CN113284092A - Automatic identification method and device for structural plane shearing failure area based on feature matching - Google Patents
Automatic identification method and device for structural plane shearing failure area based on feature matching Download PDFInfo
- Publication number
- CN113284092A CN113284092A CN202110469488.2A CN202110469488A CN113284092A CN 113284092 A CN113284092 A CN 113284092A CN 202110469488 A CN202110469488 A CN 202110469488A CN 113284092 A CN113284092 A CN 113284092A
- Authority
- CN
- China
- Prior art keywords
- image
- registered
- feature matching
- structural plane
- gray
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000010008 shearing Methods 0.000 title claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 34
- 239000011435 rock Substances 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004040 coloring Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 8
- 229920000298 Cellophane Polymers 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method and a device for automatically judging and identifying a structural plane shearing failure area based on feature matching, wherein the method comprises the following steps: acquiring an image P1 of a rock mass structural plane before a direct shear test and an image P2 after the direct shear test; registering image P1 and image P2 according to the ORB feature matching algorithm; carrying out gray processing on the registered image P1 and the registered image P2 respectively to obtain a gray image P1 'and a gray image P2'; calculating to obtain a difference image P according to the gray image P1 'and the gray image P2'; binarizing the difference image P according to an OSTU global threshold algorithm to obtain a binary image; analyzing the binary image according to an 8-link analysis method to obtain a label image PL of a damaged area; the perimeter and area of each damaged region are calculated from the label map PL. Compared with the common cellophane and CAD sketching method, the method greatly reduces human errors, reduces labor cost and avoids possible damage to structural surface contact measurement.
Description
Technical Field
The invention relates to a structural plane shearing area identification technology in the field of engineering geological exploration, in particular to a structural plane shearing damaged area automatic identification method and device based on feature matching.
Background
The rock mass is mainly composed of structural planes and rock blocks divided by the structural planes, the shear strength of the rock mass structural planes is one of the most important mechanical parameters in the stability analysis and prevention design of rock slopes, and nowadays, scholars at home and abroad always pay attention to the value taking problem of the parameters. In the current method for measuring the shear strength parameters at home and abroad, the indoor and outdoor direct shear test principle is simple, the cost is low, the test period is short, and the operation is easy, so the method is widely applied to the determination of the shear strength parameters of the rock mass structural plane. However, the error generated by measuring the area of the structural surface shear failure area in the process of indoor and outdoor direct shear tests has great influence on the test result. At present, the common method for measuring the shearing area of a structural surface by using a direct shear test is to cover transparent paper on the shearing surface, draw a contour line around the shearing surface by using a pen, and calculate the numerical value of the shearing area by using an integrator or grid paper. However, the method has the disadvantages of great human error, tedious process and long test period, and belongs to contact measurement, and for some structural surfaces with softer surfaces, the sample can be damaged to a certain extent in the measurement process. Meanwhile, the method of drawing scratches through the transparent paper enables the measurement result to be influenced by the color of the structural surface and the transparency degree of the transparent paper. Therefore, the method has great significance in researching how to improve the accuracy of the rock shearing area measurement.
Disclosure of Invention
In order to improve the efficiency and accuracy of rock shearing area measurement, the invention utilizes an ORB image feature detection algorithm to register and align structural plane images before and after a test, so that the structural plane images before and after shearing are completely registered and aligned; graying the two aligned images respectively, and performing difference on the two grayscale images to obtain a difference image before and after shearing; and (3) carrying out binarization processing on the difference image before and after shearing by using an OTSU algorithm, marking each damaged area by using an 8-connectivity analysis method to obtain a label image of each damaged area, and finally calculating the perimeter and the area of each damaged area according to the label image. The method provides a rapid and reliable measuring method for measuring the shear area of the rock mass structural plane.
The technical scheme adopted by the invention for solving the technical problems is as follows: a method and a device for automatically judging a structural plane shear failure region based on feature matching are provided.
In order to achieve the aim, the invention provides a structural plane shearing failure region automatic identification method based on feature matching, which comprises the following steps of:
acquiring an image P1 of a rock mass structural plane before a direct shear test and an image P2 after the direct shear test;
registering the image P1 and the image P2 according to an ORB feature matching algorithm to obtain a registered image P1 and a registered image P2;
performing graying processing on the registered image P1 and the registered image P2 respectively to obtain a grayscale image P1 'and a grayscale image P2';
calculating a difference image P according to the gray image P1 'and the gray image P2';
carrying out binarization processing on the difference image P according to an OSTU global threshold algorithm to obtain a binary image;
analyzing the binary image according to an 8-link analysis method to obtain a label image PL of a damaged area;
and calculating the perimeter and the area of each damaged area according to the label graph PL.
Preferably, the step of registering the image P1 and the image P2 according to an ORB feature matching algorithm to obtain a registered image P1 and a registered image P2 comprises:
finding feature points in the images P1, P2 according to an ORB feature matching algorithm;
calculating to obtain an affine transformation matrix according to the characteristic points;
based on the image P2, the image P1 and the image P2 are registered according to the affine transformation matrix, and the image P1 before the test is aligned with the image P2 after the test.
Preferably, the grayscale images P1 'and P2' are 8-bit grayscale images.
Preferably, after the step of calculating a difference image P according to a gray image P1 'and the gray image P2', the method further comprises:
and cutting the difference image P, removing irrelevant areas and setting a scale.
Preferably, after the step of calculating the perimeter and the area of each damaged area according to the label map PL, the method further includes:
and analyzing the binary image by using an 8-neighborhood analysis algorithm, and coloring in blocks.
In addition, in order to achieve the above object, the present invention further provides an automatic identification apparatus for structural plane shear failure regions based on feature matching, which includes the following modules:
the acquisition module is used for acquiring an image P1 of the rock mass structural plane before the direct shear test and an image P2 after the direct shear test;
a registration module, configured to register the image P1 and the image P2 according to an ORB feature matching algorithm, so as to obtain a registered image P1 and a registered image P2;
a graying processing module, configured to perform graying processing on the registered image P1 and the registered image P2 respectively to obtain a grayscale image P1 'and a grayscale image P2';
the calculation module is used for calculating a difference image P according to the gray image P1 'and the gray image P2';
the binarization processing module is used for carrying out binarization processing on the difference image P according to an OSTU global threshold algorithm to obtain a binary image;
the analysis module is used for analyzing the binary image according to an 8-link analysis method to obtain a label image PL of a damaged area;
the calculation module is further used for calculating the perimeter and the area of each damaged area according to the label map PL.
The technical scheme provided by the invention has the beneficial effects that: the rock mass structural plane images before and after the test are acquired by a non-contact photogrammetry method, the structural plane shear failure area is rapidly and accurately extracted, and the threshold value does not need to be determined manually. Compared with the common cellophane and CAD sketching method, the method greatly reduces human errors, reduces labor cost and avoids possible damage to structural surface contact measurement.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of the method for automatically judging the structural plane shear failure area based on feature matching according to the present invention;
FIG. 2 is a corresponding technical roadmap of FIG. 1;
FIG. 3 is an image of a structural plane of a sample of the present invention prior to direct shear testing;
FIG. 4 is a structural plane image after a direct shear test of a sample of the present invention;
FIG. 5 is a rock sample image feature detection result before and after shearing according to the present invention;
FIG. 6 is an image feature matching result of the present invention;
FIG. 7 is a pre-cropping and post-cropping image difference map of the present invention;
FIG. 8 is a graph of the difference after trimming out the invalid region according to the present invention;
FIG. 9 is a diagram illustrating a binarization result according to the present invention;
FIG. 10 is a schematic illustration of an 8 neighborhood analysis method of the present invention for blocking coloring of different failure regions;
fig. 11 is a structural diagram of the automatic structural plane shear failure region identification device based on feature matching according to the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
The embodiment of the invention provides an indoor underground emergency scene three-dimensional modeling method based on a mobile phone crowdsourcing imaging terminal.
Referring to fig. 1 and fig. 2, fig. 1 is a flowchart illustrating an implementation of a structural plane shearing failure region automatic identification method based on feature matching, and fig. 2 is a technical route diagram corresponding to fig. 1;
in this embodiment, a method for automatically identifying a structural plane shear failure region based on feature matching includes the following steps:
s1, acquiring an image P1 of the rock mass structural plane before the direct shear test and an image P2 after the direct shear test.
In this embodiment, an image P1 (refer to fig. 3) of the rock mass structural plane before the direct shear test and an image P2 (refer to fig. 4) after the direct shear test are collected by a digital camera and are imported into a computer for storage.
S2, registering the image P1 and the image P2 according to an ORB feature matching algorithm, and obtaining a registered image P1 and a registered image P2.
In this embodiment, step S2 specifically includes:
s21, extracting feature points in the images P1 and P2 according to an ORB feature matching algorithm (refer to FIG. 5);
s22, obtaining an affine transformation matrix according to the feature point calculation;
s23, based on the image P2, the image P1 and the image P2 are registered according to the affine transformation matrix, and the pre-trialing image P1 and the post-trialing image P2 are aligned (refer to fig. 6).
S3, performing graying processing on the registered image P1 and the registered image P2 respectively to obtain a grayscale image P1 'and a grayscale image P2'.
And S4, calculating a difference image P according to the gray image P1 'and the gray image P2' (refer to FIG. 7).
In this embodiment, the method further includes: the difference image P is cut out, the irrelevant area is removed (see fig. 8), and a scale is set.
S5, binarizing the difference image P according to the OSTU global threshold algorithm to obtain a binary image (refer to fig. 9).
And S6, analyzing the binary image according to an 8-way analysis method to obtain a label image PL of the damaged area.
And S7, calculating the perimeter and the area of each damaged area according to the label graph PL.
In the present embodiment, the grayscale images P1 'and P2' are 8-bit grayscale images.
Referring to fig. 10, in this embodiment, the binarized image is also analyzed by an 8-neighborhood analysis algorithm, and is colored in blocks.
By the method, the digital images before and after the image structural plane shear test can be effectively utilized to automatically judge and identify the damaged area, and the working efficiency is greatly improved.
Referring to fig. 11, in this embodiment, there is further provided an automatic identification apparatus for structural plane shear failure regions based on feature matching, including the following modules:
the acquisition module 1 is used for acquiring an image P1 of a rock mass structural plane before a direct shear test and an image P2 after the direct shear test;
a registration module 2, configured to register the image P1 and the image P2 according to an ORB feature matching algorithm, so as to obtain a registered image P1 and a registered image P2;
a graying processing module 3, configured to perform graying processing on the registered image P1 and the registered image P2 respectively to obtain a grayscale image P1 'and a grayscale image P2';
the calculating module 4 is used for calculating a difference image P according to the gray image P1 'and the gray image P2';
a binarization processing module 5, configured to perform binarization processing on the difference image P according to an OSTU global threshold algorithm to obtain a binary image;
the analysis module 6 is used for analyzing the binary image according to an 8-way analysis method to obtain a label image PL of a damaged area;
the calculating module 4 is further configured to calculate a perimeter and an area of each damaged area according to the label map PL.
The method aligns the structural plane images before and after the test by using an ORB image feature matching algorithm, grays the images according to the difference of the sample images before and after the direct shear test, extracts the change region after difference, and obtains accurate data of the rock mass structural plane shearing damage region. The method can accurately extract the structural plane shearing damage area by using a photogrammetry method, and is favorable for developing the subsequent rock structural plane parameter research.
According to the invention, the rock mass structural plane images before and after the test are acquired by a non-contact photogrammetry method, the structural plane shear failure area is rapidly and accurately extracted, and the threshold value is not required to be manually determined. Compared with the common cellophane and CAD sketching method, the method greatly reduces human errors, reduces labor cost and avoids possible damage to structural surface contact measurement.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (6)
1. An automatic identification method for a structural surface shear failure region based on feature matching is characterized by comprising the following steps of:
acquiring an image P1 of a rock mass structural plane before a direct shear test and an image P2 after the direct shear test;
registering the image P1 and the image P2 according to an ORB feature matching algorithm to obtain a registered image P1 and a registered image P2;
performing graying processing on the registered image P1 and the registered image P2 respectively to obtain a grayscale image P1 'and a grayscale image P2';
calculating a difference image P according to the gray image P1 'and the gray image P2';
carrying out binarization processing on the difference image P according to an OSTU global threshold algorithm to obtain a binary image;
analyzing the binary image according to an 8-link analysis method to obtain a label image PL of a damaged area;
and calculating the perimeter and the area of each damaged area according to the label graph PL.
2. The method for automatically identifying structural plane shear failure regions according to claim 1, wherein the step of registering the image P1 and the image P2 according to an ORB feature matching algorithm to obtain a registered image P1 and a registered image P2 comprises:
finding feature points in the images P1, P2 according to an ORB feature matching algorithm;
calculating to obtain an affine transformation matrix according to the characteristic points;
based on the image P2, the image P1 and the image P2 are registered according to the affine transformation matrix, and the image P1 before the test is aligned with the image P2 after the test.
3. The method for automatically identifying structural plane shear failure regions according to claim 1, wherein the grayscale images P1 'and P2' are 8-bit grayscale images.
4. The method for automatically identifying structural plane shear failure regions according to claim 1, wherein after the step of calculating a difference image P from a gray image P1 'and a gray image P2', the method further comprises:
and cutting the difference image P, removing irrelevant areas and setting a scale.
5. The method for automatically identifying structural shear failure regions according to claim 1, wherein after the step of calculating the perimeter and area of each failure region according to the label graph PL, the method further comprises:
and analyzing the binary image by using an 8-neighborhood analysis algorithm, and coloring in blocks.
6. The automatic identification device for the structural surface shearing failure area based on feature matching is characterized by comprising the following modules:
the acquisition module is used for acquiring an image P1 of the rock mass structural plane before the direct shear test and an image P2 after the direct shear test;
a registration module, configured to register the image P1 and the image P2 according to an ORB feature matching algorithm, so as to obtain a registered image P1 and a registered image P2;
a graying processing module: the image processing device is used for performing graying processing on the registered image P1 and the registered image P2 respectively to obtain a grayscale image P1 'and a grayscale image P2';
the calculation module is used for calculating a difference image P according to the gray image P1 'and the gray image P2';
the binarization processing module is used for carrying out binarization processing on the difference image P according to an OSTU global threshold algorithm to obtain a binary image;
the analysis module is used for analyzing the binary image according to an 8-link analysis method to obtain a label image PL of a damaged area;
the calculation module is further used for calculating the perimeter and the area of each damaged area according to the label map PL.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110469488.2A CN113284092A (en) | 2021-04-28 | 2021-04-28 | Automatic identification method and device for structural plane shearing failure area based on feature matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110469488.2A CN113284092A (en) | 2021-04-28 | 2021-04-28 | Automatic identification method and device for structural plane shearing failure area based on feature matching |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113284092A true CN113284092A (en) | 2021-08-20 |
Family
ID=77277804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110469488.2A Pending CN113284092A (en) | 2021-04-28 | 2021-04-28 | Automatic identification method and device for structural plane shearing failure area based on feature matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113284092A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102749046A (en) * | 2012-07-23 | 2012-10-24 | 中国地质大学（武汉） | Method for measuring shearing area of rock structral plane in direct shear test |
| CN110503633A (en) * | 2019-07-29 | 2019-11-26 | 西安理工大学 | A kind of applique ceramic disk detection method of surface flaw based on image difference |
| CN111640094A (en) * | 2020-05-21 | 2020-09-08 | 上海威侃电子材料有限公司 | Method and device for eliminating edge difference of detected image |
-
2021
- 2021-04-28 CN CN202110469488.2A patent/CN113284092A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102749046A (en) * | 2012-07-23 | 2012-10-24 | 中国地质大学（武汉） | Method for measuring shearing area of rock structral plane in direct shear test |
| CN110503633A (en) * | 2019-07-29 | 2019-11-26 | 西安理工大学 | A kind of applique ceramic disk detection method of surface flaw based on image difference |
| CN111640094A (en) * | 2020-05-21 | 2020-09-08 | 上海威侃电子材料有限公司 | Method and device for eliminating edge difference of detected image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11551341B2 (en) | Method and device for automatically drawing structural cracks and precisely measuring widths thereof | |
| CN111340797B (en) | Laser radar and binocular camera data fusion detection method and system | |
| Ukhwah et al. | Asphalt pavement pothole detection using deep learning method based on YOLO neural network | |
| CN112906694B (en) | Reading correction system and method for transformer substation inclined pointer instrument image | |
| CN111626146B (en) | Merging cell table segmentation recognition method based on template matching | |
| CN111489352B (en) | Tunnel gap detection and measurement method and device based on digital image processing | |
| CN104834806A (en) | Joint roughness coefficient size effect sampling representativeness evaluation method | |
| CN108711148A (en) | A kind of wheel tyre defect intelligent detecting method based on deep learning | |
| CN110837839B (en) | High-precision unmanned aerial vehicle orthographic image manufacturing and data acquisition method | |
| CN115937203B (en) | Visual detection method, device, equipment and medium based on template matching | |
| CN103400139A (en) | Method for identifying concrete crack characteristic information | |
| CN110969610A (en) | Power equipment infrared chart identification method and system based on deep learning | |
| CN114494274A (en) | Building construction evaluation method, building construction evaluation device, electronic equipment and storage medium | |
| CN113280764A (en) | Power transmission and transformation project disturbance range quantitative monitoring method and system based on multi-satellite cooperation technology | |
| Shi et al. | A method to detect earthquake-collapsed buildings from high-resolution satellite images | |
| CN115564717A (en) | Mining area ground surface crack parameter extraction method based on unmanned aerial vehicle image | |
| CN113744252A (en) | Method, apparatus, storage medium and program product for marking and detecting defects | |
| CN113284092A (en) | Automatic identification method and device for structural plane shearing failure area based on feature matching | |
| CN114005027A (en) | Urban single tree detection system and method based on unmanned aerial vehicle image | |
| Hodgson et al. | A parameterization model for transportation feature extraction | |
| CN113837996B (en) | Automatic subway tunnel defect detection method supporting manual verification | |
| CN114821044B (en) | Square pointer instrument indication recognition method based on gradient transformation | |
| CN113065556B (en) | Digital instrument positioning and digital identifying method and device and computer equipment | |
| CN110349174B (en) | Sliding rail multi-parameter measurement method and measurement device | |
| CN113627378A (en) | Line bolt defect identification method based on combination of Phash algorithm and deep learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210820 |