CN115908954B - Geological disaster hidden danger identification system and method based on artificial intelligence and electronic equipment - Google Patents
Geological disaster hidden danger identification system and method based on artificial intelligence and electronic equipment Download PDFInfo
- Publication number
- CN115908954B CN115908954B CN202310182148.0A CN202310182148A CN115908954B CN 115908954 B CN115908954 B CN 115908954B CN 202310182148 A CN202310182148 A CN 202310182148A CN 115908954 B CN115908954 B CN 115908954B
- Authority
- CN
- China
- Prior art keywords
- image
- elevation
- layer
- geological disaster
- hidden danger
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The application provides a geological disaster hidden danger identification system, method and electronic equipment based on artificial intelligence, wherein an elevation image set of a monitoring area is acquired through an elevation image set acquisition unit, a first elevation difference image and a second elevation difference image are further determined, and the first elevation difference image and the second elevation difference image are input into a geological disaster hidden danger identification model for intelligent identification, so that a geological disaster hidden danger identification result is obtained. According to the method, the first elevation difference image (reflecting the short-medium-term deformation condition of the monitoring area) and the second elevation difference image (reflecting the medium-long-term deformation condition of the monitoring area) of the elevation image of the monitoring area can be used, and intelligent identification of geological disasters is realized by using the neural network model, so that dependence on expert experience can be reduced, identification of hidden danger areas is carried out before geological disasters occur, corresponding precautionary measures can be carried out in advance, such as operation away from the hidden danger areas, human activities are avoided from being carried out in the hidden danger areas, and the like.
Description
Technical Field
The application relates to the technical field of geological disaster monitoring, in particular to an artificial intelligence-based geological disaster hidden danger identification system, an artificial intelligence-based geological disaster hidden danger identification method and electronic equipment.
Background
Geological disasters are significant disaster events that occur in natural processes, such as collapse, landslide, debris flow, ground collapse, ground subsidence, and the like.
Existing landslide and debris flow monitoring technologies have been developed, so that casualties can be reduced as much as possible, but long-term identification of geological disaster hidden dangers is mainly dependent on expert experience at present, reliable intelligent identification is difficult to realize, and identification and precaution measures of good quality disaster hidden dangers are not facilitated in advance.
Disclosure of Invention
An aim of the embodiment of the application is to provide a geological disaster hidden danger identification system, a geological disaster hidden danger identification method and electronic equipment based on artificial intelligence so as to realize intelligent identification of a geological disaster hidden danger area and facilitate precaution in advance.
In order to achieve the above object, embodiments of the present application are realized by:
in a first aspect, an embodiment of the present application provides an artificial intelligence-based geological disaster hidden danger identification system, including: an elevation image set obtaining unit, configured to obtain an elevation image set of a monitored area, where the elevation image set includes a current elevation image of the monitored area, a first reference image, and a second reference image, where the first reference image is spaced from the current elevation imageMonth, the second reference image is spaced from the current elevation image by +.>Month (Bu)>，The method comprises the steps of carrying out a first treatment on the surface of the An elevation difference image processing unit, configured to determine a first elevation difference image based on the current elevation image and the first reference image, and determine a second elevation difference image based on the current elevation image and the second reference image; and the geological disaster hidden danger identification unit is preset with a geological disaster hidden danger identification model and is used for inputting the first elevation difference image and the second elevation difference image into the geological disaster hidden danger identification model to obtain a geological disaster hidden danger identification result output by the geological disaster hidden danger identification model.
In the embodiment of the application, the elevation image set of the monitoring area (the current elevation image, the first reference image, and the second reference image, the first reference image being spaced apart from the current elevation image) is acquired by the elevation image set acquisition unitMonth is taken as the basis for examining the deformation of the monitoring area in the short and medium period, and the second reference image is spaced from the current elevation image by +.>And month is taken as the basis for examining the long-term deformation in the monitoring area), the first elevation difference image and the second elevation difference image are further determined, and are input into a geological disaster hidden danger identification model for intelligent identification, so that a geological disaster hidden danger identification result is obtained. According to the method, the first elevation difference image (reflecting the short-medium-term deformation condition of the monitoring area) and the second elevation difference image (reflecting the medium-long-term deformation condition of the monitoring area) of the elevation image of the monitoring area can be used, and intelligent identification of geological disasters is realized by using the neural network model, so that dependence on expert experience can be reduced, identification of hidden danger areas is carried out before geological disasters occur, corresponding precautionary measures can be carried out in advance, such as operation away from the hidden danger areas, human activities are avoided from being carried out in the hidden danger areas, and the like.
With reference to the first aspect, in a first possible implementation manner of the first aspect, the geological disaster hidden danger identification model includes a preprocessing layer, a first backbone network, a second backbone network, a full-connection layer and an output layer, where the preprocessing layer is configured to generate a first input image based on an elevation difference corresponding to each pixel in the first elevation difference image, and generate a second input image based on an elevation difference corresponding to each pixel in the second elevation difference image; the first backbone network is connected with the preprocessing layer and is used for extracting the characteristics of the input first input image to obtain a first characteristic extraction result; the second backbone network is connected with the preprocessing layer and is used for extracting the characteristics of the input second input image to obtain a second characteristic extraction result; the full-connection layer is connected with the first main network and the second main network respectively and is used for integrating the first feature extraction result and the second feature extraction result; the output layer is connected with the full-connection layer through a classifier, the classifier classifies the integral characteristic result to obtain a geological disaster hidden danger identification result and outputs the geological disaster hidden danger identification result through the output layer.
In the implementation mode, the geological disaster hidden danger identification model comprises a preprocessing layer, a first main network, a second main network, a full-connection layer and an output layer, wherein the first main network and the second main network are respectively used for carrying out feature extraction on an input first input image and an input second input image to obtain a corresponding first feature extraction result and a corresponding second feature extraction result, so that hidden danger areas are identified based on the features of deformation of a monitoring area in a short medium term and the features of deformation of the monitoring area in a medium term and the characteristics of the geological disaster hidden danger areas in the short medium term and the geological disaster hidden danger areas in the medium term are considered, and the accuracy of identifying the geological disaster hidden danger areas is improved.
With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, the preprocessing layer is specifically configured to: calculating a first gray value corresponding to each pixel based on the elevation difference corresponding to each pixel in the first elevation difference image, and constructing a first input image corresponding to the first elevation difference image based on the first gray value corresponding to each pixel; and calculating a second gray value corresponding to each pixel based on the elevation difference corresponding to each pixel in the second elevation difference image, and constructing a second input image corresponding to the second elevation difference image based on the second gray value corresponding to each pixel.
With reference to the second possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, the preprocessing layer is specifically configured to: calculating a first gray value corresponding to each pixel in the first elevation difference image by adopting the following formula:
，
wherein, the liquid crystal display device comprises a liquid crystal display device,for the first difference of elevation image +.>First gray value corresponding to each pixel, < >>For the first difference of elevation image +.>Elevation difference corresponding to each pixel +.>For the maximum value of the elevation difference in the first elevation difference image,/for the maximum value of the elevation difference in the first elevation difference image>For the minimum value of the difference in elevation in the first difference in elevation image, +.>；
Calculating a second gray value corresponding to each pixel in the second elevation difference image by adopting the following formula:
，
wherein, the liquid crystal display device comprises a liquid crystal display device,for the +.>Second gray values corresponding to the individual picture elements, < >>For the +.>Personal imageElevation difference corresponding to element ++>For the maximum value of the difference of elevation in the second difference of elevation image,/for the maximum value of the difference of elevation in the second difference of elevation image>For the minimum value of the difference in elevation in the second difference in elevation image, +.>。
In the implementation manner, by using the conversion manner, the elevation difference of each pixel in the first elevation difference image (or the second elevation difference image) can be converted into a gray value, so that a corresponding first input image (or a second input image) is obtained, the elevation difference is reflected into gray, the neural network model is convenient to perform processing such as feature extraction and feature mapping, and finally the identification of geological disaster hidden danger is realized.
With reference to the first possible implementation manner of the first aspect, in a fourth possible implementation manner of the first aspect, the first backbone network includes a convolutional layerPooling layer->Convolutional layer->And pooling layer->Said convolution layer->For convolving said first input image to obtain a feature subgraph +.>The method comprises the steps of carrying out a first treatment on the surface of the The pooling layer->For the characteristic subgraph->Performing maximum pooling treatment to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the Said convolution layer->For the characteristic subgraph->Performing convolution processing to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the The pooling layer->For the characteristic subgraph->Performing maximum pooling treatment to obtain characteristic subgraph->。
With reference to the first possible implementation manner of the first aspect, in a fifth possible implementation manner of the first aspect, the second backbone network includes a convolutional layerPooling layer->Convolutional layer->And pooling layer->Said convolution layer->For convolving said second input image to obtain a feature subgraph +.>The method comprises the steps of carrying out a first treatment on the surface of the The pooling layer->For the characteristic subgraph->Performing maximum pooling treatment to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the Said convolution layer->For the characteristic subgraph->Performing convolution processing to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the The pooling layer->For the characteristic subgraph->Performing maximum pooling treatment to obtain characteristic subgraph->。
With reference to the first possible implementation manner of the first aspect, in a sixth possible implementation manner of the first aspect, the full connection layer includes a sub-connection layerSub-connection layer->Sub-connection layer->And sub-connection layer->Said subconnection layer->The first intermediate feature extraction module is connected with the first backbone network and used for integrating the first feature extraction result to obtain a first intermediate feature; the sub-connection layer->The second intermediate feature extraction module is connected with the second backbone network and used for integrating the second feature extraction result to obtain a second intermediate feature; the sub-connection layer->Respectively with the sub-connection layer->And the sub-connection layer->The connection is used for integrating the first intermediate feature and the second intermediate feature to obtain a third intermediate feature; the sub-connection layerIs connected with the sub-connecting layer->And the full connection is used for integrating the third intermediate features to obtain an integrated feature result so as to map the integrated feature result into the classifier.
In a second aspect, an embodiment of the present application provides an artificial intelligence based geological disaster hidden danger identification method, which is applied to the geological disaster hidden danger identification system according to the first aspect or any one of possible implementation manners of the first aspect, where the method includes: acquiring the height of a monitored areaA set of elevation images, wherein the set of elevation images comprises a current elevation image of the monitored area, a first reference image, and a second reference image, wherein the first reference image is spaced from the current elevation imageMonth, the second reference image is spaced from the current elevation image by +.>Month (Bu)>，The method comprises the steps of carrying out a first treatment on the surface of the Determining a first elevation difference image based on the current elevation image and the first reference image, and determining a second elevation difference image based on the current elevation image and the second reference image; inputting the first elevation difference image and the second elevation difference image into a preset geological disaster hidden danger identification model to obtain a geological disaster hidden danger identification result output by the geological disaster hidden danger identification model.
In a third aspect, an embodiment of the present application provides a storage medium, where the storage medium includes a stored program, and when the program runs, the device where the storage medium is controlled to execute the geological disaster hidden danger identification method based on artificial intelligence according to the second aspect.
In a fourth aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a memory and a processor, where the memory is configured to store information including program instructions, and the processor is configured to control execution of the program instructions, and when the program instructions are loaded and executed by the processor, implement the geological disaster hidden danger identification method based on artificial intelligence according to the second aspect.
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a geological disaster hidden danger identification model provided in an embodiment of the present application.
Fig. 2 is a schematic diagram of an artificial intelligence-based geological disaster hidden danger recognition system according to an embodiment of the present application.
Fig. 3 is a flowchart of a geological disaster hidden danger identification method based on artificial intelligence according to an embodiment of the present application.
Fig. 4 is a block diagram of an electronic device according to an embodiment of the present application.
Icon: 10-an artificial intelligence-based geological disaster hidden danger identification system; 11-an elevation image set acquisition unit; 12-an elevation difference image processing unit; 13-a geological disaster hidden danger identification unit; 20-an electronic device; 21-a memory; a 22-communication module; a 23-bus; 24-processor.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
In order to facilitate understanding of the scheme, in this embodiment, a geological disaster hidden danger identification model is first introduced.
Referring to fig. 1, fig. 1 is a schematic diagram of a geological disaster hidden danger recognition model provided in an embodiment of the present application. The geological disaster potential identification model can comprise a preprocessing layer, a first backbone network, a second backbone network, a full connection layer and an output layer.
Illustratively, the preprocessing layer is mainly used for preprocessing the input elevation difference images (such as the first elevation difference image and the second elevation difference image) so as to obtain standardized input images (the first input image and the second input image).
Specifically, the preprocessing layer may calculate a gray value corresponding to each pixel by using an elevation difference corresponding to each pixel in the elevation difference image, so as to construct an input image corresponding to the elevation difference image. The number of pixels in the constructed input image corresponds to the number of pixels of the elevation difference image.
For example, the preprocessing layer may calculate the gray value corresponding to each pixel in the elevation difference image using the following formula:
， （1）
wherein, the liquid crystal display device comprises a liquid crystal display device,is the +.>Gray values corresponding to individual picture elements +.>Is the +.>Elevation difference corresponding to each pixel +.>Is the maximum value of the elevation difference in the elevation difference image, < >>For the minimum value of the elevation difference in the elevation difference image,。
by using the conversion mode, the elevation difference of each pixel in the elevation difference image can be converted into a gray value, so that a corresponding input image is obtained, the elevation difference is reflected into the gray, and the neural network model is convenient to process such as feature extraction and feature mapping.
The first backbone network is connected to the preprocessing layer, and is used for performing feature extraction on an input image (first input image) input into the first backbone network to obtain a first feature extraction result.
In particular, the first backbone network may include a plurality of convolutional layers and a pooling layer, the convolutional layers and the pooling layer being staggered. For example, the first backbone network may include a convolutional layerPooling layer->Convolutional layer->And pooling layer->。
Convolutional layerFor convolving the first input image to obtain a feature sub-graph +.>The method comprises the steps of carrying out a first treatment on the surface of the Pooling layer->For->Performing maximum pooling treatment to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the Convolutional layer->For->Performing convolution processing to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the PoolingLayer->For->Performing maximum pooling treatment to obtain characteristic subgraph->。
The second backbone network is illustratively connected to the preprocessing layer, and is configured to perform feature extraction on an input image (second input image) input into the second backbone network, so as to obtain a second feature extraction result.
In particular, the second backbone network may also include a plurality of convolution layers and pooling layers, the convolution layers and pooling layers being staggered. For example, the second backbone network may include a convolutional layerPooling layer->Convolutional layer->And pooling layer->。
Convolutional layerFor convolving the second input image to obtain a feature sub-graph +.>The method comprises the steps of carrying out a first treatment on the surface of the Pooling layer->For->Performing maximum pooling treatment to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the Convolutional layer->For->Performing convolution processing to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the Pooling layer->For->Performing maximum pooling treatment to obtain characteristic subgraph->。
Based on the size of the input image, the first backbone network and the second backbone network can also design more convolution layers and pooling layers so as to extract more features and improve the accuracy of recognition.
The full connection layer is connected to the first backbone network and the second backbone network, and is used for integrating the first feature extraction result and the second feature extraction result.
In particular, the full connection layer may include a sub-connection layerSub-connection layer->Sub-connection layer->And sub-connection layer->。
Sub-connection layerAnd the first intermediate feature is connected with the first backbone network and used for integrating the first feature extraction result to obtain a first intermediate feature. Sub-connection layer->And the second intermediate feature is connected with a second backbone network and used for integrating the second feature extraction result to obtain a second intermediate feature. Sub-connection layer->Respectively with sub-connection layer->And sub-connection layer->And the connection is used for integrating the first intermediate feature and the second intermediate feature to obtain a third intermediate feature. Sub-connection layer->And sub-connection layer->And the full connection is used for integrating the third intermediate features to obtain an integrated feature result.
The output layer is illustratively connected to the full connection layer via a classifier (e.g., softmax, facilitating multiple classification), and the sub-connection layer of the full connection layerThe integrated characteristic results can be mapped into a classifier, and the classifier classifies the integrated characteristic results to obtain the geological disaster hidden danger identification results and outputs the geological disaster hidden danger identification results through an output layer.
The above is an introduction to the model architecture of the geological disaster hidden danger recognition model, and here, training of the geological disaster hidden danger recognition model will be further introduced so as to obtain an applicable geological disaster hidden danger recognition model.
First, a desired structureAnd building a training set. The training images may be selected from a validated (e.g., a region where an accident such as a collapse or a landslide occurs, a previously stored set of elevation images of the region is selected) or a set of elevation images of a hidden danger region marked by an expert, the set of elevation images of the hidden danger region may include a plurality of elevation images, such as an elevation image at a first time point (as a current elevation image), a plurality of elevation images at a second time point (as a first reference image), and a plurality of elevation images at a third time point (as a second reference image), and the elevation image at the second time point (the first reference image) is spaced from the elevation image at the first time point (the current elevation image)Moon, the interval between the elevation image at the third time point (second reference image) and the elevation image at the first time point (current elevation image)>Month (Bu)>，/>。
Selecting an elevation image set of 200-400 hidden trouble areas according to 7:2: the scale of 1 is divided into a training set, a validation set and a test set.
The first elevation difference image (determined based on the elevation image of the first time point and the elevation image of the second time point) and the second elevation difference image (determined based on the elevation image of the first time point and the elevation image of the third time point) are obtained by using the elevation image set in the training set (each time, the elevation image of the first time point, the elevation image of the second time point and the elevation image of the third time point in the elevation image set) as the input of the geological disaster hidden danger identification model. The training process of the model is approximately equivalent to that of the existing neural network model, and parameters of the model are optimized through designed loss functions (such as square absolute error loss, ioU loss or CIoU loss), so that the training of the model is completed.
And then, the model can be verified by using the elevation image set in the verification set, the model is evaluated by using indexes such as accuracy, recall rate and precision rate, and the trained geological disaster hidden danger recognition model can be obtained by testing the model by using the test set.
Based on the geological disaster potential identification model, the present embodiment provides an artificial intelligence-based geological disaster potential identification system 10. Referring to fig. 2, fig. 2 is a schematic diagram of an artificial intelligence-based geological disaster potential identification system 10 according to an embodiment of the present application. The artificial intelligence based geological disaster potential identification system 10 may include an elevation image set acquisition unit 11, an elevation difference image processing unit 12, and a geological disaster potential identification unit 13 (in which a geological disaster potential identification model is built).
To facilitate an introduction to the operation of the artificial intelligence based geologic hazard identification system 10, the present invention is described herein in connection with an artificial intelligence based geologic hazard identification method (which may be performed by the electronic device 20). Referring to fig. 3, the method for identifying geological disaster potential based on artificial intelligence may include step S10, step S20 and step S30.
In order to realize the identification of the geological disaster hidden danger, the electronic device 20 may execute step S10 to realize the function of the elevation image set acquisition unit 11 in the geological disaster hidden danger identification system 10 based on artificial intelligence.
Step S10: acquiring an elevation image set of a monitoring area, wherein the elevation image set comprises a current elevation image, a first reference image and a second reference image of the monitoring area, and the first reference image is separated from the current elevation imageMonth, the second reference image is spaced from the current elevation image by +.>Month (Bu)>，/>。
In this embodiment, the electronic device 20 may acquire an elevation image set of the monitored area. The elevation image of the monitored area may be an oversized elevation image (a current elevation image, a first reference image, and a second reference image). In order to facilitate the processing of the geological disaster hidden trouble recognition model, an oversized original elevation image may be divided into a plurality of standard-sized elevation images, for example, a plurality of elevation images (the size of which represents the grid number of the elevation images) divided into 128×128 (or 256×256, 64×64, etc.), each divided elevation image corresponds to a number, three elevation images corresponding to the same number from different original elevation images (one of the current elevation image, the first reference image and the second reference image) form a new elevation image set, and consistent numbers are used along, so that a plurality of elevation image sets are obtained, and each of the plurality of elevation image sets is an elevation image set of a monitoring area (different area).
The first reference image is spaced from the current elevation imageMonth, second reference image is spaced from current elevation image +.>The month of the year,，/>. Here, by +.>，/>By way of example, but not limitation.
After obtaining the elevation image set of the monitored area, the electronic device 20 may execute step S20 to implement the function of the elevation difference image processing unit 12.
Step S20: a first elevation difference image is determined based on the current elevation image and the first reference image, and a second elevation difference image is determined based on the current elevation image and the second reference image.
In this embodiment, after registering the current elevation image and the first reference image, the electronic device 20 obtains the elevation difference (positive or negative) corresponding to each pixel by using the elevation of each pixel in the current elevation image and the first reference image (positive or negative), and distinguishes the positive or negative of the elevation difference by the sign "-"), so as to determine the first elevation difference image. The same electronic device 20 may determine a second elevation difference image using the current elevation image and the second reference image.
After determining the first elevation difference image and the second elevation difference image, the electronic device 20 may execute step S30 to implement the function of the geological disaster hidden danger identification unit 13, where the geological disaster hidden danger identification model is preset in the geological disaster hidden danger identification unit 13.
Step S30: inputting the first elevation difference image and the second elevation difference image into a preset geological disaster hidden danger identification model to obtain a geological disaster hidden danger identification result output by the geological disaster hidden danger identification model.
In this embodiment, the electronic device 20 may input the first elevation difference image and the second elevation difference image into a preset geological disaster hidden danger identification model.
Based on this, the electronic device 20 may generate a first input image based on the elevation difference corresponding to each pixel in the first elevation difference image and generate a second input image based on the elevation difference corresponding to each pixel in the second elevation difference image using the preprocessing layer of the geological disaster potential identification model.
For example, electronic device 20 may calculate the first gray value corresponding to each pixel based on the elevation difference corresponding to each pixel in the first elevation difference image using the preprocessing layer.
For example, the following formula may be used to calculate a first gray value corresponding to each pixel in the first elevation difference image:
， （2）
wherein, the liquid crystal display device comprises a liquid crystal display device,is the +.>First gray value corresponding to each pixel, < >>Is the +.>Elevation difference corresponding to each pixel +.>For the maximum value of the difference of elevation in the first difference of elevation image, +.>For the minimum value of the difference in elevation in the first difference in elevation image,/for>。
After the first gray value corresponding to each pixel in the first elevation difference image is calculated, a first input image corresponding to the first elevation difference image can be constructed based on the first gray value corresponding to each pixel. That is, a gray-scale image (for example, 128×128) of a corresponding size is constructed with a first gray-scale value corresponding to each pixel, as a first input image.
Similarly, the electronic device 20 may calculate the second gray value corresponding to each pixel in the second elevation difference image by using the preprocessing layer of the geological disaster hidden danger recognition model.
For example, the following formula may be used to calculate a second gray value for each pixel in the second elevation difference image:
， （3）
wherein, the liquid crystal display device comprises a liquid crystal display device,is the +.>Second gray values corresponding to the individual picture elements, < >>Is the +.>Elevation difference corresponding to each pixel +.>For the maximum value of the difference of elevation in the second difference of elevation image, +.>For the minimum value of the difference in elevation in the second difference in elevation image,/for>。
After the second gray value corresponding to each pixel in the second elevation difference image is calculated, a second input image corresponding to the second elevation difference image can be constructed based on the second gray value corresponding to each pixel. That is, a gray image (for example, 128×128) of a corresponding size is constructed with a second gray value corresponding to each pixel, as a second input image.
By using the conversion form, the elevation difference of each pixel in the first elevation difference image (or the second elevation difference image) can be converted into a gray level value, so that a corresponding first input image (or second input image) is obtained, the elevation difference is reflected into gray level, the neural network model is convenient to process feature extraction, feature mapping and the like, and finally the identification of geological disaster hidden danger is realized.
After the first input image and the second input image are obtained, the first input image may be input to the first backbone network, and the second input image may be input to the second backbone network.
The first backbone network is connected with the preprocessing layer and is used for carrying out feature extraction on the input first input image to obtain a first feature extraction result.
Exemplary, the first backbone network includes a convolutional layerPooling layer->Convolutional layer->And pooling layer->The following are examples: convolutional layer->The first input image can be convolved to obtain a feature sub-graph +.>The method comprises the steps of carrying out a first treatment on the surface of the Pooling layer->Can be used for characteristic subgraphPerforming maximum pooling treatment to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the Convolutional layer->Can be about the characteristic sub-graph>Performing convolution processing to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the Pooling layer->Can be about the characteristic sub-graph>Performing maximum pooling treatment to obtain characteristic subgraph->. Here, the feature subgraph->I.e. representing the first feature extraction result.
And the second backbone network is connected with the preprocessing layer and is used for carrying out feature extraction on the input second input image to obtain a second feature extraction result.
Exemplary, the second backbone network includes a convolutional layerPooling layer->Convolutional layer->And pooling layer->The following are examples: convolutional layer->The second input image can be convolved to obtain a feature sub-graph +.>The method comprises the steps of carrying out a first treatment on the surface of the Pooling layer->Can be used for characteristic subgraphPerforming maximum pooling treatment to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the Convolutional layer->Can be about the characteristic sub-graph>Performing convolution processing to obtain characteristic subgraph->The method comprises the steps of carrying out a first treatment on the surface of the Pooling layer->Can be about the characteristic sub-graph>Performing maximum pooling treatment to obtain characteristic subgraph->. Here, the feature subgraph->I.e. representing the second feature extraction result.
The full-connection layer is connected with the first main network and the second main network respectively and is used for integrating the first feature extraction result and the second feature extraction result.
Exemplary, the sub-connection layer is included in the full connection layerSub-connection layer->Sub-connection layer->And sub-connection layer->The following are examples:
sub-connection layerAnd the first intermediate feature is connected with the first backbone network and used for integrating the first feature extraction result to obtain a first intermediate feature. The first intermediate feature is obtained by integrating the extracted features of the first input image after the feature extraction of the first input image by the first backbone network.
Sub-connection layerAnd the second intermediate feature is connected with a second backbone network and used for integrating the second feature extraction result to obtain a second intermediate feature. The second intermediate feature is obtained by integrating the extracted features of the second input image after the feature extraction of the second input image by the second backbone network.
Sub-connection layerAre respectively connected with the sub-connecting layers->And sub-connection layer->And connecting, namely integrating the first intermediate feature and the second intermediate feature to obtain a third intermediate feature.
And sub-connection layerAnd sub-connection layer->And the full connection is used for integrating the third intermediate features to obtain an integrated feature result so as to map the integrated feature result into a classifier (for example, a softmax function, and the set category can comprise a plurality of geological disaster hidden danger categories such as landslide hidden danger, collapse hidden danger, debris flow hidden danger, collapse hidden danger and the like).
The output layer can be connected with the full-connection layer through a classifier, the classifier classifies the integral characteristic result to obtain a geological disaster hidden danger identification result (the final geological disaster hidden danger category is determined through the probability of each category), and the geological disaster hidden danger identification result is output through the output layer.
The hidden danger area is identified based on the characteristics of the deformation of the monitoring area in the short middle period and the characteristics of the deformation of the monitoring area in the medium and long periods, so that the characteristics of the hidden danger area of the geological disaster in the short middle period and the characteristics of the hidden danger area of the geological disaster in the medium and long periods can be considered, and the accuracy of identifying the hidden danger area of the geological disaster can be improved.
Because each elevation image set can be a small part of the monitoring area, the hidden danger area with geological disaster hidden danger can be identified from the monitoring area, the corresponding part can be determined from the monitoring area to serve as the hidden danger area through the number of the elevation image set, and accurate hidden danger area positioning can be realized.
Referring to fig. 4, fig. 4 is a block diagram illustrating a structure of an electronic device 20 according to an embodiment of the present application. The electronic device 20 may include: a communication module 22 connected to the outside through a network, one or more processors 24 for executing program instructions, a bus 23, and a different form of memory 21, such as a disk, ROM, or RAM, or any combination thereof. The memory 21, the communication module 22 and the processor 24 may be connected by a bus 23.
Illustratively, the memory 21 has a program stored therein. The processor 24 can call and run the programs from the memory 21, so that an artificial intelligence-based geological disaster hidden danger identification method can be realized by running the programs, and further, the geological disaster hidden danger identification of the monitored area is realized.
The embodiment of the application also provides a storage medium, which comprises a stored program, wherein when the program runs, equipment where the storage medium is located is controlled to execute the geological disaster hidden danger identification method based on artificial intelligence.
In summary, the embodiments of the present application provide a geological disaster hidden trouble recognition system, method and electronic device based on artificial intelligence, where an elevation image set (current elevation image, the first elevation image) of a monitored area is obtained by an elevation image set obtaining unit 11A reference image and a second reference image, the first reference image being spaced from the current elevation imageMonth is taken as the basis for examining the deformation of the monitoring area in the short and medium period, and the second reference image is spaced from the current elevation image by +.>And month is taken as the basis for examining the long-term deformation in the monitoring area), the first elevation difference image and the second elevation difference image are further determined, and are input into a geological disaster hidden danger identification model for intelligent identification, so that a geological disaster hidden danger identification result is obtained. According to the method, the first elevation difference image (reflecting the short-medium-term deformation condition of the monitoring area) and the second elevation difference image (reflecting the medium-long-term deformation condition of the monitoring area) of the elevation image of the monitoring area can be used, and intelligent identification of geological disasters is realized by using the neural network model, so that dependence on expert experience can be reduced, identification of hidden danger areas is carried out before geological disasters occur, corresponding precautionary measures can be carried out in advance, such as operation away from the hidden danger areas, human activities are avoided from being carried out in the hidden danger areas, and the like.
In the embodiments provided herein, it should be understood that the disclosed systems and methods may be implemented in other ways. The system embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions in actual implementation, and e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
Further, the units described as separate units may or may not be physically separate, and units displayed as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (9)
1. Geological disaster hidden danger identification system based on artificial intelligence, characterized by comprising:
an elevation image set obtaining unit, configured to obtain an elevation image set of a monitored area, where the elevation image set includes a current elevation image of the monitored area, a first reference image, and a second reference image, where the first reference image is spaced from the current elevation imageMonth, the second reference image is spaced from the current elevation image by +.>The month of the year,，/>；
an elevation difference image processing unit, configured to determine a first elevation difference image based on the current elevation image and the first reference image, and determine a second elevation difference image based on the current elevation image and the second reference image;
the geological disaster hidden danger identification unit is preset with a geological disaster hidden danger identification model and is used for inputting the first elevation difference image and the second elevation difference image into the geological disaster hidden danger identification model to obtain a geological disaster hidden danger identification result output by the geological disaster hidden danger identification model;
wherein the geological disaster hidden trouble recognition model comprises a preprocessing layer, a first main network, a second main network, a full-connection layer and an output layer,
the preprocessing layer is used for generating a first input image based on the elevation difference corresponding to each pixel in the first elevation difference image, and generating a second input image based on the elevation difference corresponding to each pixel in the second elevation difference image;
the first backbone network is connected with the preprocessing layer and is used for extracting the characteristics of the input first input image to obtain a first characteristic extraction result;
the second backbone network is connected with the preprocessing layer and is used for extracting the characteristics of the input second input image to obtain a second characteristic extraction result;
the full-connection layer is connected with the first main network and the second main network respectively and is used for integrating the first feature extraction result and the second feature extraction result;
the output layer is connected with the full-connection layer through a classifier, the classifier classifies the integral characteristic result to obtain a geological disaster hidden danger identification result and outputs the geological disaster hidden danger identification result through the output layer.
2. The geological disaster potential identification system based on artificial intelligence according to claim 1, wherein the preprocessing layer is specifically configured to:
calculating a first gray value corresponding to each pixel based on the elevation difference corresponding to each pixel in the first elevation difference image, and constructing a first input image corresponding to the first elevation difference image based on the first gray value corresponding to each pixel;
and calculating a second gray value corresponding to each pixel based on the elevation difference corresponding to each pixel in the second elevation difference image, and constructing a second input image corresponding to the second elevation difference image based on the second gray value corresponding to each pixel.
3. The geological disaster potential identification system based on artificial intelligence according to claim 2, wherein the preprocessing layer is specifically configured to:
calculating a first gray value corresponding to each pixel in the first elevation difference image by adopting the following formula:wherein->For the first difference of elevation image +.>First gray value corresponding to each pixel, < >>For the first difference of elevation image +.>Elevation difference corresponding to each pixel +.>For the maximum value of the elevation difference in the first elevation difference image,/for the maximum value of the elevation difference in the first elevation difference image>For a minimum value of the difference in elevation in the first difference in elevation image,the method comprises the steps of carrying out a first treatment on the surface of the Calculating each of the second elevation difference images using the following formulaAnd a second gray value corresponding to the pixel:wherein->For the +.>Second gray values corresponding to the individual picture elements, < >>For the +.>Elevation difference corresponding to each pixel +.>For the maximum value of the difference of elevation in the second difference of elevation image,/for the maximum value of the difference of elevation in the second difference of elevation image>For a minimum value of the difference in elevation in the second difference in elevation image,。
4. the artificial intelligence based geological disaster identification system of claim 1, wherein said first backbone network comprises a convolution layerPooling layer->Convolutional layer->And pooling layer->，
The convolution layerFor convolving said first input image to obtain a feature subgraph +.>；
The pooling layerFor the characteristic subgraph->Performing maximum pooling treatment to obtain characteristic subgraph->；
The convolution layerFor the characteristic subgraph->Performing convolution processing to obtain characteristic subgraph->；
The pooling layerFor the characteristic subgraph->Performing maximum pooling treatment to obtain characteristic subgraph->。
5. The artificial intelligence based geological disaster identification system of claim 1, wherein said second backbone network comprises a convolution layerPooling layer->Convolutional layer->And pooling layer->，
The convolution layerFor convolving said second input image to obtain a feature subgraph +.>；
The pooling layerFor the characteristic subgraph->Performing maximum pooling treatment to obtain characteristic subgraph->；
The convolution layerFor the characteristic subgraph->Performing convolution processing to obtain characteristic subgraph->；
The pooling layerFor the characteristic subgraph->Performing maximum pooling treatment to obtain characteristic subgraph->。
6. The artificial intelligence based geological disaster potential identification system of claim 1, wherein said full connection layer comprises a sub-connection layerSub-connection layer->Sub-connection layer->And sub-connection layer->，
The sub-connection layerThe first intermediate feature extraction module is connected with the first backbone network and used for integrating the first feature extraction result to obtain a first intermediate feature;
the sub-connection layerThe second intermediate feature extraction module is connected with the second backbone network and used for integrating the second feature extraction result to obtain a second intermediate feature;
the sub-connection layerRespectively with the sub-connection layer->And the sub-connection layer->The connection is used for integrating the first intermediate feature and the second intermediate feature to obtain a third intermediate feature;
the sub-connection layerIs connected with the sub-connecting layer->And the full connection is used for integrating the third intermediate features to obtain an integrated feature result so as to map the integrated feature result into the classifier.
7. An artificial intelligence based geological disaster potential identification method, characterized in that it is applied to the artificial intelligence based geological disaster potential identification system as set forth in any one of claims 1 to 6, the method comprising:
acquiring an elevation image set of a monitoring area, wherein the elevation image set comprises a current elevation image, a first reference image and a second reference image of the monitoring area, wherein the first reference image is separated from the current elevation image by a month, and the second reference image is separated from the current elevation imageMonth (Bu)>，/>The method comprises the steps of carrying out a first treatment on the surface of the Determining a first elevation difference image based on the current elevation image and the first reference image, and determining a second elevation difference image based on the current elevation image and the second reference image; inputting the first elevation difference image and the second elevation difference image into a preset geological disaster hidden danger identification model to obtain a geological disaster hidden danger identification result output by the geological disaster hidden danger identification model.
8. A storage medium comprising a stored program, wherein the program, when run, controls a device in which the storage medium resides to perform the artificial intelligence-based geological disaster risk identification method according to claim 7.
9. An electronic device comprising a memory for storing information including program instructions and a processor for controlling execution of the program instructions that when loaded and executed by the processor implement the artificial intelligence based geological disaster identification method as set forth in claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310182148.0A CN115908954B (en) | 2023-03-01 | 2023-03-01 | Geological disaster hidden danger identification system and method based on artificial intelligence and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310182148.0A CN115908954B (en) | 2023-03-01 | 2023-03-01 | Geological disaster hidden danger identification system and method based on artificial intelligence and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115908954A CN115908954A (en) | 2023-04-04 |
| CN115908954B true CN115908954B (en) | 2023-07-28 |
Family
ID=86495068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310182148.0A Active CN115908954B (en) | 2023-03-01 | 2023-03-01 | Geological disaster hidden danger identification system and method based on artificial intelligence and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115908954B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114219687A (en) * | 2021-11-02 | 2022-03-22 | 三峡大学 | Intelligent identification method for potential construction safety hazards by fusing human-computer vision |
| CN114267155A (en) * | 2021-11-05 | 2022-04-01 | 国能大渡河革什扎水电开发有限公司 | Geological disaster monitoring and early warning system based on video recognition technology |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9767565B2 (en) * | 2015-08-26 | 2017-09-19 | Digitalglobe, Inc. | Synthesizing training data for broad area geospatial object detection |
| CN109376777A (en) * | 2018-10-18 | 2019-02-22 | 四川木牛流马智能科技有限公司 | Cervical cancer tissues pathological image analysis method and equipment based on deep learning |
| CN110057344B (en) * | 2019-04-30 | 2020-08-07 | 北京交通大学 | Sedimentation detection method and platform |
| CN112464807A (en) * | 2020-11-26 | 2021-03-09 | 北京灵汐科技有限公司 | Video motion recognition method and device, electronic equipment and storage medium |
| CN112732092B (en) * | 2021-01-22 | 2023-04-07 | 河北工业大学 | Surface electromyogram signal identification method based on double-view multi-scale convolution neural network |
| CN113159174B (en) * | 2021-04-21 | 2022-05-06 | 云南师范大学 | DEM (digital elevation model) matching and deformation quantity detecting method and device without control points |
| CN115019145A (en) * | 2022-06-15 | 2022-09-06 | 交通运输部公路科学研究所 | Method for monitoring settlement deformation of road surface of Qinghai-Tibet plateau highway |
| CN114821376B (en) * | 2022-06-27 | 2022-09-20 | 中咨数据有限公司 | Unmanned aerial vehicle image geological disaster automatic extraction method based on deep learning |
| CN115272874B (en) * | 2022-09-28 | 2022-12-09 | 中国科学院、水利部成都山地灾害与环境研究所 | Debris flow disaster identification and frequency calculation method based on remote sensing image |
-
2023
- 2023-03-01 CN CN202310182148.0A patent/CN115908954B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114219687A (en) * | 2021-11-02 | 2022-03-22 | 三峡大学 | Intelligent identification method for potential construction safety hazards by fusing human-computer vision |
| CN114267155A (en) * | 2021-11-05 | 2022-04-01 | 国能大渡河革什扎水电开发有限公司 | Geological disaster monitoring and early warning system based on video recognition technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115908954A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111369581A (en) | Image processing method, device, equipment and storage medium | |
| CN113159147A (en) | Image identification method and device based on neural network and electronic equipment | |
| CN103685851B (en) | Signal processing apparatus, signal processing method, output device, output method and program | |
| WO2021120961A1 (en) | Brain addiction structure map evaluation method and apparatus | |
| CN108229375B (en) | Method and device for detecting face image | |
| CN111666890A (en) | Spine deformation crowd identification method and device, computer equipment and storage medium | |
| CN115239672A (en) | Defect detection method and device, equipment and storage medium | |
| CN114913923A (en) | Cell type identification method aiming at open sequencing data of single cell chromatin | |
| CN112862023B (en) | Object density determination method and device, computer equipment and storage medium | |
| CN114240779A (en) | Point cloud denoising method, device, equipment and storage medium | |
| CN115908954B (en) | Geological disaster hidden danger identification system and method based on artificial intelligence and electronic equipment | |
| CN112861950A (en) | Method and device for identifying copied image, electronic equipment and storage medium | |
| CN111369598B (en) | Deep learning model training method and device, and application method and device | |
| CN111652242B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN114170221B (en) | Method and system for confirming brain diseases based on images | |
| CN111325756A (en) | Three-dimensional image artery and vein segmentation method and system based on deep learning network | |
| CN116309170A (en) | Defogging method and device for inspection images of power transmission line | |
| CN115346091A (en) | Method and device for generating Mura defect image data set | |
| CN113657293A (en) | Living body detection method, living body detection device, electronic apparatus, medium, and program product | |
| Chen et al. | Built-up Area Extraction Combing Densely Connected Dual-Attention Network and Multi-Scale Context | |
| CN115660985B (en) | Cataract fundus image restoration method, cataract fundus image restoration model training method and cataract fundus image restoration model training device | |
| CN115831356B (en) | Auxiliary prediction diagnosis method based on artificial intelligence algorithm | |
| CN116205726B (en) | Loan risk prediction method and device, electronic equipment and storage medium | |
| CN115147705B (en) | Face copying detection method and device, electronic equipment and storage medium | |
| CN115801845B (en) | Industrial Internet data acquisition method and related equipment based on edge calculation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |