CN115619782B - Shaft 360 panorama splicing detection system and method based on machine vision - Google Patents
Shaft 360 panorama splicing detection system and method based on machine vision Download PDFInfo
- Publication number
- CN115619782B CN115619782B CN202211610253.1A CN202211610253A CN115619782B CN 115619782 B CN115619782 B CN 115619782B CN 202211610253 A CN202211610253 A CN 202211610253A CN 115619782 B CN115619782 B CN 115619782B
- Authority
- CN
- China
- Prior art keywords
- shaft
- image
- images
- characteristic points
- detection
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 238000012552 review Methods 0.000 claims description 28
- 238000005259 measurement Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 239000013589 supplement Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001454 recorded image Methods 0.000 description 1
- 230000003068 static effect Effects 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
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention is suitable for the technical field of visual detection, and provides a shaft 360 panorama splicing detection system and method based on machine vision, which comprises the following steps: controlling the elevator to move along the inside of the shaft by operating a program; shooting the inner wall of the shaft for 360 degrees through a plurality of high-speed cameras to obtain a plurality of shaft images, and shooting each high-speed camera once every set time value; transversely splicing the shaft images shot at the same time according to the characteristic points to obtain a plurality of transversely spliced images, vertically splicing the transversely spliced images according to the characteristic points to obtain a panoramic image, marking a plurality of characteristic points on the inner wall of the shaft, uniformly distributing the characteristic points, and setting transverse values and vertical values of the characteristic points; and performing similarity calculation on the panoramic image and the detection standard image, and generating an alarm signal when the similarity is smaller than a standard value. The invention does not need to stop in the shooting process, realizes automatic detection and analysis and is more convenient to use.
Description
Technical Field
The invention relates to the technical field of visual detection, in particular to a shaft 360 panorama splicing detection system and method based on machine vision.
Background
In actual use, timing inspection needs to be carried out on the shaft, and potential safety hazards are checked in time. But because equipment is complicated various in the pit shaft, the environment is abominable, can use fish eye wide angle lens to assist the inspection at present, current technical scheme core: the fisheye wide-angle lens is simply used for realizing 360-degree panoramic images through 360-degree rotation, and whether abnormity exists is detected manually according to spliced images. The current scheme has the following disadvantages: real-time high-speed shooting cannot be realized and automatic detection cannot be realized. Reasons for the inability to detect at high speed: stopping the fish-eye wide-angle lens after reaching one position, controlling the fish-eye wide-angle lens to rotate for one circle, shooting a shaft, then reaching the next position, and repeating the processes; the reason that automatic detection cannot be realized is as follows: the scheme is that recorded image videos are manually checked and analyzed frame by frame. Therefore, it is desirable to provide a system and a method for detecting a panoramic stitching of a wellbore 360 based on machine vision, which aim to solve the above problems.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a shaft 360 panoramic stitching detection system and method based on machine vision so as to solve the problems in the background technology.
The invention is realized in such a way that a shaft 360 panoramic splicing detection method based on machine vision comprises the following steps:
the method comprises the following steps that a lift is controlled to move along the inside of a shaft through an operation program, the operation program comprises moving speed, moving time and moving coordinates, and a plurality of high-speed cameras and highlight stroboscopic light supplement lamps are installed on the lift;
shooting the inner wall of a shaft for 360 degrees through a plurality of high-speed cameras to obtain a plurality of shaft images, wherein each high-speed camera carries out shooting at set time intervals, and two adjacent shaft images have overlapping parts;
transversely splicing the shaft images shot at the same time according to the characteristic points to obtain a plurality of transversely spliced images, vertically splicing the transversely spliced images according to the characteristic points to obtain a panoramic image, marking a plurality of characteristic points on the inner wall of the shaft, uniformly distributing the characteristic points, setting transverse values and vertical values of the characteristic points, and enabling each shaft image to have only one characteristic point;
and performing similarity calculation on the panoramic image and the detection standard image, and generating an alarm signal when the similarity is smaller than a standard value.
As a further scheme of the invention: according to the characteristic point, transversely splicing the shaft images shot at the same moment to obtain a plurality of transversely spliced images, the method specifically comprises the following steps:
transversely arranging a plurality of shaft images shot at the same time;
identifying characteristic points in each shaft image, and determining the distance between two adjacent shaft images in the arrangement according to the transverse value of the characteristic points;
and cutting the overlapped part of the two adjacent shaft images to obtain a transverse spliced image.
As a further scheme of the invention: the step of calculating the similarity between the panoramic image and the detection standard image specifically comprises:
respectively calculating the hash values of the panoramic image and the detection standard image by using a hash method based on DCT to obtain h _1 and h _2;
calculating a Hamming distance dis _ h between h _1 and h _2;
and calculating to obtain the similarity between the panoramic image and the detection standard image according to the Hamming distance dis _ h.
As a further scheme of the invention: the method further comprises the following steps:
measuring the distance of a core detection point by a plurality of laser distance measuring sensors to obtain a distance value, wherein the plurality of laser distance measuring sensors are arranged on the lifter;
and when the distance value is greater than the corresponding distance set value, generating alarm information.
As a further scheme of the invention: the method further comprises the following steps:
receiving a review instruction, wherein the review instruction comprises a moving coordinate;
and moving the elevator to the moving coordinate, and shooting the inner wall of the shaft for 360 degrees to obtain a shaft image.
Another object of the present invention is to provide a machine vision-based wellbore 360 panoramic stitching detection system, which comprises:
the system comprises a lift movement control module, a shaft control module and a control module, wherein the lift movement control module is used for controlling a lift to move along the inside of a shaft through an operation program, the operation program comprises a movement speed, a movement time and a movement coordinate, and the lift is provided with a plurality of high-speed cameras and a high-brightness stroboscopic light supplementing lamp;
the 360-degree shooting module is used for shooting the inner wall of the shaft at 360 degrees through a plurality of high-speed cameras to obtain a plurality of shaft images, each high-speed camera shoots once every set time value, and two adjacent shaft images have overlapping parts;
the shaft image splicing module is used for transversely splicing shaft images shot at the same time according to the characteristic points to obtain a plurality of transversely spliced images, and vertically splicing the transversely spliced images according to the characteristic points to obtain a panoramic image, wherein the inner wall of the shaft is marked with a plurality of characteristic points which are uniformly distributed and provided with a transverse value and a vertical value of the characteristic points, and each shaft image has one characteristic point;
and the similarity detection module is used for calculating the similarity of the panoramic image and the detection standard image and generating an alarm signal when the similarity is smaller than a standard value.
As a further scheme of the invention: the wellbore image stitching module comprises:
the transverse arrangement unit is used for transversely arranging a plurality of shaft images shot at the same time;
the interval determining unit is used for identifying characteristic points in each shaft image and determining the distance between two adjacent shaft images in the arrangement according to the transverse values of the characteristic points;
and the overlapping part cutting unit is used for cutting the overlapping parts of the two adjacent shaft images to obtain a transverse spliced image.
As a further scheme of the invention: the similarity detection module includes:
a hash value calculation unit which calculates the hash values of the panoramic image and the detection standard image respectively by using a hash method based on DCT to obtain h _1 and h _2;
a Hamming distance calculation unit for calculating a Hamming distance dis _ h between h _1 and h _2;
and the similarity calculation unit is used for calculating the similarity between the panoramic image and the detection standard image according to the Hamming distance dis _ h.
As a further scheme of the invention: the system further comprises a core point detection module, wherein the core point detection module specifically comprises:
the core point ranging unit is used for ranging the core detection points through a plurality of laser ranging sensors to obtain a distance value, and the lifter is provided with a plurality of laser ranging sensors;
and the alarm information generation unit generates alarm information when the distance value is greater than the corresponding distance set value.
As a further scheme of the invention: the system further comprises a remote review module, wherein the remote review module specifically comprises:
the device comprises a review instruction receiving unit, a review processing unit and a review processing unit, wherein the review instruction receiving unit is used for receiving a review instruction which comprises a moving coordinate;
and the rechecking image determining unit is used for enabling the elevator to move to the moving coordinate and shooting the inner wall of the shaft for 360 degrees to obtain a shaft image.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, a plurality of shaft images are obtained by shooting the inner wall of the shaft by 360 degrees through a plurality of high-speed cameras, so that high-speed shooting is realized, stopping is not required in the shooting process, and the efficiency is high. According to the invention, the shaft images shot at the same time can be transversely spliced according to the characteristic points to obtain a plurality of transversely spliced images, the transversely spliced images are vertically spliced according to the characteristic points to obtain a panoramic image, the panoramic image and the detection standard image are subjected to similarity calculation, and when the similarity is smaller than a standard value, an alarm signal is generated, so that automatic detection and analysis are realized, and the use is more convenient.
Drawings
Fig. 1 is a flowchart of a method for detecting a panoramic stitching of a wellbore 360 based on machine vision.
Fig. 2 is a flow chart of a shaft 360 panorama stitching detection method based on machine vision, in which shaft images shot at the same time are transversely stitched according to feature points to obtain a plurality of transversely stitched images.
Fig. 3 is a flowchart of similarity calculation between a panoramic image and a detection standard image in a wellbore 360 panoramic stitching detection method based on machine vision.
Fig. 4 is a flow chart of performing distance measurement on a core detection point through a plurality of laser distance measurement sensors in a shaft 360 panoramic stitching detection method based on machine vision.
Fig. 5 is a flowchart for receiving a review instruction in a wellbore 360 panoramic stitching detection method based on machine vision.
Fig. 6 is a schematic structural diagram of a wellbore 360 panoramic stitching detection system based on machine vision.
Fig. 7 is a schematic structural diagram of a wellbore image stitching module in a wellbore 360 panoramic stitching detection system based on machine vision.
Fig. 8 is a schematic structural diagram of a similarity detection module in a wellbore 360 panoramic stitching detection system based on machine vision.
Fig. 9 is a schematic structural diagram of a core point detection module in a wellbore 360 panoramic stitching detection system based on machine vision.
Fig. 10 is a schematic structural diagram of a remote review module in a machine vision-based wellbore 360 panoramic stitching detection system.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Specific implementations of the present invention are described in detail below with reference to specific embodiments.
As shown in fig. 1, an embodiment of the present invention provides a method for detecting a panoramic stitching of a wellbore 360 based on machine vision, the method including the following steps:
s100, controlling a lifter to move along the inside of a shaft through an operation program, wherein the operation program comprises moving speed, moving time and moving coordinates, and the lifter is provided with a plurality of high-speed cameras and highlight stroboscopic light supplement lamps;
s200, shooting the inner wall of the shaft for 360 degrees through a plurality of high-speed cameras to obtain a plurality of shaft images, wherein each high-speed camera carries out shooting at set time intervals, and two adjacent shaft images have overlapping parts;
s300, transversely splicing the shaft images shot at the same time according to the characteristic points to obtain a plurality of transversely spliced images, vertically splicing the plurality of transversely spliced images according to the characteristic points to obtain a panoramic image, marking a plurality of characteristic points on the inner wall of the shaft, uniformly distributing the characteristic points, setting a transverse value and a vertical value of the characteristic points, and only one characteristic point exists in each shaft image;
s400, similarity calculation is carried out on the panoramic image and the detection standard image, and when the similarity is smaller than a standard value, an alarm signal is generated.
In the embodiment of the invention, firstly, a plurality of high-speed cameras are installed on a lift, preferably, the number of the high-speed cameras is 5, so that 360-degree shooting can be well performed, in addition, a highlight stroboscopic light supplement lamp is installed on the lift for light supplement, so that the shooting effect is better, the embodiment of the invention can control the lift to move along the inside of a shaft through an operation program, the operation program comprises a moving speed, moving time and a moving coordinate, the moving speed is a fixed value, the moving coordinate changes along with the moving time, the moving coordinate reflects the position of the lift, when the lift moves along the inside of the shaft, the high-speed cameras perform shooting at intervals of a set time value, the set time value is related to the moving speed, the understanding is easy, the larger the moving speed is, the smaller the set time value is, and thus shaft images along the vertical direction can be continuous. It should be noted that, the inner wall of the shaft is marked with a plurality of characteristic points, the characteristic points are bright in color and convenient for automatic identification, the characteristic points are uniformly distributed in an array, and are provided with transverse values and vertical values of the characteristic points, each shaft image has only one characteristic point, that is, each transverse row has five characteristic points, the five characteristic points correspond to the positions of 5 high-speed cameras, and the vertical value of the characteristic points is equal to the moving speed and a set time value; after the shaft image is collected, transversely splicing shaft images shot at the same time according to the characteristic points to obtain a plurality of transversely spliced images, vertically splicing the plurality of transversely spliced images according to the characteristic points to obtain a panoramic image, finally calculating the similarity of the panoramic image and a detection standard image, and generating an alarm signal when the similarity is smaller than a standard value, wherein the detection standard image is stored in advance, the detection standard image is shot under the condition that the shaft is completely normal, and if the similarity is smaller than the standard value, the condition that the shaft is abnormal is indicated, so that the alarm signal can be generated.
As shown in fig. 2, as a preferred embodiment of the present invention, the step of performing lateral stitching on wellbore images taken at the same time according to feature points to obtain a plurality of laterally stitched images specifically includes:
s301, transversely arranging a plurality of shaft images shot at the same time;
s302, identifying characteristic points in each shaft image, and determining the distance between two adjacent shaft images in the arrangement according to the transverse values of the characteristic points;
and S303, cutting the overlapped part of the two adjacent shaft images to obtain a transverse spliced image.
In the embodiment of the invention, a plurality of shaft images shot at the same time are transversely arranged, and then characteristic points in each shaft image are identified, it needs to be noted that the focal length of a high-speed camera is fixed during shooting, the position of the high-speed camera relative to the inner wall of a shaft is also fixed, and the inner wall of the shaft is a vertical surface, so that the distance between the characteristic points reflected on the images is also fixed, the distance between two adjacent shaft images in the arrangement can be further determined according to the transverse value of the characteristic points, the position of each shaft image is determined, the overlapped part of the two adjacent shaft images is cut, and a transversely spliced image is obtained, thus ensuring seamless splicing; similarly, when vertical splicing is carried out, feature points also need to be identified, the distance between two adjacent horizontal spliced images is determined according to the vertical value of the feature points, and splicing and cutting are carried out.
As shown in fig. 3, as a preferred embodiment of the present invention, the step of calculating the similarity between the panoramic image and the detection standard image specifically includes:
s401, respectively calculating hash values of the panoramic image and the detection standard image by using a hash method based on DCT to obtain h _1 and h _2;
s402, calculating a Hamming distance dis _ h between h _1 and h _2;
and S403, calculating the similarity between the panoramic image and the detection standard image according to the Hamming distance dis _ h.
In the embodiment of the invention, the picture is identified by a hash method based on DCT (discrete cosine transform) as an AI picture identification method in the prior art, the hash method based on DCT extracts the low-frequency component of the picture by using discrete cosine transform, firstly converts the picture into a gray-scale image with standard size, and then performs DCT transform on the gray-scale image.
The step of calculating the similarity between the panoramic image and the detection standard image according to the hamming distance dis _ h specifically includes: judging the value of dis _ h; when dis _ h is less than or equal to 10, the similarity P =1-dis _ h/100; when dis _ h is more than or equal to 25, the similarity P =4 × 64-dis _ h)/195; when 10 < dis _ h < 25, the similarity P = [ (25-dis _ h)/150 +0.8] + 0.5+ pc 0.5, which is the Pearson correlation coefficient. In the embodiment of the present invention, if the hamming distance dis _ h is within the setting range 10 < dis _ h < 25, the hash values of two pictures need to be calculated by using a hash method based on radial projection, the hash method based on radial projection first calculates the variance of pixel values in 180 directions at equal angular intervals through the center of a gray image, then calculates the DCT of the feature vector formed by the 180 variances, and extracts a 64-bit hash value from the DCT coefficient matrix as a fingerprint.
As shown in fig. 4, as a preferred embodiment of the present invention, the method further includes:
s501, ranging a core detection point through a plurality of laser ranging sensors to obtain a distance value, wherein the plurality of laser ranging sensors are installed on the elevator;
and S502, when the distance value is larger than the corresponding distance set value, generating alarm information.
In the embodiment of the invention, the laser ranging sensor is arranged to be capable of ranging the core detection points, each core detection point is correspondingly provided with a distance set value, and when the distance value is greater than the corresponding distance set value, the displacement degree of the core detection points is deviated, so that alarm information is generated.
As shown in fig. 5, as a preferred embodiment of the present invention, the method further includes:
s601, receiving a review instruction, wherein the review instruction comprises a moving coordinate;
and S602, moving the elevator to the moving coordinate, and shooting the inner wall of the shaft for 360 degrees to obtain a shaft image.
In the embodiment of the invention, when a worker needs to remotely check the condition of a certain position, the worker directly inputs the rechecking instruction, the rechecking instruction comprises the moving coordinate, and the moving coordinate is the position coordinate to be checked. Therefore, remote rechecking is more convenient.
As shown in fig. 6, an embodiment of the present invention further provides a system for detecting a panoramic stitching of a wellbore 360 based on machine vision, the system including:
the system comprises a lift movement control module 100, a controller and a controller, wherein the lift movement control module is used for controlling a lift to move along the inside of a shaft through an operation program, the operation program comprises a movement speed, a movement time and a movement coordinate, and the lift is provided with a plurality of high-speed cameras and a high-brightness stroboscopic light supplement lamp;
the 360-degree shooting module 200 is used for shooting the inner wall of the shaft at 360 degrees through a plurality of high-speed cameras to obtain a plurality of shaft images, each high-speed camera shoots once every set time value, and two adjacent shaft images have overlapping parts;
the shaft image splicing module 300 is configured to transversely splice shaft images shot at the same time according to feature points to obtain a plurality of transversely spliced images, and vertically splice the plurality of transversely spliced images according to the feature points to obtain a panoramic image, wherein a plurality of feature points are marked on the inner wall of a shaft, the feature points are uniformly distributed and provided with a feature point transverse value and a feature point vertical value, and each shaft image has only one feature point;
and the similarity detection module 400 is configured to perform similarity calculation on the panoramic image and the detection standard image, and generate an alarm signal when the similarity is smaller than a standard value.
In the embodiment of the invention, firstly, a plurality of high-speed cameras are installed on a lift, preferably, the number of the high-speed cameras is 5, so that 360-degree shooting can be well performed, in addition, a highlight stroboscopic light supplement lamp is installed on the lift for light supplement, so that the shooting effect is better, the embodiment of the invention can control the lift to move along the inside of a shaft through an operation program, the operation program comprises a moving speed, moving time and a moving coordinate, the moving speed is a fixed value, the moving coordinate changes along with the moving time, the moving coordinate reflects the position of the lift, when the lift moves along the inside of the shaft, the high-speed cameras perform shooting at intervals of a set time value, the set time value is related to the moving speed, the understanding is easy, the larger the moving speed is, the smaller the set time value is, and thus shaft images along the vertical direction can be continuous. It should be noted that, the inner wall of the shaft is marked with a plurality of characteristic points, the characteristic points are bright in color and convenient for automatic identification, the characteristic points are uniformly distributed in an array, and are provided with transverse values and vertical values of the characteristic points, each shaft image has only one characteristic point, that is, each transverse row has five characteristic points, the five characteristic points correspond to the positions of 5 high-speed cameras, and the vertical value of the characteristic points is equal to the moving speed and a set time value; after the shaft image is collected, transversely splicing shaft images shot at the same time according to the characteristic points to obtain a plurality of transversely spliced images, vertically splicing the plurality of transversely spliced images according to the characteristic points to obtain a panoramic image, finally calculating the similarity of the panoramic image and a detection standard image, and generating an alarm signal when the similarity is smaller than a standard value, wherein the detection standard image is stored in advance, the detection standard image is shot under the condition that the shaft is completely normal, and if the similarity is smaller than the standard value, the condition that the shaft is abnormal is indicated, so that the alarm signal can be generated.
As shown in fig. 7, as a preferred embodiment of the present invention, the borehole image stitching module 300 includes:
a transverse arrangement unit 301, configured to transversely arrange a plurality of wellbore images captured at the same time;
a distance determining unit 302, configured to identify a feature point in each wellbore image, and determine a distance between two adjacent wellbore images in the arrangement according to a lateral value of the feature point;
and an overlapping part clipping unit 303, configured to clip overlapping parts of two adjacent wellbore images to obtain a horizontal stitched image.
As shown in fig. 8, as a preferred embodiment of the present invention, the similarity detecting module 400 includes:
a hash value calculation unit 401, which calculates hash values of the panoramic image and the detection standard image by a hash method based on DCT, respectively, to obtain h _1 and h _2;
a hamming distance calculation unit 402 for calculating a hamming distance dis _ h between h _1 and h _2;
and a similarity calculation unit 403, configured to calculate a similarity between the panoramic image and the detection standard image according to the hamming distance dis _ h.
As shown in fig. 9, as a preferred embodiment of the present invention, the system further includes a core point detecting module 500, where the core point detecting module 500 specifically includes:
a core point ranging unit 501, configured to perform ranging on a core detection point through a plurality of laser ranging sensors to obtain a distance value, where the elevator is installed with a plurality of laser ranging sensors;
the alarm information generation unit 502 generates alarm information when the distance value is greater than the corresponding distance set value.
As shown in fig. 10, as a preferred embodiment of the present invention, the system further includes a remote review module 600, where the remote review module 600 specifically includes:
a review instruction receiving unit 601, configured to receive a review instruction, where the review instruction includes a moving coordinate;
and a review image determining unit 602, configured to move the elevator to the movement coordinate, and take a 360-degree photograph of the inner wall of the wellbore to obtain an image of the wellbore.
The present invention has been described in detail with reference to the preferred embodiments thereof, and it should be understood that the invention is not limited thereto, but is intended to cover modifications, equivalents, and improvements within the spirit and scope of the present invention.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a portion of sub-steps or stages of other steps.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (7)
1. A shaft 360 panoramic splicing detection method based on machine vision is characterized by comprising the following steps:
the method comprises the steps that a lift is controlled to move along the inside of a shaft through an operation program, the operation program comprises moving speed, moving time and moving coordinates, and a plurality of high-speed cameras and highlight stroboscopic light supplementing lamps are installed on the lift;
shooting the inner wall of a shaft for 360 degrees through a plurality of high-speed cameras to obtain a plurality of shaft images, wherein each high-speed camera carries out shooting at set time intervals, and two adjacent shaft images have overlapping parts;
transversely splicing the shaft images shot at the same time according to the characteristic points to obtain a plurality of transversely spliced images, vertically splicing the transversely spliced images according to the characteristic points to obtain a panoramic image, marking a plurality of characteristic points on the inner wall of the shaft, uniformly distributing the characteristic points, setting transverse values and vertical values of the characteristic points, and enabling each shaft image to have only one characteristic point;
carrying out similarity calculation on the panoramic image and the detection standard image, and generating an alarm signal when the similarity is smaller than a standard value;
the step of transversely splicing the shaft images shot at the same moment according to the characteristic points to obtain a plurality of transversely spliced images specifically comprises the following steps:
transversely arranging a plurality of shaft images shot at the same time;
identifying characteristic points in each shaft image, and determining the distance between two adjacent shaft images in the arrangement according to the transverse values of the characteristic points;
cutting the overlapped part of two adjacent shaft images to obtain a transverse spliced image;
the step of calculating the similarity between the panoramic image and the detection standard image specifically comprises:
respectively calculating the hash values of the panoramic image and the detection standard image by using a hash method based on DCT to obtain h _1 and h _2;
calculating a Hamming distance dis _ h between h _1 and h _2;
calculating according to the Hamming distance dis _ h to obtain the similarity between the panoramic image and the detection standard image;
the method further comprises the following steps:
the method comprises the steps that distance measurement is conducted on a core detection point through a plurality of laser distance measurement sensors to obtain a distance value, and the plurality of laser distance measurement sensors are installed on the lifter;
and when the distance value is greater than the corresponding distance set value, generating alarm information.
2. The machine-vision based wellbore 360 panorama stitching detection method of claim 1, further comprising:
receiving a review instruction, wherein the review instruction comprises a moving coordinate;
and moving the elevator to the moving coordinate, and shooting the inner wall of the shaft for 360 degrees to obtain a shaft image.
3. 360 panorama concatenation detecting system of pit shaft based on machine vision, its characterized in that, the system includes:
the system comprises a lift movement control module, a shaft control module and a control module, wherein the lift movement control module is used for controlling a lift to move along the inside of a shaft through an operation program, the operation program comprises a movement speed, a movement time and a movement coordinate, and the lift is provided with a plurality of high-speed cameras and a high-brightness stroboscopic light supplementing lamp;
the 360-degree shooting module is used for shooting the inner wall of the shaft at 360 degrees through a plurality of high-speed cameras to obtain a plurality of shaft images, each high-speed camera shoots once every set time value, and two adjacent shaft images have overlapping parts;
the shaft image splicing module is used for horizontally splicing shaft images shot at the same time according to the characteristic points to obtain a plurality of horizontally spliced images, vertically splicing the plurality of horizontally spliced images according to the characteristic points to obtain a panoramic image, the inner wall of the shaft is marked with a plurality of characteristic points which are uniformly distributed and provided with characteristic point horizontal values and characteristic point vertical values,
there is one and only one feature point in each wellbore image;
and the similarity detection module is used for calculating the similarity of the panoramic image and the detection standard image and generating an alarm signal when the similarity is smaller than a standard value.
4. The machine-vision based wellbore 360 panorama stitching detection system of claim 3, wherein the wellbore image stitching module comprises:
the transverse arrangement unit is used for transversely arranging a plurality of shaft images shot at the same time;
the interval determining unit is used for identifying characteristic points in each shaft image and determining the distance between two adjacent shaft images in the arrangement according to the transverse values of the characteristic points;
and the overlapping part cutting unit is used for cutting the overlapping parts of the two adjacent shaft images to obtain a transverse spliced image.
5. The machine-vision-based wellbore 360 panoramic stitching detection system of claim 4, wherein the similarity detection module comprises:
a hash value calculation unit which calculates the hash values of the panoramic image and the detection standard image respectively by using a hash method based on DCT to obtain h _1 and h _2;
a Hamming distance calculation unit for calculating a Hamming distance dis _ h between h _1 and h _2;
and the similarity calculation unit is used for calculating the similarity between the panoramic image and the detection standard image according to the Hamming distance dis _ h.
6. The machine-vision based wellbore 360 panorama stitching detection system of claim 5, further comprising a core point detection module, the core point detection module particularly comprising:
the core point ranging unit is used for ranging the core detection points through a plurality of laser ranging sensors to obtain a distance value, and the lifter is provided with a plurality of laser ranging sensors;
and the alarm information generating unit generates alarm information when the distance value is greater than the corresponding distance set value.
7. The machine-vision-based wellbore 360 panoramic stitching detection system of claim 6, further comprising a remote review module, the remote review module comprising in particular:
the device comprises a review instruction receiving unit, a review processing unit and a review processing unit, wherein the review instruction receiving unit is used for receiving a review instruction which comprises a moving coordinate;
and the rechecking image determining unit is used for enabling the elevator to move to the moving coordinate and shooting the inner wall of the shaft for 360 degrees to obtain a shaft image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211610253.1A CN115619782B (en) | 2022-12-15 | 2022-12-15 | Shaft 360 panorama splicing detection system and method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211610253.1A CN115619782B (en) | 2022-12-15 | 2022-12-15 | Shaft 360 panorama splicing detection system and method based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115619782A CN115619782A (en) | 2023-01-17 |
| CN115619782B true CN115619782B (en) | 2023-04-07 |
Family
ID=84880374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211610253.1A Active CN115619782B (en) | 2022-12-15 | 2022-12-15 | Shaft 360 panorama splicing detection system and method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115619782B (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957015B (en) * | 2016-06-15 | 2019-07-12 | 武汉理工大学 | A kind of 360 degree of panorama mosaic methods of threaded barrel inner wall image and system |
| CN112689850A (en) * | 2020-03-19 | 2021-04-20 | 深圳市大疆创新科技有限公司 | Image processing method, image processing apparatus, image forming apparatus, removable carrier, and storage medium |
| CN111583114B (en) * | 2020-04-30 | 2023-02-24 | 安徽工业大学 | Automatic measuring device and measuring method for pipeline threads |
-
2022
- 2022-12-15 CN CN202211610253.1A patent/CN115619782B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115619782A (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7839431B2 (en) | Image processing system and method for improving repeatability | |
| EP3641298B1 (en) | Method and device for capturing target object and video monitoring device | |
| CN111160172A (en) | Parking space detection method and device, computer equipment and storage medium | |
| CN111178295A (en) | Parking space detection and model training method and device, vehicle, equipment and storage medium | |
| JP2005024463A (en) | Stereo wide visual field image processing apparatus | |
| US9091904B2 (en) | Camera device with rotary base | |
| CN104917957B (en) | For controlling the equipment and its system of video camera imaging | |
| JP7019064B2 (en) | Camera installation support device and method, installation angle calculation method, program and recording medium | |
| CN112954315A (en) | Image focusing measurement method and system for security camera | |
| CN114838668A (en) | Tunnel displacement monitoring method and system | |
| CN110602376B (en) | Snapshot method and device and camera | |
| CN115619782B (en) | Shaft 360 panorama splicing detection system and method based on machine vision | |
| Drews Jr et al. | Tracking system for underwater inspection using computer vision | |
| EP4354853A1 (en) | Thermal-image-monitoring system using plurality of cameras | |
| JP2017161403A (en) | Imaging device, method, and program, and display control device and program | |
| CN110634136B (en) | Pipeline wall damage detection method, device and system | |
| KR100844640B1 (en) | Method for object recognizing and distance measuring | |
| TWI604261B (en) | A method for capturing multi-dimensional visual image and the system thereof | |
| JP2007274653A (en) | Video monitoring device and method | |
| CN115980042B (en) | Lightning stroke path monitoring system and method based on multi-source image registration | |
| RU2804376C1 (en) | Device for panoramic spatial photography | |
| KR102632655B1 (en) | Video Analyzing Apparatus and Method for Determining Whether Target Vehicle Is Driving or Stopping for Illegal Parking Enforcement, and Illegal Parking Enforcement System | |
| US20240127604A1 (en) | Road surface information collecting device, road surface deterioration detecting system, and road surface information collecting method | |
| JP4274038B2 (en) | Image processing apparatus and image processing method | |
| CN116577337B (en) | Pipeline disease detection method and system |
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 |