CN114155378A - Method and device for automatically extracting coal mining subsidence ground cracks and storage medium - Google Patents
Method and device for automatically extracting coal mining subsidence ground cracks and storage medium Download PDFInfo
- Publication number
- CN114155378A CN114155378A CN202111373863.XA CN202111373863A CN114155378A CN 114155378 A CN114155378 A CN 114155378A CN 202111373863 A CN202111373863 A CN 202111373863A CN 114155378 A CN114155378 A CN 114155378A
- Authority
- CN
- China
- Prior art keywords
- ground
- image
- gray level
- level image
- gaussian
- 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.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method, a device and a storage medium for automatically extracting coal mining subsidence ground cracks, wherein the method comprises the following steps: collecting a plurality of unmanned aerial vehicle images, splicing the images to obtain an orthoimage of a ground crack monitoring area, and converting the orthoimage into a first gray image after geometric correction; gaussian matching filtering of different rotation angles is carried out on the first gray level image to obtain a second gray level image of which the ground crack information has maximum response to the Gaussian matching filtering of the corresponding rotation angle, and the corresponding rotation angle is recorded as a target rotation angle; carrying out Gaussian first derivative filtering processing on the first gray level image under a target rotation angle to obtain a third gray level image; performing linear operation on the second gray level image and the third gray level image to obtain a fourth gray level image; performing ground fracture primary extraction by using the fourth gray level image; and eliminating noise in the primary extracted ground fracture by a morphological filtering method of path opening operation to realize fine extraction of the ground fracture. The method can quickly and accurately acquire the coal mining subsidence ground crack distribution and the form information thereof.
Description
Technical Field
The disclosure relates to the field of unmanned aerial vehicle photogrammetry and image processing, in particular to a method and a device for automatically extracting coal mining subsidence ground cracks and a storage medium.
Background
China is a big country for energy production and consumption, coal resources dominate in energy production and consumption structures for a long time, and the total quantity of coal production in China in 2018 is as high as 39.5 hundred million tons. The ecological environment of the northwest arid region of China is fragile, and meanwhile, the region is a key construction region of the coal industry of China, and the influence of underground coal mining activities in the region on the ecological environment of the earth surface is mainly a large amount of earth cracks generated by earth surface deformation. The existing research shows that the occurrence of coal mining subsidence ground cracks causes the change of soil characteristics, the quality of soil is reduced, the water content of the ground surface soil in the crack occurrence area is reduced, the ground surface water and soil loss condition is aggravated, and the safety production of mines is seriously threatened. Therefore, the rapid investigation and mapping of the coal mining subsidence ground cracks in the arid region are necessary for ecological restoration of the mining region.
The traditional coal mining subsidence ground crack mapping is mainly manual ground investigation, and measures such as a total station instrument, a GPS and the like are used for measuring the plane position of the ground crack on the spot and drawing a ground crack distribution diagram. Because the cracks in the mining area are densely distributed, the ground investigation method wastes time and labor, and the workload is large. Meanwhile, the traditional measuring means can only obtain the initial crack distribution condition and cannot reflect the real crack form completely. According to the actual ground fissure exploration data, the ground fissure width is usually in the sub-meter level, and the current resolution of the optical satellite image cannot clearly reflect the ground fissure condition. At present, unmanned aerial vehicle photogrammetry and remote sensing technology develop rapidly, show huge application potential in mining area ground crack investigation field. However, most of the ground fissure extraction applications based on unmanned aerial vehicle photogrammetry and remote sensing still adopt a visual interpretation mode at present, namely, a ground fissure distribution map is drawn manually from a high-resolution image of an unmanned aerial vehicle, automatic extraction is not achieved, and a large amount of manpower and material resources are consumed. The existing automatic detection methods for the ground cracks in the mining area are mostly experimental property researches, regional verification experiments of the size of a coal face are not carried out, and only a few automatic detection methods are successfully applied to extraction of the ground cracks in the coal mining subsidence in western aeolian sandy areas in China. However, the topography of the western wind-blown sand area is relatively single, and such automatic extraction methods may not be suitable or have poor effects when facing regions with complex topography, such as loess gully regions.
Disclosure of Invention
The present disclosure is directed to solving one of the problems set forth above.
Therefore, the coal mining subsidence ground crack automatic extraction method capable of rapidly, efficiently and accurately acquiring coal mining subsidence ground crack distribution and morphological information thereof provided by the embodiment of the first aspect of the disclosure comprises the following steps:
the method comprises the steps of defining an image acquisition range of unmanned aerial vehicle photogrammetry according to underground coal mining positions and mining subsidence information, laying ground image control points and measuring three-dimensional coordinates of the ground image control points;
collecting a plurality of unmanned aerial vehicle images in the image acquisition range, performing image splicing to obtain an orthoimage of a ground fracture monitoring area, performing geometric correction on the orthoimage of the ground fracture monitoring area by using the three-dimensional coordinates of the ground image control points, and converting the orthoimage of the ground fracture monitoring area after geometric correction into a first gray image;
performing Gaussian matching filtering processing of different rotation angles on the first gray level image to realize the adaptivity of the Gaussian matching filtering processing, obtaining a second gray level image of ground fracture information having maximum response to the Gaussian matching filtering processing of the corresponding rotation angle, and recording the corresponding rotation angle as a target rotation angle;
performing Gaussian first derivative filtering processing on the first gray level image under the target rotation angle to weaken the error response to a non-ground fissure structure in Gaussian matching filtering to obtain a third gray level image;
performing linear operation on the second gray level image and the third gray level image to enhance ground fracture information and inhibit non-ground fracture information to obtain a fourth gray level image;
segmenting the fourth gray level image to realize the primary extraction of the ground fissure;
and eliminating the noise in the ground fissure which is preliminarily extracted by a morphological filtering method of path opening operation so as to realize the fine extraction of the ground fissure.
The automatic extraction method for the coal mining subsidence ground crack provided by the embodiment of the first aspect of the disclosure has the following characteristics and beneficial effects:
the automatic extraction method for the coal mining subsidence ground cracks provided by the embodiment of the first aspect of the disclosure can quickly, efficiently and accurately acquire the distribution and morphological information of the coal mining subsidence ground cracks, and particularly, the method is designed according to the monitoring requirements of areas with complex landforms and geomorphology, can acquire high automatic extraction precision in the areas, can greatly reduce the workload of field investigation, is more time-saving and labor-saving compared with the traditional ground measurement means, has more obvious advantages when the local cracks are distributed densely, realizes long-time-sequence large-range monitoring of the coal mining subsidence ground cracks, and has important significance for research on the dynamic changes of the ground cracks along with underground coal mining activities, and ecological restoration of a ground surface damage mechanism and an ecological fragile area.
In some embodiments, the range of the gaussian matched filter in the Y direction is set according to a median of statistical analysis of the length of the ground fracture fragments in the first gray-scale image, and the range of the gaussian matched filter in the X direction is set according to a median of statistical analysis of the width of the ground fracture in the ground fracture monitoring region.
In some embodiments, the rotation angles are set at equal intervals.
In some embodiments, the mathematical expression for the linear operation employed is:
wherein the content of the first and second substances,
representing the fourth grayscale image; r represents the second gray scale image; d represents the third grayscale image; ctThe parameter coefficients are adjusted for sensitivity set according to the desired crack detection sensitivity.
In some embodiments, the segmentation threshold is set according to a global mean and a standard deviation of the fourth grayscale image.
In some embodiments, when the noise in the preliminarily extracted ground fracture is removed by the morphological filtering method of the path opening operation, a tolerance value of the noise is set to enhance the robustness of the morphological filtering method of the path opening operation.
The automatic extraction element of coal mining subsidence ground crack that this first aspect embodiment of disclosure provided includes:
the image acquisition and preprocessing module is used for defining an image acquisition range of unmanned aerial vehicle photogrammetry according to underground coal mining positions and mining subsidence information, laying ground image control points and measuring three-dimensional coordinates of the ground image control points; collecting a plurality of unmanned aerial vehicle images in the image acquisition range, performing image splicing to obtain an orthoimage of a ground fracture monitoring area, performing geometric correction on the orthoimage of the ground fracture monitoring area by using the three-dimensional coordinates of the ground image control points, and converting the orthoimage of the ground fracture monitoring area after geometric correction into a first gray image;
the self-adaptive Gaussian matching filter processing module is used for carrying out Gaussian matching filter processing on the first gray level image at different rotation angles so as to realize the self-adaptability of the Gaussian matching filter processing, obtain a second gray level image with ground fracture information having maximum response to the Gaussian matching filter processing of the corresponding rotation angle, and record the corresponding rotation angle as a target rotation angle;
the first Gaussian derivative filtering processing module is used for performing first Gaussian derivative filtering processing on the first gray level image under the target rotation angle so as to weaken the error response to a non-ground fracture structure in Gaussian matching filtering and obtain a third gray level image;
the linear processing module is used for carrying out linear operation on the second gray level image and the third gray level image so as to enhance ground fracture information and inhibit non-ground fracture information to obtain a fourth gray level image;
the rough extraction module is used for segmenting the fourth gray level image so as to realize the preliminary extraction of the ground fissure;
and the fine extraction module is used for eliminating the noise in the ground fissure which is preliminarily extracted by a morphological filtering method of path opening operation so as to realize fine extraction of the ground fissure.
The computer-readable storage medium stores computer instructions for causing the computer to execute the coal mining subsidence ground fracture automatic extraction method.
Drawings
Fig. 1 is an overall flowchart of an automated extraction method for a coal mining subsidence ground fracture provided in an embodiment of the first aspect of the disclosure.
Fig. 2 (a), (b), and (c) are schematic diagrams of a transverse cross section and a longitudinal cross section of the first grayscale image and the ground fissure therein, respectively, in the extraction method provided in the embodiment of the first aspect of the disclosure.
Fig. 3 is a schematic diagram of a directed graph designed by the extraction method according to the embodiment of the first aspect of the present disclosure.
Fig. 4 is an image obtained at each stage in the extraction method provided in the embodiment of the first aspect of the present disclosure, where (a) is an original image, (b) is a crack preliminary extraction result, and (c) is a fine extraction result after crack denoising.
Fig. 5 is a coal mining subsidence ground fracture extraction result obtained by using the extraction method provided by the embodiment of the first aspect of the disclosure.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the third aspect of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
On the contrary, this application is intended to cover any alternatives, modifications, equivalents, and alternatives that may be included within the spirit and scope of the application as defined by the appended claims. Furthermore, in the following detailed description of the present application, certain specific details are set forth in order to provide a better understanding of the present application. It will be apparent to one skilled in the art that the present application may be practiced without these specific details.
Referring to fig. 1, an automatic extraction method for a coal mining subsidence ground crack provided in an embodiment of the first aspect of the disclosure specifically includes the following steps:
the method comprises the following steps of defining an image acquisition range of unmanned aerial vehicle photogrammetry according to underground coal mining positions and mining subsidence information, laying ground image control points and measuring three-dimensional coordinates of the ground image control points;
collecting a plurality of unmanned aerial vehicle images in an image acquisition range, performing image splicing to obtain an orthoimage of a ground fracture monitoring area, performing geometric correction on the orthoimage of the ground fracture monitoring area by using three-dimensional coordinates of ground image control points, and converting the orthoimage of the ground fracture monitoring area after the geometric correction into a first gray level image;
performing Gaussian matching filtering processing of different rotation angles on the first gray level image to realize the adaptivity of the Gaussian matching filtering processing, obtaining a second gray level image of ground fracture information having the maximum response to the Gaussian matching filtering processing of the corresponding rotation angle, and recording the corresponding rotation angle as a target rotation angle;
performing Gaussian first derivative filtering processing on the first gray level image at a target rotation angle to weaken the error response to a non-ground fracture structure in Gaussian matching filtering to obtain a third gray level image;
performing linear operation on the second gray level image and the third gray level image to enhance ground fracture information and inhibit non-ground fracture information to obtain a fourth gray level image;
segmenting the fourth gray level image to realize the initial extraction of the ground fissure, and representing by a binary image (the pixel values are only 0 and 1, 1 is a fissure image, and 0 is a non-fissure image);
and eliminating the noise in the ground fissure which is preliminarily extracted by a morphological filtering method of path opening operation so as to realize the fine extraction of the ground fissure.
In one embodiment, underground coal mining position and mining area mining subsidence information of a certain working face of a Caragana korshinskii coal mine are acquired according to mining system data, an image acquisition range of unmanned aerial vehicle photogrammetry is set, ground image control points are arranged, and three-dimensional coordinates of the ground image control points are measured by using a total station or RTK and the like.
In some embodiments, use unmanned aerial vehicle to carry on visible light camera, set up unmanned aerial vehicle's image and acquire flight parameters, include: the method comprises the steps of acquiring image data under the conditions of good light conditions, no wind or breeze, eliminating images with poor imaging quality, generating an orthoimage of a ground fracture monitoring area by using image splicing software (such as Pix4D mapper, Photoscan, Inpho and the like) or related splicing algorithm (such as Structure-from-Motion, abbreviated as SfM), and performing geometric correction on the orthoimage of the ground fracture monitoring area by using three-dimensional coordinates of ground image control points so as to obtain an accurate geographical position for extracting the fracture.
In some embodiments, the geometrically corrected ground fissure monitoring area ortho-image (RGB ortho-image) is converted into a gray image, which is referred to as a first gray image, and the first gray image is shown in fig. 2 (a). According to the characteristics of the ground fissure in the first gray-scale image (as shown in (b) and (c) in fig. 2, which are the longitudinal and transverse gray-scale curves of the ground fissure in the first gray-scale image respectively, the abscissa in the figure is the position on the section line, the unit is pixel, the ordinate is the gray-scale value of the corresponding position, and no unit), the first gray-scale image is subjected to adaptive Gaussian matching filtering to enhance the ground fissure information in the first gray-scale image. Setting the range of Gaussian matched filtering in the Y direction to be L (if L is set to be 20) according to the median value of the statistical analysis of the length of the ground fracture segment in the first gray level image; setting Gaussian matched filtering in X directionThe range of (A) is B, B ∈ [ -3 σ, 3 σ]σ is the standard deviation of the Gaussian function, determined from the median of the statistical analysis of the fracture width of the fracture-monitored zone (e.g., σ set to 2). Referring to fig. 2 (a), (b), (c), a first gray scale image of an exemplary earth fracture fragment and a longitudinal section line l of the earth fracture in the image are shown1And the transverse section line l2The gray scale variation curve of (2). Because the initial filter has the best enhancement effect (maximum response) only on the extended crack in the Y direction, the filter needs to be rotated by a plurality of angles to perform multiple filtering on the first gray scale image, that is, each region in the first gray scale image is respectively subjected to adaptive gaussian matching filtering processing at different rotation angles through a sliding filtering window, so as to obtain a maximum response image of ground crack information to the adaptive gaussian matching filtering, which is recorded as a second gray scale image, and the corresponding rotation angle is recorded as a target rotation angle, and the rotation angle interval is preferably 15 °. Crack information in the first gray-scale image can be enhanced through the adaptive Gaussian matching filtering processing.
In some embodiments, the mathematical expression of the adaptive gaussian matched filtering process is:
where GMF represents the gaussian matched filter employed, and its arguments are the position x, y of each pixel in the first grayscale image and the standard deviation σ of the gaussian function.
In some embodiments, the filtering rotation angle corresponding to the maximum response of the crack information at (x, y), i.e. the target rotation angle, of the first gray scale image is calculated according to the following formula:
wherein the content of the first and second substances,
is a convolution operator; thetamax(x，y)Is a target rotation angle; i is(x，y)Corresponding to the block in the first gray image for the Gaussian filter at the position (x, y);
is a rotation angle of thetaiThe gaussian matched filter of (1);
a Gaussian matched filter under a target rotation angle; r(x，y)And (3) for the maximum response value of the crack information at the position (x, y), obtaining a crack information maximum response image, namely a second gray image, which is recorded as R after the first gray image is subjected to self-adaptive Gaussian matching filtering.
In some embodiments, the first grayscale image is subjected to a gaussian first derivative filtering process to attenuate false responses to non-ground fracture structures in gaussian matched filtering. The rotation angle of the Gaussian first-order guided filter of the image I at (x, y) is equal to the rotation angle theta corresponding to the maximum response of the Gaussian matched filtermax(x，y)And similarly, sequentially performing Gaussian first-order derivative filtering and mean filtering on the first gray level image I and taking an absolute value to obtain a corresponding response image, namely a third gray level image, which is marked as D. The error response in the gray-scale image after the self-adaptive Gaussian matching filtering can be greatly weakened through the Gaussian first-order derivative filtering processing.
In one embodiment, the mathematical expression for the first derivative gaussian filtering process is:
wherein FDOG stands for the gaussian first order filter employed.
In some embodiments, the filtered image, i.e., the second gray scale image, and the first order derivative of Gaussian filtered image, i.e., the third gray scale image, are matched byAnd performing linear operation on the image to obtain a filtered image with greatly enhanced ground fracture information and better suppressed non-ground fracture information, and recording the filtered image as a fourth grayscale image. The calculation formula of the linear operation is as follows:
r and D are respectively a fourth gray-scale image, a second gray-scale image and a third gray-scale image, CtThe typical value range of the sensitivity adjustment parameter coefficient set according to the required crack detection sensitivity is 3-4, and 3 is preferred.
In some embodiments, segmenting the fourth grayscale image to achieve preliminary extraction of the earth fracture includes the following steps:
according to the fourth gray image
Global mean of
And standard deviation of
To set the division threshold value T for each of the pixels,
for the fourth gray scale image
And (4) segmenting to extract the ground cracks, and further completing the crude extraction of the ground cracks.
In some embodiments, due to complex ground background information (such as vegetation, erosion gullies and/or landslides) in a mining area, a small amount of non-ground fissure noise is still contained in the ground fissure extracted preliminarily, and considering fracture characteristics (noise is generally distributed in a disorder way, and tiny fragments of the ground fissure are closely arranged and have a significant extension trend) in the preliminary extraction result, the noise is further removed by using a morphological filtering method of path opening operation, which specifically comprises the following steps:
constructing a directed graph by using coordinate sets E of all pixel positions in the binary image of the crack primary extraction result, wherein the constructed directed graph is shown in FIG. 3, and a binary adjacency relation exists in the directed graph
Indicating that there is one edge connected from pixel a to pixel b, then pixel b is defined as the back-drive of pixel a, and pixel a is the front-drive of pixel b, and the back-drive set of all pixels m in the fourth grayscale image is represented as:
defining a set of all pixel position coordinates belonging to the crack in the pixel position coordinate set E as a set N, the subsequent set of pixels in the set N can be expressed as:
if there is an adjacency
A path δ of length l may be defined as the tuple a ═ a1，a2，a3，...，al) Wherein a is1，a2，a3，...，alAre the elements in path delta. The set consisting of all elements of the path a in the pixel position coordinate set E is represented as:
ρ(a)＝{a1，a2，a3，...，al}
all paths δ of length l are recorded as |lWherein the set of fracture pixels N has a path delta set pi of length ll(X) is noted as:
let all paths δ of length l in set N be denoted as αl(N)，αl(N) is the path opening operation with the length of l of the set N, and the mathematical expression is as follows:
αl(N)＝∪{ρ(a)：a∈Πl(N)}
and setting a tolerance value K of noise, namely the calculation of the length of the whole path is not influenced by the loss of partial pixels on the path (the number of the lost pixels is less than K), enhancing the robustness of the path morphology, setting the value K according to the number of the pixels at the interval of the actual crack fine segments, and generally setting the value K between 5 and 10. While setting a minimum value of the path length (i.e., the crack length), preferably 50, the pixels included in the path below the minimum value will be determined as noise, thereby completing the fine extraction of the ground crack. In fig. 4, (a), (b), and (c) are respectively the orthoimage of the ground fracture monitoring region after the local geometric correction, the binary image for completing the coarse extraction of the ground fracture, and the binary image for completing the fine extraction of the ground fracture, which are the local images of the ground fracture monitoring region, and the extraction result of the coal mining subsidence ground fracture in the experimental research area is shown in fig. 5.
The automatic extraction element of coal mining subsidence ground crack that this first aspect embodiment of disclosure provided includes:
the image acquisition and preprocessing module is used for defining an image acquisition range of the unmanned aerial vehicle photogrammetry according to the underground coal mining position and mining subsidence information, laying ground image control points and measuring three-dimensional coordinates of the ground image control points; collecting a plurality of unmanned aerial vehicle images in an image acquisition range, performing image splicing to obtain an orthoimage of a ground fracture monitoring area, performing geometric correction on the orthoimage of the ground fracture monitoring area by using three-dimensional coordinates of ground image control points, and converting the orthoimage of the ground fracture monitoring area after the geometric correction into a first gray level image;
the self-adaptive Gaussian matching filter processing module is used for carrying out Gaussian matching filter processing on the first gray level image at different rotation angles so as to realize the self-adaptability of the Gaussian matching filter processing, obtain a second gray level image with ground fracture information having maximum response to the Gaussian matching filter processing of the corresponding rotation angle, and record the corresponding rotation angle as a target rotation angle;
the first Gaussian derivative filtering processing module is used for carrying out first Gaussian derivative filtering processing on the first gray level image under a target rotation angle so as to weaken the error response to a non-ground fracture structure in Gaussian matching filtering and obtain a third gray level image containing ground fracture information;
the linear processing module is used for carrying out linear operation on the second gray level image and the third gray level image so as to enhance ground fracture information and inhibit non-ground fracture information to obtain a fourth gray level image;
the rough extraction module is used for segmenting the fourth gray level image so as to realize the preliminary extraction of the ground fissure;
and the fine extraction module is used for eliminating the noise in the ground fissure which is preliminarily extracted by a morphological filtering method of path opening operation so as to realize fine extraction of the ground fissure.
In order to implement the above embodiments, the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor, and is used to execute the machine tool rotation axis geometric error identification method of the above embodiments.
Referring now to FIG. 6, a block diagram of an electronic device 100 suitable for use in implementing embodiments of the present disclosure is shown. It should be noted that the electronic device 100 in the embodiment of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet), a PMP (portable multimedia player), a vehicle-mounted terminal (e.g., a car navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, a server, and the like. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6, the electronic device 100 may include a processing means (e.g., a central processing unit, a graphic processor, etc.) 101 that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)102 or a program loaded from a storage means 108 into a Random Access Memory (RAM) 103. In the RAM 103, various programs and data necessary for the operation of the electronic apparatus 100 are also stored. The processing device 101, the ROM 102, and the RAM 103 are connected to each other via a bus 104. An input/output (I/O) interface 105 is also connected to bus 104.
Generally, the following devices may be connected to the I/O interface 105: input devices 106 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, etc.; an output device 107 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 108 including, for example, magnetic tape, hard disk, etc.; and a communication device 109. The communication means 109 may allow the electronic device 100 to communicate wirelessly or by wire with other devices to exchange data. While fig. 6 illustrates an electronic device 100 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the present embodiments include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication means 109, or installed from the storage means 108, or installed from the ROM 102. The computer program, when executed by the processing device 101, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: the method comprises the following steps of defining an image acquisition range of unmanned aerial vehicle photogrammetry according to underground coal mining positions and mining subsidence information, laying ground image control points and measuring three-dimensional coordinates of the ground image control points; collecting a plurality of unmanned aerial vehicle images in an image acquisition range, performing image splicing to obtain an orthoimage of a ground fracture monitoring area, performing geometric correction on the orthoimage of the ground fracture monitoring area by using three-dimensional coordinates of ground image control points, and converting the orthoimage of the ground fracture monitoring area after the geometric correction into a first gray level image; performing Gaussian matching filtering processing of different rotation angles on the first gray level image to realize the adaptivity of the Gaussian matching filtering processing, obtaining a second gray level image of ground fracture information having the maximum response to the Gaussian matching filtering processing of the corresponding rotation angle, and recording the corresponding rotation angle as a target rotation angle; performing Gaussian first derivative filtering processing on the first gray level image at a target rotation angle to weaken the error response to a non-ground fracture structure in Gaussian matching filtering to obtain a third gray level image; performing linear operation on the second gray level image and the third gray level image to enhance ground fracture information and inhibit non-ground fracture information to obtain a fourth gray level image; segmenting the fourth gray level image to realize the primary extraction of the ground fissure; and eliminating the noise in the ground fissure which is preliminarily extracted by a morphological filtering method of path opening operation so as to realize the fine extraction of the ground fissure.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, python, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by a program instructing associated hardware to complete, and the developed program may be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (8)
1. An automatic extraction method for coal mining subsidence ground cracks is characterized by comprising the following steps:
the method comprises the steps of defining an image acquisition range of unmanned aerial vehicle photogrammetry according to underground coal mining positions and mining subsidence information, laying ground image control points and measuring three-dimensional coordinates of the ground image control points;
collecting a plurality of unmanned aerial vehicle images in the image acquisition range, performing image splicing to obtain an orthoimage of a ground fracture monitoring area, performing geometric correction on the orthoimage of the ground fracture monitoring area by using the three-dimensional coordinates of the ground image control points, and converting the orthoimage of the ground fracture monitoring area after geometric correction into a first gray image;
performing Gaussian matching filtering processing of different rotation angles on the first gray level image to realize the adaptivity of the Gaussian matching filtering processing, obtaining a second gray level image of ground fracture information having maximum response to the Gaussian matching filtering processing of the corresponding rotation angle, and recording the corresponding rotation angle as a target rotation angle;
performing Gaussian first derivative filtering processing on the first gray level image under the target rotation angle to weaken the error response to a non-ground fissure structure in Gaussian matching filtering to obtain a third gray level image;
performing linear operation on the second gray level image and the third gray level image to enhance ground fracture information and inhibit non-ground fracture information to obtain a fourth gray level image;
segmenting the fourth gray level image to realize the primary extraction of the ground fissure;
and eliminating the noise in the ground fissure which is preliminarily extracted by a morphological filtering method of path opening operation so as to realize the fine extraction of the ground fissure.
2. The automatic extraction method of the coal mining subsidence ground crack according to claim 1, wherein the range of the Gaussian matched filter in the Y direction is set according to the median value of the statistical analysis of the length of the ground crack segment in the first gray scale image, and the range of the Gaussian matched filter in the X direction is set according to the median value of the statistical analysis of the width of the ground crack in the ground crack monitoring area.
3. The automatic extraction method of coal mining subsidence ground cracks as claimed in claim 1, wherein the rotation angles are set at equal intervals.
4. The automatic extraction method of coal mining subsidence ground cracks as claimed in claim 1, wherein the mathematical expression of the linear operation is as follows:
wherein the content of the first and second substances,
representing the fourth grayscale image; r represents the second gray scale image; d represents the third grayscale image; ctThe parameters are adjusted for sensitivity set according to the desired crack detection sensitivity.
5. The automatic extraction method of coal mining subsidence ground cracks as claimed in claim 1, wherein the segmentation threshold is set according to the global mean and standard deviation of the fourth grayscale image.
6. The automatic extraction method of the coal mining subsidence ground fissure as claimed in claim 1, characterized in that when the noise in the ground fissure extracted preliminarily is removed by the morphological filtering method of the path opening operation, a tolerance value of the noise is set to enhance the robustness of the morphological filtering method of the path opening operation.
7. The utility model provides a coal mining subsidence ground crack automatic extraction element which characterized in that includes:
the image acquisition and preprocessing module is used for defining an image acquisition range of unmanned aerial vehicle photogrammetry according to underground coal mining positions and mining subsidence information, laying ground image control points and measuring three-dimensional coordinates of the ground image control points; collecting a plurality of unmanned aerial vehicle images in the image acquisition range, performing image splicing to obtain an orthoimage of a ground fracture monitoring area, performing geometric correction on the orthoimage of the ground fracture monitoring area by using the three-dimensional coordinates of the ground image control points, and converting the orthoimage of the ground fracture monitoring area after geometric correction into a first gray image;
the self-adaptive Gaussian matching filter processing module is used for carrying out Gaussian matching filter processing on the first gray level image at different rotation angles so as to realize the self-adaptability of the Gaussian matching filter processing, obtain a second gray level image with ground fracture information having maximum response to the Gaussian matching filter processing of the corresponding rotation angle, and record the corresponding rotation angle as a target rotation angle;
the first Gaussian derivative filtering processing module is used for performing first Gaussian derivative filtering processing on the first gray level image under the target rotation angle so as to weaken the error response to a non-ground fracture structure in Gaussian matching filtering and obtain a third gray level image;
the linear processing module is used for carrying out linear operation on the second gray level image and the third gray level image so as to enhance ground fracture information and inhibit non-ground fracture information to obtain a fourth gray level image;
the rough extraction module is used for segmenting the fourth gray level image so as to realize the preliminary extraction of the ground fissure;
and the fine extraction module is used for eliminating the noise in the ground fissure which is preliminarily extracted by a morphological filtering method of path opening operation so as to realize fine extraction of the ground fissure.
8. A computer-readable storage medium storing computer instructions for causing a computer to perform the automated coal mining subsidence earth fracture extraction method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111373863.XA CN114155378A (en) | 2021-11-19 | 2021-11-19 | Method and device for automatically extracting coal mining subsidence ground cracks and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111373863.XA CN114155378A (en) | 2021-11-19 | 2021-11-19 | Method and device for automatically extracting coal mining subsidence ground cracks and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114155378A true CN114155378A (en) | 2022-03-08 |
Family
ID=80457106
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111373863.XA Pending CN114155378A (en) | 2021-11-19 | 2021-11-19 | Method and device for automatically extracting coal mining subsidence ground cracks and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114155378A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782847A (en) * | 2022-06-20 | 2022-07-22 | 南京航天宏图信息技术有限公司 | Mine productivity monitoring method and device based on unmanned aerial vehicle |
| CN117456194A (en) * | 2023-12-21 | 2024-01-26 | 青岛亿联建设集团股份有限公司 | Pavement crack extraction method based on image processing |
-
2021
- 2021-11-19 CN CN202111373863.XA patent/CN114155378A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782847A (en) * | 2022-06-20 | 2022-07-22 | 南京航天宏图信息技术有限公司 | Mine productivity monitoring method and device based on unmanned aerial vehicle |
| CN117456194A (en) * | 2023-12-21 | 2024-01-26 | 青岛亿联建设集团股份有限公司 | Pavement crack extraction method based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lei et al. | A novel tunnel-lining crack recognition system based on digital image technology | |
| CN111222474B (en) | Method for detecting small target of high-resolution image with any scale | |
| EP3327198B1 (en) | Crack analyzer, crack analysis method, and crack analysis program | |
| US8144937B2 (en) | System and method for airport mapping database automatic change detection | |
| CN115496918B (en) | Method and system for detecting abnormal highway conditions based on computer vision | |
| CN114155378A (en) | Method and device for automatically extracting coal mining subsidence ground cracks and storage medium | |
| Chen et al. | Towards semi-automatic discontinuity characterization in rock tunnel faces using 3D point clouds | |
| CN110598784B (en) | Machine learning-based construction waste classification method and device | |
| US10942130B2 (en) | Damage information processing device and damage information processing method | |
| WO2019153746A1 (en) | Geological linear body extraction method based on tensor voting coupled with hough transform | |
| CN112149648B (en) | Water line identification and estimation method and device based on gray variable threshold | |
| CN111476159A (en) | Method and device for training and detecting detection model based on double-angle regression | |
| CN111507971A (en) | Tunnel surface defect detection method | |
| CN111310771B (en) | Road image extraction method, device and equipment of remote sensing image and storage medium | |
| Jiang et al. | Application of canny operator threshold adaptive segmentation algorithm combined with digital image processing in tunnel face crevice extraction | |
| Ioli et al. | UAV photogrammetry for metric evaluation of concrete bridge cracks | |
| CN117233762B (en) | Reservoir monitoring method based on GB-SAR | |
| CN107369163B (en) | Rapid SAR image target detection method based on optimal entropy dual-threshold segmentation | |
| CN113838078B (en) | Method and device for identifying and extracting coal mining subsidence ground cracks and storage medium | |
| Luo et al. | Ice flow velocity mapping in East Antarctica using historical images from 1960s to 1980s: recent progress | |
| CN114972483A (en) | Lake sediment deposition amount monitoring method and device, electronic equipment and storage medium | |
| CN107038700A (en) | Soil moisture spatial distribution characteristic quantitative analysis method based on GSSIM | |
| CN113096129B (en) | Method and device for detecting cloud cover in hyperspectral satellite image | |
| CN112668578B (en) | Pointer type instrument reading method, pointer type instrument reading device, computer equipment and storage medium | |
| CN115294148A (en) | Particle size analysis method and device based on watershed algorithm and storage medium |
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 |