can be determined by the following formula (2): (2); in, A matrix form representing the sample laboratory spectral data; A matrix form representing the sample hyperspectral satellite remote sensing data; and The dimension is m×n, where m is the number of the sample laboratory spectral data, and n is the number of bands of the spectral data of each sample laboratory; B represents the transfer matrix; and E represents the error term.

[0048] In the actual calculation process, the above formula (2) can be processed based on the least squares method to obtain the transfer matrix B, that is: .

[0049] S103, based on the transfer matrix, transform the hyperspectral satellite remote sensing data of the study area to obtain laboratory-like spectral data of the study area.

[0050] The hyperspectral satellite remote sensing data can be understood as real-time collected hyperspectral satellite remote sensing data, and the purpose of the embodiment of the present application is to extract mineralization alteration information from the hyperspectral satellite remote sensing data. In the actual application process, the hyperspectral satellite remote sensing data can be collected by the GF-5 hyperspectral satellite.

[0051] Furthermore, in order to improve the quality and availability of hyperspectral satellite data acquired through satellite collection, before converting the hyperspectral satellite remote sensing data, the hyperspectral satellite remote sensing data can also be preprocessed by removing invalid bands, duplicate bands and water vapor bands, performing radiation calibration, atmospheric correction, orthorectification and other preprocessing operations.

[0052] Specifically, based on the transfer matrix, the hyperspectral satellite remote sensing data of the study area is transformed to obtain the laboratory-like spectral data of the study area, which can be obtained by the following formula (3): (3); in, Represents the class of laboratory spectral data.

[0053] S104, performing similarity analysis on the laboratory-like spectral data and standard spectral data of altered minerals to determine mineralization alteration information in the laboratory-like spectral data.

[0054] Performing similarity analysis on the quasi-laboratory spectrum data and the standard spectrum data of altered minerals refers to performing similarity analysis on the image pixel spectrum of the quasi-laboratory spectrum and the standard spectrum of altered minerals.

[0055] In order to further improve data quality and availability, before similarity analysis is performed on the quasi-laboratory spectral data and the standard spectral data of altered minerals, a filtering algorithm and an envelope removal method may be used to enhance the spectral features of the quasi-laboratory spectral data.

[0056] Specifically, the filtering algorithm may be a SG (Savitzky-Golay) filtering algorithm. The SG filtering algorithm is a commonly used data smoothing and differentiation method, which is suitable for processing spectral data containing noise. The algorithm constructs a (2M+1)×(K+1) design matrix by using a smoothing window with a width of 2M+1 and a polynomial order of K. ,in, , ; M represents the radius of the window. A smoothing window with a width of 2M+1 means that the window includes the current point and M points to its left and right. Then the polynomial fitting coefficients of the smoothing window are calculated: a= [ a 0 , a 1 , … , a N ] T = ( A T A) - 1 A T X=HX , , the smoothing value when the window center n=0 is , represents the zeroth row of the matrix H; represents the laboratory-like spectral data at position n within the smoothing window, .

[0057] After that, the envelope of the laboratory-like spectral data is calculated, and the pixel spectral curve is divided by the envelope to obtain the spectral curve after the envelope is removed, that is, ,in, represents the quasi-laboratory spectrum curve after the envelope is removed, S is the quasi-laboratory spectrum curve, and C represents the envelope.

[0058] Furthermore, the similarity analysis is performed on the laboratory-like spectral data and the standard spectral data of the altered minerals to determine the mineralization alteration information in the laboratory-like spectral data, including: respectively calculating the spectral information divergence and spectral angle between the standard spectral data of the altered mineral and the quasi-laboratory spectral data of each pixel; Determining the similarity between the standard spectral data of the altered mineral and the quasi-laboratory spectral data of each pixel according to the spectral information divergence and the spectral angle; According to the similarity between the standard spectrum data of the altered mineral and the quasi-laboratory spectrum data of each pixel, abnormal pixels of the altered mineral are determined from the quasi-laboratory spectrum data of each pixel.

[0059] Specifically, the spectral information divergence and spectral angle of the pixel's quasi-laboratory spectral data and the standard spectral data of the altered mineral are determined by the following formulas (4) to (7): (4); (5); (6); (7); in, represents the spectral information divergence; represents the relative entropy of the standard spectrum data y relative to the quasi-laboratory spectrum data x; represents the relative entropy of the quasi-laboratory spectrum data x relative to the standard spectrum data y; represents the probability of the i-th wavelength point in the laboratory-like spectrum data x; represents the probability of the i-th wavelength point in the standard spectrum data y; represents the spectral angle; represents the i-th wavelength point in the laboratory-like spectrum data x; represents the i-th wavelength point in the standard spectrum data y.

[0060] Furthermore, after obtaining the spectral information divergence and spectral angle of each pixel, the similarity between the laboratory-like spectral data and the standard spectral data of the altered mineral can be determined.

[0061] In the embodiment of the present application, the similarity can be represented by the SID_SAM index, and the SID_SAM index can be represented by the following formula (8): (8); in, The SID_SAM index represents the difference between the laboratory-like spectral data and the standard spectral data of the altered minerals. represents the spectral information divergence; represents the spectral angle.

[0062] For the laboratory-like spectral data of each pixel and the standard spectral data of the altered mineral, the smaller the value of the SID_SAM index is, the higher the similarity between the two spectra is. In the actual application process, by setting a suitable threshold, the pixels in the laboratory-like spectral data that are greater than the threshold are determined to be abnormal pixels of altered minerals, thereby determining the mineralization alteration information in the laboratory-like spectral data.

[0063] To summarize, the hyperspectral remote sensing mineralization and alteration information extraction method provided in the embodiment of the present application constructs a transfer matrix between laboratory spectral data and hyperspectral satellite remote sensing data through sample laboratory spectral data and sample hyperspectral satellite remote sensing data, and then converts the hyperspectral data collected in the study area into quasi-laboratory spectral data close to laboratory spectral data through the transfer matrix, which is beneficial to eliminating distortion in hyperspectral satellite remote sensing data, and then completes the mineralization and alteration information extraction for the hyperspectral satellite remote sensing data based on the quasi-laboratory spectral data.

[0064] This application also provides a hyperspectral remote sensing mineralization alteration information extraction device, please refer to Figure 2 , Figure 2 This is a structural diagram of the hyperspectral remote sensing mineralization and alteration information extraction device provided in an embodiment of the present application.

[0065] like Figure 2 As shown, the hyperspectral remote sensing mineralization alteration information extraction device comprises: A data acquisition unit 201 is used to acquire sample laboratory spectral data and sample hyperspectral satellite remote sensing data of rock and soil samples; The matrix calculation unit 202 is used to calculate the sample laboratory spectral data and the sample hyperspectral satellite remote sensing data by using a direct standardization algorithm to determine a transfer matrix required for transforming the sample hyperspectral satellite remote sensing data into the sample laboratory spectral data; A data transfer unit 203 is used to transform the hyperspectral satellite remote sensing data of the study area based on the transfer matrix to obtain laboratory-like spectral data of the study area; The alteration determination unit 204 is used to perform similarity analysis on the laboratory-like spectrum data and the standard spectrum data of altered minerals to determine the mineralization alteration information in the laboratory-like spectrum data.

[0066] In an optional implementation manner of the present application, the obtaining of sample laboratory spectral data of the rock and soil sample includes: Acquire first laboratory spectral data of each of the rock and soil samples in the rock and soil sample set, and determine a mean vector of each of the first laboratory spectral data and a covariance matrix of the first laboratory spectral data; Determine the Mahalanobis distance between each of the first laboratory spectral data and the mean vector according to the mean vector and the covariance matrix; Based on the Mahalanobis distance between each of the first laboratory spectral data and the mean vector, outliers are removed from the first laboratory spectral data to obtain the sample laboratory spectral data.

[0067] In an optional implementation manner of the present application, determining the Mahalanobis distance between each of the first laboratory spectral data and the mean vector according to the mean vector and the covariance matrix includes: The Mahalanobis distance between each of the first laboratory spectral data and the mean vector is determined by the following formula: ; in, represents the Mahalanobis distance between the first laboratory spectral data of the i-th rock and soil sample and the mean vector; represents the first laboratory spectrum data of the i-th rock and soil sample; represents the mean vector; Denotes the covariance matrix.

[0068] In an optional implementation of the present application, the direct standardization algorithm is used to calculate the sample laboratory spectral data and the sample hyperspectral satellite remote sensing data to determine the transfer matrix required for transforming the sample hyperspectral satellite remote sensing data to the sample laboratory spectral data, including: Using a spatial clustering algorithm to cluster the spectrum data of each sample laboratory to obtain each cluster of the spectrum data of the sample laboratory, and determining the spectrum data of the sample laboratory corresponding to the core point of each cluster as the laboratory conversion set sample data; The direct standardization algorithm is used to calculate the laboratory conversion set sample data and the sample hyperspectral satellite remote sensing data to determine the transfer matrix required for transforming the sample hyperspectral satellite remote sensing data into the laboratory conversion set sample data.

[0069] In an optional implementation manner of the present application, the transfer matrix is ​​determined by the following formula: ; in, A matrix form representing the sample laboratory spectral data; A matrix form representing the sample hyperspectral satellite remote sensing data; and The dimension is m×n, where m is the number of the sample laboratory spectral data, and n is the number of bands of each of the sample laboratory spectral data; B represents the transfer matrix; and E represents the error term.

[0070] In an optional implementation of the present application, the similarity analysis is performed on the laboratory-like spectral data and the standard spectral data of the altered minerals to determine the mineralization alteration information in the laboratory-like spectral data, including: respectively calculating the spectral information divergence and spectral angle between the standard spectral data of the altered mineral and the quasi-laboratory spectral data of each pixel; Determining the similarity between the standard spectral data of the altered mineral and the quasi-laboratory spectral data of each pixel according to the spectral information divergence and the spectral angle; According to the similarity between the standard spectrum data of the altered mineral and the quasi-laboratory spectrum data of each pixel, abnormal pixels of the altered mineral are determined from the quasi-laboratory spectrum data of each pixel.

[0071] In an optional implementation manner of the present application, the spectral information divergence and spectral angle of the pixel are determined by the following formula: ; ; ; ; The similarity can be represented by the SID_SAM index, which can be represented by the following formula: ; in, The SID_SAM index represents the difference between the laboratory-like spectral data and the standard spectral data of the altered minerals; represents the spectral information divergence; represents the relative entropy of the standard spectrum data y relative to the quasi-laboratory spectrum data x; represents the relative entropy of the quasi-laboratory spectrum data x relative to the standard spectrum data y; represents the probability of the i-th wavelength point in the laboratory-like spectrum data x; represents the probability of the i-th wavelength point in the standard spectrum data y; represents the spectral angle; represents the i-th wavelength point in the laboratory-like spectrum data x; represents the i-th wavelength point in the standard spectrum data y.

[0072] For the laboratory-like spectral data of each pixel and the standard spectral data of the altered mineral, the smaller the value of the SID_SAM index is, the higher the similarity between the two spectra is. In the actual application process, by setting a suitable threshold, the pixels in the laboratory-like spectral data that are greater than the threshold are determined to be abnormal pixels of altered minerals, thereby determining the mineralization alteration information in the laboratory-like spectral data.

[0073] The above-mentioned device embodiment provided in this embodiment and the method embodiment of this application belong to the same application concept. For technical details not fully described in this embodiment, please refer to the specific processing content of the hyperspectral remote sensing mineralization alteration information extraction method provided in the above-mentioned embodiment of this application, which will not be repeated here.

[0074] The present application also provides an electronic device, such as Figure 3 As shown, Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0075] like Figure 3 As shown, the electronic device comprises: Processor 210; A memory 200 for storing instructions executable by the processor 210; The processor 210 is used to execute the hyperspectral remote sensing mineralization alteration information extraction method disclosed in any of the above embodiments by running the instructions in the memory 200.

[0076] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected to each other via a bus. A bus may include a pathway that transfers information between components of a computer system.

[0077] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the scheme of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0078] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0079] The memory 200 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes a computer operation instruction. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0080] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a touch screen, etc.

[0081] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0082] The communication interface 220 may include any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0083] The processor 210 executes the program stored in the memory 200 and calls other devices, and can be used to implement each step of any hyperspectral remote sensing mineralization alteration information extraction method provided in the above embodiments of the present application.

[0084] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps in the hyperspectral remote sensing mineralization alteration information extraction method of various embodiments of the present application.

[0085] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0086] In addition, the embodiments of the present application may also be a storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps in the hyperspectral remote sensing mineralization alteration information extraction method of various embodiments of the present application.

[0087] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0088] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0089] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0090] The modules and sub-modules in the devices and terminals in the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0091] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0092] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0093] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0094] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0095] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0096] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0097] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for extracting mineralization and alteration information using hyperspectral remote sensing, characterized in that: include: Obtain sample laboratory spectral data and sample hyperspectral satellite remote sensing data of geotechnical samples; Using a direct standardization algorithm, the sample laboratory spectral data and the sample hyperspectral satellite remote sensing data are calculated to determine a transfer matrix required for transforming the sample hyperspectral satellite remote sensing data into the sample laboratory spectral data; Based on the transfer matrix, the hyperspectral satellite remote sensing data of the study area is transformed to obtain the laboratory-like spectral data of the study area; A similarity analysis is performed on the laboratory-like spectral data and the standard spectral data of altered minerals to determine the mineralization alteration information in the laboratory-like spectral data.

2. The method for extracting hyperspectral remote sensing mineralization alteration information according to claim 1, characterized in that: The obtaining of sample laboratory spectral data of the rock and soil sample comprises: Acquire first laboratory spectral data of each of the rock and soil samples in the rock and soil sample set, and determine a mean vector of each of the first laboratory spectral data and a covariance matrix of the first laboratory spectral data; Determine the Mahalanobis distance between each of the first laboratory spectral data and the mean vector according to the mean vector and the covariance matrix; Based on the Mahalanobis distance between each of the first laboratory spectral data and the mean vector, outliers are removed from the first laboratory spectral data to obtain the sample laboratory spectral data.

3. The method for extracting hyperspectral remote sensing mineralization alteration information according to claim 2, characterized in that: Determining the Mahalanobis distance between each of the first laboratory spectral data and the mean vector according to the mean vector and the covariance matrix includes: The Mahalanobis distance between each of the first laboratory spectral data and the mean vector is determined by the following formula: ； in, represents the Mahalanobis distance between the first laboratory spectral data of the i-th rock and soil sample and the mean vector; represents the first laboratory spectrum data of the i-th rock and soil sample; represents the mean vector; Denotes the covariance matrix.

4. The method for extracting hyperspectral remote sensing mineralization alteration information according to claim 1, characterized in that: The direct standardization algorithm is used to calculate the sample laboratory spectral data and the sample hyperspectral satellite remote sensing data to determine the transfer matrix required for transforming the sample hyperspectral satellite remote sensing data to the sample laboratory spectral data, including: Using a spatial clustering algorithm to cluster the spectrum data of each sample laboratory to obtain each cluster of the spectrum data of the sample laboratory, and determining the spectrum data of the sample laboratory corresponding to the core point of each cluster as the laboratory conversion set sample data; The direct standardization algorithm is used to calculate the laboratory conversion set sample data and the sample hyperspectral satellite remote sensing data to determine the transfer matrix required for transforming the sample hyperspectral satellite remote sensing data into the laboratory conversion set sample data.

5. The method for extracting hyperspectral remote sensing mineralization alteration information according to claim 1, characterized in that: The transfer matrix is ​​determined by the following formula: ； in, A matrix form representing the sample laboratory spectral data; A matrix form representing the sample hyperspectral satellite remote sensing data; and The dimension is m×n, where m is the number of the sample laboratory spectral data, and n is the number of bands of each of the sample laboratory spectral data; B represents the transfer matrix; and E represents the error term.

6. The method for extracting hyperspectral remote sensing mineralization alteration information according to claim 1, characterized in that: The similarity analysis of the laboratory-like spectral data and the standard spectral data of altered minerals is performed to determine the mineralization alteration information in the laboratory-like spectral data, including: respectively calculating the spectral information divergence and spectral angle between the standard spectral data of the altered mineral and the quasi-laboratory spectral data of each pixel; Determining the similarity between the standard spectral data of the altered mineral and the quasi-laboratory spectral data of each pixel according to the spectral information divergence and the spectral angle; According to the similarity between the standard spectrum data of the altered mineral and the quasi-laboratory spectrum data of each pixel, abnormal pixels of the altered mineral are determined from the quasi-laboratory spectrum data of each pixel.

7. The method for extracting hyperspectral remote sensing mineralization alteration information according to claim 6, characterized in that: The spectral information divergence and spectral angle of the pixel are determined by the following formula: ； ； ； ； The similarity is represented by the SID_SAM index, which is represented by the following formula: ； in, represents the SID_SAM index between the quasi-laboratory spectral data and the standard spectral data of the altered mineral; represents the spectral information divergence; represents the relative entropy of the standard spectrum data y relative to the quasi-laboratory spectrum data x; represents the relative entropy of the quasi-laboratory spectrum data x relative to the standard spectrum data y; represents the probability of the i-th wavelength point in the laboratory-like spectrum data x; represents the probability of the i-th wavelength point in the standard spectrum data y; represents the spectral angle; represents the i-th wavelength point in the laboratory-like spectrum data x; represents the i-th wavelength point in the standard spectrum data y.

8. A hyperspectral remote sensing mineralization alteration information extraction device, characterized in that: include: A data acquisition unit, used for acquiring sample laboratory spectral data and sample hyperspectral satellite remote sensing data of rock and soil samples; A matrix calculation unit, used for calculating the sample laboratory spectral data and the sample hyperspectral satellite remote sensing data by using a direct standardization algorithm, and determining a transfer matrix required for transforming the sample hyperspectral satellite remote sensing data into the sample laboratory spectral data; A data transfer unit, used for converting the hyperspectral satellite remote sensing data of the study area based on the transfer matrix to obtain laboratory-like spectral data of the study area; The alteration determination unit is used to perform similarity analysis on the laboratory-like spectral data and the standard spectral data of altered minerals to determine the mineralization alteration information in the laboratory-like spectral data.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the hyperspectral remote sensing mineralization alteration information extraction method according to any one of claims 1 to 7 by running instructions in the memory.

10. A computer storage medium, characterized in that: The computer storage medium stores instructions, and when the instructions are executed, the hyperspectral remote sensing mineralization alteration information extraction method according to any one of claims 1 to 7 is executed.

Images