Remote sensing surveying and mapping image intelligent processing method based on geological big data

Abstract

The invention provides a remote sensing surveying and mapping image intelligent processing method based on geological big data. The method is used for extracting hydrogeological features from a remote sensing surveying and mapping image more simply and accurately. The method comprises the steps that the electronic equipment acquires a remote sensing surveying and mapping image; the electronic equipment converts the remote sensing surveying and mapping image into a binary surveying and mapping image with the same size; the electronic equipment extracts a first hydrogeological feature from the binary surveying and mapping image, and the electronic equipment processes the remote sensing surveying and mapping image through a neural network model to obtain a second hydrogeological feature in the remote sensing surveying and mapping image output by the neural network model; and the electronic equipment fuses the first hydrogeological feature and the second hydrogeological feature to obtain a target hydrogeological feature in the remote sensing surveying and mapping image.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to an intelligent processing method for remote sensing mapping images based on geological big data. Background Technology

[0002] With the continuous development of science and technology, remote sensing technology has been widely applied in fields such as geography and geology. Remote sensing mapping image processing technology is a technique that acquires and processes image information of a target area using remote sensing equipment. Remote sensing mapping image processing technology has unique advantages in geological exploration and hydrogeological feature extraction.

[0003] First, remote sensing image processing technology can provide large-scale, high-precision surface information. Image data acquired through satellite remote sensing technology is characterized by wide coverage, good temporal continuity, and high resolution. These characteristics give remote sensing image processing technology significant advantages in geological exploration and hydrogeological feature extraction. Second, remote sensing image processing technology can effectively extract hydrogeological features. By performing image enhancement, image classification, and feature extraction on remote sensing images, hydrogeological feature information can be obtained. For example, multispectral analysis of remote sensing images can identify hydrogeological features such as water bodies and wetlands. Simultaneously, by performing texture analysis and spectral feature analysis on remote sensing images, hydrogeological features such as groundwater and rivers can be extracted. Finally, remote sensing image processing technology has high practicality and reliability in real-world applications. It has been widely used in geological exploration and hydrogeological feature extraction. For example, remote sensing image processing technology has played an important role in groundwater resource surveys, soil erosion monitoring, and geological disaster monitoring.

[0004] However, as can be seen from the above technology, its processing of remote sensing images is quite complex. Therefore, how to extract hydrogeological features from remote sensing images more simply and accurately is a current research problem. Summary of the Invention

[0005] This application provides an intelligent processing method for remote sensing images based on geological big data, which can extract hydrogeological features from remote sensing images more simply and accurately.

[0006] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, embodiments of this application provide an intelligent processing method for remote sensing mapping images based on geological big data. This method is applied to an electronic device and includes: the electronic device acquiring remote sensing mapping images; the electronic device converting the remote sensing mapping images into binary mapping images of the same size; the electronic device extracting a first hydrogeological feature from the binary mapping images; the electronic device processing the remote sensing mapping images through a neural network model to obtain a second hydrogeological feature in the remote sensing mapping images output by the neural network model; and the electronic device fusing the first hydrogeological feature and the second hydrogeological feature to obtain a target hydrogeological feature in the remote sensing mapping images.

[0007] Optionally, the electronic device extracts a first hydrogeological feature from the binarized survey image, and the electronic device processes the remote sensing image through a neural network model to obtain a second hydrogeological feature in the remote sensing image output by the neural network model. This includes: the electronic device extracts pixels with a pixel value of 0 from the binarized survey image to obtain a first set of pixels; the electronic device processes the remote sensing image through a neural network model to obtain a second set of pixels output by the neural network model; wherein, the coordinates of each pixel in the first set of pixels are the coordinates of that pixel in the binarized survey image, and the coordinates of each pixel in the first set of pixels constitute the first hydrogeological feature; wherein, each pixel in the second set of pixels is a pixel identified by the neural network model as belonging to hydrogeology, the coordinates of each pixel in the second set of pixels are the coordinates of that pixel in the binarized survey image, and the coordinates of each pixel in the second set of pixels constitute the second hydrogeological feature.

[0008] Optionally, the neural network model is a convolutional neural network model.

[0009] Optionally, the electronic device fuses the first hydrogeological feature with the second hydrogeological feature to obtain the target hydrogeological feature in the remote sensing image, including: the electronic device matches the pixel coordinates of the first pixel set and the second pixel set, and fuses the pixels in the second pixel set whose coordinates match those of the pixels in the first pixel set into the first pixel set to obtain the target pixel set, wherein the coordinates of each pixel in the target pixel set constitute the target hydrogeological feature.

[0010] Optionally, the electronic device matches the pixel coordinates of a first set of pixels with those of a second set of pixels, and merges pixels in the second set whose coordinates match those of pixels in the first set into the first set of pixels to obtain a target set of pixels. This includes: the electronic device matching the pixel coordinates of the first set of pixels with those of the second set of pixels to determine a set of pixels to be analyzed, wherein the pixels in the set of pixels to be analyzed are pixels in the second set whose coordinates are different from the coordinates of any pixel in the first set of pixels; the electronic device determines multiple pixels from the set of pixels to be analyzed whose coordinates are continuous and match those of pixels in the first set of pixels; and the electronic device adds the multiple pixels to the first set of pixels to obtain the target set of pixels.

[0011] Optionally, the electronic device determines multiple pixels from the set of pixels to be analyzed whose coordinates are continuous and match the coordinates of pixels in the first set of pixels, including: Step S1: The electronic device randomly selects a pixel to be analyzed from the set of pixels to be analyzed and determines whether there is a subset of pixels to be analyzed with continuous coordinates that contains the pixel to be analyzed; Step S2: If there is a subset of pixels to be analyzed with continuous coordinates that contains the pixel to be analyzed, the electronic device determines the minimum coordinate distance between the pixel to be analyzed and the pixels in the first set of pixels, and determines whether the minimum coordinate distance is less than a distance threshold; wherein, the minimum coordinate distance being less than the distance threshold indicates that the coordinates of the pixels in the subset of pixels to be analyzed match the coordinates of the pixels in the first set of pixels, that is, the subset of pixels to be analyzed needs to be added. The minimum coordinate spacing being greater than or equal to a distance threshold indicates that the coordinates of the pixels in the subset of pixels to be analyzed do not match those of the pixels in the first set of pixels, meaning the subset of pixels to be analyzed cannot be added to the first set of pixels. If there is no subset of pixels to be analyzed with consecutive coordinates that contains the pixels to be analyzed in the set of pixels to be analyzed, the electronic device will remove the pixels to be analyzed from the set of pixels to be analyzed, obtain an updated set of pixels to be analyzed, and then return to continue executing step S1 until the set of pixels to be analyzed is updated to have no pixels to be analyzed. Step S3: The electronic device will remove the subset of pixels to be analyzed from the set of pixels to be analyzed, obtain an updated set of pixels to be analyzed, and then return to continue executing step S1 until the set of pixels to be analyzed is updated to have no pixels to be analyzed.

[0012] Optionally, the electronic device fuses the first hydrogeological feature with the second hydrogeological feature to obtain the target hydrogeological feature in the remote sensing image, including: the electronic device maps the coordinates of each pixel in the first pixel set to a corresponding vector to obtain a first vector set, and maps the coordinates of each pixel in the second pixel set to a corresponding vector to obtain a second vector set; wherein, for any two vectors in the first or second vector set, the smaller the angle between the two vectors, the smaller the coordinate distance between the two corresponding pixels, and vice versa; the electronic device fuses the vectors in the second vector set that are spatially matched with the vectors in the first vector set into the first vector set through spatial matching of the vectors in the first vector set, to obtain a target vector set; the electronic device inversely maps each vector in the target vector set to a corresponding pixel to obtain a target pixel set, wherein the coordinates of each pixel in the target pixel set constitute the target hydrogeological feature.

[0013] Optionally, the electronic device performs spatial matching between vectors in the first vector set and vectors in the second vector set, and merges the vectors in the second vector set that spatially match the vectors in the first vector set into the first vector set to obtain a target vector set. This includes: the electronic device performing spatial matching between the first vector set and the second vector set to obtain a vector set to be analyzed, wherein the vectors in the vector set to be analyzed are vectors in the second vector set that are different from any vector in the first vector set; the electronic device determining multiple vectors from the vector set to be analyzed that are spatially continuous and whose spatial positions match the spatial positions of vectors in the first vector set; and the electronic device adding the multiple vectors to the first vector set to obtain the target vector set.

[0014] Optionally, the electronic device determines multiple vectors from the set of vectors to be analyzed that are spatially continuous and whose spatial positions match those of vectors in the first vector set, including: Step Sa: The electronic device randomly selects a vector to be analyzed from the set of vectors to be analyzed, and determines whether there is a spatially continuous subset of vectors in the set of vectors to be analyzed that contains the vector to be analyzed by analyzing the sum of adjacent vectors; Step Sb: If there is a spatially continuous subset of vectors in the set of vectors to be analyzed that contains the vector to be analyzed, the electronic device determines the maximum vector sum of the vector to be analyzed and the vectors in the first vector set, and determines whether the maximum vector sum is greater than a vector sum threshold; wherein, the maximum vector sum being greater than the vector sum threshold indicates that the vectors in the subset of vectors to be analyzed have a spatial match with the vectors in the first vector set, i.e., the vectors to be analyzed are spatially matched. The analysis vector subset needs to be added to the first vector set. The maximum vector sum being less than or equal to the vector sum threshold indicates that the vectors in the vector subset to be analyzed do not match the space of the vectors in the first vector set, that is, the vector subset to be analyzed cannot be added to the first vector set. If there is no spatially continuous vector subset to be analyzed that contains the vector to be analyzed in the vector set to be analyzed, the electronic device will delete the vector to be analyzed from the vector set to be analyzed, obtain an updated vector set to be analyzed, and then return to continue executing step Sa until the vector set to be analyzed is updated to have no vectors to be analyzed. Step Sc: The electronic device will delete the vector subset to be analyzed from the vector set to be analyzed, obtain an updated vector set to be analyzed, and then return to continue executing step Sa until the vector set to be analyzed is updated to have no vectors to be analyzed.

[0015] Secondly, embodiments of this application provide an intelligent processing device for remote sensing mapping images based on geological big data. This device is applied to an electronic device and is configured to: acquire remote sensing mapping images; convert the remote sensing mapping images into binary mapping images; extract a first hydrogeological feature from the binary mapping images; process the remote sensing mapping images through a neural network model to obtain a second hydrogeological feature in the remote sensing mapping images output by the neural network model; and combine the first hydrogeological feature with the second hydrogeological feature to obtain a target hydrogeological feature in the remote sensing mapping images.

[0016] Thirdly, embodiments of this application provide a computer-readable storage medium storing program code, which, when executed by the computer, performs the method described in the first aspect.

[0017] In summary, the above method and apparatus have the following technical effects: After converting remote sensing images into binarized survey images of the same size, the electronic device can first extract the first hydrogeological feature from the binarized survey image. Since the accuracy of the binarization extraction is not high enough, the electronic device can also process the remote sensing image through a neural network model to obtain the second hydrogeological feature in the remote sensing image. The first hydrogeological feature and the second hydrogeological feature are then fused to obtain a high-precision hydrogeological feature, such as the target hydrogeological feature. The processing relies only on binarization processing and neural network model. Compared with existing technologies, the process is simpler and consumes less computing power, thus achieving simpler and more accurate extraction of hydrogeological features from remote sensing images. Attached Figure Description

[0018] Figure 1 A flowchart illustrating the intelligent processing method for remote sensing mapping images based on geological big data provided in this application embodiment; Figure 2 A schematic diagram illustrating an application scenario of the intelligent image processing method for remote sensing mapping based on geological big data provided in this application embodiment; Figure 3 A schematic diagram illustrating the mapping relationship between pixels and vectors in the intelligent image processing method for remote sensing mapping based on geological big data provided in this application embodiment; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0020] Please see Figure 1 This application provides an intelligent processing method for remote sensing mapping images based on geological big data. The method is executed by an electronic device, and the process includes: S101, the electronic device acquires remote sensing images.

[0021] Electronic devices can be understood as terminals. A terminal can be a terminal with communication functions, or a chip or chip system installed in the terminal. This terminal device can also be called user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent, or user device. In the embodiments of this application, the terminal device can be a mobile phone, tablet computer, computer with wireless transceiver capabilities, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical care, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, vehicle-mounted terminal, RSU with terminal functions, etc.

[0022] In response to user input, electronic devices can remotely sense and map images. Alternatively, electronic devices can acquire remotely sensed images independently, such as from other devices or from a network; there are no specific limitations. Remotely sensed images can be survey images taken by satellites or drones over a specific area, and can be color images that include hydrogeological data such as rivers, wetlands, and lakes.

[0023] S102, the electronic device converts the remote sensing image into a binary image of the same size.

[0024] That is, electronic devices binarize remote sensing images, converting them into binarized survey images with the same resolution (i.e., the same number of pixels). For example, Figure 2 As shown, the binarization process is rather coarse. For a small number of areas in rivers, wetlands, and lakes where the water color differs from the majority of the area, these areas may be converted into pixels with a value of 255 pixels during binarization. Figure 2 If the black pixels are directly binarized and the image is measured, the accuracy will not be high. S103-S104 needs to be executed to improve the accuracy.

[0025] S103, the electronic device extracts the first hydrogeological feature from the binarized survey image, and the electronic device processes the remote sensing image through a neural network model to obtain the second hydrogeological feature in the remote sensing image output by the neural network model.

[0026] Electronic devices can extract pixels with a value of 0 from a binarized image (e.g., Figure 2 The white pixels (those belonging to hydrogeology) are used to obtain the first set of pixels.

[0027] In this context, the coordinates of each pixel in the first pixel set represent its coordinates within the binarized survey image. The coordinates of all pixels in the first pixel set constitute the first hydrogeological feature. The coordinate system of the binarized survey image corresponds to its resolution; for example, if the resolution of the binarized survey image is... That is, including There are 4 pixels, with x-coordinates ranging from 0 to 3480 and y-coordinates ranging from 0 to 2160. For example, pixel #1 has coordinates of (0,0), and the next pixel in the same row and adjacent to pixel #1, #2, has coordinates of (0,1), and so on. The coordinates are (3480, 2160).

[0028] Electronic devices can process remotely sensed images using a neural network model to obtain a set of second pixels output by the neural network model. The neural network model can be a convolutional neural network model.

[0029] In the second pixel set, each pixel is identified by the neural network model as belonging to the hydrogeological category. The coordinates of each pixel in the second pixel set are its coordinates in the binarized survey image. The specific principle is similar to that of the first pixel set; please refer to the reference for understanding, and it will not be repeated here. The coordinates of each pixel in the second pixel set constitute the second hydrogeological feature.

[0030] It is understandable that the coordinates of pixels in a binarized survey image and the coordinates of pixels in a remote sensing image belong to the same coordinate system. For example, the coordinates of the pixel at the bottom left corner in a binarized survey image and the pixel at the bottom left corner in a remote sensing image are both (0,0) in the coordinate system.

[0031] S104, the electronic device fuses the first hydrogeological feature with the second hydrogeological feature to obtain the target hydrogeological feature in the remote sensing image.

[0032] Method 1: Electronic devices can match the pixel coordinates of a first set of pixels with those of a second set of pixels, and then merge the pixels in the second set whose coordinates match those in the first set into the first set of pixels (i.e., supplementing missing pixels, such as pixels in a small number of areas whose water color differs from most areas), to obtain a more precise set of target pixels. The coordinates of each pixel in the target set constitute the target hydrogeological features. In other words, by restoring each pixel in the target set to its own coordinates in a binary survey image, the resulting pattern is the distribution pattern of the target hydrogeology.

[0033] Specifically, firstly, the electronic device matches the pixel coordinates of a first set of pixels with those of a second set of pixels to determine the set of pixels to be analyzed. Pixels in the set to be analyzed are those whose coordinates in the second set are different from the coordinates of any pixel in the first set. For example, if there is a pixel with coordinates (1, 10) in both the second and first sets, these two pixels have the same coordinates. Conversely, if no pixel with coordinates (1, 10) is found in the first set, it means that there is a pixel with coordinates (1, 10) in the second set that is different from the coordinates of any pixel in the first set, and thus belongs to the set of pixels to be analyzed.

[0034] Then, the electronic device determines multiple pixels from the set of pixels to be analyzed whose coordinates are continuous and match the coordinates of pixels in the first set of pixels, as follows: Step S1: The electronic device randomly selects a pixel to be analyzed from the set of pixels to be analyzed, and determines whether there is a subset of pixels to be analyzed that has continuous coordinates and contains the pixel to be analyzed.

[0035] Step S2: If there is a subset of pixels in the set of pixels to be analyzed that has continuous coordinates and contains the pixel to be analyzed, the electronic device determines the minimum coordinate distance between the pixel to be analyzed and the pixels in the first set of pixels, and determines whether the minimum coordinate distance is less than the distance threshold.

[0036] For example, if the pixel to be analyzed is pixel #A, and the coordinates of pixel #A are (11, 12) and the coordinates of pixel #B are (11, 13), then the coordinates are continuous. If the coordinates of pixel #A are (11, 12) and the coordinates of pixel #F are (13, 14), then the coordinates are not continuous. In other words, continuous coordinates mean that the values ​​of the horizontal or vertical coordinates are continuous. The electronic device determines all pixels whose coordinates are continuous with those of pixel #A. Then, for each of these pixels, the electronic device continues to analyze whether the coordinates of each pixel are continuous with other pixels (pixels that have not been analyzed before, such as excluding pixel #A when analyzing which pixels are continuous with those of pixel #B), until no pixels with continuous coordinates are found. These pixels with continuous coordinates constitute the subset of pixels to be analyzed. For example, if the coordinates of pixel #A and pixel #B are continuous, and the coordinates of pixel #B are continuous with those of pixel #C and pixel #D, and pixel #C and pixel #D have no other pixels whose coordinates are continuous with those of pixel #B, then the subset of pixels to be analyzed includes pixel #A, pixel #B, pixel #C, and pixel #D.

[0037] In this context, a minimum coordinate spacing less than a distance threshold (the specific value can be set according to actual conditions, such as 6 / 4 based on the granularity of the coordinate system (e.g., the coordinates of pixel #A are (11,12), and the coordinates of pixel #B are (11,13), with a coordinate spacing of 1) indicates that the coordinates of pixels in the subset of pixels to be analyzed match those of pixels in the first set of pixels, meaning the subset of pixels to be analyzed needs to be added to the first set of pixels. A minimum coordinate spacing greater than or equal to the distance threshold indicates that the coordinates of pixels in the subset of pixels to be analyzed do not match those of pixels in the first set of pixels, meaning the subset of pixels to be analyzed cannot be added to the first set of pixels. In other words, considering the continuity of hydrogeological trends, pixels whose positions are very close to those in the first set of pixels belong to the continuous part of the hydrogeological trend and can be considered as belonging to hydrogeological pixels; otherwise, they are pixels misidentified by the neural network model and do not belong to hydrogeological pixels.

[0038] If there is no subset of pixels to be analyzed that has continuous coordinates and contains the pixel to be analyzed, the electronic device will delete the pixel to be analyzed from the set of pixels to be analyzed, obtain an updated set of pixels to be analyzed, and then return to continue executing step S1 until the set of pixels to be analyzed is updated to have no pixels to be analyzed.

[0039] Step S3: The electronic device deletes the subset of pixels to be analyzed from the set of pixels to be analyzed, obtains an updated set of pixels to be analyzed, and then returns to continue executing step S1 until the set of pixels to be analyzed is updated to have no pixels to be analyzed, thus obtaining the aforementioned multiple pixels.

[0040] Finally, the electronic device can add these multiple pixels to the first pixel set to obtain the target pixel set.

[0041] Method 2: First, the electronic device can map the coordinates of each pixel in the first set of pixels to a corresponding vector, obtaining a first vector set, and then map the coordinates of each pixel in the second set of pixels to a corresponding vector, obtaining a second vector set. For example, one example of this mapping could be as follows: Figure 3 As shown, taking the first set of pixels as an example, the coordinate plane of the first set of pixels is mapped to a vector space. A reference point in the vector space is connected to the coordinate position of each pixel in the first set of pixels. The coordinate position pointed to by the reference point is the vector corresponding to that pixel. Based on Figure 3 It can also be seen that for any two vectors in the first or second vector set, the smaller the angle between the two vectors, the smaller the coordinate distance between the two corresponding pixels, and vice versa.

[0042] Then, the electronic device can perform spatial matching between vectors in the first vector set and vectors in the second vector set, and merge the vectors in the second vector set that spatially match the vectors in the first vector set into the first vector set to obtain the target vector set.

[0043] For example, an electronic device performs spatial matching between a first set of vectors and a second set of vectors to obtain a set of vectors to be analyzed. The vectors in this set are those that are different from any vector in the first set. Specifically, for two pixels with the same coordinates in both the first and second sets, the vectors mapped to these two pixels are the same vector, meaning they have the same direction and magnitude. Otherwise, two pixels with different coordinates are mapped to different vectors.

[0044] The electronic device determines, from the set of vectors to be analyzed, multiple vectors whose spatial positions are continuous and match the spatial positions of vectors in the first set of vectors, as follows: Step Sa: The electronic device randomly selects a vector to be analyzed from the set of vectors to be analyzed, and determines whether there is a spatially continuous subset of vectors containing the vector to be analyzed by analyzing the sum of adjacent vectors. For example, if the vector to be analyzed is vector #1, and vector #2 is located between vector #1 and vector #3, then vector #2 is the vector adjacent to vector #1 (i.e., the angle between them is the smallest). The electronic device can determine the sum of vector #1 and vector #2 (specifically, the size of the vector after addition). If the sum is less than a preset threshold, it means that the coordinates of the pixels mapped by vector #1 and vector #2 are not continuous; otherwise, the coordinates are continuous. For example, if vector #1 is adjacent to vector #2 and the sum of the vectors is less than the preset threshold, then vector #3, which is adjacent to vector #2, is determined. If vector #2 is adjacent to vector #3 and the sum of the vectors is less than the preset threshold, then vectors #4 and #5, which are adjacent to vector #3, are determined. If the sum of vector #3 with vector #4 and vector #5 is less than the preset threshold, then the subset of vectors to be analyzed is determined to include vector #1, vector #2, and vector #3.

[0045] Step Sb: If the set of vectors to be analyzed contains a spatially continuous subset of vectors that includes the vector to be analyzed, the electronic device determines the vector sum (specifically, the magnitude of the summed vector) of the vector to be analyzed and each vector in the first vector set, to determine the maximum vector sum and whether the maximum vector sum is greater than a vector sum threshold. A maximum vector sum greater than the threshold indicates that the vector in the subset of vectors to be analyzed has a spatial match with the vectors in the first vector set, meaning the subset of vectors to be analyzed needs to be added to the first vector set, and that the pixels corresponding to the subset belong to the continuous part of the hydrogeological trend. A maximum vector sum less than or equal to the threshold indicates that the vector in the subset of vectors to be analyzed does not have a spatial match with the vectors in the first vector set, meaning the subset of vectors to be analyzed cannot be added to the first vector set. If the set of vectors to be analyzed does not contain a spatially continuous subset of vectors that includes the vector to be analyzed, the electronic device deletes the vector to be analyzed from the set, obtains an updated set of vectors to be analyzed, and then returns to continue executing step Sa until the set of vectors to be analyzed is updated to have no vectors to be analyzed. Step Sc: The electronic device removes the subset of vectors to be analyzed from the set of vectors to be analyzed, obtaining an updated set of vectors to be analyzed, and then returns to continue executing step Sa until the set of vectors to be analyzed is updated to have no vectors to be analyzed.

[0046] The electronic device adds multiple vectors to the first vector set to obtain the target vector set.

[0047] Finally, the electronic device reverse maps each vector in the target vector set to a corresponding pixel (i.e., the reverse process of the above mapping) to obtain the target pixel set, where the coordinates of each pixel in the target pixel set constitute the target hydrogeological features.

[0048] In summary, after converting remote sensing images into binarized survey images of the same size, electronic devices can first extract the first hydrogeological feature from the binarized survey image. Since the accuracy of binarization extraction is not high enough, the electronic devices can also process the remote sensing images through a neural network model to obtain the second hydrogeological feature in the remote sensing images. The first and second hydrogeological features are then fused to obtain a high-precision hydrogeological feature, such as the target hydrogeological feature. The processing relies only on binarization and neural network models. Compared with existing technologies, the process is simpler and consumes less computing power, thus achieving simpler and more accurate extraction of hydrogeological features from remote sensing images.

[0049] The above combination Figure 2 The methods provided in the embodiments of this application are described in detail. The following describes an intelligent processing device for remote sensing mapping images based on geological big data, used to perform the methods provided in the embodiments of this application. This device is applied to an electronic device and is configured to: acquire remote sensing mapping images; convert the remote sensing mapping images into binary mapping images; extract a first hydrogeological feature from the binary mapping images; process the remote sensing mapping images through a neural network model to obtain a second hydrogeological feature in the remote sensing mapping images output by the neural network model; and combine the first hydrogeological feature with the second hydrogeological feature to obtain a target hydrogeological feature in the remote sensing mapping images. For details, please refer to the above method; further elaboration is not provided here.

[0050] The following is combined Figure 4 A detailed introduction to each component of the electronic device 500 is provided below: The processor 501 is the control center of the electronic device 500. It can be a single processor or a collective term for multiple processing elements. For example, the processor 501 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement the embodiments of this application, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0051] Optionally, the processor 501 can perform various functions of the electronic device 500, as described above, by running or executing software programs stored in the memory 502 and by calling data stored in the memory 502. Figure 1 The functions in the method shown.

[0052] In a specific implementation, as one example, the processor 501 may include one or more CPUs, for example... Figure 4 CPU0 and CPU1 are shown in the diagram.

[0053] In a specific implementation, as one example, the electronic device 500 may also include multiple processors. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, a processor may refer to one or more devices, circuits, and / or processing cores used for processing data (e.g., computer program instructions).

[0054] The memory 502 is used to store the software program that executes the solution of this application, and is controlled by the processor 501 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0055] Optionally, memory 502 may be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, such as random access memory (RAM) or... Other types of dynamic storage devices capable of storing information and instructions may also include electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed discs, laser discs, optical discs, universal digital discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium capable of carrying or storing desired program code having an instruction or data structure form and accessible by a computer, but not limited thereto. Memory 502 may be integrated with processor 501 or exist independently, and is related to electronic device 500. Interface circuit ( Figure 4 (Not shown in the image) is coupled to processor 501, and this embodiment does not specifically limit this.

[0056] Transceiver 503 is used for communication with other devices. For example, in a multi-beam positioning device as a terminal, transceiver 503 can be used to communicate with network devices or with another terminal.

[0057] Alternatively, transceiver 503 may include a receiver and a transmitter. Figure 4 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0058] Optionally, the transceiver 503 can be integrated with the processor 501, or it can exist independently and be connected via the interface circuit of the electronic device 500. Figure 4 (Not shown in the image) is coupled to processor 501, and this embodiment does not specifically limit this.

[0059] It should be noted that, Figure 4 The structure of the electronic device 500 shown does not constitute a limitation on the device. The actual electronic device 500 may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0060] Furthermore, the technical effects of the electronic device 500 can be referred to the technical effects of the methods in the above method embodiments, and will not be repeated here.

[0061] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A geological big data based remote sensing mapping image intelligent processing method, characterized in that, The method is applied to an electronic device, and the method comprises: The electronic device acquires a remote sensing survey image; The electronic device converts the remote sensing survey image into a binary survey image of the same size; The electronic device extracts a first hydrogeological feature from the binary survey image, and the electronic device processes the remote sensing survey image through a neural network model to obtain a second hydrogeological feature in the remote sensing survey image output by the neural network model; The electronic device fuses the first hydrogeological feature and the second hydrogeological feature to obtain a target hydrogeological feature in the remote sensing survey image.

2. The method of claim 1, wherein, The electronic device extracts a first hydrogeological feature from the binary survey image, and the electronic device processes the remote sensing survey image through a neural network model to obtain a second hydrogeological feature in the remote sensing survey image output by the neural network model, comprising: The electronic device extracts pixel points with a pixel value of 0 in the binary survey image to obtain a first pixel point set; The electronic device processes the remote sensing survey image through the neural network model to obtain a second pixel point set output by the neural network model; The coordinates of each pixel point in the first pixel point set are the coordinates of the pixel point in the binary survey image, and the coordinates of the pixel points in the first pixel point set constitute the first hydrogeological feature; The coordinates of each pixel point in the second pixel point set are the coordinates of the pixel point in the binary survey image, and the coordinates of the pixel points in the second pixel point set constitute the second hydrogeological feature.

3. The method of claim 2, wherein, The neural network model is a convolutional neural network model.

4. The method according to claim 2 or 3, characterized in that, The electronic device fuses the first hydrogeological feature and the second hydrogeological feature to obtain a target hydrogeological feature in the remote sensing survey image, comprising: The electronic device matches the pixel point coordinates of the first pixel point set and the second pixel point set, fuses the pixel points in the second pixel point set that match the coordinates of the pixel points in the first pixel point set into the first pixel point set, to obtain a target pixel point set, and the coordinates of the pixel points in the target pixel point set constitute the target hydrogeological feature.

5. The method of claim 4, wherein, The electronic device matches the pixel point coordinates of the first pixel point set and the second pixel point set, fuses the pixel points in the second pixel point set that match the coordinates of the pixel points in the first pixel point set into the first pixel point set, to obtain a target pixel point set, comprising: The electronic device matches the pixel point coordinates of the first pixel point set and the second pixel point set, determines a to-be-analyzed pixel point set, and the pixel points in the to-be-analyzed pixel point set are pixel points in the second pixel point set that have different coordinates from any pixel point in the first pixel point set; The electronic device determines a plurality of pixel points with continuous coordinates and matching coordinates of pixel points in the first pixel point set from the pixel point set to be analyzed. The electronic device adds the plurality of pixel points to the first pixel point set to obtain the target pixel point set.

6. The method of claim 5, wherein, The electronic device determines a plurality of pixel points with continuous coordinates and matching coordinates of pixel points in the first pixel point set from the pixel point set to be analyzed. Step S1: The electronic device selects a pixel point to be analyzed from the pixel point set to be analyzed, and determines whether there is a pixel point subset to be analyzed with continuous coordinates and containing the pixel point to be analyzed in the pixel point set to be analyzed. Step S2: If there is a pixel point subset to be analyzed with continuous coordinates and containing the pixel point to be analyzed in the pixel point set to be analyzed, the electronic device determines the minimum coordinate distance between the pixel point to be analyzed and the pixel points in the first pixel point set, and determines whether the minimum coordinate distance is less than a distance threshold. Wherein, if the minimum coordinate distance is less than the distance threshold, it means that the coordinates of the pixel points in the pixel point subset to be analyzed match the coordinates of the pixel points in the first pixel point set, that is, the pixel point subset to be analyzed needs to be added to the first pixel point set, and if the minimum coordinate distance is greater than or equal to the distance threshold, it means that the coordinates of the pixel points in the pixel point subset to be analyzed do not match the coordinates of the pixel points in the first pixel point set, that is, the pixel point subset to be analyzed cannot be added to the first pixel point set. Wherein, if there is no pixel point subset to be analyzed with continuous coordinates and containing the pixel point to be analyzed in the pixel point set to be analyzed, the electronic device deletes the pixel point to be analyzed from the pixel point set to be analyzed to obtain an updated pixel point set to be analyzed, and then returns to continue executing the step S1 until the pixel point set to be analyzed is updated to have no pixel point to be analyzed. Step S3: The electronic device deletes the pixel point subset to be analyzed from the pixel point set to be analyzed to obtain an updated pixel point set to be analyzed, and then returns to continue executing the step S1 until the pixel point set to be analyzed is updated to have no pixel point to be analyzed.

7. The method of claim 2 or 3, wherein, The electronic device fuses the first hydrogeological feature and the second hydrogeological feature to obtain a target hydrogeological feature in the remote sensing mapping image, comprising: The electronic device maps the coordinates of each pixel point in the first pixel point set into a corresponding vector to obtain a first vector set, and maps the coordinates of each pixel point in the second pixel point set into a corresponding vector to obtain a second vector set. Wherein, for any two vectors in the first vector set or the second vector set, if the included angle between the two vectors is smaller, the coordinate distance between the two pixel points corresponding to the two vectors is smaller, and vice versa. The electronic device fuses the vectors in the second vector set that are spatially matched with the vectors in the first vector set into the first vector set, to obtain a target vector set, by spatial matching of the vectors in the first vector set with the vectors in the second vector set. The electronic device inversely maps each vector in the target vector set into a corresponding pixel point, to obtain a target pixel point set, wherein the coordinates of the pixel points in the target pixel point set constitute the target hydrogeological feature.

8. The method of claim 7, wherein, The electronic device fuses the vectors in the second vector set that are spatially matched with the vectors in the first vector set into the first vector set, to obtain a target vector set, by spatial matching of the vectors in the first vector set with the vectors in the second vector set. The electronic device performs spatial matching on the first vector set and the second vector set, to obtain a to-be-analyzed vector set, wherein the vectors in the to-be-analyzed vector set are vectors in the second vector set that are different from any vector in the first vector set. The electronic device determines a plurality of vectors from the to-be-analyzed vector set, wherein the plurality of vectors are spatially continuous and spatially matched with the vectors in the first vector set. The electronic device adds the plurality of vectors to the first vector set, to obtain the target vector set.

9. The method of claim 8, wherein, The electronic device determines a plurality of vectors from the to-be-analyzed vector set, wherein the plurality of vectors are spatially continuous and spatially matched with the vectors in the first vector set, including: Step Sa: The electronic device selects a to-be-analyzed vector from the to-be-analyzed vector set, and determines whether there is a to-be-analyzed vector subset in the to-be-analyzed vector set that is spatially continuous and contains the to-be-analyzed vector, by analyzing the sum of adjacent vectors; Step Sb: If there is a to-be-analyzed vector subset in the to-be-analyzed vector set that is spatially continuous and contains the to-be-analyzed vector, the electronic device determines the maximum vector sum of the to-be-analyzed vector and the vectors in the first vector set, and determines whether the maximum vector sum is greater than a vector sum threshold; wherein the maximum vector sum greater than the vector sum threshold indicates that the vectors in the to-be-analyzed vector subset are spatially matched with the vectors in the first vector set, i.e., the to-be-analyzed vector subset needs to be added to the first vector set, and the maximum vector sum less than or equal to the vector sum threshold indicates that the vectors in the to-be-analyzed vector subset are not spatially matched with the vectors in the first vector set, i.e., the to-be-analyzed vector subset cannot be added to the first vector set; wherein if there is no to-be-analyzed vector subset in the to-be-analyzed vector set that is spatially continuous and contains the to-be-analyzed vector, the electronic device deletes the to-be-analyzed vector from the to-be-analyzed vector set, to obtain an updated to-be-analyzed vector set, and then returns to continue executing the step Sa until the to-be-analyzed vector set is updated to have no to-be-analyzed vector; Step Sc: the electronic device deletes the subset of vectors to be analyzed from the set of vectors to be analyzed, obtains an updated set of vectors to be analyzed, and then returns to continue executing the step Sa until the set of vectors to be analyzed is updated to have no vectors to be analyzed.

10. A geological big data-based remote sensing mapping image intelligent processing device, characterized in that, The device is applied to an electronic device, and the device is configured to: obtain a remote sensing survey image; convert the remote sensing survey image into a binary survey image; extract a first hydrogeological feature from the binary survey image, and process the remote sensing survey image through a neural network model to obtain a second hydrogeological feature in the remote sensing survey image output by the neural network model; obtain a target hydrogeological feature in the remote sensing survey image by combining the first hydrogeological feature and the second hydrogeological feature.

Images