CN112435170A - Tunnel vault image splicing method - Google Patents
Tunnel vault image splicing method Download PDFInfo
- Publication number
- CN112435170A CN112435170A CN202011415199.6A CN202011415199A CN112435170A CN 112435170 A CN112435170 A CN 112435170A CN 202011415199 A CN202011415199 A CN 202011415199A CN 112435170 A CN112435170 A CN 112435170A
- Authority
- CN
- China
- Prior art keywords
- image
- tunnel vault
- tunnel
- peak
- vault
- 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 27
- 238000005286 illumination Methods 0.000 claims abstract description 21
- 238000012937 correction Methods 0.000 claims abstract description 16
- 238000010008 shearing Methods 0.000 claims abstract description 13
- 238000013507 mapping Methods 0.000 claims abstract description 12
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 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 7
- 238000010586 diagram Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 16
- 238000004458 analytical method Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G06T3/153—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
Abstract
The invention discloses a tunnel vault image splicing method, which comprises the following steps: acquiring tunnel vault images at uniform speed along the tunnel direction; performing illumination compensation on the tunnel vault image by adopting a histogram equalization algorithm; carrying out image shearing correction on the tunnel vault image subjected to illumination compensation; and adopting position mapping splicing to the image after shearing correction to obtain a spliced tunnel vault planar image. Through the scheme, the method has the advantages of simple logic, less calculation workload, reliable conversion and the like, and has high practical value and popularization value in the technical field of tunnel image processing.
Description
Technical Field
The invention relates to the technical field of tunnel image processing, in particular to a tunnel vault image splicing method.
Background
In tunnels such as subways and railways, due to the influence of factors such as external force and vibration, the tunnels can crack and seep water, the tunnels are periodically detected according to the requirements of operation regulations, so that whether tunnel dome segments crack, are damaged and leak water is observed, and particularly, the subway tunnels are more important. At present, the tunnel detection in China mainly adopts a manual detection means, which wastes time and labor and has low efficiency;
in addition, some intelligent equipment carries cameras to automatically collect images in the prior art, but the precision requirement of the tunnel on image collection is high, for example, the subway tunnel detection specification requires that the apparent crack width of a detection duct piece reaches 0.1mm, and the high requirement is provided for the resolution of the cameras, so that the existing intelligent equipment adopts a hardware stacking method, a plurality of (generally 6-8) linear array or area array cameras with high resolution are carried at one time, each camera is responsible for shooting a picture of the duct piece in a certain direction, and the purpose is achieved by simultaneously working the plurality of cameras. However, the proposal has the disadvantages of more equipment, heavy weight and high cost, and does not meet the requirement of rapid loading and unloading of the rail equipment. For example, in the chinese patent with the patent application number "201811228215.3" and the name "a subway tunnel appearance detection method", and in the chinese patent with the patent application number "201910387411.3" and the name "a subway tunnel structure comprehensive detection vehicle", two technologies each carry a plurality of line array or area array cameras, which have the same problem.
Based on the situation, the applicant specially provides Chinese invention patents with patent application numbers of '202010138111.4' and a name of 'a tunnel track detection robot', wherein a vault acquisition assembly is provided with a rotary driving motor, a conductive slip ring, a camera, a light source support and a vault camera, and the vault acquisition assembly acquires images of a tunnel in a rotary mode.
However, the pictures acquired in this way are in the shape of a circular arc on the tunnel vault, and the robot carries the line camera and continuously rotates to scan the tunnel vault images and then moves forward along the track. A subway tunnel appearance detection method, a subway tunnel structure comprehensive detection vehicle and a tunnel track detection robot are characterized in that images shot by the subway tunnel appearance detection vehicle are curved surface images. However, in the image stitching, detection and analysis process, a planar image is required.
Therefore, a tunnel vault image splicing method with simple logic, less calculation workload and reliable conversion is urgently needed to be provided.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a tunnel vault image splicing method, which adopts the following technical scheme:
a tunnel vault image splicing method comprises the following steps:
acquiring tunnel vault images at uniform speed along the tunnel direction by adopting a rotary linear array camera;
performing illumination compensation on the tunnel vault image by adopting a histogram equalization algorithm;
carrying out image shearing correction on the tunnel vault image subjected to illumination compensation;
and adopting position mapping splicing to the image after shearing correction to obtain a spliced tunnel vault planar image.
Further, the illumination compensation of the tunnel vault image by adopting a histogram equalization algorithm comprises the following steps:
carrying out global histogram equalization on any tunnel vault image, wherein the input image and the output image meet the following formula:
where k denotes the gray value, H denotes the height of the image, W denotes the width of the image, histO(k) Representing cumulative histogram of output imageA drawing;
obtaining the gray level P of the input image and the gray level q of the output image, wherein the gray levels P and q satisfy the following formula:
among them, histI(k) A cumulative histogram representing the input image.
Further, the image shearing correction is carried out on the tunnel vault image after the illumination compensation, and the method comprises the following steps:
carrying out affine transformation on the tunnel vault image after illumination compensation, wherein the expression is as follows:
wherein I represents the tunnel vault image after illumination compensation, I' represents the image after affine out,is the angle by which the y-direction of the image is offset,is the degree of shear in the x direction; the X direction is perpendicular to the acquisition direction, namely the height direction of the image; the Y direction refers to the direction along the tunnel acquisition, i.e. the width direction of the image.
Further, the image after the shearing correction is spliced by adopting position mapping, and the method comprises the following steps:
reading the cut and corrected image, and marking to obtain a plurality of wave crests;
selecting data between a first peak and a last peak in the plurality of peaks and data of the first peak;
and adopting position mapping and splicing to obtain a tunnel vault planar image.
Further, the reading the image after the cutting correction and marking a plurality of peaks comprises the following steps:
reading N images collected by a camera and marking the image storage time of the ith image as TiTime interval of adjacent images being Di;
Drawing a waveform diagram with the image sequence number as the abscissa and the image storage time interval as the ordinate;
if the time interval DiIf the value is larger than the preset threshold value dT, the data is marked as a peak and marked as Fi=1;
If the time interval DiIf the data is less than or equal to a preset threshold value dT, the data is marked as a non-peak and marked as Fi=0。
Furthermore, the method for obtaining the tunnel vault planar image by adopting position mapping and splicing comprises the following steps:
tiling images to be spliced along the acquisition direction;
obtaining a circle with the maximum number of images shot by the camera rotating for one circle;
traversing the image to obtain the number dIndex of the interval between adjacent wave peaksiThe expression is as follows:
dIndexi=Pk-Pk-1
wherein, PkAn image index representing the kth peak; pk-1An image index representing the k-1 peak;
obtaining the maximum value of the index, wherein the expression is as follows:
iCircle=max(dIndexi)
obtaining a row-column index value of any image to be spliced, wherein the expression is as follows:
ColIdxi=PeakCnt
RowIdxi=j-PeakIdx
wherein PeakCnt represents the number of peaks, and PeakIdx represents the index value corresponding to the peak; the value of j is the same as the index value corresponding to the wave crest;
obtaining the pixel position of any image, wherein the expression is as follows:
xi=ColIdxi*W
yi=RowIdxi*H
w denotes the width of the image and H denotes the height of the image.
Compared with the prior art, the invention has the following beneficial effects:
(1) the invention skillfully adopts the rotary linear array camera to acquire images of the vault of the tunnel, and solves the technical problem that the detection equipment of the traditional tunnel detection stacking camera is large in investment; therefore, the invention can realize the detection of one camera and the splicing of the apparent image of the tunnel segment.
(2) The invention adopts a position mapping method to project the curved surface to the plane, thus ensuring more accurate detection and analysis;
(3) the method adopts the affine transformation mode to correct the image deformation caused by the rotation and the advance of the rotating camera, and carries out the image shearing correction on the tunnel vault image after the illumination compensation, and has the advantages that: the deformation caused by the rotation and the forward movement of the rotary camera can be simply, efficiently and accurately corrected, so that the image is closer to reality.
(4) The invention adopts a histogram equalization algorithm to perform illumination compensation on the tunnel vault image, and aims to eliminate the influence caused by illumination condition change or different induction curves of imaging equipment so as to enable the histogram to be in a uniformly distributed form. The invention can enhance the contrast of the image and improve the quality of the image by carrying out histogram equalization processing on the image;
in conclusion, the method has the advantages of simple logic, less calculation workload, reliable conversion and the like, and has high practical value and popularization value in the technical field of tunnel image processing.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope of protection, and it is obvious for those skilled in the art that other related drawings can be obtained according to these drawings without inventive efforts.
FIG. 1 is a comparison of the illumination compensation of the present invention.
FIG. 2 is a comparison of before and after image cropping correction according to the present invention.
FIG. 3 is a schematic diagram of a peak mark according to the present invention.
Fig. 4 is a schematic diagram of the image tiling position according to the present invention.
Detailed Description
To further clarify the objects, technical solutions and advantages of the present application, the present invention will be further described with reference to the accompanying drawings and examples, and embodiments of the present invention include, but are not limited to, the following examples. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Examples
As shown in fig. 1 to 4, the present embodiment provides a tunnel vault image stitching method; the method comprises the following steps:
firstly, acquiring tunnel vault images at uniform speed along the tunnel direction by adopting a rotary linear array camera;
secondly, performing illumination compensation on the tunnel vault image by adopting a histogram equalization algorithm;
(21) carrying out global histogram equalization on any tunnel vault image, wherein the input image and the output image meet the following formula:
where k denotes the gray value, H denotes the height of the image, W denotes the width of the image, histO(k) A cumulative histogram representing the output image;
(22) then, the cumulative histogram of the input image and the cumulative histogram of the output image satisfy the following relationship:
wherein p, q belongs to [0,255 ];
(23) the gray level P of the input image has the following correspondence with the gray level q of the output image,
among them, histI(k) A cumulative histogram representing the input image.
Thirdly, performing image shearing correction on the tunnel vault image subjected to illumination compensation;
carrying out affine transformation on the tunnel vault image after illumination compensation, wherein the expression is as follows:
wherein I represents the tunnel vault image after illumination compensation, I' represents the image after affine out,is the angle by which the y-direction of the image is offset,the x-direction shear level is 0.04711914; the Y direction is along the tunnel acquisition direction, namely the width direction of the image; the x-direction is perpendicular to the acquisition direction, i.e. the height direction of the image.
And fourthly, adopting position mapping splicing to the image after shearing correction to obtain a spliced tunnel vault planar image. (41) Reading the cut and corrected image, and marking to obtain a plurality of wave crests;
reading N images collected by a camera and marking the image storage time of the ith image as TiIn ns, the time interval between adjacent images is DiThe unit ns;
Di=Ti-Ti-1;DO=0
i=1...N
drawing a waveform diagram with the image sequence number as the abscissa and the image storage time interval as the ordinate; in this embodiment, it is clear that the peak represents that the camera has rotated one turn;
if the time interval DiIf the value is larger than the preset threshold value dT, the data is marked as a peak and marked as Fi1 is ═ 1; in this embodiment, the threshold dT takes a value of 100000000;
if the time interval DiIf the data is less than or equal to a preset threshold value dT, the data is marked as a non-peak and marked as Fi=0。
(42) Selecting data between a first peak and a last peak in the plurality of peaks and data of the first peak;
(43) and (3) adopting position mapping and splicing to obtain a tunnel vault planar image:
tiling images to be spliced along the acquisition direction;
obtaining a circle with the maximum number of images shot by the camera rotating for one circle;
traversing the image to obtain the number dIndex of the interval between adjacent wave peaksiThe expression is as follows:
dIndexi=Pk-Pk-1
wherein, PkAn image index representing the kth peak; pk-1An image index representing the k-1 peak;
obtaining the maximum value of the index, wherein the expression is as follows:
iCircle=max(dIndexi)
obtaining a row-column index value of any image to be spliced, wherein the expression is as follows:
ColIdxi=PeakCnt
RowIdxi=j-PeakIdx
wherein PeakCnt represents the number of peaks, and PeakIdx represents the index value corresponding to the peak; the value of j is the same as the index value corresponding to the wave crest;
obtaining the pixel position of any image, wherein the expression is as follows:
xi=ColIdxi*W
yi=RowIdxi*H
a rectangular area is denoted by (x, y, W, H) to mark the pixel locations where each graph should be placed in the stitched large graph.
Then (x) of graph i is recordedi,yiW, H), where xi,yiRespectively representing the pixel coordinates of the upper left corner point of the graph;
w represents the width of the image, H represents the height of the image; in this embodiment, W ═ H ═ 4096.
The above-mentioned embodiments are only preferred embodiments of the present invention, and do not limit the scope of the present invention, but all the modifications made by the principles of the present invention and the non-inventive efforts based on the above-mentioned embodiments shall fall within the scope of the present invention.
Claims (6)
1. A tunnel vault image splicing method is characterized by comprising the following steps:
acquiring tunnel vault images at uniform speed along the tunnel direction by adopting a rotary linear array camera;
performing illumination compensation on the tunnel vault image by adopting a histogram equalization algorithm;
carrying out image shearing correction on the tunnel vault image subjected to illumination compensation;
and adopting position mapping splicing to the image after shearing correction to obtain a spliced tunnel vault planar image.
2. The tunnel vault image stitching method according to claim 1, wherein the illumination compensation of the tunnel vault image by using a histogram equalization algorithm comprises the following steps:
carrying out global histogram equalization on any tunnel vault image, wherein the input image and the output image meet the following formula:
where k represents the gray scale value and H represents the height of the imageDegree, W denotes the width of the image, histO(k) A cumulative histogram representing the output image;
obtaining the gray level P of the input image and the gray level q of the output image, wherein the gray levels P and q satisfy the following formula:
among them, histI(k) A cumulative histogram representing the input image.
3. The tunnel vault image stitching method according to claim 1, wherein the image shearing correction is performed on the illumination-compensated tunnel vault image, and the method comprises the following steps:
carrying out affine transformation on the tunnel vault image after illumination compensation, wherein the expression is as follows:
wherein I represents the tunnel vault image after illumination compensation, I' represents the image after affine out,is the angle by which the y-direction of the image is offset,is the degree of shear in the x direction; the X direction is perpendicular to the acquisition direction, namely the height direction of the image; the Y direction refers to the direction along the tunnel acquisition, i.e. the width direction of the image.
4. The tunnel vault image stitching method according to claim 1, wherein the position mapping stitching is adopted for the image after the shearing correction, and the method comprises the following steps:
reading the cut and corrected image, and marking to obtain a plurality of wave crests;
selecting data between a first peak and a last peak in the plurality of peaks and data of the first peak;
and adopting position mapping and splicing to obtain a tunnel vault planar image.
5. The tunnel vault image stitching method according to claim 4, wherein the reading of the image after the cutting correction and the marking of the plurality of peaks comprises the following steps:
reading N images collected by a camera and marking the image storage time of the ith image as TiTime interval of adjacent images being Di;
Drawing a waveform diagram with the image sequence number as the abscissa and the image storage time interval as the ordinate;
if the time interval DiIf the value is larger than the preset threshold value dT, the data is marked as a peak and marked as Fi=1;
If the time interval DiIf the data is less than or equal to a preset threshold value dT, the data is marked as a non-peak and marked as Fi=0。
6. The tunnel vault image splicing method according to claim 4, wherein the tunnel vault plane image is obtained by adopting position mapping splicing, and the method comprises the following steps:
tiling images to be spliced along the acquisition direction;
obtaining a circle with the maximum number of images shot by the camera rotating for one circle;
traversing the image to obtain the number dIndex of the interval between adjacent wave peaksiThe expression is as follows:
dIndexi=Pk-Pk-1
wherein, PkAn image index representing the kth peak; pk-1An image index representing the k-1 peak;
obtaining the maximum value of the index, wherein the expression is as follows:
iCircle=max(dIndexi)
obtaining a row-column index value of any image to be spliced, wherein the expression is as follows:
ColIdxi=PeakCnt
RowIdxi=j-PeakIdx
wherein PeakCnt represents the number of peaks, and PeakIdx represents the index value corresponding to the peak; the value of j is the same as the index value corresponding to the wave crest;
obtaining the pixel position of any image, wherein the expression is as follows:
xi=ColIdxi*W
yi=RowIdxi*H
w denotes the width of the image and H denotes the height of the image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011415199.6A CN112435170B (en) | 2020-12-04 | 2020-12-04 | Tunnel vault image splicing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011415199.6A CN112435170B (en) | 2020-12-04 | 2020-12-04 | Tunnel vault image splicing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112435170A true CN112435170A (en) | 2021-03-02 |
CN112435170B CN112435170B (en) | 2023-11-03 |
Family
ID=74691999
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011415199.6A Active CN112435170B (en) | 2020-12-04 | 2020-12-04 | Tunnel vault image splicing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112435170B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015049765A (en) * | 2013-09-03 | 2015-03-16 | 公益財団法人鉄道総合技術研究所 | Method of correcting distortion of tunnel lining surface image |
CN109358065A (en) * | 2018-10-22 | 2019-02-19 | 湖南拓达结构监测技术有限公司 | A kind of subway tunnel appearance detecting method |
CN109801216A (en) * | 2018-12-20 | 2019-05-24 | 武汉武大卓越科技有限责任公司 | The quick joining method of Tunnel testing image |
CN110033407A (en) * | 2019-03-29 | 2019-07-19 | 华中科技大学 | A kind of shield tunnel surface image scaling method, joining method and splicing system |
CN110827199A (en) * | 2019-10-29 | 2020-02-21 | 武汉大学 | Tunnel image splicing method and device based on guidance of laser range finder |
-
2020
- 2020-12-04 CN CN202011415199.6A patent/CN112435170B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015049765A (en) * | 2013-09-03 | 2015-03-16 | 公益財団法人鉄道総合技術研究所 | Method of correcting distortion of tunnel lining surface image |
CN109358065A (en) * | 2018-10-22 | 2019-02-19 | 湖南拓达结构监测技术有限公司 | A kind of subway tunnel appearance detecting method |
CN109801216A (en) * | 2018-12-20 | 2019-05-24 | 武汉武大卓越科技有限责任公司 | The quick joining method of Tunnel testing image |
CN110033407A (en) * | 2019-03-29 | 2019-07-19 | 华中科技大学 | A kind of shield tunnel surface image scaling method, joining method and splicing system |
CN110827199A (en) * | 2019-10-29 | 2020-02-21 | 武汉大学 | Tunnel image splicing method and device based on guidance of laser range finder |
Also Published As
Publication number | Publication date |
---|---|
CN112435170B (en) | 2023-11-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107471218B (en) | Binocular vision-based hand-eye coordination method for double-arm robot | |
CN1094015C (en) | Improved chromakeying system | |
CN1255767C (en) | Production of reconfiguration image data according to partial data moving distance and angle | |
CN107830813A (en) | The longaxones parts image mosaic and flexural deformation detection method of laser wire tag | |
CN1667358A (en) | Surveying method and surveying instrument | |
CN1685367A (en) | Fast two dimensional object localization based on oriented edges | |
CN102170514A (en) | Superwide-width high-speed scanner with low cost | |
CN113251926B (en) | Method and device for measuring size of irregular object | |
CN112833784B (en) | Steel rail positioning method combining monocular camera with laser scanning | |
CN112816418B (en) | Mobile phone metal middle frame defect imaging system and detection method | |
CN1878319A (en) | Video camera marking method based on plane homographic matrix characteristic line | |
CN108596869A (en) | A kind of Tunnel Lining Cracks rapid detection method | |
CN111080631A (en) | Fault positioning method and system for detecting floor defects of spliced images | |
CN113269671A (en) | Bridge apparent panorama generation method based on local and global features | |
CN115535525A (en) | Conveyor belt longitudinal tearing detection system and method based on image matching | |
CN113554559B (en) | Three-dimensional reconstruction method and device with multiple complex curved surface rotational symmetry models | |
CN112435170A (en) | Tunnel vault image splicing method | |
CN109064536B (en) | Page three-dimensional reconstruction method based on binocular structured light | |
CN106530230A (en) | PCB photoelectric image obtaining and pre-treating method | |
CN110956664B (en) | Real-time repositioning method for camera position of handheld three-dimensional scanning system | |
CN115077423B (en) | Portable high-speed turnout detection trolley and method based on line laser technology | |
CN1766928A (en) | A kind of motion object center of gravity track extraction method based on the dynamic background sport video | |
CN1888913A (en) | Rotating speed measuring method based on rotary blurred image | |
CN112862790B (en) | Subway tunnel crack positioning device and method based on linear array camera | |
CN114019950A (en) | Tunnel structure apparent disease intelligent inspection robot |
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 |