CN112017114A - Method and system for splicing full image by using half image in tunnel detection - Google Patents

Method and system for splicing full image by using half image in tunnel detection Download PDF

Info

Publication number
CN112017114A
CN112017114A CN202010510612.0A CN202010510612A CN112017114A CN 112017114 A CN112017114 A CN 112017114A CN 202010510612 A CN202010510612 A CN 202010510612A CN 112017114 A CN112017114 A CN 112017114A
Authority
CN
China
Prior art keywords
picture
feature points
matching
image
radial
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
Application number
CN202010510612.0A
Other languages
Chinese (zh)
Other versions
CN112017114B (en
Inventor
谢俊
黄玉春
钟芸
黄伟宏
刘小辉
唐钰昇
任涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Communications Planning Survey And Design Institute Co ltd
Chongqing Traffic Engineering Quality Inspection Co ltd
Wuhan Jingshi Telemetry Technology Co ltd
Original Assignee
Chongqing Communications Planning Survey And Design Institute Co ltd
Chongqing Traffic Engineering Quality Inspection Co ltd
Wuhan Jingshi Telemetry Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Communications Planning Survey And Design Institute Co ltd, Chongqing Traffic Engineering Quality Inspection Co ltd, Wuhan Jingshi Telemetry Technology Co ltd filed Critical Chongqing Communications Planning Survey And Design Institute Co ltd
Priority to CN202010510612.0A priority Critical patent/CN112017114B/en
Publication of CN112017114A publication Critical patent/CN112017114A/en
Application granted granted Critical
Publication of CN112017114B publication Critical patent/CN112017114B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • 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
    • G06T7/0004—Industrial image inspection
    • 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
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30132—Masonry; Concrete
    • 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
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Image Processing (AREA)

Abstract

The invention relates to a method and a system for splicing a full image by a half image in tunnel detection, wherein the method comprises the following steps: detecting and matching feature points of overlapping areas of the two half images to be spliced at set intervals along the radial direction to obtain matched feature points of the half images; obtaining the matching characteristic point of each picture in the radial direction by a linear interpolation method according to the matching characteristic point of the half image; taking the radial coordinate of each picture in the half images on one side as a reference, and matching the radial coordinates of each picture contained in the two half images; and correspondingly splicing the pictures contained in the two half images according to the matching characteristic points. Images acquired twice before and after the tunnel measurement are spliced, the full appearance of the tunnel face is restored, and the technical problems of registration, deformation elimination and the like of the images to be spliced of the tunnel due to different acquisition time, acquisition visual angles and vehicle speed are solved.

Description

Method and system for splicing full image by using half image in tunnel detection
Technical Field
The invention relates to the technical field of tunnel detection, in particular to a method and a system for splicing a half image and a full image in tunnel detection.
Background
Image stitching is a technique for stitching several overlapped images (obtained at different times, different viewing angles or different sensors) into a large seamless high-resolution image.
Because the tunnel measuring vehicle can only drive in one direction in the tunnel, in order to ensure the definition and accuracy of the acquired image, the acquisition of the influence on the whole tunnel needs to be acquired twice. Under the condition, in order to generate a large-scale tunnel full-view image, the full-scale splicing of the tunnel images relates to the splicing problem that the serial numbers of two-time collected images in the same area are inconsistent and the image deformation of an overlapped area is inconsistent, which is caused by different time, different visual angles and different vehicle speeds.
How to completely splice a large tunnel face image is a technical problem to be solved urgently by the technical staff in the field.
Disclosure of Invention
The invention provides a method for splicing a full image by detecting a half image in a tunnel, aiming at the technical problems in the prior art, and solves the technical problems of registration, deformation elimination and the like of images to be spliced in the tunnel in the prior art, which are caused by different acquisition time, acquisition visual angles and vehicle speed.
The technical scheme for solving the technical problems is as follows: a method for splicing a half image and a full image in tunnel detection comprises the steps that the half image comprises a plurality of pictures arranged along the radial direction, and the radial direction is the advancing direction of a tunnel measuring vehicle in a tunnel;
the method comprises the following steps:
step 1, detecting and matching feature points of an overlapping area of two half images spliced at set intervals along a radial direction to obtain matched feature points of the half images;
step 2, obtaining the matching characteristic points of each picture in the radial direction by a linear interpolation method according to the matching characteristic points of the half images;
step 3, taking the radial coordinate of each picture in the half images on one side as a reference, and matching the radial coordinates of each picture contained in the two half images;
and 4, correspondingly splicing the pictures contained in the two half images according to the matching characteristic points.
A system for splicing a half image and a full image for tunnel detection is disclosed, wherein the half image comprises a plurality of pictures arranged along a radial direction, and the radial direction is the advancing direction of a tunnel measuring vehicle in a tunnel;
the system comprises:
the matched feature point detection screening module detects and matches feature points of an overlapped area of the two half images spliced at set intervals along the radial direction to obtain matched feature points of the half images;
the matching feature point determining module is used for obtaining the matching feature point of each picture in the radial direction by a linear interpolation method according to the matching feature points of the half images;
the radial matching module is used for matching the radial coordinates of each picture in the two half images by taking the radial coordinate of each picture in the half image on one side as a reference;
and the splicing module is used for correspondingly splicing each picture contained in the two half images according to the matching characteristic points.
The invention has the beneficial effects that: the invention provides a method for splicing full images of tunnel detection half images, which splices the images acquired by a tunnel measuring vehicle twice before and after, restores the full appearance of a tunnel face, solves the technical problems of registration, deformation elimination and the like of images to be spliced of a tunnel caused by different acquisition time, acquisition visual angle and vehicle speed, has high definition of the spliced tunnel section images, can synthesize the spliced section images into tunnel images with large view fields for automatically extracting tunnel diseases, and can directly calculate the size of the actual disease distribution range according to the pixel resolution ratio and evaluate the danger level of the diseases due to high splicing precision. The invention can greatly save manpower and improve the detection efficiency of tunnel defects.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, the step 1 comprises:
step 101, detecting and matching feature points according to set intervals;
102, screening the characteristic points through a Law algorithm to obtain excellent characteristic points;
step 103, calculating the slope of each pair of matched excellent feature points, establishing a group of each slope range according to a set interval, and selecting a pair of matched feature points in the group with the largest number of excellent feature points as the matched feature points of the half-frame image.
Further, in the step 101, an Open CV algorithm is adopted to perform detection and matching of the feature points:
detecting the characteristic points by using a FAST algorithm, wherein the characteristic point description operator is constructed by using an ORB algorithm;
and matching the characteristic points by using a FLANN algorithm.
Further, the process of matching the radial coordinates of each picture included in the two half images in the step 3 includes:
step 301, taking the adjacent matching feature points of the half-frame image obtained in the step 1 as a unit, calculating a ratio k of radial coordinate differences of the adjacent matching feature points on one side and the other side, and determining that the radial length of each picture on the side where the adjacent matching feature points are located is k times of the original length of the picture;
step 302, cutting and merging each picture on one side according to the radial length of each picture on one side, so that the proportion of the matched feature points of each picture on one side to the upper and lower sides of the picture on which the matched feature points are located is the same as that of the picture on the other side;
and step 303, performing radial expansion and contraction on each picture at one side to enable the radial lengths of the pictures at the two sides to be the same.
Further, before the step 4 correspondingly splices the pictures, the method includes: and performing trapezoidal deformation on the corresponding pictures at the two sides according to the transverse coordinate difference of the radially adjacent matched feature points.
Further, the trapezoidal deformation process in step 4 includes:
step 401, taking the adjacent matching feature points of the half-frame image obtained in the step 1 as a unit, respectively calculating a ratio k of a transverse coordinate difference value and a radial coordinate difference value of the adjacent matching feature points at two sides1And k2；
Step 402, calculating d1And d2Wherein x is1＝k1y1+d1，x2＝k2y2+d2，(x1，y1) Coordinates of matching feature points for a picture with one side being trapezoidally deformed, (x)2，y2) Coordinates of matching feature points of the image with the other side subjected to trapezoidal deformation;
step 403, performing trapezoidal deformation according to the horizontal lengths of the upper side and the lower side of the image with trapezoidal deformation on the two sides, wherein:
xupper left of＝k1yOn the upper part+d1，xLeft lower part＝k1yLower part+d1；
xUpper right part＝k2yOn the upper part+d2，xLower right＝k2yLower part+d2；
xUpper left ofAnd xLeft lower partTransverse length, x, of the upper and lower sides of the picture, respectively, with trapezoidal deformation of one sideUpper right partAnd xLower rightThe transverse lengths, y, of the upper and lower sides of the picture being trapezoidally deformed on the other side, respectivelyOn the upper partAnd yLower partThe radial coordinates of the upper and lower sides of the image subjected to trapezoidal deformation are respectively shown.
Further, the process of correspondingly splicing the pictures in the step 4 includes: cutting off repeated parts according to the coordinates of the matched feature points, and correcting the value of transverse cutting according to an empirical value during cutting;
and then correspondingly splicing the pictures, and stretching the spliced pictures to the width which is the same as the transverse width of the first full-width image of the tunnel after splicing.
The beneficial effect of adopting the further scheme is that: after the left and right half corresponding images are obtained, if obvious radial dislocation is caused by direct splicing, the left and right half corresponding images are spliced after trapezoidal deformation so as to ensure the continuity of the radial images.
Drawings
FIG. 1 is a flowchart of a method for detecting a full image spliced by half images in a tunnel according to the present invention;
fig. 2 is a schematic diagram of a method for calculating coordinates of matching points by linear interpolation according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a right image obtaining method corresponding to left image content according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a trapezoidal correction method for a stitched image according to an embodiment of the present invention;
FIG. 5 is a block diagram of a system for detecting a full image spliced by half images in a tunnel according to an embodiment of the present invention;
fig. 6 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
In the drawings, the components represented by the respective reference numerals are listed below:
101. the device comprises a matching feature point detection screening module 102, a matching feature point determination module 103, a radial matching module 104, a splicing module 201, a processor 202, a communication interface 203, a memory 204 and a communication bus.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flowchart of a method for splicing a full image by using a half image for tunnel detection according to the present invention, where the half image includes a plurality of pictures arranged along a radial direction, and the radial direction is a traveling direction of a tunnel measuring vehicle in a tunnel; as can be seen from fig. 1, the method for detecting a full image spliced by half images in a tunnel according to the present invention includes:
step 1, detecting and matching feature points of an overlapping area of two half images spliced according to a set interval along a radial direction to obtain matched feature points of the half images.
And 2, obtaining the matching characteristic points of each picture in the radial direction by a linear interpolation method according to the matching characteristic points of the half images.
According to the driving speed of the vehicle, the original half-frame image is basically an individual image per meter along the radial direction, as shown in fig. 2, the method for calculating the coordinates of the matching points by linear interpolation provided by the embodiment of the invention is shown, the linear interpolation is that the straight line passing through two points is used for approximating an original function, and the matching characteristic points of each individual image are obtained by the linear interpolation method according to the matching characteristic points of the left half-frame image and the right half-frame image obtained in the step 1.
And 3, taking the radial coordinate of each picture in the half image on one side as a reference, and matching the radial coordinates of each picture contained in the two half images.
And 4, correspondingly splicing each picture contained in the two half images according to the matched characteristic points.
The invention provides a method for splicing full images of tunnel detection half images, which splices the images acquired by a tunnel measuring vehicle twice before and after, restores the full appearance of a tunnel face, solves the technical problems of registration, deformation elimination and the like of images to be spliced of a tunnel caused by different acquisition time, acquisition visual angle and vehicle speed, has high definition of the spliced tunnel section images, can synthesize the spliced section images into tunnel images with large view fields for automatically extracting tunnel diseases, and can directly calculate the size of the actual disease distribution range according to the pixel resolution ratio and evaluate the danger level of the diseases due to high splicing precision. The invention can greatly save manpower and improve the detection efficiency of tunnel defects.
Example 1
The embodiment 1 provided by the invention is an embodiment of a method for splicing a full image by detecting a half image in a tunnel, and the embodiment comprises the following steps:
step 1, detecting and matching feature points of an overlapping area of two half images spliced according to a set interval along a radial direction to obtain matched feature points of the half images.
Preferably, step 1 comprises:
and 101, detecting and matching the characteristic points according to a set interval.
The set interval is flexibly set according to the detected tunnel length and the efficiency requirement, and can be 5 meters or 10 meters for example.
Further, an Open CV algorithm is adopted to detect and match the feature points:
and detecting the characteristic points by using a FAST algorithm, and constructing a characteristic point description operator by using an ORB algorithm.
And matching the characteristic points by using a FLANN algorithm.
And 102, screening the characteristic points through a Law algorithm to obtain excellent characteristic points.
After the feature points are detected and matched according to the set intervals, the number of the obtained feature points is large, so that the feature points are screened by adopting a Laue algorithm.
And 103, calculating the slope of each pair of matched excellent feature points, establishing a group of each slope range according to the set interval, and selecting a pair of matched feature points in the group with the largest number of excellent feature points as the matched feature points of the half-frame image.
The number of the feature points after screening is still large, further screening can be performed by detecting the slope between the matched feature points, if more slopes belong to a group in a slope range, a pair of matched feature points is selected from the group as the matched feature points of the half-frame image, and the interval of slope setting can be flexibly set according to the actual situation, for example, can be set to 0.01.
And 2, obtaining the matching characteristic points of each picture in the radial direction by a linear interpolation method according to the matching characteristic points of the half images.
And 3, taking the radial coordinate of each picture in the half image on one side as a reference, and matching the radial coordinates of each picture contained in the two half images.
Preferably, as shown in fig. 3, which is a schematic diagram of a right image obtaining method corresponding to the content of a left image according to an embodiment of the present invention, as can be seen from fig. 3, the process of performing radial coordinate matching on each picture included in two half images in step 3 includes:
step 301, taking the adjacent matching feature points of the half-frame image obtained in step 1 as a unit, calculating a ratio k of radial coordinate differences of the adjacent matching feature points on one side and the other side, and determining that the radial length of each picture on the side where the adjacent matching feature points are located is k times of the original length of the picture.
And step 302, cutting and merging the pictures on one side according to the radial length of the pictures on one side, so that the ratio of the matched feature points of the pictures on one side to the upper and lower sides of the picture on the other side is the same as that on the other side.
And step 303, performing radial expansion and contraction on each picture at one side to enable the radial lengths of the pictures at the two sides to be the same.
In the embodiment shown in fig. 2 and 3 in conjunction with fig. 2 and 3, each picture has a radial length of 2000 mm, a lateral length of 10000 mm, and a zero point of the upper right corner of the left image and the upper left corner of the right image.
The coordinates of the adjacent matching characteristic points A and B of the left half image are respectively (x)Left 1，yLeft 1) And (x)Left 2，yLeft 2) The coordinates of the adjacent matching feature points C and D of the right half image are respectively (x)Right 1，yRight 1) And (x)Right 2，yRight 2) And when the right picture is cut according to the left picture:
can be calculated to obtain
Figure BDA0002528071380000081
When cutting is carried out, the radial length of each picture on the right side is 2000k, and the ratio of the matching characteristic points of the pictures to the distances between the upper side and the lower side of the cut and spliced pictures is ensured to be the same.
And 4, correspondingly splicing each picture contained in the two half images according to the matched characteristic points.
Preferably, as shown in fig. 4, which is a schematic view of a trapezoidal correction method for a stitched image according to an embodiment of the present invention, as can be seen from fig. 4, before the step 4 correspondingly stitching each picture, the method includes: and performing trapezoidal deformation on the corresponding pictures at the two sides according to the transverse coordinate difference of the radially adjacent matched feature points.
The process of trapezoidal deformation comprises the following steps:
step 401, taking the adjacent matching feature points of the half-frame image obtained in step 1 as a unit, respectively calculating a ratio k of a transverse coordinate difference value and a radial coordinate difference value of the adjacent matching feature points on the two sides1And k2。
Step 402, calculating d1And d2Wherein x is1＝k1y1+d1，x2＝k2y2+d2，(x1，y1) Coordinates of matching feature points for a picture with one side being trapezoidally deformed, (x)2，y2) Coordinates of matching feature points of the image with the other side subjected to trapezoidal deformation.
Step 403, performing trapezoidal deformation according to the horizontal lengths of the upper side and the lower side of the image with trapezoidal deformation on the two sides, wherein:
xupper left of＝k1yOn the upper part+d1，xLeft lower part＝k1yLower part+d1；
xUpper right part＝k2yOn the upper part+d2，xLower right＝k2yLower part+d2。
xUpper left ofAnd xLeft lower partTransverse length, x, of the upper and lower sides of the picture, respectively, with trapezoidal deformation of one sideUpper right partAnd xLower rightThe transverse lengths, y, of the upper and lower sides of the picture being trapezoidally deformed on the other side, respectivelyOn the upper partAnd yLower partThe radial coordinates of the upper and lower sides of the image subjected to trapezoidal deformation are respectively shown.
The transverse coordinate is the coordinate in the radial vertical direction, after the left and right half corresponding images are obtained, if obvious radial dislocation is caused by direct splicing, the left and right half corresponding images are spliced after trapezoidal deformation, so that the continuity of the radial images is ensured.
Preferably, the process of correspondingly splicing the pictures in the step 4 includes: and cutting off repeated parts according to the coordinates of the matched feature points, and then correspondingly splicing the pictures.
Specifically, the value of the transverse cut is corrected according to the empirical value during cutting.
And stretching the spliced pictures into the first full-width picture of the tunnel with the same transverse width after splicing.
Example 2
The embodiment 2 provided by the invention is an embodiment of a system for splicing a full image by detecting a half image in a tunnel, the half image comprises a plurality of pictures arranged along the radial direction, and the radial direction is the advancing direction of a tunnel measuring vehicle in the tunnel; fig. 5 is a block diagram of a system for detecting a tunnel and splicing a half image with a full image according to an embodiment of the present invention, and as shown in fig. 5, the system includes: a matching feature point detection screening module 101, a matching feature point determination module 102, a radial matching module 103, and a stitching module 104.
The matching feature point detection screening module 101 detects and matches feature points of an overlapping region of two half-width images to be spliced at a set interval along the radial direction to obtain matching feature points of the half-width images.
And the matching feature point determining module 102 obtains the matching feature point of each picture in the radial direction by a linear interpolation method according to the matching feature points of the half-frame image.
The radial matching module 103 performs radial coordinate matching of each picture included in the two half images with reference to the radial coordinate of each picture in one half image.
And the splicing module 104 correspondingly splices the pictures contained in the two half images according to the matching characteristic points.
Fig. 6 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 6, the electronic device may include: the system comprises a processor 201, a communication interface 202, a memory 203 and a communication bus 204, wherein the processor 201, the communication interface 202 and the memory 203 are communicated with each other through the communication bus 204. The processor 201 may call a computer program stored on the memory 203 and executable on the processor 201 to perform the method for splicing the full image by the tunnel detection half images provided by the above embodiments, for example, including: step 1, detecting and matching feature points of an overlapping area of two half images spliced at set intervals along a radial direction to obtain matched feature points of the half images; step 2, obtaining the matching characteristic points of each picture in the radial direction by a linear interpolation method according to the matching characteristic points of the half images; step 3, taking the radial coordinate of each picture in the half images on one side as a reference, and matching the radial coordinates of each picture contained in the two half images; and 4, correspondingly splicing each picture contained in the two half images according to the matched characteristic points.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, is implemented to perform the method for splicing a full image by using a half image for tunnel detection provided in the foregoing embodiments, for example, the method includes: step 1, detecting and matching feature points of an overlapping area of two half images spliced at set intervals along a radial direction to obtain matched feature points of the half images; step 2, obtaining the matching characteristic points of each picture in the radial direction by a linear interpolation method according to the matching characteristic points of the half images; step 3, taking the radial coordinate of each picture in the half images on one side as a reference, and matching the radial coordinates of each picture contained in the two half images; and 4, correspondingly splicing each picture contained in the two half images according to the matched characteristic points.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. A method for splicing a half image and a full image in tunnel detection comprises the steps that the half image comprises a plurality of pictures arranged along the radial direction, and the radial direction is the advancing direction of a tunnel measuring vehicle in a tunnel;
characterized in that the method comprises:
step 1, detecting and matching feature points of an overlapping area of two half images spliced at set intervals along a radial direction to obtain matched feature points of the half images;
step 2, obtaining the matching characteristic points of each picture in the radial direction by a linear interpolation method according to the matching characteristic points of the half images;
step 3, taking the radial coordinate of each picture in the half images on one side as a reference, and matching the radial coordinates of each picture contained in the two half images;
and 4, correspondingly splicing the pictures contained in the two half images according to the matching characteristic points.
2. The method of claim 1, wherein step 1 comprises:
step 101, detecting and matching feature points according to set intervals;
102, screening the characteristic points through a Law algorithm to obtain excellent characteristic points;
step 103, calculating the slope of each pair of matched excellent feature points, establishing a group of each slope range according to a set interval, and selecting a pair of matched feature points in the group with the largest number of excellent feature points as the matched feature points of the half-frame image.
3. The method according to claim 2, wherein the detection and matching of the feature points are performed by using an Open CV algorithm in step 101:
detecting the characteristic points by using a FAST algorithm, wherein the characteristic point description operator is constructed by using an ORB algorithm;
and matching the characteristic points by using a FLANN algorithm.
4. The method according to claim 1, wherein the process of matching radial coordinates of each picture included in the two half images in step 3 comprises:
step 301, taking the adjacent matching feature points of the half-frame image obtained in the step 1 as a unit, calculating a ratio k of radial coordinate differences of the adjacent matching feature points on one side and the other side, and determining that the radial length of each picture on the side where the adjacent matching feature points are located is k times of the original length of the picture;
step 302, cutting and merging each picture on one side according to the radial length of each picture on one side, so that the proportion of the matched feature points of each picture on one side to the upper and lower sides of the picture on which the matched feature points are located is the same as that of the picture on the other side;
and step 303, performing radial expansion and contraction on each picture at one side to enable the radial lengths of the pictures at the two sides to be the same.
5. The method according to claim 1, wherein before the step 4 of correspondingly splicing the pictures, the method comprises: and performing trapezoidal deformation on the corresponding pictures at the two sides according to the transverse coordinate difference of the adjacent matched feature points.
6. The method of claim 5, wherein the trapezoidal deformation in step 4 comprises:
step 401, taking the adjacent matching feature points of the half-frame image obtained in the step 1 as a unit, respectively calculating a ratio k of a transverse coordinate difference value and a radial coordinate difference value of the adjacent matching feature points at two sides1And k2；
Step 402, calculating d1And d2Wherein x is1＝k1y1+d1，x2＝k2y2+d2，(x1，y1) Coordinates of matching feature points for a picture with one side being trapezoidally deformed, (x)2，y2) Coordinates of matching feature points of the image with the other side subjected to trapezoidal deformation;
step 403, performing trapezoidal deformation according to the horizontal lengths of the upper side and the lower side of the image with trapezoidal deformation on the two sides, wherein:
xupper left of＝k1yOn the upper part+d1，xLeft lower part＝k1yLower part+d1；
xUpper right part＝k2yOn the upper part+d2，xLower right＝k2yLower part+d2；
xUpper left ofAnd xLeft lower partPictures with trapezoidal deformation on one sideTransverse length of upper and lower edges, xUpper right partAnd xLower rightThe transverse lengths, y, of the upper and lower sides of the picture being trapezoidally deformed on the other side, respectivelyOn the upper partAnd yLower partThe radial coordinates of the upper and lower sides of the image subjected to trapezoidal deformation are respectively shown.
7. The method according to claim 1, wherein the process of correspondingly splicing the pictures in the step 4 comprises: cutting off repeated parts according to the coordinates of the matched feature points, and correcting the value of transverse cutting according to an empirical value during cutting; and then correspondingly splicing the pictures, and stretching the spliced pictures to the width which is the same as the transverse width of the first full-width image of the tunnel after splicing.
8. A system for splicing a half image and a full image for tunnel detection is disclosed, wherein the half image comprises a plurality of pictures arranged along a radial direction, and the radial direction is the advancing direction of a tunnel measuring vehicle in a tunnel;
characterized in that the system comprises:
the matched feature point detection screening module detects and matches feature points of an overlapped area of the two half images spliced at set intervals along the radial direction to obtain matched feature points of the half images;
the matching feature point determining module is used for obtaining the matching feature point of each picture in the radial direction by a linear interpolation method according to the matching feature points of the half images;
the radial matching module is used for matching the radial coordinates of each picture in the two half images by taking the radial coordinate of each picture in the half image on one side as a reference;
and the splicing module is used for correspondingly splicing each picture contained in the two half images according to the matching characteristic points.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method of tunnel detection of a full image stitched from a half image according to any one of claims 1 to 7.
10. A non-transitory computer readable storage medium, having stored thereon a computer program, which when executed by a processor, performs the steps of the method of tunnel detection half-image stitching a full image according to any one of claims 1 to 7.
CN202010510612.0A 2020-06-08 2020-06-08 Method and system for splicing full images of half images in tunnel detection Active CN112017114B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010510612.0A CN112017114B (en) 2020-06-08 2020-06-08 Method and system for splicing full images of half images in tunnel detection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010510612.0A CN112017114B (en) 2020-06-08 2020-06-08 Method and system for splicing full images of half images in tunnel detection

Publications (2)

Publication Number Publication Date
CN112017114A true CN112017114A (en) 2020-12-01
CN112017114B CN112017114B (en) 2023-08-04

Family

ID=73506886

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010510612.0A Active CN112017114B (en) 2020-06-08 2020-06-08 Method and system for splicing full images of half images in tunnel detection

Country Status (1)

Country Link
CN (1) CN112017114B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006163532A (en) * 2004-12-02 2006-06-22 Sony Corp Graphic information generation device and method, image processor, and information processor
CN102622732A (en) * 2012-03-14 2012-08-01 上海大学 Front-scan sonar image splicing method
CN105550995A (en) * 2016-01-27 2016-05-04 武汉武大卓越科技有限责任公司 Tunnel image splicing method and system
CN107085854A (en) * 2016-12-14 2017-08-22 中南大学 A kind of creation method of the railroad track two-dimensional map based on image processing techniques
CN107945113A (en) * 2017-11-17 2018-04-20 北京天睿空间科技股份有限公司 The antidote of topography's splicing dislocation
US9990753B1 (en) * 2017-01-11 2018-06-05 Macau University Of Science And Technology Image stitching
CN110390640A (en) * 2019-07-29 2019-10-29 齐鲁工业大学 Graph cut image split-joint method, system, equipment and medium based on template

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006163532A (en) * 2004-12-02 2006-06-22 Sony Corp Graphic information generation device and method, image processor, and information processor
CN102622732A (en) * 2012-03-14 2012-08-01 上海大学 Front-scan sonar image splicing method
CN105550995A (en) * 2016-01-27 2016-05-04 武汉武大卓越科技有限责任公司 Tunnel image splicing method and system
CN107085854A (en) * 2016-12-14 2017-08-22 中南大学 A kind of creation method of the railroad track two-dimensional map based on image processing techniques
US9990753B1 (en) * 2017-01-11 2018-06-05 Macau University Of Science And Technology Image stitching
CN107945113A (en) * 2017-11-17 2018-04-20 北京天睿空间科技股份有限公司 The antidote of topography's splicing dislocation
CN110390640A (en) * 2019-07-29 2019-10-29 齐鲁工业大学 Graph cut image split-joint method, system, equipment and medium based on template

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
GAVRILOVA 等: "Detection of resampling supplemented with noise inconsistencies analysis for image forensic", 《INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCES AND ITS APPLICATIONS, PROCEEDINGS》 *
张宝龙;李洪蕊;李丹;戴凤智;: "一种针对车载全景***的图像拼接算法的仿真", 电子与信息学报 *

Also Published As

Publication number Publication date
CN112017114B (en) 2023-08-04

Similar Documents

Publication Publication Date Title
US10210605B2 (en) Method and device for detecting boundary of region on display motherboard
CN116165216B (en) Liquid crystal display micro scratch flaw 3D detection method, system and computing equipment
CN108871185B (en) Method, device and equipment for detecting parts and computer readable storage medium
CN103927749A (en) Image processing method and device and automatic optical detector
CN109801216A (en) The quick joining method of Tunnel testing image
CN107367245B (en) Invalid point detection and elimination method in optical three-dimensional profile measurement
CN115535525A (en) Conveyor belt longitudinal tearing detection system and method based on image matching
US10516822B2 (en) Method and device for merging images of calibration devices
CN107578001B (en) Method and device for testing resolution of fingerprint acquisition equipment
CN112017114B (en) Method and system for splicing full images of half images in tunnel detection
JP5149403B2 (en) Image inspection method and image inspection apparatus
CN101762967B (en) Photographing width measurement assistant strip, wide-angle image photographing method, method and device for partially splicing two adjacent images
CN114427835B (en) Method and device for detecting center of supporting hole in mine under low illumination
JP5157575B2 (en) Defect detection method
CN109146916A (en) A kind of moving body track method and device
CN108303640B (en) Line detection method and device
JP2019120644A (en) Surface inspection device and surface inspection method
CN109215068B (en) Image magnification measuring method and device
JP2016144993A (en) Image processing apparatus
CN113866183B (en) Fault detection method and device for strip steel surface detector
CN115015290B (en) Foreign matter detection method and device for glass fiber cloth cover
CN116958104B (en) Material surface image processing method, device and storage medium
JP5134097B2 (en) Image inspection method and image inspection apparatus
JPH06103968B2 (en) Image processor for overhead line inspection
CN116363211A (en) Calibration method and device for display screen space geometric correction

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