CN116597389A - Geological disaster monitoring and early warning method based on image processing - Google Patents
Geological disaster monitoring and early warning method based on image processing Download PDFInfo
- Publication number
- CN116597389A CN116597389A CN202310875725.4A CN202310875725A CN116597389A CN 116597389 A CN116597389 A CN 116597389A CN 202310875725 A CN202310875725 A CN 202310875725A CN 116597389 A CN116597389 A CN 116597389A
- Authority
- CN
- China
- Prior art keywords
- edge
- image
- marking
- crack
- sequence
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012544 monitoring process Methods 0.000 title claims abstract description 18
- 239000003550 marker Substances 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 6
- 235000008694 Humulus lupulus Nutrition 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 239000012634 fragment Substances 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 abstract description 12
- 239000002689 soil Substances 0.000 description 3
- 238000010606 normalization Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
Abstract
The invention relates to the technical field of image data processing, in particular to a geological disaster monitoring and early warning method based on image processing, which comprises the following steps: collecting a geological overlook image, carrying out grey-scale treatment on the geological overlook image, carrying out binarization and region division on the geological overlook image after grey-scale treatment, obtaining a mark sequence of a divided region, calculating the crack edge rate in the divided region according to the mark sequence, obtaining a mark image according to the crack edge rate, obtaining the crack edge of an accurate geological collapse region by using the mark image, carrying out density clustering on the crack edge of the accurate geological collapse region, and predicting the collapse region. According to the method, the acquired geological image is analyzed, the marked image is acquired according to the characteristics of the cracks of the geological collapse area to carry out watershed segmentation, so that the excessive segmentation of a watershed algorithm is avoided; and after the crack edge of the suspected collapse area is obtained, obtaining an accurate crack edge in combination with the feature, and predicting the collapse area.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a geological disaster monitoring and early warning method based on image processing.
Background
Geological disasters refer to disasters caused by damage and rupture of ground surface layers or substances such as underground rocks and soil, wherein ground subsidence is a common geological disaster, and mainly refers to underground cavities formed by damage of overlying strata, so that rock and soil bodies sink or collapse in the cavities to form collapse pits with different forms on the ground surface. The collapse is not completely without symptoms, and cracks surrounding the collapse pit are often formed in the collapse area before the collapse, so that annular or arc-shaped cracks with unequal sizes are formed, and the initially smaller cracks can be gradually expanded to cause geological collapse along with the time, so that early warning is needed to be generated when the situation that the ground is above is found to prompt people to bypass.
The traditional watershed segmentation algorithm has good response to weak edges in the image, but is sensitive to textures and noise in the gradient image because of the self texture characteristics of the uncollapsed area, and easily causes an oversarting phenomenon, which can lead to meaningless segmentation results, so that the image needs to be adaptively marked.
Disclosure of Invention
The invention provides a geological disaster monitoring and early warning method based on image processing, which aims to solve the existing problems.
The geological disaster monitoring and early warning method based on image processing adopts the following technical scheme:
the embodiment of the invention provides a geological disaster monitoring and early warning method based on image processing, which comprises the following steps:
acquiring a gray level image of a geological overlook image;
carrying out mean value filtering treatment on a gray level image of the geological overlooking image to obtain a filtered image, marking the gray level value of a pixel point in the filtered image as 1 when the gray level value of the pixel point in the filtered image is larger than the gray level value of the pixel point in the corresponding gray level image, marking the gray level value of the pixel point in the filtered image as 0 when the gray level value of the pixel point in the filtered image is smaller than or equal to the gray level value of the pixel point in the corresponding gray level image, obtaining a binary image, and dividing the binary image into areas;
acquiring a marking sequence of a dividing region, acquiring the jump number of the marking sequence according to the marking change in the marking sequence, acquiring the crack edge rate of the marking sequence according to the jump number of the marking sequence and the number of the continuous marks in the marking sequence, acquiring the crack edge rate of the dividing region according to the crack edge rate of the marking sequence, and acquiring a marking image according to the crack edge rate of the dividing region;
dividing watershed according to the marked image to obtain a divided area, obtaining the difference of two different divided edges according to the curvature of pixel points on any two different divided edges in the divided area, and obtaining the edge of the target crack according to the difference;
and carrying out density clustering on the edges of the target cracks, and predicting a collapsed region.
Further, the specific acquisition method for acquiring the mark sequence of the divided region is as follows:
using the pixel point marked as 1 nearest to the upper left corner pixel point in any divided area as a starting point, and judging whether other pixels marked as 1 exist in eight adjacent areas of the starting pointIf no other 1-marked pixel points exist in the eight adjacent areas of the selected starting point, the pixel point marked as 1 nearest to the pixel point at the upper left corner in the divided area is selected again as a new starting point, whether other 1-marked pixel points exist in the eight adjacent areas of the new starting point is judged, if other 1-marked pixel points exist in the eight adjacent areas of the selected new starting point, a two-dimensional Cartesian coordinate system is established by taking the selected new starting point as a coordinate center, the angle marks of the other 1-marked pixel points in the eight adjacent areas of the new starting point are counted, the mark with an included angle of 0-90 degrees is marked as "+", the mark with an included angle of 90-180 degrees is marked as "-", and the mark with an included angle of 180-270 degrees is marked as "";"marking the angle between 270-360 degrees as">And counting the included angles of the pixel points with the mark value of 1 in the eight neighborhood of the starting point by taking the pixel points with the mark of 1 in the eight neighborhood of the new starting point as the starting point and establishing a two-dimensional Cartesian coordinate system, carrying out angle marking according to the degrees of the included angles, traversing in sequence until the pixel points with the mark value of 1 are not in the eight neighborhood of the starting point, obtaining a mark sequence, and obtaining all the mark sequences in any divided area.
Further, the step of obtaining the crack edge rate of the marking sequence according to the jump number of the marking sequence and the number of the continuous marks in the marking sequence comprises the following specific steps:
，
in the method, in the process of the invention,for the +.>The number of hops of the tag sequence,/-, is->An exponential function with a natural constant as a base, +.>As a hyperbolic tangent function;
the acquisition method of (1) is as follows: marking fragments of the marker sequence with the same and continuously distributed markers and the number of the continuous markers being more than or equal to 2 as continuous markers in the marker sequence to obtain the +.>The number of consecutive tags in the tag sequence is denoted +.>；
Is->The number of markers comprised by the longest consecutive marker in the marker sequence,/->Is->The>The number of marks included in each successive mark, +.>For the +.>Crack edge rate for each marker sequence.
Further, the step of obtaining the crack edge rate of the dividing region according to the crack edge rate of the marking sequence and obtaining the marking image according to the crack edge rate of the dividing region comprises the following specific steps:
and acquiring the crack edge rates of all the mark sequences in any one of the divided areas, selecting the maximum crack edge rate in the mark sequences as the crack edge rate of the divided areas, presetting an edge threshold, marking the divided areas with the crack edge rate larger than the edge threshold as 0 when the crack edge rate of the divided areas is larger than the edge threshold, and marking the divided areas with the crack edge rate smaller than or equal to the edge threshold as 1 when the crack edge rate of the divided areas is smaller than or equal to the edge threshold, so as to finally obtain the marked image.
Further, the method obtains the difference of two different dividing edges according to the curvature of the pixel points on any two different dividing edges in the dividing region, and comprises the following specific steps:
marking any one parting line in the parting region as a current edge, and marking the other parting line except the current edge in the parting region as a comparison edge;
，
in the method, in the process of the invention,for the current edge->Curvature of individual pixels, +.>For the total number of pixels on the current edge, < >>To compare the%>Curvature of individual pixels, +.>To compare the total number of pixels on the edge, +.>For the distance between the centre of the current edge and the centre of the comparison edge, < >>As hyperbolic tangent function, +.>Representing the difference between the current edge and the comparison edge.
Further, the distance between the centers of the circles of the current edge and the comparison edge is specifically as follows:
and performing circle fitting on the current edge and the comparison edge by using a least square method to obtain the circle center positions of the current edge and the comparison edge, and obtaining the distance between the circle centers of the current edge and the comparison edge according to the circle center positions.
Further, the method for obtaining the edge of the target crack according to the difference comprises the following specific steps:
and acquiring the difference between any one edge and all other edges, presetting a difference threshold, taking two edges corresponding to the difference threshold as crack edges of a collapse area, when the difference is larger than or equal to the difference threshold, indicating that the crack edges which are not the collapse area exist in the two edges, acquiring the difference between all edges and other edges, and obtaining an edge set with the difference smaller than the difference threshold, wherein the edges in the edge set are marked as target crack edges.
The technical scheme of the invention has the beneficial effects that: the acquired geological image is analyzed, and the mark image is acquired according to the characteristics of the cracks of the geological collapse area to carry out watershed segmentation, so that the excessive segmentation of a watershed algorithm is avoided; and after the crack edge of the suspected collapse area is obtained, obtaining an accurate crack edge in combination with the feature, and predicting the collapse area.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of the image processing-based geological disaster monitoring and early warning method of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of the geological disaster monitoring and early warning method based on image processing according to the invention, which is provided by combining the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the geological disaster monitoring and early warning method based on image processing provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a geological disaster monitoring and early warning method based on image processing according to an embodiment of the present invention is shown, and the method includes the following steps:
and S001, collecting a geological overlook image and carrying out grey-scale treatment on the geological overlook image.
Specifically, a camera is installed at the bottom of the unmanned aerial vehicle, the unmanned aerial vehicle with the camera is utilized to shoot a geological overlook image in the air, after the geological overlook image is obtained, the geological overlook image is subjected to graying, and a gray level map of the geological overlook image is obtained, which is biased to the analysis of the subsequent steps.
So far, the unmanned aerial vehicle carrying the shooting camera acquires a geological overlooking image, and the geological overlooking image after graying is obtained.
It should be noted that, ground subsidence is a relatively common geological disaster, mainly refers to that an overlying strata is destroyed to form a subsurface cavity, so that a rock-soil body is sunk or collapses in the cavity, collapse pits with different forms are formed on the ground surface, the collapse is not completely free of symptoms, cracks surrounding the collapse pits are often formed in a subsidence area before collapse, annular or arc-shaped cracks with different sizes are formed, texture features exist in a geological surface area, and meanwhile, edges of the collapse area cannot be positioned due to inaccuracy of edges detected by an edge detection algorithm because part of the cracks are relatively small, a watershed segmentation algorithm has good response to weak edges in an image, but the watershed segmentation algorithm is sensitive to textures and noise in a gradient image because of the fact that the normal area of the geological surface also has self texture features, and overspartitional phenomenon is easily caused.
Further, in order to avoid the over-division phenomenon, the following description is made. According to the embodiment, the image is divided into the areas, the crack edge rate of each area is obtained, the marked image is obtained according to the crack edge rate of each area, and watershed segmentation is carried out according to the marked image, so that excessive segmentation is avoided. And obtaining the accurate edge of the collapse area according to the characteristics of the edge of the collapse area.
And step S002, binarizing and dividing the grey geological overlook image into areas.
It should be noted that, because the geological region has self texture features and the gray value distribution is discrete, for the crack edge, the gray value of the pixel point is smaller, the gray value of the edge pixel point after the mean value filtering treatment is influenced by the surrounding brighter pixel point, so that the gray value is larger, the filtered image and the gray value of the pixel point corresponding to the gray image are compared to obtain a binary image, and the binary image is further divided into regions.
Specifically, the average value filtering processing is performed on the gray level image of the geological overlooking image to obtain a filtered image, the gray level value of the pixel point at the corresponding position in the filtered image is compared with the gray level value of the pixel point in the gray level image, when the gray level value of the pixel point in the filtered image is larger than the gray level value of the pixel point in the corresponding gray level image, the gray level value of the pixel point is marked as 1, and when the gray level value of the pixel point in the filtered image is smaller than or equal to the gray level value of the pixel point in the corresponding gray level image, the gray level value of the pixel point is marked as 0, so that a pair of binary images is obtained.
Further, the binary image is processedThe equal division of the regions is described by taking n=10 as an example in this embodiment.
Thus, each divided region of the binary image is obtained.
And S003, acquiring a mark sequence of the dividing region, calculating the crack edge rate in the dividing region according to the mark sequence, and obtaining a mark image according to the crack edge rate.
It should be noted that, in step S002, a binary image has been acquired and a split region operation has been performed, in which the pixel point of the crack edge in the collapsed region is marked as 1, and since the crack edge satisfies a certain direction extension, if only one pixel point is isolated, the point is unlikely to be a crack edge point, and the crack edge rate of each split region is calculated according to the direction characteristics of the crack edge.
Specifically, the pixel point marked as 1 nearest to the upper left corner pixel point in any divided area is taken as a starting point, whether other pixel points marked as 1 exist or not is judged in eight adjacent areas of the starting point, if no other pixel points marked as 1 exist in the eight adjacent areas of the selected starting point, the pixel point marked as 1 nearest to the upper left corner pixel point in the divided area is selected again as a new starting point, whether other pixel points marked as 1 exist or not is judged in the eight adjacent areas of the new starting point, if other pixel points marked as 1 exist in the eight adjacent areas of the selected new starting point, a two-dimensional Cartesian coordinate system is established by taking the selected new starting point as a coordinate center, the angle marks of the other pixel points marked as 1 in the eight adjacent areas of the new starting point are counted, and the mark with an included angle of 0-90 degrees is marked as'A sign of +, "90-180 degrees, and" 180-270 degrees ""marking the angle between 270-360 degrees as">And counting the included angles of the pixel points with the mark value of 1 in the eight neighborhood of the starting point by taking the pixel points with the mark of 1 in the eight neighborhood of the new starting point as the starting point and establishing a two-dimensional Cartesian coordinate system, carrying out angle marking according to the degrees of the included angles, traversing in sequence until the pixel points with the mark value of 1 are not in the eight neighborhood of the starting point, obtaining a mark sequence, and obtaining all the mark sequences in any divided area.
It should be noted that, the multiple marker sequences obtained after the statistics are all continuous in the divided regions, i.e. all eight neighborhood connections.
Further, the jump times of the marking sequence are obtained according to the marking change in the marking sequence, and the crack edge rate is obtained according to the jump times of the marking sequence and the number of the continuous marks in the marking sequence, specifically as follows:
，
in the method, in the process of the invention,for the +.>The number of hops of the tag sequence,/-, is->An exponential function with a natural constant as a base, +.>Is a hyperbolic tangent function used for normalization;
the acquisition method of (1) is as follows: marking fragments of the marker sequence with the same and continuously distributed markers and the number of the continuous markers being more than or equal to 2 as continuous markers in the marker sequence to obtain the +.>The number of consecutive tags in the tag sequence is denoted +.>；
Is->The number of markers comprised by the longest consecutive marker in the marker sequence,/->Is->The>The number of marks included in each successive mark, +.>For the +.>Crack edge rate for each marker sequence.
When the number of hops of the marking sequence is larger, the probability that the sequence contains the edge sequence is smaller,for the significance of the longest continuous segment number in the current marking sequence, when the significance of the longest continuous segment number in the current marking sequence is larger, the current marking sequence is describedEdge rate of cracks in the column is large, +.>As for the crack edge rate of the current marking sequence, when the jump number of the sequence is smaller and the significance of the number of the longest continuous segments is larger, the possibility that the sequence contains cracks is high, namely the crack edge rate in the area corresponding to the sequence is high.
Further, the crack edge rate of all the mark sequences in any one of the divided areas is obtained, the largest crack edge rate in the mark sequences is selected as the crack edge rate of the divided areas, an edge threshold is preset, when the crack edge rate of the divided areas is larger than the edge threshold, the divided areas possibly contain the edges of the geological collapse areas, the divided areas with the crack edge rate larger than the edge threshold of the divided areas are marked as 0, when the crack edge rate of the divided areas is smaller than or equal to the edge threshold, the divided areas do not contain the edges of the geological collapse areas, and the divided areas with the crack edge rate smaller than or equal to the edge threshold of the divided areas are marked as 1, so that the marked image is finally obtained. In this embodiment, an edge threshold of 0.6 is taken as an example.
Thus, a marker image is acquired.
And S004, acquiring the accurate crack edge of the geological collapse area by using the marked image.
Specifically, a gradient image of a gray image is obtained by using a sobel operator, and watershed segmentation is performed on the gray image by using the gradient image based on a mark image, so that a plurality of segmentation areas are obtained.
The method is characterized in that the split edges of the split areas are the crack edges of the possible geological collapse areas, the characteristics of the edges of the collapse areas are combined to obtain the accurate geological collapse edges, the cracks of the known collapse areas are annular cracks formed around the collapse areas, the difference among the cracks is calculated according to the characteristics, and the cracks with small difference are the cracks of the collapse areas.
Specifically, any one of the divided edges in the divided region is designated as a current edge, and another divided edge other than the current edge in the divided region is designated as a comparison edge, so that the following description is facilitated. And performing circle fitting on the current edge and the comparison edge by using a least square method to obtain the circle center positions of the current edge and the comparison edge.
Further, the difference between the current edge and the comparison edge is obtained according to the curvatures of the current edge pixel point and the comparison edge pixel point, specifically as follows:
，
in the method, in the process of the invention,for the current edge->Curvature of individual pixels, +.>For the total number of pixels on the current edge, < >>To compare the%>Curvature of individual pixels, +.>To compare the total number of pixels on the edge, +.>For the distance between the centre of the current edge and the centre of the comparison edge, < >>Is a hyperbolic tangent function for normalization, +.>Representing the difference between the current edge and the comparison edge.
It should be noted that the number of the substrates,representing the average curvature of the current edge +.>Representing the average curvature of the comparison edge, a smaller difference in average curvature of the two edges indicates a smaller difference in the two edges, i.e., the two edges may be edges of the collapsed region, and a smaller distance between the current edge and the center of the comparison edge indicates a smaller difference in the two edges, i.e., the two edges may be cracks of the collapsed region.
Further, the difference between any one edge and all other edges is obtained, a difference threshold is set, two edges corresponding to the difference threshold are used as crack edges of a collapse area, when the difference is larger than or equal to the difference threshold, the crack edges which are not the collapse area exist in the two edges, the difference between all edges and other edges is obtained, an edge set with the difference smaller than the difference threshold is obtained, and the edges in the edge set are marked as target crack edges, namely the accurate crack edges of the geological collapse area. In this embodiment, the difference threshold is 0.4.
Thus, the accurate crack edge of the geological collapse area is obtained.
And S005, performing density clustering on the crack edges of the accurate geological collapse area, and predicting the collapse area.
Specifically, DBSCAN clustering is performed on the target crack edge pixel points obtained in the step S004, and convex hull detection is performed on the clustering result to generate a collapse area.
And early warning can be made in advance according to the predicted collapse area to remind pedestrians to detour.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. The geological disaster monitoring and early warning method based on image processing is characterized by comprising the following steps of:
acquiring a gray level image of a geological overlook image;
carrying out mean value filtering treatment on a gray level image of the geological overlooking image to obtain a filtered image, marking the gray level value of a pixel point in the filtered image as 1 when the gray level value of the pixel point in the filtered image is larger than the gray level value of the pixel point in the corresponding gray level image, marking the gray level value of the pixel point in the filtered image as 0 when the gray level value of the pixel point in the filtered image is smaller than or equal to the gray level value of the pixel point in the corresponding gray level image, obtaining a binary image, and dividing the binary image into areas;
acquiring a marking sequence of a dividing region, acquiring the jump number of the marking sequence according to the marking change in the marking sequence, acquiring the crack edge rate of the marking sequence according to the jump number of the marking sequence and the number of the continuous marks in the marking sequence, acquiring the crack edge rate of the dividing region according to the crack edge rate of the marking sequence, and acquiring a marking image according to the crack edge rate of the dividing region;
dividing watershed according to the marked image to obtain a divided area, obtaining the difference of two different divided edges according to the curvature of pixel points on any two different divided edges in the divided area, and obtaining the edge of the target crack according to the difference;
and carrying out density clustering on the edges of the target cracks, and predicting a collapsed region.
2. The geological disaster monitoring and early warning method based on image processing according to claim 1, wherein the marking sequence of the divided areas is obtained by the following specific obtaining method:
judging whether other 1-marked pixels exist in eight adjacent areas of the starting point by taking the 1-marked pixel nearest to the upper left corner pixel in any divided area as the starting point, if not, re-selecting the 1-marked pixel nearest to the upper left corner pixel in the divided area as a new starting point, and judging whether other 1-marked pixels exist in the eight adjacent areas of the new starting pointIf other pixel points marked as 1 exist in the eight adjacent domains of the selected new starting point, a two-dimensional Cartesian coordinate system is established by taking the selected new starting point as a coordinate center, other pixel point angle marks marked as 1 in the eight adjacent domains of the new starting point are counted, the mark with an included angle of 0-90 degrees is marked as "+", the mark with an included angle of 90-180 degrees is marked as "-", and the mark with an included angle of 180-270 degrees is marked as ";"marking the angle between 270-360 degrees as">And counting the included angles of the pixel points with the mark value of 1 in the eight neighborhood of the starting point by taking the pixel points with the mark of 1 in the eight neighborhood of the new starting point as the starting point and establishing a two-dimensional Cartesian coordinate system, carrying out angle marking according to the degrees of the included angles, traversing in sequence until the pixel points with the mark value of 1 are not in the eight neighborhood of the starting point, obtaining a mark sequence, and obtaining all the mark sequences in any divided area.
3. The geological disaster monitoring and early warning method based on image processing according to claim 1, wherein the step of obtaining the crack edge rate of the marking sequence according to the jump number of the marking sequence and the number of the continuous marks in the marking sequence comprises the following specific steps:
，
in the method, in the process of the invention,for the +.>The number of hops of the tag sequence,/-, is->An exponential function with a natural constant as a base, +.>As a hyperbolic tangent function;
the acquisition method of (1) is as follows: marking fragments of the marker sequence with the same and continuously distributed markers and the number of the continuous markers being more than or equal to 2 as continuous markers in the marker sequence to obtain the +.>The number of consecutive tags in the tag sequence is denoted +.>；
Is->The number of markers comprised by the longest consecutive marker in the marker sequence,/->Is->The>The number of marks included in each successive mark, +.>For the +.>Crack edge rate for each marker sequence.
4. The geological disaster monitoring and early warning method based on image processing according to claim 1, wherein the step of obtaining the crack edge rate of the divided area according to the crack edge rate of the marking sequence and obtaining the marking image according to the crack edge rate of the divided area comprises the following specific steps:
and acquiring the crack edge rates of all the mark sequences in any one of the divided areas, selecting the maximum crack edge rate in the mark sequences as the crack edge rate of the divided areas, presetting an edge threshold, marking the divided areas with the crack edge rate larger than the edge threshold as 0 when the crack edge rate of the divided areas is larger than the edge threshold, and marking the divided areas with the crack edge rate smaller than or equal to the edge threshold as 1 when the crack edge rate of the divided areas is smaller than or equal to the edge threshold, so as to finally obtain the marked image.
5. The geological disaster monitoring and early warning method based on image processing according to claim 1, wherein the difference between two different dividing edges is obtained according to the curvature of the pixel points on any two different dividing edges in the dividing region, comprising the following specific steps:
marking any one parting line in the parting region as a current edge, and marking the other parting line except the current edge in the parting region as a comparison edge;
，
in the method, in the process of the invention,for the current edge->Curvature of individual pixels, +.>For the total number of pixels on the current edge, < >>To compare the%>Curvature of individual pixels, +.>To compare the total number of pixels on the edge, +.>For the distance between the centre of the current edge and the centre of the comparison edge, < >>As hyperbolic tangent function, +.>Representing the difference between the current edge and the comparison edge.
6. The geological disaster monitoring and early warning method based on image processing according to claim 5, wherein the distance between the centers of the circles of the current edge and the comparison edge is as follows:
and performing circle fitting on the current edge and the comparison edge by using a least square method to obtain the circle center positions of the current edge and the comparison edge, and obtaining the distance between the circle centers of the current edge and the comparison edge according to the circle center positions.
7. The geological disaster monitoring and early warning method based on image processing according to claim 1, wherein the obtaining the target crack edge according to the difference comprises the following specific steps:
and acquiring the difference between any one edge and all other edges, presetting a difference threshold, taking two edges corresponding to the difference threshold as crack edges of a collapse area, when the difference is larger than or equal to the difference threshold, indicating that the crack edges which are not the collapse area exist in the two edges, acquiring the difference between all edges and other edges, and obtaining an edge set with the difference smaller than the difference threshold, wherein the edges in the edge set are marked as target crack edges.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310875725.4A CN116597389B (en) | 2023-07-18 | 2023-07-18 | Geological disaster monitoring and early warning method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310875725.4A CN116597389B (en) | 2023-07-18 | 2023-07-18 | Geological disaster monitoring and early warning method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116597389A true CN116597389A (en) | 2023-08-15 |
| CN116597389B CN116597389B (en) | 2023-09-15 |
Family
ID=87599479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310875725.4A Active CN116597389B (en) | 2023-07-18 | 2023-07-18 | Geological disaster monitoring and early warning method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116597389B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958717A (en) * | 2023-09-20 | 2023-10-27 | 山东省地质测绘院 | Intelligent geological big data cleaning method based on machine learning |
| CN117237339A (en) * | 2023-11-10 | 2023-12-15 | 山东多沃基础工程有限公司 | Ground screw punching point position selection method and system based on image processing |
| CN117291843A (en) * | 2023-11-24 | 2023-12-26 | 山东金太阳农业发展有限公司 | Efficient management method for image database |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012016242A2 (en) * | 2010-07-30 | 2012-02-02 | Aureon Biosciences, Inc. | Systems and methods for segmentation and processing of tissue images and feature extraction from same for treating, diagnosing, or predicting medical conditions |
| WO2018107939A1 (en) * | 2016-12-14 | 2018-06-21 | 国家海洋局第二海洋研究所 | Edge completeness-based optimal identification method for image segmentation |
| CN109523479A (en) * | 2018-11-10 | 2019-03-26 | 东莞理工学院 | A kind of bridge pier surface gaps visible detection method |
| CN110059555A (en) * | 2019-03-14 | 2019-07-26 | 中国人民解放军战略支援部队信息工程大学 | Based on the signal modulation classifying identification methods and device for differentiating spectrogram watershed image segmentation and decision tree more |
| CN111046783A (en) * | 2019-12-09 | 2020-04-21 | 山西能源学院 | Slope geological disaster boundary extraction method for improving watershed algorithm |
| CN111046884A (en) * | 2019-12-09 | 2020-04-21 | 太原理工大学 | Slope geological disaster extraction method of multi-feature auxiliary watershed algorithm |
| US20200394757A1 (en) * | 2019-06-17 | 2020-12-17 | Scholly Fiberoptic Gmbh | Method for marking an image region in an image of an image sequence |
| CN112365494A (en) * | 2020-11-30 | 2021-02-12 | 北京理工大学 | Ore material image segmentation method based on deep learning edge prediction |
| WO2021056997A1 (en) * | 2019-09-27 | 2021-04-01 | 成都星时代宇航科技有限公司 | Dual image display method and apparatus, and terminal and storage medium |
| US20210233647A1 (en) * | 2018-11-02 | 2021-07-29 | Hologic, Inc. | Digital imaging system and method |
| CN114511551A (en) * | 2022-02-22 | 2022-05-17 | 金华高等研究院(金华理工学院筹建工作领导小组办公室) | Ground damage identification system based on machine vision |
| CN115294139A (en) * | 2022-10-08 | 2022-11-04 | 中国电建集团江西省电力设计院有限公司 | Image-based slope crack monitoring method |
-
2023
- 2023-07-18 CN CN202310875725.4A patent/CN116597389B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012016242A2 (en) * | 2010-07-30 | 2012-02-02 | Aureon Biosciences, Inc. | Systems and methods for segmentation and processing of tissue images and feature extraction from same for treating, diagnosing, or predicting medical conditions |
| WO2018107939A1 (en) * | 2016-12-14 | 2018-06-21 | 国家海洋局第二海洋研究所 | Edge completeness-based optimal identification method for image segmentation |
| US20210233647A1 (en) * | 2018-11-02 | 2021-07-29 | Hologic, Inc. | Digital imaging system and method |
| CN109523479A (en) * | 2018-11-10 | 2019-03-26 | 东莞理工学院 | A kind of bridge pier surface gaps visible detection method |
| CN110059555A (en) * | 2019-03-14 | 2019-07-26 | 中国人民解放军战略支援部队信息工程大学 | Based on the signal modulation classifying identification methods and device for differentiating spectrogram watershed image segmentation and decision tree more |
| US20200394757A1 (en) * | 2019-06-17 | 2020-12-17 | Scholly Fiberoptic Gmbh | Method for marking an image region in an image of an image sequence |
| WO2021056997A1 (en) * | 2019-09-27 | 2021-04-01 | 成都星时代宇航科技有限公司 | Dual image display method and apparatus, and terminal and storage medium |
| CN111046783A (en) * | 2019-12-09 | 2020-04-21 | 山西能源学院 | Slope geological disaster boundary extraction method for improving watershed algorithm |
| CN111046884A (en) * | 2019-12-09 | 2020-04-21 | 太原理工大学 | Slope geological disaster extraction method of multi-feature auxiliary watershed algorithm |
| CN112365494A (en) * | 2020-11-30 | 2021-02-12 | 北京理工大学 | Ore material image segmentation method based on deep learning edge prediction |
| CN114511551A (en) * | 2022-02-22 | 2022-05-17 | 金华高等研究院(金华理工学院筹建工作领导小组办公室) | Ground damage identification system based on machine vision |
| CN115294139A (en) * | 2022-10-08 | 2022-11-04 | 中国电建集团江西省电力设计院有限公司 | Image-based slope crack monitoring method |
Non-Patent Citations (3)
| Title |
|---|
| WEIXING WANG: "A modified Watersheds Image Segmentation Algorithm for Blood Cell", 《2006 INTERNATIONAL CONFERENCE ON COMMUNICATIONS, CIRCUITS AND SYSTEMS》 * |
| 曾晟;梁乃兴;薛轲;张莹莹;: "基于扩展极大值变换沥青混合料数字图像预处理方法研究", 中外公路, no. 02 * |
| 王道峰;周传林;: "图像分析技术在混凝土桥梁裂缝识别与计算中的应用", 筑路机械与施工机械化, no. 11 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958717A (en) * | 2023-09-20 | 2023-10-27 | 山东省地质测绘院 | Intelligent geological big data cleaning method based on machine learning |
| CN116958717B (en) * | 2023-09-20 | 2023-12-12 | 山东省地质测绘院 | Intelligent geological big data cleaning method based on machine learning |
| CN117237339A (en) * | 2023-11-10 | 2023-12-15 | 山东多沃基础工程有限公司 | Ground screw punching point position selection method and system based on image processing |
| CN117237339B (en) * | 2023-11-10 | 2024-02-27 | 山东多沃基础工程有限公司 | Ground screw punching point position selection method and system based on image processing |
| CN117291843A (en) * | 2023-11-24 | 2023-12-26 | 山东金太阳农业发展有限公司 | Efficient management method for image database |
| CN117291843B (en) * | 2023-11-24 | 2024-03-15 | 山东金太阳农业发展有限公司 | Efficient management method for image database |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116597389B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116597389B (en) | Geological disaster monitoring and early warning method based on image processing | |
| US6449384B2 (en) | Method and apparatus for rapidly determining whether a digitized image frame contains an object of interest | |
| Bansal et al. | Geo-localization of street views with aerial image databases | |
| Ünsalan et al. | A system to detect houses and residential street networks in multispectral satellite images | |
| CN107092871B (en) | Remote sensing image building detection method based on multiple dimensioned multiple features fusion | |
| CN111027511B (en) | Remote sensing image ship detection method based on region of interest block extraction | |
| CN110379007B (en) | Three-dimensional highway curve reconstruction method based on vehicle-mounted mobile laser scanning point cloud | |
| US11804025B2 (en) | Methods and systems for identifying topographic features | |
| CN106651880B (en) | Offshore moving target detection method based on multi-feature fusion thermal infrared remote sensing image | |
| CN108491498A (en) | A kind of bayonet image object searching method based on multiple features detection | |
| CN108509950B (en) | Railway contact net support number plate detection and identification method based on probability feature weighted fusion | |
| CN110866926B (en) | Infrared remote sensing image rapid and fine sea-land segmentation method | |
| CN112132892B (en) | Target position labeling method, device and equipment | |
| CN115761658A (en) | Highway pavement condition detection method based on artificial intelligence | |
| CN108648200B (en) | Indirect urban high-resolution impervious surface extraction method | |
| CN109961065B (en) | Sea surface ship target detection method | |
| CN111914817B (en) | Road identification method and system based on seed points | |
| CN108694415A (en) | Image characteristic extracting method, device and water source image classification method, device | |
| Raikar et al. | Automatic building detection from satellite images using internal gray variance and digital surface model | |
| CN115880325A (en) | Building outline automatic extraction method based on point cloud dimension and spatial distance clustering | |
| CN112734745B (en) | Unmanned aerial vehicle thermal infrared image heating pipeline leakage detection method fusing GIS data | |
| CN115495611B (en) | Space scene retrieval method oriented to autonomous positioning of unmanned aerial vehicle | |
| CN115147461B (en) | Disaster real-time early warning method, system and equipment | |
| CN114863145B (en) | Sparse light connection point matching method for luminous images | |
| CN115953674A (en) | Remote sensing detection and identification method and system for circular grave relics |
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 |