CN-122023832-A - Geological remote sensing interpretation method and system for mineral resource investigation

CN122023832ACN 122023832 ACN122023832 ACN 122023832ACN-122023832-A

Abstract

The application relates to the technical field of image data processing, in particular to a geological remote sensing interpretation method and a geological remote sensing interpretation system for mineral resource investigation, wherein the method comprises the steps of obtaining a geological remote sensing image to be analyzed of a mineral resource area; the method comprises the steps of analyzing the distribution uniformity degree of pixel point gray values of all local areas in an image to be analyzed to obtain image smoothness, obtaining LBP values of all pixel points in the image to be analyzed and a historical standard sample image, clustering, obtaining each growth area of each image by using a seed growth algorithm, determining an image detail evaluation index of the image to be analyzed through the integral distribution of edge complexity of the growth areas of the image to be analyzed and the historical standard sample image belonging to each cluster, obtaining image enhancement effect quality evaluation, adjusting a wavelet threshold value by combining the image detail evaluation index, and interpreting the enhanced image. The application aims to improve the accuracy of geological remote sensing image interpretation in mineral resource exploration.

Inventors

XIE GEN
YANG GUICAI
YAN JIAPAN
ZHAO YOUZHI

Assignees

中国地质调查局地球物理调查中心

Dates

Publication Date: 20260512
Application Date: 20260414

Claims (9)

1. A geological remote sensing interpretation method for mineral resource exploration, which is characterized by comprising the following steps: Obtaining a geological remote sensing image to be analyzed of a mineral resource area to be surveyed; Dividing the acquired image to be analyzed according to a preset size, and primarily enhancing the gray value dispersion degree of the local area and the number of the pixels of the image based on the divided gray value dispersion degree; Obtaining LBP values of all pixel points in an image to be analyzed and a historical standard sample image, clustering, using a seed growing algorithm for the pixel points belonging to each cluster in each image to obtain each growing area of each image, analyzing the number and shape distribution characteristics of edges in each growing area to determine the edge complexity of each growing area; based on the image detail evaluation index and the image smoothness, obtaining image enhancement effect quality evaluation, and adjusting a wavelet threshold value by combining the image detail evaluation index until the image enhancement effect quality evaluation is larger than a preset threshold value, and interpreting the enhanced image; the edge complexity of each growth area is determined specifically as follows: For each edge line in each growth area, the average angle difference value of tangent angles corresponding to the j-th pixel point on the edge line i and all the pixel points in the same edge line in the neighborhood range is recorded as The maximum angle difference value is recorded as ; The specific calculation method of the edge complexity is as follows: Wherein, the Representing the edge complexity of each growth region, S represents the number of edge lines in each growth region, Representing the number of pixels on the ith edge line, Representing the average absolute difference of the lengths of edge line i from the lengths of the other edge lines in the growth area, Represents the maximum value of the difference in length of the edge line i from other edge lines in the growth region, The normalization function is represented as a function of the normalization, Representing a preset value.
2. The geological remote sensing interpretation method of mineral resource exploration according to claim 1, wherein the preliminary enhancement is carried out by the following specific steps: Calculating the standard deviation of the gray value of each local area pixel point, and taking the average value of the standard deviations obtained in all local areas as the noise level of the image; the formula of the preset wavelet threshold value is as follows Wherein G is a preset wavelet threshold, Noise level for the image; the number of pixels of the image to be analyzed; a logarithmic function representing a base of a natural constant; and performing preliminary enhancement on the image to be analyzed by adopting a wavelet transformation image enhancement algorithm with a preset wavelet threshold.
3. The geological remote sensing interpretation method of mineral resource exploration according to claim 1, wherein the process of obtaining the smoothness of the image is as follows: The method comprises the steps of dividing gray levels of all pixel points of each local area, uniformly dividing the local area into a preset number of sub-areas in a central symmetrical mode by taking the geometric center of each local area as the center, analyzing the number difference of the pixel points of each gray level in different sub-areas in each local area, and determining the local area uniformity of each local area; And taking the average value of the uniformity of all the local areas in the image to be analyzed as the image smoothness.
4. A geological remote sensing interpretation method for mineral resource exploration as claimed in claim 3, characterized in that said determining the local area uniformity of each local area is: And for each local area, combining the divided subareas in pairs, calculating the pixel point quantity difference of each gray level in the combination, accumulating the quantity differences corresponding to all the gray levels, carrying out normalization processing, and taking the difference between the natural number 1 and the obtained normalization processing result as the local area uniformity of each local area.
5. The geological remote sensing interpretation method of mineral resource exploration according to claim 1, wherein the history complex texture features are obtained by the following steps: the average value of the absolute value of the difference value of the average edge complexity corresponding to each cluster in each historical standard sample image and other historical standard sample images is obtained, and normalization processing is carried out; Taking the difference value between the natural number 1 and the obtained normalization result as the historical complex texture characteristic of each cluster.
6. The geological remote sensing interpretation method of mineral resource exploration according to claim 1, wherein the specific acquisition process of the current complex texture features is as follows: And obtaining and normalizing the absolute value of the difference between the average edge complexity of all the growing areas belonging to each cluster in the image to be analyzed and the average edge complexity of all the growing areas belonging to each cluster in the historical standard sample image, and taking the difference between the natural number 1 and the obtained normalization result as the current complex texture characteristic of each cluster.
7. The geological remote sensing interpretation method of mineral resource exploration according to claim 1, wherein the specific process of determining the image detail evaluation index of the image to be analyzed is as follows: and obtaining the difference value between the current complex texture feature and the historical complex texture feature of each cluster, and averaging the difference values obtained by all the clusters to obtain an image detail evaluation index.
8. The geological remote sensing interpretation method of mineral resource exploration according to claim 2, wherein the specific process of obtaining the quality evaluation of the image enhancement effect and combining the image detail evaluation index to adjust the wavelet threshold is as follows: the specific formula of the image enhancement effect quality evaluation is as follows: Wherein, the An image enhancement effect quality evaluation is represented, The image detail evaluation index is represented by the image, The smoothness of the image is indicated and, Representing the noise level of the image, The normalization function is represented as a function of the normalization, Representing a preset value; if the image enhancement effect quality evaluation is larger than the preset threshold, the wavelet threshold is not adjusted, otherwise, if the image detail evaluation index is smaller than the preset detail history reference value, the method comprises the following steps: The wavelet threshold is reduced, wherein, The step length is preset; Representing the original wavelet threshold; representing the adjusted wavelet threshold; if the image detail evaluation index is greater than or equal to a preset detail history reference value, the method comprises the following steps of: the wavelet threshold is increased.
9. A geological remote interpretation system for mineral resource exploration, comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that the processor implements the steps of the method as claimed in any one of claims 1-8 when executing the computer program.

Description

Geological remote sensing interpretation method and system for mineral resource investigation Technical Field The application relates to the technical field of image data processing, in particular to a geological remote sensing interpretation method and system for mineral resource investigation. Background Traditional mineral exploration mainly depends on means such as ground geological survey, geophysical exploration, geochemical sampling and the like, and has the problems of long period, high cost, intensive manpower, large environmental disturbance and the like, although the precision is high. When a remote sensing technology is used for acquiring a survey target image, external factors such as vapor in the atmosphere, aerosol scattering and the like can cause random noise of a sensor and high-frequency ground surface background interference in the remote sensing imaging process, so that image details are fuzzy, and similar targets are difficult to distinguish effectively. Therefore, enhancement processing is required for the remote sensing image to improve the image quality. However, wavelet transform image enhancement algorithms typically employ a fixed threshold. For external disturbance factors which change at any time, the use of such fixed thresholds may not effectively cope with the changes, resulting in unexpected image enhancement effects, thereby increasing the difficulty of mineral resource exploration and interpretation based on these images. Disclosure of Invention In view of the foregoing, it is desirable to provide a geological remote sensing interpretation method and system for mineral resource exploration, which solve the above problems. The first aspect of the application provides a geological remote sensing interpretation method for mineral resource exploration, which comprises the following steps: Obtaining a geological remote sensing image to be analyzed of a mineral resource area to be surveyed; Dividing the acquired image to be analyzed according to a preset size, and primarily enhancing the gray value dispersion degree of the local area and the number of the pixels of the image based on the divided gray value dispersion degree; Obtaining LBP values of all pixel points in an image to be analyzed and a historical standard sample image, clustering, using a seed growing algorithm for the pixel points belonging to each cluster in each image to obtain each growing area of each image, analyzing the number and shape distribution characteristics of edges in each growing area to determine the edge complexity of each growing area; based on the image detail evaluation index and the image smoothness, obtaining image enhancement effect quality evaluation, and adjusting a wavelet threshold value by combining the image detail evaluation index until the image enhancement effect quality evaluation is larger than a preset threshold value, and interpreting the enhanced image; the edge complexity of each growth area is determined specifically as follows: For each edge line in each growth area, the average angle difference value of tangent angles corresponding to the j-th pixel point on the edge line i and all the pixel points in the same edge line in the neighborhood range is recorded as The maximum angle difference value is recorded as; The specific calculation method of the edge complexity is as follows: Wherein, the Representing the edge complexity of each growth region, S represents the number of edge lines in each growth region,Representing the number of pixels on the ith edge line,Representing the average absolute difference of the lengths of edge line i from the lengths of the other edge lines in the growth area,Represents the maximum value of the difference in length of the edge line i from other edge lines in the growth region,The normalization function is represented as a function of the normalization,Representing a preset value. Preferably, the preliminary reinforcement is performed by the following specific processes: Calculating the standard deviation of the gray value of each local area pixel point, and taking the average value of the standard deviations obtained in all local areas as the noise level of the image; the formula of the preset wavelet threshold value is as follows Wherein G is a preset wavelet threshold,Noise level for the image; the number of pixels of the image to be analyzed; a logarithmic function representing a base of a natural constant; and performing preliminary enhancement on the image to be analyzed by adopting a wavelet transformation image enhancement algorithm with a preset wavelet threshold. Preferably, the process of obtaining the image smoothness is as follows: The method comprises the steps of dividing gray levels of all pixel points of each local area, uniformly dividing the local area into a preset number of sub-areas in a central symmetrical mode by taking the geometric center of each local area as the center, analyzing the number difference of the pixe