CN115527109A - Underwater concrete disease monitoring method and device, underwater robot and medium - Google Patents

Underwater concrete disease monitoring method and device, underwater robot and medium Download PDF

Info

Publication number
CN115527109A
CN115527109A CN202211047513.9A CN202211047513A CN115527109A CN 115527109 A CN115527109 A CN 115527109A CN 202211047513 A CN202211047513 A CN 202211047513A CN 115527109 A CN115527109 A CN 115527109A
Authority
CN
China
Prior art keywords
information
distance
diseases
determining
disease
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
CN202211047513.9A
Other languages
Chinese (zh)
Other versions
CN115527109B (en
Inventor
李富军
程国伟
王海燕
高松
刘会元
侯路
朱冬然
朱明华
张延勇
郭士奇
司启龙
巩凡
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.)
Handan Yirun Engineering Consulting Co ltd
Original Assignee
Handan Yirun Engineering Consulting 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 Handan Yirun Engineering Consulting Co ltd filed Critical Handan Yirun Engineering Consulting Co ltd
Priority to CN202211047513.9A priority Critical patent/CN115527109B/en
Publication of CN115527109A publication Critical patent/CN115527109A/en
Application granted granted Critical
Publication of CN115527109B publication Critical patent/CN115527109B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/182—Network patterns, e.g. roads or rivers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Perforating, Stamping-Out Or Severing By Means Other Than Cutting (AREA)

Abstract

The method comprises the steps of obtaining a surface image of the concrete, carrying out feature recognition on the surface image, judging whether the concrete has diseases or not, wherein the diseases comprise cracks and pits, determining the positions of the diseases in the surface image if the concrete has the diseases, controlling the high-pressure water spraying device to work towards the diseases based on the positions, and controlling the distance sensor to work towards the diseases based on the positions to obtain depth information of the diseases. This application has the effect of knowing the disease degree of depth of concrete under water more accurately.

Description

Underwater concrete disease monitoring method and device, underwater robot and medium
Technical Field
The application relates to the field of concrete detection, in particular to a method and a device for monitoring diseases of underwater concrete, an underwater robot and a medium.
Background
The underwater concrete is mainly used in the fields of river channel construction and the like. However, the underwater concrete can be damaged by cracks, depressions and the like after being used for a long time or when encountering geological activities and other conditions, and at present, the underwater concrete surface image is only acquired by using an underwater robot and other related professional equipment, so that whether the underwater concrete is damaged or not can be known. However, when a disease occurs, under the action of water flow, sludge, impurities and the like in water can be deposited in the disease, so that the specific depth of a crack or a depression cannot be known, and further, workers can not know the disease comprehensively. Therefore, how to more accurately know the disease depth of the underwater concrete becomes a problem.
Disclosure of Invention
In order to accurately know the disease depth of underwater concrete, the application provides a method and a device for monitoring diseases of underwater concrete, an underwater robot and a medium.
In a first aspect, the application provides a method for monitoring underwater concrete diseases, which adopts the following technical scheme:
an underwater concrete disease monitoring method comprises the following steps:
acquiring a surface image of concrete;
performing feature recognition on the surface image, and judging whether the concrete has diseases, wherein the diseases comprise cracks and depressions;
if the disease exists, determining the position of the disease in the surface image;
controlling a high-pressure water spraying device to work towards the diseases based on the position;
and controlling the distance sensor to work towards the disease based on the position to obtain the depth information of the disease.
By adopting the technical scheme, the surface image of the concrete is obtained, so that the disease condition of the concrete is conveniently analyzed. The method comprises the steps of carrying out feature recognition on a surface image so as to judge whether cracks and/or dents exist in concrete, determining the position of the diseases on the surface image if the cracks and/or dents exist in the concrete, controlling a high-pressure water spraying device to face the diseases according to the positions of the diseases after the positions of the diseases are determined, so that sludge impurities and the like in the diseases are washed out, the diseases are clearer and more real, and controlling a distance sensor to face the diseases after the sludge impurities and the like in the diseases are removed, so that the depth information of the diseases can be more accurately obtained.
In another possible implementation manner, the performing feature recognition on the surface image and determining whether the concrete has a disease includes:
and inputting the surface image into a trained network model for crack and/or recess recognition so as to judge whether the concrete has diseases or not.
By adopting the technical scheme, the surface image is input into the trained network model for crack and/or depression recognition, so that whether the concrete has cracks and/or depressions can be accurately recognized.
In another possible implementation manner, the determining the position of the disease in the surface image includes:
performing edge detection on the disease to obtain outline information of the disease, wherein pixels in the outline information range are occupied pixels of the disease;
drawing a coordinate system on the surface image;
if the fault is a crack, determining the corresponding relation between the coordinate of each pixel occupied by the crack and the crack, and determining the coordinate of each pixel occupied by the crack as the position of the crack;
and if the defect is a recess, determining the coordinates of a central pixel in the pixels occupied by the recess, and determining the coordinates of the central pixel as the position of the recess.
By adopting the technical scheme, after the existence of the disease is identified, edge detection is carried out on the disease to obtain the outline information of the disease, then a coordinate system is drawn on the surface image, if the disease is a crack, the corresponding relation between the occupied pixels in the outline information range and the crack is established, and the occupied pixels are the position of the crack. If the defect is a pit, the position of the pit is determined to be more accurate through the coordinates of the pixel at the center point of the pit.
In another possible implementation manner, the controlling the high-pressure water spraying device to work towards the disease based on the position includes:
if only pits exist, determining the distance value from the coordinate of the center point of each pit to a preset coordinate, wherein the preset coordinate represents the coordinate of the high-pressure water spraying device, sequencing the distance values corresponding to the pits from small to large, and determining a first moving path according to a sequencing result, wherein the first moving path is a moving path when a spray head of the high-pressure water spraying device sprays water to each pit in sequence, and controlling the high-pressure water spraying device to work towards a defect according to the first moving path;
if only cracks exist, determining a second moving path of the spray head on each crack according to the pixels occupied by each crack, sequencing the number of the pixels occupied by each crack, and determining a third moving path according to a sequencing result, wherein the third moving path is a moving path of the spray head of the high-pressure water spraying device when spraying water to each crack in sequence, and controlling the high-pressure water spraying device to work towards the fault according to the second moving path and the third moving path;
if the surface image is sunken and has cracks, determining the priority of the diseases in the surface image according to a preset priority, and controlling the high-pressure water spraying device to work towards the diseases based on the preset priority, the first moving path, the second moving path and the third moving path.
By adopting the technical scheme, the high-pressure water spraying devices are sequenced according to the distances from each pit to the high-pressure water spraying devices, the scouring sequence of each pit is determined according to the sequencing result, the first moving path is determined, and the high-pressure water spraying devices are controlled to work according to the first moving path, so that the scouring effect from near to far is achieved. The method comprises the steps of firstly determining the scouring path of each crack according to the pixels occupied by each crack, then sorting the number of the pixels occupied by each crack, determining the scouring sequence of each crack according to the sorting result and determining the third moving path, so that the cracks are scoured more orderly, and if depressions and cracks exist at the same time, controlling the high-pressure water spraying device to work towards the defects according to the corresponding preset priority of the depressions and the defects, the first moving path, the second moving path and the third moving path, so that the cleaning is more intelligent and convenient.
In another possible implementation manner, if the defect is a depression, the method further includes:
and adjusting the water spraying coverage area of the high-pressure water spraying device based on the number of the occupied pixels.
Through adopting above-mentioned technical scheme, adjust high pressure water jet equipment's water spray coverage area according to sunken shared pixel quantity to make high pressure water jet equipment can reach better washing effect to the sunken homoenergetic of equidimension not.
In another possible implementation manner, the pixels outside the contour information range are concrete plane pixels, and the obtaining of the depth information of the disease based on the operation of the position control distance sensor includes:
if the fault is a crack, determining a plurality of sampling points on a moving path of the second spray head;
determining a tangent corresponding to each sampling point on the moving path of the second spray head, and drawing a vertical line of the corresponding tangent on each sampling point;
determining pixel points which are closest to the contour information and located on the vertical line outside the contour information range of the crack as first reference pixel points;
controlling the distance sensor to collect first distance information and acquiring first angle information of the distance sensor when the first distance information is collected, wherein the first distance information is the distance from the distance sensor to a first reference pixel point corresponding to each sampling point;
controlling the distance sensor to acquire second distance information and acquiring second angle information of the distance sensor when the second distance information is acquired, wherein the second distance information is the distance from the distance sensor to each sampling point;
determining depth information of the fracture at each sampling point based on the first angle information, the second angle information, the first distance information, and the second distance information of each sampling point.
By adopting the technical scheme, the change of the concrete plane state is relatively smooth, so that the plane height of the first reference pixel point can represent the height of the crack position when the crack does not appear. The first reference pixel point is used as the plane height before the crack occurs, so that the first reference pixel point is used as the plane reference point of the sampling point, and the depth information of the sampling point is more accurate according to the first reference pixel point. The vertical height component from the sampling point to the distance sensor is determined according to the first angle information and the first distance information, then the vertical height component from the first reference pixel point to the distance sensor is determined according to the second angle information and the second distance information, finally the depth of the crack at the sampling point can be determined according to the two vertical height components, and the depth of the crack at the sampling point is determined to be more accurate by determining the vertical height component at the first reference pixel point.
In another possible implementation manner, the controlling the distance sensor to operate based on the position to obtain depth information of the disease includes:
if the defect is a recess, determining any second reference pixel point which is closest to the contour information outside the contour information of the recess;
controlling the distance sensor to acquire third distance information and acquiring third angle information of the distance sensor when the third distance information is acquired, wherein the third distance information is the distance from the distance sensor to the second reference pixel point;
controlling the distance sensor to acquire fourth distance information and acquiring fourth angle information of the distance sensor when the fourth distance information is acquired, wherein the fourth distance information is the distance from the distance sensor to the central pixel;
determining depth information of the depression based on the third angle information, fourth angle information, third distance information, and fourth distance information.
By adopting the technical scheme, the central pixel of each pit and the second reference pixel point on the concrete plane around the pit are determined, then the third angle information and the third distance information are obtained, the vertical height component of the second reference pixel point can be determined according to the third distance information and the third angle information, the vertical height component of the central pixel point can be determined according to the fourth distance information and the fourth angle information, and then the pit depth information is obtained, the reference vertical height component of the concrete plane is determined according to the second reference pixel point, and then the accurate pit depth can be determined according to the vertical height component of the pit and the reference vertical height component.
In a second aspect, the application provides an underwater concrete disease monitoring device, which adopts the following technical scheme:
an underwater concrete disease monitoring device, comprising:
the acquisition module is used for acquiring a surface image of the concrete;
the judging module is used for carrying out feature recognition on the surface image and judging whether the concrete has diseases or not, wherein the diseases comprise cracks and pits;
the position determining module is used for determining the position of the disease in the surface image when the disease exists;
the first control module is used for controlling the high-pressure water spraying device to work towards the diseases based on the position;
and the second control module is used for controlling the distance sensor to work based on the position to obtain the depth information of the disease.
By adopting the technical scheme, the acquisition module acquires the surface image of the concrete, so that the disease condition of the concrete is conveniently analyzed. The method comprises the steps of carrying out feature recognition on a surface image, judging whether cracks and/or sunken diseases exist in concrete or not by a judging module, determining the positions of the diseases on the surface image by a position determining module if the cracks and/or sunken diseases exist in the concrete, controlling a high-pressure water spraying device to work towards the diseases according to the positions of the diseases by a first control module after the positions of the diseases are determined, washing away sludge impurities and the like in the diseases, enabling the diseases to be clearer and truer, and controlling a distance sensor to work towards the diseases by a second control module after the sludge impurities and the like in the diseases are removed, so that the depth information of the diseases can be obtained more accurately.
In another possible implementation manner, the determining module, when performing feature recognition on the surface image and determining whether the concrete has a disease, is specifically configured to:
and inputting the surface image into a trained network model for crack and/or recess recognition so as to judge whether the concrete has diseases or not.
In another possible implementation manner, when determining the position of the lesion on the surface image, the position determining module is specifically configured to:
performing edge detection on the disease to obtain the outline information of the disease, wherein pixels in the outline information range are the pixels occupied by the disease;
drawing a coordinate system on the surface image;
if the crack is damaged, determining the corresponding relation between the coordinates of each occupied pixel of the crack and the crack respectively, and determining the coordinates of the occupied pixels as the position of the crack;
and if the defect is a recess, determining the coordinates of a central pixel in the pixels occupied by the recess, and determining the coordinates of the central pixel as the position of the recess.
In another possible implementation manner, the first control module, when controlling the high-pressure water spraying device to work towards the disease based on the position, is specifically configured to:
if only depressions exist, determining the distance value from the central point coordinate of each depression to a preset coordinate, wherein the preset coordinate represents the coordinate of the high-pressure water spraying device, sequencing the distance values corresponding to the depressions from small to large, determining a first moving path according to the sequencing result, wherein the first moving path is a moving path when a spray head of the high-pressure water spraying device sprays water to each depression in sequence, and controlling the high-pressure water spraying device to work towards a defect according to the first moving path;
if only cracks exist, determining a second moving path of the spray head on each crack according to the pixels occupied by each crack, sequencing the number of the pixels occupied by each crack, and determining a third moving path according to a sequencing result, wherein the third moving path is a moving path of the spray head of the high-pressure water spraying device when spraying water to each crack in sequence, and controlling the high-pressure water spraying device to work towards the fault according to the second moving path and the third moving path;
if the surface image is sunken and has cracks, determining the priority of the diseases existing in the surface image according to a preset priority, and controlling the high-pressure water spraying device to work towards the diseases based on the preset priority, the first moving path, the second moving path and the third moving path.
In another possible implementation manner, the apparatus further includes:
and the adjusting module is used for adjusting the water spraying coverage area of the high-pressure water spraying device based on the number of the occupied pixels.
In another possible implementation manner, the pixels outside the contour information range are concrete plane pixels, and the second control module is specifically configured to, when controlling the distance sensor to work toward the defect based on the position to obtain the depth information of the defect:
if the fault is a crack, determining a plurality of sampling points on a moving path of the second spray head;
determining a tangent corresponding to each sampling point on the moving path of the second spray head, and drawing a vertical line of the corresponding tangent on each sampling point;
determining pixel points which are closest to the contour information and located on the vertical line outside the contour information range of the crack as first reference pixel points;
controlling the distance sensor to collect first distance information and acquiring first angle information of the distance sensor when the first distance information is collected, wherein the first distance information is the distance from the distance sensor to a first reference pixel point corresponding to each sampling point;
controlling the distance sensor to acquire second distance information and acquiring second angle information of the distance sensor when the second distance information is acquired, wherein the second distance information is the distance from the distance sensor to each sampling point;
determining depth information of the fracture at each sampling point based on the first angle information, the second angle information, the first distance information, and the second distance information of each sampling point.
In another possible implementation manner, when the second control module controls the distance sensor to work toward the disease based on the position to obtain the depth information of the disease, the second control module is specifically configured to:
if the defect is a recess, determining any second reference pixel point which is closest to the contour information except the contour information of the recess;
controlling the distance sensor to acquire third distance information and acquiring third angle information of the distance sensor when the third distance information is acquired, wherein the third distance information is the distance from the distance sensor to the second reference pixel point;
controlling the distance sensor to acquire fourth distance information and acquiring fourth angle information of the distance sensor when the fourth distance information is acquired, wherein the fourth distance information is the distance from the distance sensor to the central pixel;
determining depth information of the depression based on the third angle information, fourth angle information, third distance information, and fourth distance information.
In a third aspect, the present application provides an underwater robot, which adopts the following technical scheme:
an underwater robot, comprising:
a high pressure water spray device;
a distance sensor;
one or more processors;
a memory;
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more application programs configured to: a method for monitoring underwater concrete diseases according to any one of the possible implementation manners of the first aspect is performed.
In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solutions:
a computer-readable storage medium, which, when executed in a computer, causes the computer to perform a method of underwater concrete disease monitoring as set forth in any one of the first aspect.
In summary, the present application includes at least one of the following beneficial technical effects:
1. and acquiring a surface image of the concrete, thereby facilitating the analysis of the disease condition of the concrete. The method comprises the steps of carrying out feature recognition on a surface image so as to judge whether cracks and/or dents exist in concrete, determining the position of a disease on the surface image if the cracks and/or dents exist in the concrete, controlling a high-pressure water spraying device to face the disease according to the position of the disease after the position of the disease is determined, so that sludge sundries and the like in the disease are washed out, the disease is clearer and more real, and controlling a distance sensor to face the disease after the sludge sundries and the like in the disease are removed, so that the depth information of the disease can be more accurately obtained;
2. the high-pressure water spraying devices are arranged according to the distance between each pit and the high-pressure water spraying device, the scouring sequence of each pit is determined according to the sequencing result, the first moving path is determined, and the high-pressure water spraying devices are controlled to work according to the first moving path, so that the scouring effect is achieved from near to far. The method comprises the steps of firstly determining the scouring path of each crack according to the pixels occupied by each crack, then sorting the number of the pixels occupied by each crack, determining the scouring sequence of each crack according to the sorting result and determining the third moving path, so that the cracks are scoured more orderly, and if depressions and cracks exist at the same time, controlling the high-pressure water spraying device to work towards the defects according to the corresponding preset priority of the depressions and the defects, the first moving path, the second moving path and the third moving path, so that the cleaning is more intelligent and convenient.
Drawings
Fig. 1 is a schematic flow chart of an underwater concrete disease monitoring method according to an embodiment of the present application.
Fig. 2 is an exemplary diagram of step S1052 and step S1053 in the embodiment of the present application.
Fig. 3 is an exemplary diagram of step S1056 in the embodiment of the present application.
Fig. 4 is a schematic structural diagram of an underwater concrete disease monitoring device according to an embodiment of the present application.
Fig. 5 is a schematic structural diagram of an underwater robot according to an embodiment of the present application.
Detailed Description
The present application is described in further detail below with reference to the attached drawings.
A person skilled in the art, after reading the present specification, may make modifications to the present embodiments as necessary without inventive contribution, but only within the scope of the claims of the present application are protected by patent laws.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship, unless otherwise specified.
The embodiments of the present application will be described in further detail with reference to the drawings attached hereto.
The embodiment of the application provides an underwater concrete disease monitoring method, which is executed by an underwater robot, and as shown in fig. 1, the method comprises a step S101, a step S102, a step S103, a step S104 and a step S105, wherein,
s101, acquiring a surface image of the concrete.
For the embodiments of the present application, the worker may arrange the underwater robot on the concrete under water. The underwater robot is provided with a camera device, and the camera device faces the surface of the concrete to collect surface images of the concrete.
And S102, carrying out feature recognition on the surface image and judging whether the concrete has diseases or not.
Wherein the diseases comprise cracks and depressions.
For the embodiment of the application, after the surface image of the concrete is obtained, the surface image is subjected to feature recognition, whether cracks and/or sunken diseases exist on the surface of the concrete is recognized, and therefore the effect of judging whether the pits or the cracks exist on the surface of the concrete is achieved.
And S103, if the defect exists, determining the position of the defect in the surface image.
For the embodiment of the application, if the disease exists, the position of the disease is determined on the surface image. After the position of the disease is obtained, the disease is conveniently monitored in the follow-up process, and then the data of the disease can be accurately collected.
And S104, controlling the high-pressure water spraying device to work towards the diseases based on the position.
For the embodiment of the application, the underwater environment is complex, and sludge impurities and the like can exist in the pits and/or cracks. Thereby influence the staff and learn the true condition of crack andor depressed part, after determining the position of disease, according to the work of disease position control high pressure water jet equipment, high pressure water jet equipment's shower nozzle is according to the position towards the disease water spray to debris such as silt in depressed andor the crack are cleared up.
And S105, controlling the distance sensor to work towards the diseases based on the positions, and obtaining the depth information of the diseases.
For the embodiment of the application, after the sludge impurities in the diseases are removed, the high-pressure water spraying device can obtain the real conditions of the diseases. And at the moment, the distance sensor is controlled to collect the depth information of the diseases according to the positions of the diseases, so that the finally obtained depth information of the diseases is more accurate.
In a possible implementation manner of the embodiment of the present application, the step S102 of performing feature recognition on the surface image to determine whether the concrete has a disease specifically includes a step S1021 (not shown in the figure), wherein,
and S1021, inputting the surface image into the trained network model for crack and/or pit recognition to judge whether the concrete has diseases.
For the embodiment of the application, the network model can use a convolutional neural network, when the convolutional neural network is trained, a training sample set is firstly made, the training sample set consists of a plurality of images of pits and cracks, each image corresponds to a disease type, and the training sample set is input into the convolutional neural network for training, so that an accurate network model is obtained. And inputting the surface image into a trained network model after the surface image is acquired by the camera, and carrying out crack and/or depression recognition on the surface image by the trained network model.
In a possible implementation manner of the embodiment of the present application, the determining the position of the disease in the surface image in step S103 specifically includes step S1031 (not shown in the figure), step S1032 (not shown in the figure), step S1033 (not shown in the figure), and step S1034 (not shown in the figure), wherein,
and S1031, performing edge detection on the diseases to obtain the outline information of the diseases.
Wherein, the pixels in the outline information range are the occupied pixels of the diseases.
For the embodiment of the application, before edge detection is performed on a disease, the surface image can be preprocessed, noise in the surface image is reduced through filtering, and gray level transformation is performed on the surface image after noise reduction to obtain a gray level image of the surface image. And then the gray value of the disease is different from that of the concrete plane. Thereby determining the range of the diseases. And the position where the gray value of the disease and the gray value of the concrete plane are subjected to step change is the outline information of the disease.
S1032, a coordinate system is drawn on the surface image.
For the present application examples. In order to facilitate obtaining the position of the disease, a coordinate system can be drawn on the surface image. And drawing a coordinate system to obtain the coordinates of each pixel point on the surface image. And determining the position of the disease according to the coordinates of each pixel point.
And S1033, if the crack is detected as the fault, determining the corresponding relation between the coordinates of each pixel occupied by the crack and the crack, and determining the coordinates of the pixels occupied by the crack as the position of the crack.
For the embodiment of the application, the crack is generally in a strip shape, so if the type of the disease is the crack, the pixel in the crack profile information range is the pixel occupied by the crack, and the position of the crack can be represented. Therefore, after the contour information of the crack is determined, the corresponding relation between each occupied pixel and the crack is determined. I.e. which pixels the crack corresponds to, thereby determining the location of the crack.
S1034, if the defect is a recess, determining the coordinates of the central pixel in the pixels occupied by the recess, and determining the coordinates of the central pixel as the position of the recess.
For the present application examples. The depressions are generally in a relatively full circle or other shapes, and therefore, after the contour information of the depressions is determined, the positions of the depressions can be represented by the pixels at the central positions in the range of the depression contour information because the distances from the pixels at the central positions in the range of the depression contour information to the pixels on the contour information are relatively balanced.
The central pixel can be determined by calculating the distance from each pixel in the contour information range to each pixel on the contour information and then calculating the variance corresponding to each pixel in the contour information range through a variance calculation formula. A smaller variance indicates a more uniform location of the pixel to each pixel on the contour information, so the pixel with the smallest variance can be determined as the center pixel of the depression.
In a possible implementation manner of the embodiment of the present application, the step S104 of controlling the high-pressure water spraying device to work towards the fault based on the position specifically includes a step S1041 (not shown in the figure), a step S1042 (not shown in the figure), and a step S1043 (not shown in the figure), wherein,
s1041, if only depressions exist, determining a distance value from a center point coordinate of each depression to a preset coordinate respectively, wherein the preset coordinate represents a coordinate of the high-pressure water spraying device, sequencing the distance values corresponding to each depression from small to large, determining a first moving path according to a sequencing result, wherein the first moving path is a moving path when a spray head of the high-pressure water spraying device sprays water to each depression in sequence, and controlling the high-pressure water spraying device to work towards a disease according to the first moving path.
For the embodiment of the application, the position of the high-pressure water spraying device on the underwater robot is fixed, the initial water spraying direction position of the spray head of the high-pressure water spraying device is fixed, and the preset coordinate is the initial water spraying position of the spray head of the high-pressure water spraying device. The underwater robot calculates the distance from the central pixel of each recess to the preset coordinate, the closer the distance is, the more suitable the distance is, the flushing is preferably performed, therefore, after the distance from each recess to the high-pressure water spraying device is determined, the distances are sequenced from small to large, and a first moving path of the spray head is planned according to the sequencing result. And the high-pressure water spraying device on the underwater robot cleans the depression in the surface image according to the first moving path. The first moving path is the shortest path for the nozzle of the high-pressure water spraying device to move, and the concave part is flushed according to the first moving path, so that the flushing time is saved, and the flushing efficiency is improved.
S1042, if only cracks exist, determining a second moving path of the spray head on each crack according to the pixels occupied by each crack, sequencing the number of the pixels occupied by each crack, and determining a third moving path according to the sequencing result, wherein the third moving path is a moving path of the spray head of the high-pressure water spraying device when the spray head sprays water on each crack in sequence, and controlling the high-pressure water spraying device to work towards the fault according to the second moving path and the third moving path.
For the embodiment of the present application, if the type of the damage is a crack, since the crack has a length, a moving path when the high-pressure water spraying device flushes each crack, that is, a second moving path, needs to be determined. The underwater robot can determine the trend of the crack according to the occupied pixels of the crack, so that a second moving path is planned according to the occupied pixels, the crack is flushed by a nozzle of the high-pressure water spraying device according to the second moving path, and therefore sludge impurities in the crack can be more comprehensively cleaned. In the embodiment of the present application, since the deeper the crack, the weaker the ability to reflect light rays, and therefore the lower the gray value represented on the gray image, the second moving path may also be determined from the pixel with the lowest gray value within the range of the contour information.
The cracks are sorted from small to large according to the number of the occupied pixels of the cracks, namely, the small cracks are cleaned first and then the large cracks are cleaned, so that the cracks are cleaned more orderly. And obtaining the cleaning sequence of each crack according to the sequencing result, namely the moving path of the spray head of the high-pressure water spraying device, namely a third moving path. The cracks can also be sorted from large to small according to the occupied pixels of the cracks, namely, the larger cracks are cleaned firstly, the smaller cracks are cleaned later, and the cracks can also be cleaned more orderly.
And S1043, if the pits and cracks exist, determining the priority of the diseases existing in the surface image according to a preset priority, and controlling the high-pressure water spraying device to work towards the diseases based on the preset priority, the first moving path, the second moving path and the third moving path.
For the embodiment of the application, assuming that the surface image has the depression and the crack at the same time, the cleaning sequence of the two diseases is determined according to the preset priority. And if the preset priority is that the priority of the depression is greater than that of the crack, the underwater robot firstly cleans the depression and then cleans the crack. If the preset priority is that the priority of the crack is larger than the priority of the pit, the underwater robot firstly cleans the crack and then cleans the pit. In the embodiment of the present application, if only one type of defect exists in the surface image, the type of defect may be cleaned directly according to the moving path corresponding to the type of defect.
In a possible implementation manner of the embodiment of the present application, if the defect is a recess, the method further includes step S106 (not shown in the figure), wherein,
and S106, adjusting the water spraying coverage area of the high-pressure water spraying device based on the number of the occupied pixels.
For the embodiment of the present application, the number of pixels occupied by the pits is different, which indicates that the size and the occupied range of the pits are also different. Therefore, the covering area of the corresponding spray head for spraying water is determined according to the number of the pixels occupied by the depressions, and the cleaning effect is improved. For example, the corresponding nozzle coverage area under different occupied pixel numbers can be calculated according to a linear function, and the nozzle coverage area can be adjusted by rotating the nozzle angle along the axial direction of the nozzle. Taking y =0.5x +10 as an example, y is the angle to which the spray head needs to rotate, 0.5 is a proportionality coefficient, and 10 is an initial angle or a minimum angle. Assuming that the number of pixels occupied by the depressions is 200, the angle to which the head needs to be rotated is 110 °. After the angle required to be rotated is determined, the underwater robot controls the spray head to rotate to a position of 110 degrees, so that the coverage area of the spray head is adjusted. The scaling factor 0.5 and the initial angle 10 are examples, and may be other values, which are not limited herein.
In the embodiment of the application, preset pixel intervals corresponding to the number of occupied pixels can be further determined, each preset pixel interval corresponds to a rotation angle, and the rotation angle of the sprayer is determined by determining the preset pixel intervals corresponding to the number of occupied pixels.
In a possible implementation manner of the embodiment of the present application, the pixels outside the contour information range are concrete plane pixels, and the step S105 is to control the distance sensor to operate toward the defect based on the position to obtain the depth information of the defect, which specifically includes the steps S1051 (not shown in the figure), S1052 (not shown in the figure), S1053 (not shown in the figure), S1054 (not shown in the figure), S1055 (not shown in the figure), and S1056 (not shown in the figure), wherein,
s1051, if the fault is a crack, determining a plurality of sampling points on the moving path of the second nozzle.
For the embodiment of the application, since the slit has a long strip shape, a plurality of sampling points need to be determined on the second moving path of the slit. Thereby collecting depth information at the sampling point in the fracture. It is to be understood that the greater the number of sampling points, the more accurate the monitoring of the fracture.
And S1052, determining a tangent corresponding to each sampling point on the moving path of the second spray head, and drawing a perpendicular line of the corresponding tangent on the sampling point.
For the embodiment of the present application, as shown in fig. 2, a in fig. 2 is profile information of the crack, B is a second moving path, and point C is a sampling point in the crack. And if the second moving path at the point C is a curve, determining a tangent D of the underwater robot at the point C in the second moving path. If the second moving path at the point C is a straight line, the underwater robot determines a tangent line D at the point C in the second moving path as the moving path itself. After the tangent line D is determined, the perpendicular line E to the tangent line is drawn at point C. As shown in fig. 2, D in fig. 2 is a tangent line, and E in fig. 2 is a perpendicular line to D.
And S1053, determining the pixel point which is positioned outside the outline information range of the crack, is closest to the outline information and is positioned on the vertical line as a first reference pixel point.
For the embodiment of the application, the underwater robot determines that the contour information is closest to the contour information, and the point located on the vertical line is a first reference pixel point, namely point F in fig. 2, where the first reference pixel point F is a first reference pixel point on the concrete plane corresponding to the sampling point C in an associated manner. The first reference pixel point F is a point which is closest to the sampling point C on the concrete plane, and the concrete plane state changes more smoothly, so that the height of the first reference pixel point F can represent the height of the crack when the crack does not appear. The first reference pixel point F is used as the plane height before the crack occurs, so that the first reference pixel point is used as the plane reference point of the sampling point C, and the depth information of the sampling point C is determined to be most accurate according to the first reference pixel point.
S1054, controlling the distance sensor to collect the first distance information and acquiring the first angle information of the distance sensor when the first distance information is collected.
The first distance information is the distance from the distance sensor to the first reference pixel point corresponding to each sampling point.
For the embodiment of the application, the underwater robot controls the distance sensor to work towards the first reference pixel point according to the coordinate of the first reference pixel point, and therefore the distance from the distance sensor to the first reference pixel point is collected. I.e., first distance information, assuming that the first distance information is 5 centimeters (cm). The nozzle of the high-pressure water spraying device is also provided with an angle sensor, the angle sensor collects an included angle formed by a distance sensor probe and a horizontal plane, and the current first angle information collected by the angle sensor is assumed to be 50 degrees.
And S1055, controlling the distance sensor to collect the second distance information and acquiring second angle information of the distance sensor when the second distance information is collected.
And the second distance information is the distance from the distance sensor to each sampling point respectively.
For the embodiment of the application, the distance sensor is controlled to work towards the sampling point according to the coordinates of the sampling point, so that the distance from the distance sensor to the sampling point is collected, namely the second distance information, and the second distance information is assumed to be 6cm. Assume that the second angle information collected by the angle sensor is 60 °.
S1056, determining depth information of the crack at each sampling point based on the first angle information, the second angle information, the first distance information and the second distance information of each sampling point.
For the embodiment of the present application, referring to fig. 3, in fig. 3, O is a distance sensor, in fig. 3, M is a vertical height component from the distance sensor to a first reference pixel point, and in fig. 3, N is a vertical height component from a sampling point to the distance sensor. And determining a vertical height component M from the first reference pixel point to the distance sensor according to the trigonometric function of the first angle information and the first distance information.
Taking step S1054 and step S1055 as an example, it can be determined that the vertical height component M from the distance sensor to the first reference pixel is 3.83cm according to the trigonometric function of 50 ° and the first distance information of 5cm. According to the 60-degree trigonometric function of the second angle information and the 6cm second distance information, the vertical height component N from the sampling point to the distance sensor is determined to be 5.19cm. And after obtaining 3.83cm and 5.19cm, the underwater robot performs difference making to obtain the depth information of the sampling point of 1.36cm. I.e. the depth of the crack is 1.36cm.
In the embodiment of the application, the distance sensor may first measure the distance of the first reference pixel point, then measure the distance of the sampling point corresponding to the first reference pixel point, and finally perform a difference on the group of first reference pixel points and the sampling point to obtain the depth of the crack at the sampling point. And then according to the corresponding relation between the sampling points and the first reference pixel points, performing subtraction on every two corresponding sampling points and the first pixel section respectively to obtain the depth of the crack at the sampling points. And the distance measurement can also be carried out on each sampling point, then the distance measurement is carried out on all the first reference pixel points, and then the depth of the crack at the sampling point is obtained according to the corresponding relation between the sampling point and the first reference pixel points.
In a possible implementation manner of the embodiment of the present application, the step S106 is to control the distance sensor to work toward the disease based on the position to obtain the depth information of the disease, and specifically includes the steps S1061 (not shown), S1062 (not shown), S1063 (not shown), and S1064 (not shown), wherein,
and S1061, if the defect is a recess, determining any second reference pixel point which is closest to the contour information except the contour information of the recess.
For the embodiment of the application, a plurality of pixel points closest to the contour information exist outside the contour information, any one of the pixel points closest to the contour information can be used as a second reference pixel point, and the second reference pixel point represents a first reference pixel point on the concrete plane corresponding to the depression.
And S1062, controlling the distance sensor to acquire third distance information and acquiring third angle information of the distance sensor when the third distance information is acquired.
And the third distance information is the distance from the distance sensor to the second reference pixel point.
For the embodiment of the application, the underwater robot controls the distance sensor to measure the distance towards the position of the third pixel point according to the coordinate of the second reference pixel point, and therefore third distance information is obtained. Assuming that the third distance information is 4cm, the acquired third angle information acquired by the angle sensor is 45 °.
And S1063, controlling the distance sensor to acquire fourth distance information and acquiring fourth angle information of the distance sensor when the fourth distance information is acquired.
Wherein the fourth distance information is a distance from the distance sensor to the center pixel.
For the embodiment of the application, the underwater robot controls the distance sensor to face the position of the central pixel for distance measurement according to the coordinate of the central pixel, so that third distance information is obtained. Assuming that the third distance information is 5.5cm, the obtained fourth angle information is 60 °.
S1064, determining depth information of the recess based on the third angle information, the fourth angle information, the third distance information, and the fourth distance information.
For the embodiment of the application, taking the step S1062 and the step S1063 as examples, the underwater robot may determine that the distance from the distance sensor to the second reference pixel point to the spray head is 2.82cm in the vertical direction according to the angle between the spray head of the current high-pressure water spraying device and the horizontal plane, that is, the third angle information of 45 degrees, and according to the trigonometric function of 45 degrees and the third distance information of 4 cm. According to a 60 deg. trigonometric function and the fourth distance information 5.5cm. It can be determined that the height from the sensor to the central pixel of the depression in the vertical direction is 4.7cm. And performing difference on 4.7cm and 2.82cm to obtain the depth information of the recess of 1.88cm.
In the embodiment of the application, the underwater robot can be further provided with the laser radar device, the underwater robot scans the surface form of the concrete through the laser radar device in the process of moving underwater, so that a three-dimensional image model of the surface of the concrete is obtained, the three-dimensional image model is displayed through display devices such as a display screen, and therefore workers can know the specific structural form of the underwater concrete conveniently.
The embodiment introduces an underwater concrete disease monitoring method from the perspective of a method flow, and the following embodiment introduces an underwater concrete disease monitoring device from the perspective of a virtual module or a virtual unit, and is specifically described in the following embodiment.
The embodiment of the application provides an underwater concrete disease monitoring device 20, as shown in fig. 4, the underwater concrete disease monitoring device 20 may specifically include:
an obtaining module 201, configured to obtain a surface image of concrete;
the judging module 202 is used for performing feature recognition on the surface image and judging whether the concrete has diseases, wherein the diseases comprise cracks and depressions;
the position determining module 203 is used for determining the position of the disease in the surface image when the disease exists;
the first control module 204 is used for controlling the high-pressure water spraying device to work towards the diseases based on the positions;
and the second control module 205 is configured to control the distance sensor to work based on the position to obtain depth information of the disease.
By adopting the technical scheme, the acquisition module 201 acquires the surface image of the concrete, so that the disease condition of the concrete is conveniently analyzed. The surface image is subjected to feature recognition, the judging module 202 can judge whether cracks and/or dents exist in the concrete, if yes, the position determining module 203 determines the position of the flaws on the surface image, after the position of the flaws is determined, the first control module 204 can control the high-pressure water spraying device to work towards the flaws according to the position of the flaws, so that sludge sundries and the like in the flaws are washed out, the flaws are clearer and more real, and after the sludge sundries and the like in the flaws are removed, the second control module 205 controls the distance sensor to work towards the flaws, so that the depth information of the flaws can be more accurately obtained.
In a possible implementation manner of the embodiment of the present application, the determining module 202 is specifically configured to, when performing feature recognition on the surface image and determining whether a disease exists in the concrete:
and inputting the surface image into a trained network model for crack and/or recess recognition so as to judge whether the concrete has diseases.
In a possible implementation manner of the embodiment of the present application, when determining the position of the disease in the surface image, the position determining module 203 is specifically configured to:
carrying out edge detection on the diseases to obtain outline information of the diseases, wherein pixels in the outline information range are occupied by the diseases;
drawing a coordinate system on the surface image;
if the fault is a crack, determining the corresponding relation between the coordinates of each pixel occupied by the crack and the crack respectively, and determining the coordinates of the pixels occupied as the position of the crack;
and if the defect is a pit, determining the coordinates of a central pixel in the pixels occupied by the pit, and determining the coordinates of the central pixel as the position of the pit.
In a possible implementation manner of the embodiment of the application, the first control module 204 is specifically configured to, when controlling the high-pressure water spraying device to work towards a disease based on the position:
if only pits exist, determining the distance value from the coordinate of the center point of each pit to a preset coordinate, wherein the preset coordinate represents the coordinate of the high-pressure water spraying device, sequencing the distance values corresponding to the pits from small to large, and determining a first moving path according to a sequencing result, wherein the first moving path is a moving path when a nozzle of the high-pressure water spraying device sprays water to each pit in sequence, and controlling the high-pressure water spraying device to work towards the defect according to the first moving path;
if only cracks exist, determining a second moving path of the spray head on each crack according to the pixels occupied by each crack, sequencing the number of the pixels occupied by each crack, and determining a third moving path according to a sequencing result, wherein the third moving path is a moving path of the spray head of the high-pressure water spraying device when spraying water to each crack in sequence, and controlling the high-pressure water spraying device to work towards the fault according to the second moving path and the third moving path;
if the pits and cracks exist, determining the priority of the diseases existing in the surface image according to the preset priority, and controlling the high-pressure water spraying device to work towards the diseases based on the preset priority, the first moving path, the second moving path and the third moving path.
In a possible implementation manner of the embodiment of the present application, the apparatus 20 further includes:
and the adjusting module is used for adjusting the water spraying coverage area of the high-pressure water spraying device based on the number of the occupied pixels.
In a possible implementation manner of the embodiment of the present application, the pixels outside the contour information range are concrete plane pixels, and the second control module 205 is specifically configured to, when obtaining depth information of a disease by controlling the distance sensor to operate toward the disease based on the position:
if the damage is a crack, determining a plurality of sampling points on a moving path of the second spray head;
determining a tangent corresponding to each sampling point on the moving path of the second spray head, and drawing a perpendicular line of the corresponding tangent on each sampling point;
determining pixel points which are closest to the contour information and located on the vertical line outside the contour information range of the crack as first reference pixel points;
the method comprises the steps of controlling a distance sensor to collect first distance information and acquiring first angle information of the distance sensor when the first distance information is collected, wherein the first distance information is the distance from the distance sensor to a first reference pixel point corresponding to each sampling point;
controlling the distance sensor to acquire second distance information and acquiring second angle information of the distance sensor when the second distance information is acquired, wherein the second distance information is the distance from the distance sensor to each sampling point respectively;
determining depth information of the fracture at each sampling point based on the first angle information, the second angle information, the first distance information, and the second distance information of each sampling point.
In a possible implementation manner of the embodiment of the present application, when the second control module 206 controls the distance sensor to work toward the disease based on the position to obtain the depth information of the disease, the second control module is specifically configured to:
if the defect is a recess, determining any second reference pixel point which is closest to the contour information outside the contour information of the recess;
controlling the distance sensor to acquire third distance information and acquiring third angle information of the distance sensor when the third distance information is acquired, wherein the third distance information is the distance from the distance sensor to the second reference pixel point;
controlling the distance sensor to acquire fourth distance information and acquiring fourth angle information of the distance sensor when the fourth distance information is acquired, wherein the fourth distance information is the distance from the distance sensor to the central pixel;
determining depth information of the recess based on the third angle information, fourth angle information, third distance information, and fourth distance information.
In the embodiment of the present application, the first control module 204 and the second control module 205 may be the same control module or different control modules.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the underwater concrete disease monitoring device 20 described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
In the embodiment of the present application, there is provided an underwater robot, as shown in fig. 5, the underwater robot 30 shown in fig. 5 includes: a processor 301 and a memory 303. Wherein processor 301 is coupled to memory 303, such as via bus 302. Optionally, the underwater robot 30 may also include a transceiver 304. It should be noted that the transceiver 304 is not limited to one in practical applications, and the structure of the underwater robot 30 does not constitute a limitation to the embodiment of the present application.
The Processor 301 may be a CPU (Central Processing Unit), a general-purpose Processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other Programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 301 may also be a combination of computing functions, e.g., comprising one or more microprocessors in combination, a DSP and a microprocessor in combination, or the like.
Bus 302 may include a path that transfers information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 302 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 5, but this is not intended to represent only one bus or type of bus.
The Memory 303 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), a magnetic Disc storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to these.
The memory 303 is used for storing application program codes for executing the scheme of the application, and the processor 301 controls the execution. The processor 301 is configured to execute application program code stored in the memory 303 to implement the aspects illustrated in the foregoing method embodiments.
The underwater robot 30 further comprises a high pressure water spray 305 and a distance sensor 306. The high pressure water spray 305 may be disposed at the bottom of the underwater robot 30 with the spray head of the high pressure water spray 305 facing the concrete surface. The distance sensor 306 may be disposed at the bottom of the underwater robot 30 with the probe of the distance sensor 306 facing the concrete surface. The signal line of the high-pressure water jet device 305 is connected to the bus 302, and the signal line of the distance sensor 306 is connected to the bus 302. The high-pressure water spray device 305 sprays high-speed water flow to clean sludge and sundries in the disease. The distance sensor 306 faces the disease to achieve the purpose of distance measurement. An angle sensor may also be disposed on the underwater robot 30 for detecting the angle formed by the distance sensor 306 and the horizontal plane. The underwater robot shown in fig. 5 is only an example, and should not bring any limitation to the function and the range of use of the embodiment of the present application.
The present application provides a computer-readable storage medium, on which a computer program is stored, which, when running on a computer, enables the computer to execute the corresponding content in the foregoing method embodiments. Compared with the related art, the surface image of the concrete is obtained in the embodiment of the application, so that the disease condition of the concrete is conveniently analyzed. The method comprises the steps of carrying out feature recognition on a surface image so as to judge whether cracks and/or dents exist in concrete, determining the position of the flaws on the surface image if the flaws exist, controlling a high-pressure water spraying device to face the flaws according to the position of the flaws after the position of the flaws is determined, so that sludge sundries and the like in the flaws are washed away, the flaws are clearer and truer, and controlling a distance sensor to face the flaws after the sludge sundries and the like in the flaws are removed, so that the depth information of the flaws can be more accurately obtained.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of execution is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations should also be regarded as the protection scope of the present application.

Claims (10)

1. An underwater concrete disease monitoring method is characterized by comprising the following steps:
acquiring a surface image of concrete;
carrying out feature recognition on the surface image, and judging whether the concrete has diseases or not, wherein the diseases comprise cracks and depressions;
if the surface image has the diseases, determining the positions of the diseases in the surface image;
controlling the high-pressure water spraying device to work towards the diseases based on the positions;
and controlling the distance sensor to work towards the disease based on the position to obtain the depth information of the disease.
2. The method for monitoring the underwater concrete diseases according to claim 1, wherein the step of performing feature recognition on the surface image to judge whether the concrete has the diseases comprises the following steps:
and inputting the surface image into a trained network model for crack and/or recess recognition so as to judge whether the concrete has diseases.
3. The method for monitoring the underwater concrete diseases according to claim 1, wherein the determining the positions of the diseases on the surface image comprises:
performing edge detection on the disease to obtain outline information of the disease, wherein pixels in the outline information range are occupied pixels of the disease;
drawing a coordinate system on the surface image;
if the crack is damaged, determining the corresponding relation between the coordinates of each occupied pixel of the crack and the crack respectively, and determining the coordinates of the occupied pixels as the position of the crack;
and if the defect is a recess, determining the coordinates of a central pixel in the pixels occupied by the recess, and determining the coordinates of the central pixel as the position of the recess.
4. The underwater concrete disease monitoring method according to claim 3, wherein the controlling of the high-pressure water spraying device to work towards the disease based on the position comprises:
if only pits exist, determining the distance value from the coordinate of the center point of each pit to a preset coordinate, wherein the preset coordinate represents the coordinate of the high-pressure water spraying device, sequencing the distance values corresponding to the pits from small to large, and determining a first moving path according to a sequencing result, wherein the first moving path is a moving path when a spray head of the high-pressure water spraying device sprays water to each pit in sequence, and controlling the high-pressure water spraying device to work towards a defect according to the first moving path;
if only cracks exist, determining a second moving path of the spray head on each crack according to the pixels occupied by each crack, sequencing the number of the pixels occupied by each crack, determining a third moving path according to the sequencing result, wherein the third moving path is a moving path of the spray head of the high-pressure water spraying device when the spray head sprays water on each crack in sequence, and controlling the high-pressure water spraying device to work towards the fault according to the second moving path and the third moving path;
if the surface image is sunken and has cracks, determining the priority of the diseases existing in the surface image according to a preset priority, and controlling the high-pressure water spraying device to work towards the diseases based on the preset priority, the first moving path, the second moving path and the third moving path.
5. The method for monitoring diseases of underwater concrete according to claim 3, wherein if the diseases are pits, the method further comprises:
and adjusting the water spraying coverage area of the high-pressure water spraying device based on the number of the occupied pixels.
6. The method for monitoring the underwater concrete diseases according to claim 3, wherein the pixels outside the outline information range are concrete plane pixels, and the distance sensor is controlled to work towards the diseases based on the position to obtain the depth information of the diseases, and the method comprises the following steps:
if the fault is a crack, determining a plurality of sampling points on a moving path of the second spray head;
determining a tangent corresponding to each sampling point on the moving path of the second spray head, and drawing a vertical line of the corresponding tangent on each sampling point;
determining pixel points which are closest to the contour information and located on the vertical line outside the contour information range of the crack as first reference pixel points;
the method comprises the steps of controlling a distance sensor to collect first distance information and acquiring first angle information of the distance sensor when the first distance information is collected, wherein the first distance information is the distance from the distance sensor to a first reference pixel point corresponding to each sampling point;
controlling the distance sensor to acquire second distance information and acquiring second angle information of the distance sensor when the second distance information is acquired, wherein the second distance information is the distance from the distance sensor to each sampling point;
determining depth information of the fracture at each sampling point based on the first angle information, the second angle information, the first distance information, and the second distance information of each sampling point.
7. The underwater concrete disease monitoring method according to claim 3 or 6, wherein the step of controlling the distance sensor to work towards the disease based on the position to obtain the depth information of the disease comprises the following steps:
if the defect is a recess, determining any second reference pixel point which is closest to the contour information outside the contour information of the recess;
controlling the distance sensor to acquire third distance information and acquiring third angle information of the distance sensor when the third distance information is acquired, wherein the third distance information is the distance from the distance sensor to the second reference pixel point;
controlling the distance sensor to acquire fourth distance information and acquiring fourth angle information of the distance sensor when the fourth distance information is acquired, wherein the fourth distance information is the distance from the distance sensor to the central pixel;
determining depth information of the depression based on the third angle information, fourth angle information, third distance information, and fourth distance information.
8. The utility model provides an underwater concrete disease monitoring devices which characterized in that includes:
the acquisition module is used for acquiring a surface image of the concrete;
the judging module is used for carrying out feature recognition on the surface image and judging whether the concrete has diseases or not, wherein the diseases comprise cracks and depressions;
the position determining module is used for determining the position of the disease on the surface image when the disease exists;
the first control module is used for controlling the high-pressure water spraying device to work towards the diseases based on the position;
and the second control module is used for controlling the distance sensor to work based on the position to obtain the depth information of the disease.
9. An underwater robot, comprising:
a high pressure water spray device;
a distance sensor;
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: an underwater concrete disease monitoring method according to any one of claims 1 to 7 is carried out.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that when the computer program is executed in a computer, the computer is caused to execute a method for underwater concrete disease monitoring according to any one of claims 1 to 7.
CN202211047513.9A 2022-08-29 2022-08-29 Underwater concrete disease monitoring method and device, underwater robot and medium Active CN115527109B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211047513.9A CN115527109B (en) 2022-08-29 2022-08-29 Underwater concrete disease monitoring method and device, underwater robot and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211047513.9A CN115527109B (en) 2022-08-29 2022-08-29 Underwater concrete disease monitoring method and device, underwater robot and medium

Publications (2)

Publication Number Publication Date
CN115527109A true CN115527109A (en) 2022-12-27
CN115527109B CN115527109B (en) 2023-04-28

Family

ID=84698579

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211047513.9A Active CN115527109B (en) 2022-08-29 2022-08-29 Underwater concrete disease monitoring method and device, underwater robot and medium

Country Status (1)

Country Link
CN (1) CN115527109B (en)

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5675085A (en) * 1994-10-28 1997-10-07 H & B System Inc. Method and apparatus for measuring depth of crack for reinforced concrete construction
CN109781740A (en) * 2019-03-13 2019-05-21 水利部交通运输部国家能源局南京水利科学研究院 Remote control checks the method and apparatus of concrete microcrack
CN110118788A (en) * 2019-04-30 2019-08-13 东南大学 Submerged structure Defect inspection contact visual sensing equipment and image processing method
CN110939461A (en) * 2019-10-25 2020-03-31 中铁隧道局集团有限公司 Intelligent concrete spraying method
CN111521136A (en) * 2020-05-09 2020-08-11 大连理工大学 Reinforced concrete structure crack depth detection method and detection device based on horizontal shear wave
CN111832448A (en) * 2020-06-30 2020-10-27 宁夏工商职业技术学院（宁夏化工技工学校、宁夏机电工程学校、宁夏农业机械化学校） Disease identification method and system for grape orchard
CN112033972A (en) * 2020-09-14 2020-12-04 长安大学 Road crack detection device
CN112440374A (en) * 2020-11-30 2021-03-05 四川仟坤建设集团有限责任公司 Concrete curing water injection system
CN113610054A (en) * 2021-08-27 2021-11-05 广州慧瞳科技有限公司 Underwater structure disease depth detection method, system and device and storage medium
CN113718777A (en) * 2021-08-03 2021-11-30 中国化学工程第十六建设有限公司 Mass concrete crack prevention construction method
CN113989230A (en) * 2021-10-28 2022-01-28 华东交通大学 Improved YOLOv 4-based road pavement disease detection method
CN114293481A (en) * 2021-12-31 2022-04-08 山东省交通工程监理咨询有限公司 Underwater overhaul robot, system and method for bridge pier
CN114359251A (en) * 2022-01-11 2022-04-15 招商局重庆交通科研设计院有限公司 Automatic identification method for concrete surface damage
CN114550028A (en) * 2022-01-18 2022-05-27 北京旷视科技有限公司 Method for acquiring task progress of vehicle, electronic device, medium and product

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5675085A (en) * 1994-10-28 1997-10-07 H & B System Inc. Method and apparatus for measuring depth of crack for reinforced concrete construction
CN109781740A (en) * 2019-03-13 2019-05-21 水利部交通运输部国家能源局南京水利科学研究院 Remote control checks the method and apparatus of concrete microcrack
CN110118788A (en) * 2019-04-30 2019-08-13 东南大学 Submerged structure Defect inspection contact visual sensing equipment and image processing method
CN110939461A (en) * 2019-10-25 2020-03-31 中铁隧道局集团有限公司 Intelligent concrete spraying method
CN111521136A (en) * 2020-05-09 2020-08-11 大连理工大学 Reinforced concrete structure crack depth detection method and detection device based on horizontal shear wave
CN111832448A (en) * 2020-06-30 2020-10-27 宁夏工商职业技术学院（宁夏化工技工学校、宁夏机电工程学校、宁夏农业机械化学校） Disease identification method and system for grape orchard
CN112033972A (en) * 2020-09-14 2020-12-04 长安大学 Road crack detection device
CN112440374A (en) * 2020-11-30 2021-03-05 四川仟坤建设集团有限责任公司 Concrete curing water injection system
CN113718777A (en) * 2021-08-03 2021-11-30 中国化学工程第十六建设有限公司 Mass concrete crack prevention construction method
CN113610054A (en) * 2021-08-27 2021-11-05 广州慧瞳科技有限公司 Underwater structure disease depth detection method, system and device and storage medium
CN113989230A (en) * 2021-10-28 2022-01-28 华东交通大学 Improved YOLOv 4-based road pavement disease detection method
CN114293481A (en) * 2021-12-31 2022-04-08 山东省交通工程监理咨询有限公司 Underwater overhaul robot, system and method for bridge pier
CN114359251A (en) * 2022-01-11 2022-04-15 招商局重庆交通科研设计院有限公司 Automatic identification method for concrete surface damage
CN114550028A (en) * 2022-01-18 2022-05-27 北京旷视科技有限公司 Method for acquiring task progress of vehicle, electronic device, medium and product

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
XUAN ZHENG ET AL.: "Lightweight Bridge Crack Detection Method Based on SegNet and Bottleneck Depth-Separable Convolution With Residuals" *
丁威等: "基于残差网络的混凝土结构病害分类识别研究" *
刘学增等: "混凝土裂缝深度的激光超声探测方法" *
高松: "水利渠道施工中防渗漏技术应用探讨" *

Also Published As

Publication number Publication date
CN115527109B (en) 2023-04-28

Similar Documents

Publication Publication Date Title
JP6620477B2 (en) Method and program for detecting cracks in concrete
CN115375686B (en) Glass edge flaw detection method based on image processing
CN113643276B (en) Textile texture defect automatic detection method based on statistical analysis
CN110874596A (en) Intelligent recognition early warning method and system for instrument
US8942465B2 (en) Methods and systems for processing images for inspection of an object
CN112669286A (en) Infrared thermal image-based method for identifying defects and evaluating damage degree of external thermal insulation system of external wall
CN108968825A (en) A kind of sweeping robot and robot sweep the floor method
CN113720914B (en) Ultrasonic flaw detection system and ultrasonic flaw detection method
CN109556533B (en) Automatic extraction method for multi-line structured light stripe image
CN115527109B (en) Underwater concrete disease monitoring method and device, underwater robot and medium
US6459807B1 (en) System and method for locating irregular edges in image data
CN116362696A (en) Building digital template library management platform and method
CN116642420A (en) Online glue type detection device and method for gluing automobile windshield glass
CN105043962B (en) A kind of method of quantitative measurment sandstone matter cultural artifact surface weathering speed
CN116385356A (en) Method and system for extracting regular hexagonal hole features based on laser vision
CN116452944A (en) Surface crack identification method and device
CN112785594B (en) Automatic bridge structure crack identification method based on image two-dimensional amplitude estimation
CN108645385A (en) A kind of heavy construction steel construction intelligence deformation detecting system
Zurakowska et al. Visual assessment of sandstone building façades: condition factors related to cleaning
Li Generalized Hough transform: fast detection for hybrid multi-circle and multi-rectangle
CN112066893B (en) Method and device for measuring height of key cap of keyboard
CN111583242B (en) Morphological vertex extraction method and detection device for honeycomb regularity detection
CN113362459B (en) Characteristic extraction method for damaged boundary of rock landslide
CN114897892B (en) Method for calculating characteristic parameters of apparent cracks and holes of PC (polycarbonate) member
CN111366086B (en) Carriage pose measurement system and method for automatic loading

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