Geological analysis method and device for water terrain based on remote sensing technology

Abstract

The present invention discloses a method and device for geological analysis of water terrain based on remote sensing technology. The method comprises: collecting a water image set consisting of multiple water images detected by a remote sensing detection terminal, the water image set being used to prepare a training set for a water analysis model; extracting the target water image from the multiple water images when it is determined that a target water image has a water area occupancy rate higher than an occupancy rate threshold among the multiple water images; reducing the occupancy rate of the water area of ​​the target water image according to a preset rule so that the occupancy rate of the water area of ​​the target water image is no higher than the occupancy rate threshold; inputting the water image set after the rate reduction process into a preset neural network for training to obtain a water analysis model, and analyzing the geology of the water terrain using the water analysis model. The present invention solves the problem of low accuracy in geological analysis of water terrain in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of geological surveying and mapping, and in particular to a geological analysis method and device for water terrain based on remote sensing technology. Background Art

[0002] With the development of remote sensing technology, a large number of sensors such as optical, thermal infrared and microwave have been widely used in geological analysis. Specifically, by obtaining remote sensing image data in the same area and performing computational processing, a real-life image of the area is obtained, and the corresponding geological data of the area is obtained by analyzing the real-life image.

[0003] At present, the methods for analyzing real-scene images mainly include manual analysis and computer intelligent analysis. Specifically, manual analysis mainly involves relevant geological professionals visually observing real-scene images to obtain corresponding geological data, while computer intelligent analysis mainly uses a specifically trained geological analysis model to input the acquired real-scene images into the corresponding geological analysis model to obtain the corresponding geological data. Due to the advantages of high efficiency and accuracy of the model analysis method, the analysis model method is widely used in the analysis of geological data.

[0004] However, in the existing technology, geological analysis models share a common model for analysis, that is, the same model is used to analyze and identify geological data of different terrains such as plains, valleys and hills. In order to improve accuracy, one-to-one models are now often used for analysis. For example, a specifically trained water area analysis model is used to analyze the geology of water area terrain, where the water area terrain is a terrain with a relatively high proportion of water in the current area. When the water area analysis model is trained, there will be a situation where the proportion of water area in the collected real-life image is too high, resulting in fewer other geological features in the real-life image, which leads to the model's poor recognition ability of other features, and ultimately leads to the problem of low accuracy of geological analysis. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method and device for geological analysis of water terrain based on remote sensing technology, aiming to solve the problem of inaccurate geological analysis of water terrain in the prior art.

[0006] The present invention is achieved in that:

[0007] A geological analysis method for water body topography based on remote sensing technology, comprising:

[0008] Collecting a water area image set consisting of multiple water area images detected by a remote sensing detection terminal, wherein the water area image set is used to prepare a training set for a water area analysis model;

[0009] determining whether there is a target water area image with a water area occupancy rate higher than an occupancy rate threshold among the multiple water area images;

[0010] When it is determined that a target water area image with a water area occupancy rate higher than an occupancy rate threshold exists among the multiple water area images, extracting the target water area image from the multiple water area images;

[0011] performing a rate reduction process on the occupancy rate of the water area of ​​the target water area image according to a preset rule, so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold;

[0012] The water area image set after the rate reduction process is input into a preset neural network for training to obtain the water area analysis model, so as to analyze the geology of the water area terrain through the water area analysis model.

[0013] Furthermore, in the above-mentioned geological analysis method of water area terrain based on remote sensing technology, the step of reducing the encroachment rate of the water area of ​​the target water area image according to a preset rule so that the encroachment rate of the water area of ​​the target water area image is not higher than the encroachment rate threshold comprises:

[0014] Dividing the target water area image into a plurality of preset equally divided sub-areas according to a preset rule, and extracting a target sub-area that does not contain the water area from the plurality of sub-areas;

[0015] Other sub-regions in the target water area image that are all water areas are randomly removed, and the target sub-region is filled with the removed other sub-regions so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0016] Furthermore, in the above-mentioned geological analysis method of water area terrain based on remote sensing technology, the step of reducing the encroachment rate of the water area of ​​the target water area image according to a preset rule so that the encroachment rate of the water area of ​​the target water area image is not higher than the encroachment rate threshold further includes:

[0017] performing grayscale and binarization processing on the target water area image in sequence to obtain a binarized image of the target water area image;

[0018] The binary image is processed to determine the replenishment amount of the non-water area, and the non-water area is replenished according to the replenishment amount of the non-water area so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0019] Furthermore, in the above-mentioned geological analysis method of water terrain based on remote sensing technology, the steps of processing the binary image to determine the recharge amount of the non-water area, and recharging the non-water area according to the recharge amount of the non-water area so that the encroachment rate of the water area of ​​the target water area image is not higher than the encroachment rate threshold include:

[0020] Determining a target non-water area for replenishment from the non-water area, and determining an outer contour of the target non-water area;

[0021] The extension amount of the target non-water area is determined according to the replenishment amount of the non-water area and the outer contour of the target non-water area, and the target non-water area is extended outward by the extension amount so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0022] Furthermore, in the above-mentioned geological analysis method of water area terrain based on remote sensing technology, the step of dividing the target water area image into a plurality of pre-set equally divided sub-regions according to a preset rule, and extracting the target sub-region that does not contain water area from the plurality of sub-regions comprises:

[0023] Taking any vertex in the target water area image as the coordinate origin, mapping the target water area image into a preset coordinate system;

[0024] The target water area image is divided into a plurality of sub-areas by dividing the target water area image in a horizontal and vertical manner.

[0025] Furthermore, in the above-mentioned geological analysis method of water area terrain based on remote sensing technology, after the step of dividing the target water area image into a plurality of sub-areas by dividing the target water area image into horizontal and vertical segments respectively, the method further includes:

[0026] Determine the center point of the target sub-region and use it as a radiation radius to determine the respective filling areas of the target sub-region;

[0027] Other sub-regions that are all water areas in the respective filling areas of the target sub-regions are randomly removed, and then the target sub-regions are filled with the removed other sub-regions so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0028] Furthermore, the above-mentioned geological analysis method of water area topography based on remote sensing technology further comprises:

[0029] Grayscale and binarization processing are sequentially performed on the water area image, and a black-white pixel ratio of the water area image after the grayscale and binarization processing is obtained to determine the occupancy rate of the water area in the water area image.

[0030] Another aspect of the present invention provides a geological analysis device for water terrain based on remote sensing technology, the device comprising:

[0031] An acquisition module is used to acquire a water area image set consisting of multiple water area images detected by a remote sensing detection terminal, wherein the water area image set is used to prepare a training set for a water area analysis model;

[0032] A judgment module, configured to judge whether there is a target water area image with a water area occupancy rate higher than an occupancy rate threshold among the plurality of water area images;

[0033] an extraction module configured to extract the target water area image from the multiple water area images when it is determined that there is a target water area image with a water area occupancy rate higher than an occupancy rate threshold among the multiple water area images;

[0034] a rate reduction module, configured to perform a rate reduction process on the occupancy rate of the water area of ​​the target water area image according to a preset rule, so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold;

[0035] The analysis module is used to input the water area image set after rate reduction processing into a preset neural network for training to obtain the water area analysis model, so as to analyze the geology of the water area terrain through the water area analysis model.

[0036] Another object of the present invention is to provide a readable storage medium having a computer program stored thereon, wherein the program implements the steps of the above method when executed by a processor.

[0037] Another object of the present invention is to provide an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the above method are implemented when the processor executes the program.

[0038] The present invention collects a water area image set consisting of multiple water area images detected by a remote sensing detection terminal, and adjusts the water area occupancy rate of the water area image to ensure that the water area characteristics are equivalent to other characteristics, thereby ensuring the quality of the data set and further improving the accuracy of model training, solving the problem of inaccurate geological analysis due to poor model training accuracy in the existing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flow chart of a method for geological analysis of water terrain based on remote sensing technology provided in a first embodiment of the present invention;

[0040] Figure 2A schematic diagram of the division of sub-regions in the first method of geological analysis of water terrain based on remote sensing technology provided by an embodiment of the present invention;

[0041] Figure 3 Schematic diagram of the second sub-region division in the geological analysis method of water terrain based on remote sensing technology provided by one embodiment of the present invention

[0042] Figure 4 A schematic diagram of the division of sub-regions according to the third method of geological analysis of water terrain based on remote sensing technology provided by an embodiment of the present invention;

[0043] Figure 5 A schematic diagram of the extension of a target sub-region in a geological analysis method for water terrain based on remote sensing technology provided by an embodiment of the present invention;

[0044] Figure 6 This is a structural block diagram of a geological analysis device for water terrain based on remote sensing technology provided in the fourth embodiment of the present invention.

[0045] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0046] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0047] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed types.

[0049] The following will describe in detail how to improve the accuracy of geological analysis of water terrain with reference to specific embodiments and accompanying drawings.

[0050] Example 1

[0051] See also Figure 1 , shown is a geological analysis method of water terrain based on remote sensing technology in the first embodiment of the present invention, and the method includes steps S10 to S14.

[0052] Step S10 , collecting a water area image set consisting of a plurality of water area images detected by a remote sensing detection terminal, wherein the water area image set is used to prepare a training set for a water area analysis model.

[0053] The remote sensing detection terminal is mainly used to detect remote sensing data of the water area image acquisition area, thereby imaging the area based on the detected remote sensing data to obtain a water area image containing a real-life image of the area. Specifically, the remote sensing detection terminal includes but is not limited to detection satellites and drones with remote sensing detection functions. In this embodiment, multiple water terrains are mainly detected to obtain a water image set suitable for model training, consisting of multiple water images of different water terrains, so as to prepare a training set for the water analysis model. More specifically, in practice, to facilitate the classification of geological analysis and improve the accuracy of geological analysis, the geology of different terrains will be analyzed using different trained models. For example, the geology of terrain rich in water areas will be analyzed using a pre-trained water analysis model. Specifically, areas in the collected image where the proportion of water areas is higher than a set ratio, such as 50%, are classified as water terrain. That is, when the water area in the image is higher than 50%, the geological data in the image is analyzed using the water analysis model. In specific implementation, the set ratio can be set according to actual conditions, such as 50%, 55%, and 60%, etc., and is not limited here.

[0054] Step S11 , determining whether there is a target water area image with a water area occupancy rate higher than an occupancy rate threshold among the multiple water area images.

[0055] Among them, the water area occupancy rate is the percentage of the area of ​​the water area in the water area image after the detected water terrain is imaged to the area of ​​the water area image. In practice, the water terrain may have a situation where the current water area occupies a large proportion, that is, the water area occupancy rate is higher than the occupancy rate threshold. Among them, the occupancy rate threshold can be set according to the actual situation, and the purpose of setting the occupancy rate threshold is to find the target water image with more water area in the water image, so that the water area in the target water image can be reduced to ensure that the water characteristics in the target water image are equivalent to the geological characteristics of other areas. In specific implementation, the water area occupancy rate threshold can be set to 55%, 60% and 65%, etc. For example, a large lake or sea area, the terrain is mainly water and other exposed geology in the water, such as some islands in the sea area. In actual detection, a larger range is generally detected, in which a water map will appear. The water area in the image is relatively wide, and the embodiment of the present invention mainly analyzes the geology of this type of terrain. When performing geological analysis of water terrain, the geology of other areas in the water image except the water area is mainly analyzed. When this type of water image is used for model training, since it contains fewer features of other areas, the trained model will have poor ability to identify the area, which will in turn affect the model analysis effect. Therefore, it is necessary to perform corresponding processing on the target water image detected by the terrain to ensure the training effect of the model. It should be noted that in the embodiment of the present invention, it is first determined whether the currently detected area is water terrain based on the proportion of water in the detected image, and then it is determined whether the image needs to be processed to reduce the corresponding water area (increase other areas) based on the water occupancy rate in the water image to obtain a high-quality geological analysis model training set for water terrain, thereby ensuring the training effect of the geological analysis model for training water terrain.

[0056] Furthermore, in some optional embodiments of the present invention, the method further includes:

[0057] Grayscale and binarization processing are sequentially performed on the water area image, and a black-white pixel ratio of the water area image after the grayscale and binarization processing is obtained to determine the occupancy rate of the water area in the water area image.

[0058] Specifically, the proportion of the relevant area in the water area image is determined by grayscale and binarization processing the water area image in sequence, wherein the water area image after binarization processing can make the water area appear white and other areas appear black, and the proportion of the relevant area is determined based on the ratio of black and white pixels. When this embodiment is implemented, the binary image processing and the area calculation in the binary image can be performed by Matlab tools. In addition, in some optional embodiments of the present invention, the area of ​​other geological areas in the non-water area can be obtained by calculating the area of ​​the connected domain to determine the area proportion of the water area in the water area image, thereby determining the occupancy rate of the water area.

[0059] Step S12 : when it is determined that a target water area image exists among the plurality of water area images, the target water area image is extracted from the plurality of water area images.

[0060] Specifically, since when facing water terrain, the main focus is on data analysis of the geology of other areas of the water terrain, the feature quantities of other features in the water terrain should be guaranteed as much as possible. Therefore, when conducting model training, in order to ensure the effect of model training and the ability of the trained model to recognize features, when making a data set for model training, the water features in a water image should be guaranteed to be equivalent to other geological features as much as possible, or too many water features in the water image should be avoided as much as possible. Among them, when the water area occupancy rate in the water image used for training set production is high, the target water image is extracted from the water image set to perform corresponding processing on the target water image to improve the quality of the water analysis model training set.

[0061] Step S13 , reducing the occupancy rate of the water area of ​​the target water area image according to a preset rule, so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0062] Specifically, the occupancy rate of the water area of ​​the target water image is reduced to ensure that the occupancy rate of the water area of ​​the target water image is not higher than the occupancy rate threshold. When the occupancy rate of the water area is higher than the occupancy rate threshold, there will be fewer other features in the water image. Therefore, in order to ensure the feature quantity of other features in the water image, it is only necessary to ensure that the occupancy rate of the water area is not higher than the occupancy rate threshold.

[0063] In addition, in some optional embodiments of the present invention, a reasonable range can be set to limit the reduction rate of the occupancy rate reduction processing, that is, to ensure that the occupancy rate of the water area of ​​the target water image is within a reasonable range, for example, to ensure that the area of ​​the water area in the target water image is between 50% and 55%, that is, to ensure that the water features in a target water image are equivalent to other features.

[0064] In step S14, the water area image set after the rate reduction process is input into a preset neural network for training to obtain the water area analysis model, so as to identify the geology of the water area terrain through the water area analysis model.

[0065] Among them, the water area analysis model obtained by inputting the water area image set after feature equalization adjustment into the preset neural network for training is more accurate than the water area analysis model obtained by training the unprocessed water area image set. Specifically, the selection of the preset neural network and the corresponding training process are known to those skilled in the art and will not be described here. For example, a deep learning platform is constructed based on a convolutional neural network for model training, wherein the neural network model includes but is not limited to CNN, UNet and ResNet, etc. In some optional embodiments of the present invention, the size of the training set image can also be adjusted according to the requirements of model training, for example, the size of the training set image is adjusted to a uniform preset size.

[0066] In summary, the geological analysis method of water terrain based on remote sensing technology in the above-mentioned embodiment of the present invention collects a water image set consisting of multiple water images detected by a remote sensing detection terminal, and adjusts the water area occupancy rate of the water image to ensure that the water characteristics are equivalent to other characteristics, thereby ensuring the quality of the data set, and then improving the accuracy of model training, solving the problem of inaccurate geological analysis due to poor model training accuracy in the existing technology.

[0067] Example 2

[0068] The second embodiment of the present invention also proposes a geological analysis method for water terrain based on remote sensing technology. The geological analysis method for water terrain based on remote sensing technology in this embodiment differs from the geological analysis method for water terrain based on remote sensing technology in the first embodiment in that:

[0069] Step S13 includes:

[0070] Dividing the target water area image into a plurality of preset equally divided sub-areas according to a preset rule, and extracting a target sub-area that does not contain the water area from the plurality of sub-areas;

[0071] Other sub-regions in the target water area image that are all water areas are randomly removed, and the target sub-region is filled with the removed other sub-regions so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0072] Specifically, by dividing the target water area image into a plurality of sub-areas of preset equal divisions, the partial area that does not contain water can be filled into the partial area that contains water by filling, so that the occupancy rate of the water area is not higher than the occupancy rate threshold and is within a reasonable range. In specific implementation, the number of target sub-areas that need to be filled can also be determined based on the value of the preset equal division and the occupancy rate of the current water area. Specifically, by obtaining the occupancy rate of the water area, the corresponding occupancy rate that needs to be reduced is determined, and the occupancy rate is reflected by the area, so that the area that needs to be filled can be determined, and then the number of sub-areas that need to be filled is determined according to the area of ​​a single sub-area, so as to ensure that the partial area that contains water is accurately filled. In specific implementation, in order to improve the accuracy of filling and facilitate filling, the target water area image can be divided into as many sub-areas as possible.

[0073] In some optional embodiments of the present invention, the step of dividing the target water area image into a plurality of pre-set equally divided sub-areas according to a preset rule includes:

[0074] Taking any vertex in the target water area image as the coordinate origin, mapping the target water area image into a preset coordinate system;

[0075] The target water area image is divided into a plurality of sub-areas by dividing the target water area image in a horizontal and vertical manner.

[0076] Specifically, the target water area image is first mapped to a preset coordinate system, and the target water area image is divided into a plurality of preset equally divided sub-areas by horizontal and vertical segmentation, so that the position information of each sub-area can be accurately known, so that accurate filling can be performed according to the position information of the sub-area. After segmentation, Figure 2 As shown, there will be sub-regions that are entirely water, sub-regions that are partially water and partially non-water, and region A that is entirely non-water. Therefore, sub-regions S1, S2, and S3 that are entirely water can be replaced by target sub-regions that do not contain water, thereby ensuring that the water features in a target water image are equivalent to other features.

[0077] Furthermore, in some optional embodiments of the present invention, in order to further improve the authenticity of the features of the dataset for model training and remove the influence of the shape factors of other geological features, in some preferred embodiments of the present invention, such as Figure 3 As shown, when randomly filling other sub-areas after segmentation, the outer contour of the connected area A that does not contain the water area is determined, and the reference rectangle D containing the outer contour is determined based on this, so that the connected area that does not contain the water area can be scaled according to the ratio value of the reference rectangle D and the equally divided sub-area, and then the contour points a, b, c, d and e of the outer contour are determined, and the contour points are filled to any vertex of the sub-area that needs to be filled as a filling reference, and then the scaled connected area that does not contain the water area is filled to other sub-areas according to the filling reference, wherein, when selecting the outer contour point as the filling point, one of the outer contour points can be randomly selected as the reference for any vertex of the sub-area that needs to be filled, or the outer contour points can be numbered and filled in the vertices of different sub-areas in the order of the numbers.

[0078] In addition, in some optional embodiments of the present invention, after the step of dividing the target water area image into a plurality of sub-areas by dividing the target water area image horizontally and vertically, the step further includes:

[0079] Determine the center point of the target sub-region and determine the respective filling areas of the target sub-region with a preset radiation radius;

[0080] Other sub-regions that are all water areas in the respective filling areas of the target sub-regions are randomly removed, and then the target sub-regions are filled with the removed other sub-regions so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0081] Specifically, the center point of the target sub-area is determined, and the respective filling areas are determined based on the target sub-area, so that the target sub-area is filled into the respective filling areas, thereby ensuring that the geological characteristics of the filling are as close as possible to the characteristics of the filling area itself without much deviation, and the extensiveness of the feature acquisition. The preset radiation radius can be set manually or according to the area of ​​the target water area. For example, when the water area is large, the radiation radius is small. Since there are fewer areas to be filled, a smaller radiation radius is set to ensure feature concentration. More specifically, as Figure 4 As shown, the target image includes two areas B and C that do not include water areas, and respective filling areas B' and C' of the areas B and C are determined, and the target areas Q1 and Q2 are filled in the respective filling areas B' and C'.

[0082] In addition, in some optional embodiments of the present invention, the standard radiation radius of other geological areas corresponding to different areas that need to be filled can be determined based on experience or historical data. In specific implementation, the area that needs to be filled in the filling area can be determined by obtaining the area of ​​the area not containing water and the proportion of the corresponding water area, and the preset radiation radius can be reduced or doubled based on the ratio of the area to the previous standard filling area, so that the respective filling areas of the areas not containing water can be accurately determined, so that the areas in the target water image can be accurately filled.

[0083] In summary, the geological analysis method of water terrain based on remote sensing technology in the above-mentioned embodiment of the present invention collects a water image set consisting of multiple water images detected by a remote sensing detection terminal, and adjusts the water area occupancy rate of the water image to ensure that the water characteristics are equivalent to other characteristics, thereby ensuring the quality of the data set, and then improving the accuracy of model training, solving the problem of inaccurate geological analysis due to poor model training accuracy in the existing technology.

[0084] Example 3

[0085] The third embodiment of the present invention also proposes a geological analysis method for water terrain based on remote sensing technology. The geological analysis method for water terrain based on remote sensing technology in this embodiment differs from the geological analysis method for water terrain based on remote sensing technology in the first embodiment in that:

[0086] Step S13 further includes:

[0087] performing grayscale and binarization processing on the target water area image in sequence to obtain a binarized image of the target water area image;

[0088] The binary image is processed to determine the replenishment amount of the non-water area, and the non-water area is replenished according to the replenishment amount of the non-water area so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0089] The supply amount of the non-water area can be determined according to the binary image, so that the non-water area can be replenished according to the supply amount of the non-water area.

[0090] In addition, in some optional embodiments of the present invention, the step of processing the binary image to determine the supply amount of the non-water area, and replenishing the non-water area according to the supply amount of the non-water area so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold includes:

[0091] Determining a target non-water area for replenishment from the non-water area, and determining an outer contour of the target non-water area;

[0092] The extension amount of the target non-water area is determined according to the replenishment amount of the non-water area and the outer contour of the target non-water area, and the target non-water area is extended outward by the extension amount so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0093] Specifically, such as Figure 5 As shown, the extension amount A' of the target non-water area can be determined by the pre-determined non-water area replenishment amount and the outer contour A of the target non-water area, and the extension can be performed on the original target water area image to ensure that the occupancy rate of the water area of ​​the target water area image is within a reasonable range, so that the characteristics of the water area in the target water area image are comparable to those of other areas. The beneficial effect of this is to ensure that other geological features are relatively concentrated.

[0094] The steps of processing the binary image to determine the supply amount of the non-water area, determining the supply area of ​​the non-water area according to the supply amount of the non-water area, and filling the supply area in the target water area image so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold further include:

[0095] determining a target non-water area for replenishment from the non-water area, and determining a replenishment amount for the target non-water area;

[0096] The target non-water area is extended and replenished toward the non-closed boundary of the target non-water area, so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0097] In summary, the geological analysis method of water terrain based on remote sensing technology in the above-mentioned embodiment of the present invention collects a water image set consisting of multiple water images detected by a remote sensing detection terminal, and adjusts the water area occupancy rate of the water image to ensure that the water characteristics are equivalent to other characteristics, thereby ensuring the quality of the data set, and then improving the accuracy of model training, solving the problem of inaccurate geological analysis due to poor model training accuracy in the existing technology.

[0098] Example 4

[0099] See also Figure 6 , shown is a geological analysis device for water terrain based on remote sensing technology proposed in a fourth embodiment of the present invention, the device comprising:

[0100] An acquisition module 100 is used to acquire a water area image set consisting of multiple water area images detected by a remote sensing detection terminal, wherein the water area image set is used to prepare a training set for a water area analysis model;

[0101] A judgment module 200 is configured to judge whether there is a target water area image with a water area occupancy rate higher than an occupancy rate threshold among the plurality of water area images;

[0102] An extraction module 300 is configured to extract the target water area image from the multiple water area images when it is determined that there is a target water area image with a water area occupancy rate higher than an occupancy rate threshold among the multiple water area images;

[0103] a rate reduction module 400 for reducing the occupancy rate of the water area of ​​the target water area image according to a preset rule so that the occupancy rate of the water area of ​​the target water area image does not exceed the occupancy rate threshold;

[0104] The analysis module 500 is used to input the water area image set after the rate reduction process into a preset neural network for training to obtain the water area analysis model, so as to analyze the geology of the water area terrain through the water area analysis model.

[0105] Furthermore, in the above-mentioned geological analysis device for water terrain based on remote sensing technology, the rate reduction module includes:

[0106] a dividing unit, configured to divide the target water area image into a plurality of sub-areas of preset equal divisions according to a preset rule, and extract a target sub-area that does not contain the water area from the plurality of sub-areas;

[0107] The filling unit is used to randomly remove other sub-regions that are all water areas in the target water area image, and fill the other sub-regions after the target sub-region is removed so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0108] Furthermore, in the above-mentioned geological analysis system for water terrain based on remote sensing technology, the rate reduction module further includes:

[0109] a grayscale unit, configured to sequentially perform grayscale and binarization processing on the target water area image to obtain a binarized image of the target water area image;

[0110] A replenishment unit is used to process the binary image to determine the replenishment amount of the non-water area, and replenish the non-water area according to the replenishment amount of the non-water area, so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0111] Furthermore, in the above-mentioned geological analysis device for water terrain based on remote sensing technology, the supply unit is specifically used to:

[0112] Determining a target non-water area for replenishment from the non-water area, and determining an outer contour of the target non-water area;

[0113] The extension amount of the target non-water area is determined according to the replenishment amount of the non-water area and the outer contour of the target non-water area, and the target non-water area is extended outward by the extension amount so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0114] Furthermore, in the above-mentioned geological analysis device for water terrain based on remote sensing technology, the division unit includes:

[0115] a mapping subunit, configured to map the target water area image into a preset coordinate system by taking any vertex in the target water area image as a coordinate origin;

[0116] The segmentation subunit is configured to divide the target water area image into a plurality of sub-areas by dividing the target water area image in a horizontal and vertical manner.

[0117] Furthermore, the above-mentioned geological analysis device for water terrain based on remote sensing technology, wherein the device also includes:

[0118] a center point determination unit, configured to determine the center point of the target sub-region and determine the respective filling areas of the target sub-regions with a preset radiation radius;

[0119] The removal unit is used to randomly remove other sub-regions that are all water areas in the respective filling areas of the target sub-regions, and then fill the other sub-regions after the removal with the target sub-region so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

[0120] Furthermore, the above-mentioned geological analysis device for water terrain based on remote sensing technology, wherein the device also includes:

[0121] The occupancy rate determining unit is used to sequentially perform grayscale and binarization processing on the water area image, and obtain the black and white pixel ratio of the water area image after the grayscale and binarization processing to determine the occupancy rate of the water area in the water area image.

[0122] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments and will not be repeated here.

[0123] Example 5

[0124] Another aspect of the present invention further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the above-mentioned embodiments one to three.

[0125] Example 6

[0126] On the other hand, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and runnable on the processor, and when the processor executes the program, the steps of the method described in any one of the above embodiments one to three are implemented.

[0127] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0128] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0129] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0130] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0131] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0132] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A geological analysis method for water terrain based on remote sensing technology, characterized in that: The method comprises: Collecting a water area image set consisting of multiple water area images detected by a remote sensing detection terminal, wherein the water area image set is used to prepare a training set for a water area analysis model; determining whether there is a target water area image with a water area occupancy rate higher than an occupancy rate threshold among the multiple water area images; When it is determined that a target water area image with a water area occupancy rate higher than an occupancy rate threshold exists among the multiple water area images, extracting the target water area image from the multiple water area images; performing a rate reduction process on the occupancy rate of the water area of ​​the target water area image according to a preset rule, so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold; The water area image set after the rate reduction process is input into a preset neural network for training to obtain the water area analysis model, so as to analyze the geology of the water area terrain through the water area analysis model.

2. The geological analysis method of water area topography based on remote sensing technology according to claim 1, characterized in that: The step of reducing the occupancy rate of the water area of ​​the target water area image according to a preset rule so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold comprises: Dividing the target water area image into a plurality of preset equally divided sub-areas according to a preset rule, and extracting a target sub-area that does not contain the water area from the plurality of sub-areas; Other sub-regions in the target water area image that are all water areas are randomly removed, and the target sub-region is filled with the removed other sub-regions so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

3. The geological analysis method of water area topography based on remote sensing technology according to claim 1, characterized in that: The step of reducing the occupancy rate of the water area of ​​the target water area image according to a preset rule so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold further includes: performing grayscale and binarization processing on the target water area image in sequence to obtain a binarized image of the target water area image; The binary image is processed to determine the replenishment amount of the non-water area, and the non-water area is replenished according to the replenishment amount of the non-water area, so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

4. The geological analysis method of water area topography based on remote sensing technology according to claim 3, characterized in that: The steps of processing the binary image to determine the replenishment amount of the non-water area, and replenishing the non-water area according to the replenishment amount of the non-water area so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold include: Determining a target non-water area for replenishment from the non-water area, and determining an outer contour of the target non-water area; The extension amount of the target non-water area is determined according to the replenishment amount of the non-water area and the outer contour of the target non-water area, and the target non-water area is extended outward by the extension amount so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

5. The method for geological analysis of water area topography based on remote sensing technology according to claim 2, characterized in that: The step of dividing the target water area image into a plurality of preset equally divided sub-areas according to a preset rule, and extracting the target sub-area not containing the water area from the plurality of sub-areas comprises: Taking any vertex in the target water area image as the coordinate origin, mapping the target water area image into a preset coordinate system; The target water area image is divided into a plurality of sub-areas by dividing the target water area image in a horizontal and vertical manner.

6. The geological analysis method of water area topography based on remote sensing technology according to claim 5, characterized in that: After the step of dividing the target water area image into a plurality of sub-areas by dividing the target water area image into horizontal and vertical segments respectively, the following step further comprises: Determine the center point of the target sub-region and determine the respective filling areas of the target sub-region with a preset radiation radius; Other sub-regions that are all water areas in the respective filling areas of the target sub-regions are randomly removed, and then the target sub-regions are filled with the removed other sub-regions so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold.

7. The method for geological analysis of water area topography based on remote sensing technology according to any one of claims 1 to 6, characterized in that: The method further comprises: Grayscale and binarization processing are sequentially performed on the water area image, and a black-white pixel ratio of the water area image after the grayscale and binarization processing is obtained to determine the occupancy rate of the water area in the water area image.

8. A geological analysis device for water terrain based on remote sensing technology, characterized in that: The device comprises: An acquisition module is used to acquire a water area image set consisting of multiple water area images detected by a remote sensing detection terminal, wherein the water area image set is used to prepare a training set for a water area analysis model; A judgment module, configured to judge whether there is a target water area image with a water area occupancy rate higher than an occupancy rate threshold among the plurality of water area images; an extraction module configured to extract the target water area image from the multiple water area images when it is determined that there is a target water area image with a water area occupancy rate higher than an occupancy rate threshold among the multiple water area images; a rate reduction module, configured to perform a rate reduction process on the occupancy rate of the water area of ​​the target water area image according to a preset rule, so that the occupancy rate of the water area of ​​the target water area image is not higher than the occupancy rate threshold; The analysis module is used to input the water area image set after rate reduction processing into a preset neural network for training to obtain the water area analysis model, so as to analyze the geology of the water area terrain through the water area analysis model.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.

Images