CN118096602B - Stone repairing and scanning method and system - Google Patents

Stone repairing and scanning method and system Download PDF

Info

Publication number
CN118096602B
CN118096602B CN202410502565.3A CN202410502565A CN118096602B CN 118096602 B CN118096602 B CN 118096602B CN 202410502565 A CN202410502565 A CN 202410502565A CN 118096602 B CN118096602 B CN 118096602B
Authority
CN
China
Prior art keywords
flaw
determining
repair
scanning
stone
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
Application number
CN202410502565.3A
Other languages
Chinese (zh)
Other versions
CN118096602A (en
Inventor
李婷
吕峰
王志兴
刘胜杰
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.)
China Construction Design And Research Institute Co ltd
Original Assignee
China Construction Design And Research Institute 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 China Construction Design And Research Institute Co ltd filed Critical China Construction Design And Research Institute Co ltd
Priority to CN202410502565.3A priority Critical patent/CN118096602B/en
Publication of CN118096602A publication Critical patent/CN118096602A/en
Application granted granted Critical
Publication of CN118096602B publication Critical patent/CN118096602B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/50Depth or shape recovery
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • G06T7/62Analysis of geometric attributes of area, perimeter, diameter or volume
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The invention provides a stone repairing and scanning method and system. Wherein the method comprises the following steps: controlling a machine end to scan each stone in a site to be repaired, determining the stone as the stone to be repaired in response to the scanning result of the machine end on any stone as a determined flaw, and acquiring a scanning image of the stone to be repaired; performing image recognition on the scanned image, determining the outline of the flaw in the scanned image, and determining each scanning repair point positioned in the outline of the flaw; acquiring each repair depth corresponding to each scanning repair point, and determining the area volume of a flaw area in the flaw outline according to each repair depth; under the condition that the volume of the repairing material carried by the machine end is not smaller than the area volume, controlling the machine end to fill the repairing material volume into the defect area in the stone to be repaired to obtain the repaired stone; and responding to the repair completion signal sent by the machine end, and controlling the machine end to perform multidimensional repair condition inspection on the repaired stone. The invention at least improves the repairing efficiency of the stone.

Description

Stone repairing and scanning method and system
Technical Field
The invention relates to a data processing technology, in particular to a stone repairing and scanning method and system.
Background
Tiles on the ground in a market can cause defects due to long-time trampling and other reasons, for example, the situation that grooves or cracks appear on stone materials can influence the bearing capacity of the stone materials, and accidental injury accidents such as stumbling and falling of personnel can be easily caused. The grooves or cracks on the stone material can also influence the image of a merchant and customer experience, so that the image of the merchant and economic benefits are reduced, and the tile is repaired in time after being cracked.
The inventor finds that the existing stone repairing mode is mostly carried out manually in the research, or the existing equipment can not clearly scan out the specific volume of the flaw area on the stone and repair the flaw area in time, so that certain manpower and time are wasted.
Disclosure of Invention
The present invention has been made in view of the above problems, and it is an object of the present invention to provide a stone repair scanning method and system that overcomes or at least partially solves the above problems.
According to one aspect of the present invention, there is provided a stone repair scanning method comprising the steps of:
Controlling a machine end to scan each stone in a site to be repaired, determining the stone as the stone to be repaired in response to the scanning result of the machine end on any stone as a determined flaw, and acquiring a scanning image of the stone to be repaired;
performing image recognition on the scanned image, determining a flaw outline in the scanned image, and determining each scanning repair point positioned in the flaw outline;
Acquiring each repair depth corresponding to each scanning repair point, and determining the area volume of the defect area in the defect outline according to each repair depth;
controlling the machine end to fill the repairing material into a defect area in the stone to be repaired under the condition that the material volume of the repairing material carried by the machine end is not smaller than the area volume, so as to obtain the repaired stone;
and responding to the repair completion signal sent by the machine end, and controlling the machine end to perform multidimensional repair condition inspection on the repaired stone.
Optionally, in the method according to the present invention, performing image recognition on the scanned image, determining a flaw contour in the scanned image, and determining each scan repair point located within the flaw contour, includes:
Inputting the scanning image into a pre-trained contour recognition model, and determining the flaw contour in the scanning image;
Determining a flaw center point located in the flaw profile, and establishing a flaw coordinate system based on the flaw center point;
Based on the flaw coordinate system, acquiring a flaw coordinate set formed by flaw coordinate points in the flaw outline, and determining an abscissa maximum absolute value and an ordinate maximum absolute value in the flaw coordinate set;
determining a first interval and a second interval based on the abscissa maximum absolute value and the ordinate maximum absolute value respectively;
generating first dividing lines with first intervals and second dividing lines with second intervals respectively on the basis of two sides of a Y axis and two sides of an X axis of the flaw coordinate system;
And acquiring the coordinates of each point corresponding to each intersection point between the first dividing lines and the second dividing lines, and determining each intersection point corresponding to each point coordinate in the flaw coordinate set as each scanning repair point.
Optionally, in the method according to the present invention, determining the first interval and the second interval based on the abscissa maximum absolute value and the ordinate maximum absolute value, respectively, includes:
A pre-established number dividing table is called, wherein the number dividing table comprises different numerical intervals and dividing intervals respectively corresponding to the different numerical intervals;
traversing the quantity dividing table, respectively determining a first numerical value interval and a second numerical value interval which comprise the maximum absolute value of the abscissa and the maximum absolute value of the ordinate, and respectively determining a first interval and a second interval which correspond to the first numerical value interval and the second numerical value interval.
Optionally, in the method according to the present invention, generating each first division line having a first interval and each second division line having a second interval based on the Y-axis side and the X-axis side of the defect coordinate system, respectively, includes:
Establishing a transparent dividing image layer corresponding to the image size of the scanned image based on the scanned image;
generating first dividing lines with first intervals and second dividing lines with second intervals on the basis of two sides of a Y axis and two sides of an X axis of the flaw coordinate system in the transparent dividing layer respectively;
Responding to a modification request of a management end, and sending a scanning image with the transparent division layer to the management end for display;
And responding to interaction of the management end on any dividing line in the transparent dividing layer, and moving and adjusting the dividing line along the direction perpendicular to the extending direction of the dividing line.
Optionally, in the method according to the present invention, acquiring coordinates of each point corresponding to each intersection point between each first dividing line and each second dividing line, and determining each intersection point corresponding to each point coordinate in the flaw coordinate set as each scan repair point, including:
Acquiring coordinates of each point corresponding to each intersection point between each first dividing line and each second dividing line;
summarizing each intersection point corresponding to each point coordinate in the flaw coordinate set to obtain an in-region combination;
Summarizing each intersection point corresponding to each point coordinate outside the flaw coordinate set to obtain an out-of-area combination;
Determining each intersection point close to the flaw outline in the out-of-area combination as each edge intersection point, and respectively obtaining the horizontal distance and the vertical distance between each edge intersection point and the flaw outline;
When the horizontal distance of any edge intersection point is smaller than a first interval under a preset multiple, generating a first newly added intersection point parallel to the edge intersection point on the flaw profile;
When the vertical distance of any edge intersection point is smaller than a second interval under a preset multiple, generating a second newly-added intersection point vertical to the edge intersection point on the flaw profile;
And summarizing the first newly added intersection point and the second newly added intersection point into the region for combination, and determining each intersection point positioned in the region for combination as each scanning repair point.
Optionally, in the method according to the present invention, determining the area volume of the flaw area located in the flaw profile according to each repair depth includes:
establishing a virtual blank model and a virtual clone model which is the same as the virtual blank model;
Determining a corresponding relation between a model center point of the virtual blank model and the flaw center point, and respectively generating virtual point positions corresponding to the scanning repair points in the virtual blank model based on the corresponding relation;
according to the repair depths corresponding to the scanning repair points, performing model updating based on the virtual point positions on the virtual blank model to obtain a virtual defect model comprising a virtual defect area;
respectively carrying out model change based on the same regular shape on the virtual flaw model and the virtual clone model to obtain a first model and a second model;
a volume difference between the first model and the second model is determined and the volume difference is determined as the region volume.
Optionally, in the method according to the present invention, controlling the machine end to perform multi-dimensional repair condition inspection on the repaired stone comprises:
Controlling the machine end to acquire an acquired image of the repaired stone, and determining a repair contour corresponding to the flaw contour in the acquired image based on a comparison result of the acquired image and the scanning image;
Acquiring region pixel points of a repair region in the repair contour, and determining a region pixel value corresponding to the region pixel points as a first inspection item;
Determining scanning check points which are positioned in the repair area and correspond to the scanning repair points respectively, controlling the machine end to scan the scanning check points, acquiring the inspection depths corresponding to the scanning check points respectively, and determining the inspection depths as second inspection items;
And performing qualification inspection based on the first inspection item and the second inspection item respectively, and filling inspection results into a pre-established inspection list.
Optionally, in the method according to the present invention, performing the qualification inspection based on the first inspection item includes:
generating a comparison contour surrounding the restoration contour by extending a preset distance outwards along the restoration contour in the acquired image, and determining a region between the comparison contour and the restoration contour as a comparison region;
Determining the horizontal comparison length and the vertical comparison length of the comparison area in the horizontal direction and the vertical direction respectively, and determining the direction corresponding to the highest length of the horizontal comparison length and the vertical comparison length as the dividing direction;
performing equidistant region division on the comparison region based on the division direction to obtain each comparison sub-region;
respectively acquiring any sub-region pixel point in each contrast sub-region, and determining each sub-region pixel point as each contrast pixel point;
Respectively carrying out difference calculation on the regional pixel values and the contrast pixel values of each contrast pixel point to obtain each first absolute difference value, and calling a first preset difference value interval;
If all the first absolute difference values are located in the first preset difference value interval, determining that the inspection result of the first inspection item is qualified;
And if at least one of the first absolute differences is not located in the first preset difference interval, determining that the inspection result of the first inspection item is unqualified.
Optionally, in the method according to the present invention, performing the qualification inspection based on the second inspection item includes:
generating a comparison contour surrounding the restoration contour by extending a preset distance outwards along the restoration contour in the acquired image, and determining a region between the comparison contour and the restoration contour as a comparison region;
Determining the horizontal comparison length and the vertical comparison length of the comparison area in the horizontal direction and the vertical direction respectively, and determining the direction corresponding to the highest length of the horizontal comparison length and the vertical comparison length as the dividing direction;
performing equidistant region division on the comparison region based on the division direction to obtain each comparison sub-region;
Respectively acquiring any sub-region pixel point in each contrast sub-region, and determining each sub-region pixel point as each scanning contrast point;
Controlling the machine end to scan each scanning comparison point, obtaining each comparison depth corresponding to each scanning comparison point, and carrying out mean value calculation based on each comparison depth to obtain a depth mean value;
respectively carrying out difference calculation on each inspection depth and the depth mean value to obtain each second absolute difference value, and calling a second preset difference value interval;
If the second absolute differences are all located in the second preset difference interval, determining that the inspection result of the second inspection item is qualified;
And if at least one of the second absolute differences is not located in the second preset difference interval, determining that the inspection result of the second inspection item is unqualified.
According to yet another aspect of the present invention, there is provided a stone repair scanning system comprising: the determining module is configured to control the machine end to scan each stone in the site to be repaired, determine the stone as the stone to be repaired in response to the scanning result of the machine end on any stone as a determined flaw, and acquire a scanning image of the stone to be repaired;
the identification module is configured to carry out image identification on the scanned image, determine a flaw outline in the scanned image and determine each scanning repair point positioned in the flaw outline;
the volume acquisition module is configured to acquire each repair depth corresponding to each scanning repair point and determine the area volume of the flaw area in the flaw outline according to each repair depth;
the repairing module is configured to control the machine end to fill the repairing material into the defect area in the stone to be repaired to obtain repaired stone comprising the repairing area under the condition that the material volume of the repairing material carried by the machine end is not smaller than the area volume;
The inspection module is configured to respond to the repair completion signal sent by the machine end and control the machine end to conduct multi-dimensional repair condition inspection on the repair area in the repaired stone.
According to the scheme of the invention, the server can control the machine end to scan each stone in the site to be repaired, and the stone is determined to be the stone to be repaired in response to the scanning result of the machine end on any stone as the determined flaw, and the scanning image of the stone to be repaired is obtained. And performing image recognition on the scanned image, determining the flaw outline in the scanned image, determining each scanning repair point positioned in the flaw outline, thereby obtaining each repair depth respectively corresponding to each scanning repair point, and determining the area volume of the flaw area positioned in the flaw outline according to each repair depth. Under the condition that the material volume of the repairing material carried by the machine end is not smaller than the area volume, the server controls the machine end to fill the repairing material into the defect area in the stone to be repaired, and the repaired stone is obtained. After the machine end sends the repair completion signal, the server controls the machine end to carry out multidimensional repair condition inspection on the repaired stone. The invention can rapidly determine the flaw area and area volume of the stone to be repaired, repair the stone, and check the multi-dimensional repair condition after repair, thereby improving the repair efficiency of the stone and ensuring the repair effect to a great extent.
Drawings
Fig. 1 shows a flow chart of a stone repair scanning method according to one embodiment of the invention;
fig. 2 shows a schematic structural view of a machine end in the present embodiment;
3-5 show progress diagrams of corresponding repair of stone materials in combination with actual application scenes;
Fig. 6 shows a block diagram of a stone repair scanning system according to another embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Tiles on the ground in a market can cause defects due to long-time trampling and other reasons, for example, the situation that grooves or cracks appear on stone materials can influence the bearing capacity of the stone materials, and accidental injury accidents such as stumbling and falling of personnel can be easily caused. The grooves or cracks on the stone material can also influence the image of a merchant and customer experience, so that the image of the merchant and economic benefits are reduced, and the tile is repaired in time after being cracked.
The inventor finds that the existing stone repairing mode is mostly carried out manually in the research, or the existing equipment can not clearly scan out the specific volume of the flaw area on the stone and repair the flaw area in time, so that certain manpower and time are wasted.
The present inventors have proposed the present invention in order to solve the problems in the prior art described above. One embodiment of the present invention provides a stone repair scanning method that may be performed in a computing device.
Fig. 1 shows a flow chart of a proposed stone repair scanning method according to an embodiment of the present invention, as shown in fig. 1, the object of the present embodiment is to implement a stone repair scanning method, starting with step S102, in step S102, comprising the following steps:
And controlling a machine end to scan each stone in a site to be repaired, determining the stone as the stone to be repaired in response to the scanning result of the machine end on any stone as a determined flaw, and acquiring a scanning image of the stone to be repaired.
For example, in this embodiment, the machine end may be understood as a robot with an infrared scanning function, a carrying function and a moving function, and the server may control the machine end to scan all stones in the site to be repaired, such as floor tiles in a mall. The machine end with the infrared scanning function can measure the distance between the ground and the sensor in real time, when the infrared measurement result exceeds the normal distance, the machine end is used for scanning a stone with defects such as grooves or cracks, namely, when the scanning result of the machine end on any stone is a determined defect, the stone is determined to be a stone to be repaired, and meanwhile, the scanning image of the stone to be repaired is recorded.
Fig. 2 is a schematic diagram of a machine end in the present embodiment, and as shown in fig. 2, the machine end includes a machine body 201 and a moving pulley 202, wherein the moving pulley 202 can drive the machine body 201 to move, so as to complete a corresponding scanning operation.
In step S104, the following are included:
and carrying out image recognition on the scanned image, determining the outline of the flaw in the scanned image, and determining each scanning repair point positioned in the outline of the flaw.
For example, in this embodiment, the server performs image recognition on the acquired scanned image of the stone to be repaired, and recognizes the outline of the flaw area on the stone, that is, the flaw outline. And each scanning repair point in the defect profile is determined, so that the defect distribution condition in the defect profile can be approximately determined according to the depth of each scanning repair point obtained by infrared scanning of each scanning repair point by the machine end, and the certain workload of a subsequent server is reduced.
Further, the above-mentioned "image recognition is performed on the scanned image, a flaw outline in the scanned image is determined, and each scanning repair point located in the flaw outline" further includes the following steps:
Inputting the scanning image into a pre-trained contour recognition model, and determining the flaw contour in the scanning image;
Determining a flaw center point located in the flaw profile, and establishing a flaw coordinate system based on the flaw center point;
Based on the flaw coordinate system, acquiring a flaw coordinate set formed by flaw coordinate points in the flaw outline, and determining an abscissa maximum absolute value and an ordinate maximum absolute value in the flaw coordinate set;
determining a first interval and a second interval based on the abscissa maximum absolute value and the ordinate maximum absolute value respectively;
generating first dividing lines with first intervals and second dividing lines with second intervals respectively on the basis of two sides of a Y axis and two sides of an X axis of the flaw coordinate system;
And acquiring the coordinates of each point corresponding to each intersection point between the first dividing lines and the second dividing lines, and determining each intersection point corresponding to each point coordinate in the flaw coordinate set as each scanning repair point.
For example, in this embodiment, the contour recognition model may be obtained by performing corresponding model training on a pre-built image recognition model, and before performing model training, a corresponding contour training sample set may be obtained in advance, where the contour training sample set may include a plurality of contour training images corresponding to contours of different flaws. After the corresponding contour training sample set is obtained, model training can be carried out on the pre-built image recognition model through the contour training sample set, so that the contour recognition model is obtained.
After the contour recognition model is obtained, the obtained scanning image can be input into the contour recognition model, and the contour recognition model can perform contour recognition on the scanning image, so that the flaw contour in the scanning image is determined.
The server determines a center point of the defect outline based on the identified defect outline, further establishes a defect coordinate system by taking the defect center point as a round point, and obtains a corresponding defect coordinate set based on the defect coordinate system, wherein the defect coordinate set comprises defect coordinate points of each scanning repair point in the defect outline in the defect coordinate system, and the positions of points with maximum absolute values on an abscissa and an ordinate of the defect coordinate set are respectively judged, namely, the maximum absolute value of the abscissa and the maximum absolute value of the ordinate in the defect coordinate set are determined, and the first interval and the second interval are respectively determined based on the maximum absolute value of the abscissa and the maximum absolute value of the ordinate. And then lines, namely dividing lines, are respectively generated on two sides of the flaw coordinate system according to the positions of the X axis and the Y axis. And generating a plurality of first dividing lines at two sides of the Y axis according to the first interval distance, and generating a plurality of second dividing lines at two sides of the X axis according to the second interval distance. At this time, the server can acquire the coordinates of each point corresponding to each intersection point between each first dividing line and each second dividing line, so as to determine each intersection point corresponding to each point coordinate in the flaw coordinate set as each scanning repair point, thereby saving certain workload of the server.
Further, the above "determining the first interval and the second interval based on the abscissa maximum absolute value and the ordinate maximum absolute value", respectively "further includes the following steps:
A pre-established number dividing table is called, wherein the number dividing table comprises different numerical intervals and dividing intervals respectively corresponding to the different numerical intervals;
traversing the quantity dividing table, respectively determining a first numerical value interval and a second numerical value interval which comprise the maximum absolute value of the abscissa and the maximum absolute value of the ordinate, and respectively determining a first interval and a second interval which correspond to the first numerical value interval and the second numerical value interval.
For example, in this embodiment, before determining the first interval and the second interval, the server will call up a pre-established number division table, where the number division table includes different number intervals and division intervals corresponding to the different number intervals, respectively, and the server will determine a number interval including the maximum absolute value of the abscissa, that is, a first number interval, in the number division table, and determine an interval distance corresponding to the first number interval, that is, a first interval; and then a numerical interval comprising the maximum absolute value of the ordinate, namely a second numerical interval, is found in the quantity dividing table, and the interval distance corresponding to the second numerical interval, namely a second interval, is determined. For example, the unit of the flaw coordinate system is mm, when the maximum absolute value of the abscissa is determined to be 6mm, a numerical interval containing 6mm is found in the number dividing table, for example [4 mm-7 mm ], the [4 mm-7 mm ] is the first numerical interval, the interval corresponding to the first numerical interval is found to be 2mm, and the first interval of the abscissa is 2mm.
Further, the above-mentioned "generating each first dividing line having the first interval and each second dividing line having the second interval based on the Y-axis side and the X-axis side of the flaw coordinate system" further includes the following steps:
Establishing a transparent dividing image layer corresponding to the image size of the scanned image based on the scanned image;
generating first dividing lines with first intervals and second dividing lines with second intervals on the basis of two sides of a Y axis and two sides of an X axis of the flaw coordinate system in the transparent dividing layer respectively;
Responding to a modification request of a management end, and sending a scanning image with the transparent division layer to the management end for display;
And responding to interaction of the management end on any dividing line in the transparent dividing layer, and moving and adjusting the dividing line along the direction perpendicular to the extending direction of the dividing line.
For example, in this embodiment, after determining the first interval and the second interval, the server first establishes a transparent division layer corresponding to the current scan image according to the image size, and in the transparent division layer, division lines are generated on two sides of the transparent division layer according to the positions of the X axis and the Y axis. And generating a plurality of first dividing lines at two sides of the Y axis according to the first interval distance, and generating a plurality of second dividing lines at two sides of the X axis according to the second interval distance. After the server automatically generates the first dividing line and the second dividing line, the management end can also change the position of any dividing line according to the requirement, and after the management end sends a modification request, the server can send the scanned image of the transparent dividing image layer to the management end for display. When the management end hits any dividing line in the transparent dividing layer, the dividing line can be moved and adjusted along the direction perpendicular to the extending direction of the dividing line according to the requirement, so that the method has certain flexibility and meets the customization requirement for the management end.
Further, the above-mentioned "obtaining coordinates of each point corresponding to each intersection point between the first dividing line and the second dividing line, and determining each intersection point corresponding to each point coordinate in the flaw coordinate set as each scan repair point" further includes the following steps:
Acquiring coordinates of each point corresponding to each intersection point between each first dividing line and each second dividing line;
summarizing each intersection point corresponding to each point coordinate in the flaw coordinate set to obtain an in-region combination;
Summarizing each intersection point corresponding to each point coordinate outside the flaw coordinate set to obtain an out-of-area combination;
Determining each intersection point close to the flaw outline in the out-of-area combination as each edge intersection point, and respectively obtaining the horizontal distance and the vertical distance between each edge intersection point and the flaw outline;
When the horizontal distance of any edge intersection point is smaller than a first interval under a preset multiple, generating a first newly added intersection point parallel to the edge intersection point on the flaw profile;
When the vertical distance of any edge intersection point is smaller than a second interval under a preset multiple, generating a second newly-added intersection point vertical to the edge intersection point on the flaw profile;
And summarizing the first newly added intersection point and the second newly added intersection point into the region for combination, and determining each intersection point positioned in the region for combination as each scanning repair point.
For example, in this embodiment, the server obtains the point coordinates of each intersection point between the first dividing line and the second dividing line, and then divides all the intersection points according to the positions of the point coordinates. Summarizing all the intersecting points corresponding to the point coordinates in the flaw coordinate set, and obtaining an in-region combination after summarizing; summarizing all the intersecting points corresponding to the point coordinates outside the flaw coordinate set to obtain an out-of-area combination; and all the intersecting points close to the flaw outline in the out-of-area combination can be determined as the intersecting points of the edges, so that the integrity of the flaw area can be ensured to a great extent, and the horizontal distance and the vertical distance between the intersecting points of the edges and the flaw outline can be respectively obtained.
When the horizontal distance of any edge intersection is smaller than the first interval at a preset multiple, for example, the preset multiple is 0.3, it can be understood that the horizontal distance between the edge intersection and the flaw profile is closer in this case, so as to generate a first new intersection parallel to the edge intersection on the flaw profile; similarly, when the vertical distance of any edge intersection point is smaller than a second interval under a preset multiple, a second newly added intersection point vertical to the edge intersection point is generated on the flaw outline. After the first newly added intersection point and the second newly added intersection point are generated, the server gathers the first newly added intersection point and the second newly added intersection point into the combination in the area, and determines all the intersection points in the combination in the area as each scanning repair point, so that the integrity of the flaw area can be ensured to the greatest extent in the subsequent scanning process, and the certain workload of the server is reduced.
In step S106, the following are included:
And acquiring each repair depth corresponding to each scanning repair point, and determining the area volume of the defect area in the defect outline according to each repair depth.
For example, in this embodiment, the machine end may obtain the depth corresponding to each scanned repair point, that is, the repair depth, by performing infrared scanning on each scanned repair point. And the area volume of the flaw area in the flaw outline can be approximately determined according to each repair depth.
Further, the above-mentioned "determining the area volume of the flaw area located in the flaw profile according to each repair depth" further includes the following steps:
establishing a virtual blank model and a virtual clone model which is the same as the virtual blank model;
Determining a corresponding relation between a model center point of the virtual blank model and the flaw center point, and respectively generating virtual point positions corresponding to the scanning repair points in the virtual blank model based on the corresponding relation;
according to the repair depths corresponding to the scanning repair points, performing model updating based on the virtual point positions on the virtual blank model to obtain a virtual defect model comprising a virtual defect area;
respectively carrying out model change based on the same regular shape on the virtual flaw model and the virtual clone model to obtain a first model and a second model;
a volume difference between the first model and the second model is determined and the volume difference is determined as the region volume.
For example, in this embodiment, the server establishes a virtual blank model, establishes a virtual clone model having the same size and shape as the virtual blank model, aligns the model center point of the virtual blank model with the defect center point, and generates virtual points corresponding to the scan repair points in the virtual blank model. The server updates the virtual blank model based on the virtual point positions according to the repair depths corresponding to the scanning repair points, namely, the repair depths of the updated virtual point positions are the repair depths corresponding to the scanning repair points, and a virtual defect model comprising a virtual defect area is obtained.
The server may change the virtual flaw model and the virtual clone model into a model with the same regular shape, for example, uniformly change the virtual flaw model and the virtual clone model into a rectangle, the virtual flaw model is changed into a first model, and the virtual clone model is changed into a second model. Thus, the volume difference between the first model and the second model can be more intuitively calculated, and the volume difference is determined as the area volume of the flaw area.
In step S108, the following are included:
And controlling the machine end to fill the repairing material into the defect area in the stone to be repaired under the condition that the material volume of the repairing material carried by the machine end is not smaller than the area volume, so as to obtain the repaired stone.
For example, in this embodiment, it may be understood that the machine end has a function of carrying repairing material, when the material volume of the repairing material carried by the machine end is not smaller than the area volume of the defect area, that is, the repairing material carried by the machine end can completely repair the current defect area, at this time, the server may control the machine end to repair the defect area in the stone to be repaired, that is, control the machine end to fill the repairing material into the defect area in the stone to be repaired, and the stone obtained after the filling is the repaired stone.
In step S110, the following are included:
and responding to the repair completion signal sent by the machine end, and controlling the machine end to perform multidimensional repair condition inspection on the repaired stone.
For example, in this embodiment, after the machine end completes repairing the defective area, a repair completion signal is sent. After the server receives the repairing completion signal, the machine end is controlled to perform multidimensional repairing condition inspection on the repaired stone, and the repairing effect of the machine end on the stone can be guaranteed.
Further, the above-mentioned "control the machine end to perform multi-dimensional repair condition inspection on the repaired stone", further includes the following steps:
Controlling the machine end to acquire an acquired image of the repaired stone, and determining a repair contour corresponding to the flaw contour in the acquired image based on a comparison result of the acquired image and the scanning image;
Acquiring region pixel points of a repair region in the repair contour, and determining a region pixel value corresponding to the region pixel points as a first inspection item;
Determining scanning check points which are positioned in the repair area and correspond to the scanning repair points respectively, controlling the machine end to scan the scanning check points, acquiring the inspection depths corresponding to the scanning check points respectively, and determining the inspection depths as second inspection items;
And performing qualification inspection based on the first inspection item and the second inspection item respectively, and filling inspection results into a pre-established inspection list.
For example, in the embodiment, the server controls the machine end to perform multi-dimensional repair condition inspection on the repaired stone from two aspects of repair color and repair depth. Firstly, the server performs image acquisition work on the repaired stone again by controlling the machine end to obtain an acquired image of the repaired stone. And comparing the acquired image with the scanning image before stone restoration, and determining a restoration contour in the acquired image according to a comparison result, wherein the restoration contour corresponds to the flaw contour.
At the moment, the server acquires the regional pixel points of the repair region in the repair contour, and determines the regional pixel values corresponding to the regional pixel points as a first inspection item, wherein the first inspection item is a dimension of the machine end from the repair color to inspect the repair condition of the repaired stone; the server determines scanning check points corresponding to the scanning repair points in the repair area, so that the machine end is controlled to scan the scanning check points again, the depth of each scanning check point is obtained, namely the inspection depth, the inspection depth is determined as a second inspection item, and the second inspection item is the dimension of the machine end from the repair depth to inspect the repaired stone. The server performs qualification inspection on the stone repairing effect based on the first inspection item and the second inspection item, and fills the inspection result into a pre-established inspection list.
Further, the "qualification inspection based on the first inspection item" further includes the following steps:
generating a comparison contour surrounding the restoration contour by extending a preset distance outwards along the restoration contour in the acquired image, and determining a region between the comparison contour and the restoration contour as a comparison region;
Determining the horizontal comparison length and the vertical comparison length of the comparison area in the horizontal direction and the vertical direction respectively, and determining the direction corresponding to the highest length of the horizontal comparison length and the vertical comparison length as the dividing direction;
performing equidistant region division on the comparison region based on the division direction to obtain each comparison sub-region;
respectively acquiring any sub-region pixel point in each contrast sub-region, and determining each sub-region pixel point as each contrast pixel point;
Respectively carrying out difference calculation on the regional pixel values and the contrast pixel values of each contrast pixel point to obtain each first absolute difference value, and calling a first preset difference value interval;
If all the first absolute difference values are located in the first preset difference value interval, determining that the inspection result of the first inspection item is qualified;
And if at least one of the first absolute differences is not located in the first preset difference interval, determining that the inspection result of the first inspection item is unqualified.
For example, in this embodiment, the server first generates a comparison contour around the repair contour by extending a preset distance outward along the repair contour in the acquired image, where the preset distance is 1cm, and then generates a contour around the repair contour by extending a distance of 1cm outward along the repair contour, where the contour is the comparison contour, and the area between the comparison contour and the repair contour is the comparison area.
The server can determine the horizontal comparison length in the horizontal direction and the vertical comparison length in the vertical direction of the comparison area, compare the horizontal comparison length with the vertical comparison length, select the longest comparison length, determine the corresponding direction as the dividing direction, and then divide the comparison area into areas with equal intervals according to the dividing direction, wherein the areas obtained after division are all the comparison subareas. At this time, the server can acquire the pixel point of any one of the contrast subareas, and determine the pixel point of each subarea as each contrast pixel point.
And then, carrying out difference calculation on the regional pixel values and the contrast pixel values of each contrast pixel point respectively, wherein the absolute value of a difference calculation result is a first absolute difference value, so that each first absolute difference value is obtained, and a first preset difference value interval is called, wherein the first preset difference value interval can be freely set by a management end, for example, the first preset difference value interval is [ 0-30 ]. If the first absolute difference values are all located in the first preset difference value interval, the difference between the pixel values of the indicated area and the pixel values of the comparison is not large, and then the inspection result of the first inspection item can be determined to be qualified; if one or more of the first absolute differences are not located in the first preset difference interval, the difference between the pixel value of the area and the pixel value of the contrast is excessively large, and then the checking result of the first checking item can be determined to be unqualified.
In this embodiment, the server obtains the stone color outside the repair area and compares the stone color inside the repair area, and checks the repair condition from the dimension of the repair color according to the comparison result. And a first preset difference interval is set, so that the accuracy of the inspection result can be improved to a great extent.
Further, the "qualification inspection based on the second inspection item" further includes the following steps:
generating a comparison contour surrounding the restoration contour by extending a preset distance outwards along the restoration contour in the acquired image, and determining a region between the comparison contour and the restoration contour as a comparison region;
Determining the horizontal comparison length and the vertical comparison length of the comparison area in the horizontal direction and the vertical direction respectively, and determining the direction corresponding to the highest length of the horizontal comparison length and the vertical comparison length as the dividing direction;
performing equidistant region division on the comparison region based on the division direction to obtain each comparison sub-region;
Respectively acquiring any sub-region pixel point in each contrast sub-region, and determining each sub-region pixel point as each scanning contrast point;
Controlling the machine end to scan each scanning comparison point, obtaining each comparison depth corresponding to each scanning comparison point, and carrying out mean value calculation based on each comparison depth to obtain a depth mean value;
respectively carrying out difference calculation on each inspection depth and the depth mean value to obtain each second absolute difference value, and calling a second preset difference value interval;
If the second absolute differences are all located in the second preset difference interval, determining that the inspection result of the second inspection item is qualified;
And if at least one of the second absolute differences is not located in the second preset difference interval, determining that the inspection result of the second inspection item is unqualified.
For example, in this embodiment, the server first generates a comparison contour around the repair contour by extending a preset distance outward along the repair contour in the acquired image, where the preset distance is 1cm, and then generates a contour around the repair contour by extending a distance of 1cm outward along the repair contour, where the contour is the comparison contour, and the area between the comparison contour and the repair contour is the comparison area.
The server can determine the horizontal comparison length in the horizontal direction and the vertical comparison length in the vertical direction of the comparison area, compare the horizontal comparison length with the vertical comparison length, select the longest comparison length, determine the corresponding direction as the dividing direction, and then divide the comparison area into areas with equal intervals according to the dividing direction, wherein the areas obtained after division are all the comparison subareas. At this time, the server can acquire the pixel point of any one of the contrast subareas, and determine the pixel point of each subarea as each scanning contrast point.
The server controls the machine end to scan each scanning comparison point, the depth of each scanning comparison point can be scanned, namely, each comparison depth corresponding to each scanning comparison point is obtained, average value calculation is carried out on all comparison depths to obtain a depth average value, difference value calculation is carried out on each inspection depth and the depth average value respectively, the absolute value of the difference value calculation result is a second absolute difference value, each second absolute difference value is obtained, a second preset difference value interval is called, the second preset difference value interval can be freely set by the management end, for example, the second preset difference value interval is [0 mm-2 mm ]. If the second absolute difference value is in a second preset difference value interval, the fact that the difference between the inspection depth and the depth average value is not large is indicated, and at the moment, the inspection result of the second inspection item can be determined to be qualified; if one or more second absolute differences in the second absolute differences are not in the second preset difference interval, the difference between the inspection depth and the depth average value is excessively large, and then the inspection result of the second inspection item can be determined to be unqualified. In this embodiment, the server can check the repair situation from the dimension of the repair depth according to the difference result. And a second preset difference interval is set, so that the objectivity of the inspection result can be ensured to a great extent.
For example, fig. 3 to 5 are schematic views of corresponding progress of repairing stone materials in a corresponding practical application scenario, and fig. 3 is stone materials in an unrepaired state, so that a defect area in the stone materials can be clearly seen; FIG. 4 shows a stone in the process of being repaired, it being clear that the defective areas in the stone have been correspondingly filled; fig. 5 shows the stone in the repaired state, and it can be clearly seen that the defective area in the stone has been completely repaired.
According to the scheme of the invention, the server can control the machine end to scan each stone in the site to be repaired, and the stone is determined to be the stone to be repaired in response to the scanning result of the machine end on any stone as the determined flaw, and the scanning image of the stone to be repaired is obtained. And performing image recognition on the scanned image, determining the flaw outline in the scanned image, determining each scanning repair point positioned in the flaw outline, thereby obtaining each repair depth respectively corresponding to each scanning repair point, and determining the area volume of the flaw area positioned in the flaw outline according to each repair depth. Under the condition that the material volume of the repairing material carried by the machine end is not smaller than the area volume, the server controls the machine end to fill the repairing material into the defect area in the stone to be repaired, and the repaired stone is obtained. After the machine end sends the repair completion signal, the server controls the machine end to carry out multidimensional repair condition inspection on the repaired stone. The invention can rapidly determine the flaw area and area volume of the stone to be repaired, repair the stone, and check the multi-dimensional repair condition after repair, thereby improving the repair efficiency of the stone and ensuring the repair effect to a great extent.
Another embodiment of the present invention provides a stone repair scanning system, fig. 6 is a block diagram of a corresponding system, and the system includes:
The determining module is configured to control the machine end to scan each stone in the site to be repaired, determine the stone as the stone to be repaired in response to the scanning result of the machine end on any stone as a determined flaw, and acquire a scanning image of the stone to be repaired;
the identification module is configured to carry out image identification on the scanned image, determine a flaw outline in the scanned image and determine each scanning repair point positioned in the flaw outline;
the volume acquisition module is configured to acquire each repair depth corresponding to each scanning repair point and determine the area volume of the flaw area in the flaw outline according to each repair depth;
the repairing module is configured to control the machine end to fill the repairing material into the defect area in the stone to be repaired to obtain repaired stone comprising the repairing area under the condition that the material volume of the repairing material carried by the machine end is not smaller than the area volume;
The inspection module is configured to respond to the repair completion signal sent by the machine end and control the machine end to conduct multi-dimensional repair condition inspection on the repair area in the repaired stone.
In the description provided herein, algorithms and displays are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with examples of the invention. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It should be appreciated that the teachings of the present invention as described herein may be implemented in a variety of programming languages and that the foregoing description of specific languages is provided for disclosure of preferred embodiments of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in a device as described in this embodiment, or alternatively may be located in one or more devices different from the devices in this example. The modules in the foregoing examples may be combined into one module or may be further divided into a plurality of sub-modules.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Furthermore, some of the embodiments are described herein as methods or combinations of method elements that may be implemented by a processor of a computer system or by other means of performing the functions. Thus, a processor with the necessary instructions for implementing the described method or method element forms a means for implementing the method or method element. Furthermore, the elements of the apparatus embodiments described herein are examples of the following apparatus: the apparatus is for carrying out the functions performed by the elements for carrying out the objects of the invention.
As used herein, unless otherwise specified the use of the ordinal terms "first," "second," "third," etc., to describe a general object merely denote different instances of like objects, and are not intended to imply that the objects so described must have a given order, either temporally, spatially, in ranking, or in any other manner.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of the above description, will appreciate that other embodiments are contemplated within the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is intended to be illustrative, but not limiting, of the scope of the invention, which is defined by the appended claims.

Claims (7)

1. The stone repairing and scanning method is characterized by comprising the following steps of:
Controlling a machine end to scan each stone in a site to be repaired, determining the stone as the stone to be repaired in response to the scanning result of the machine end on any stone as a determined flaw, and acquiring a scanning image of the stone to be repaired;
performing image recognition on the scanned image, determining a flaw outline in the scanned image, and determining each scanning repair point positioned in the flaw outline;
Acquiring each repair depth corresponding to each scanning repair point, and determining the area volume of the defect area in the defect outline according to each repair depth;
controlling the machine end to fill the repairing material into a defect area in the stone to be repaired under the condition that the material volume of the repairing material carried by the machine end is not smaller than the area volume, so as to obtain the repaired stone;
Responding to a repair completion signal sent by the machine end, and controlling the machine end to perform multidimensional repair condition inspection on the repaired stone;
The method for identifying the scanning image, determining the flaw outline in the scanning image and determining each scanning repair point in the flaw outline comprises the following steps:
Inputting the scanning image into a pre-trained contour recognition model, and determining the flaw contour in the scanning image;
Determining a flaw center point located in the flaw profile, and establishing a flaw coordinate system based on the flaw center point;
Based on the flaw coordinate system, acquiring a flaw coordinate set formed by flaw coordinate points in the flaw outline, and determining an abscissa maximum absolute value and an ordinate maximum absolute value in the flaw coordinate set;
determining a first interval and a second interval based on the abscissa maximum absolute value and the ordinate maximum absolute value respectively;
generating first dividing lines with first intervals and second dividing lines with second intervals respectively on the basis of two sides of a Y axis and two sides of an X axis of the flaw coordinate system;
Acquiring the coordinates of each point corresponding to each intersection point between the first dividing lines and the second dividing lines, and determining each intersection point corresponding to each point coordinate in the flaw coordinate set as each scanning repair point;
wherein determining the area volume of the flaw area in the flaw profile according to each repair depth comprises:
establishing a virtual blank model and a virtual clone model which is the same as the virtual blank model;
Determining a corresponding relation between a model center point of the virtual blank model and the flaw center point, and respectively generating virtual point positions corresponding to the scanning repair points in the virtual blank model based on the corresponding relation;
according to the repair depths corresponding to the scanning repair points, performing model updating based on the virtual point positions on the virtual blank model to obtain a virtual defect model comprising a virtual defect area;
respectively carrying out model change based on the same regular shape on the virtual flaw model and the virtual clone model to obtain a first model and a second model;
determining a volume difference between the first model and the second model, and determining the volume difference as the region volume;
Wherein, control the machine end to carry out multidimensional restoration condition inspection to the stone material that has been repaired, include:
Controlling the machine end to acquire an acquired image of the repaired stone, and determining a repair contour corresponding to the flaw contour in the acquired image based on a comparison result of the acquired image and the scanning image;
Acquiring region pixel points of a repair region in the repair contour, and determining a region pixel value corresponding to the region pixel points as a first inspection item;
Determining scanning check points which are positioned in the repair area and correspond to the scanning repair points respectively, controlling the machine end to scan the scanning check points, acquiring the inspection depths corresponding to the scanning check points respectively, and determining the inspection depths as second inspection items;
And performing qualification inspection based on the first inspection item and the second inspection item respectively, and filling inspection results into a pre-established inspection list.
2. The stone repair scanning method according to claim 1, wherein,
Determining a first interval and a second interval based on the abscissa maximum absolute value and the ordinate maximum absolute value, respectively, includes:
A pre-established number dividing table is called, wherein the number dividing table comprises different numerical intervals and dividing intervals respectively corresponding to the different numerical intervals;
traversing the quantity dividing table, respectively determining a first numerical value interval and a second numerical value interval which comprise the maximum absolute value of the abscissa and the maximum absolute value of the ordinate, and respectively determining a first interval and a second interval which correspond to the first numerical value interval and the second numerical value interval.
3. The stone repair scanning method according to claim 1, wherein,
Generating each first dividing line with a first interval and each second dividing line with a second interval based on two sides of a Y axis and two sides of an X axis of the flaw coordinate system respectively, wherein the method comprises the following steps:
Establishing a transparent dividing image layer corresponding to the image size of the scanned image based on the scanned image;
generating first dividing lines with first intervals and second dividing lines with second intervals on the basis of two sides of a Y axis and two sides of an X axis of the flaw coordinate system in the transparent dividing layer respectively;
Responding to a modification request of a management end, and sending a scanning image with the transparent division layer to the management end for display;
And responding to interaction of the management end on any dividing line in the transparent dividing layer, and moving and adjusting the dividing line along the direction perpendicular to the extending direction of the dividing line.
4. The stone repair scanning method according to claim 1, wherein,
Acquiring coordinates of each point corresponding to each intersection point between the first dividing line and the second dividing line, and determining each intersection point corresponding to each point coordinate in the flaw coordinate set as each scanning repair point, including:
Acquiring coordinates of each point corresponding to each intersection point between each first dividing line and each second dividing line;
summarizing each intersection point corresponding to each point coordinate in the flaw coordinate set to obtain an in-region combination;
Summarizing each intersection point corresponding to each point coordinate outside the flaw coordinate set to obtain an out-of-area combination;
Determining each intersection point close to the flaw outline in the out-of-area combination as each edge intersection point, and respectively obtaining the horizontal distance and the vertical distance between each edge intersection point and the flaw outline;
When the horizontal distance of any edge intersection point is smaller than a first interval under a preset multiple, generating a first newly added intersection point parallel to the edge intersection point on the flaw profile;
When the vertical distance of any edge intersection point is smaller than a second interval under a preset multiple, generating a second newly-added intersection point vertical to the edge intersection point on the flaw profile;
And summarizing the first newly added intersection point and the second newly added intersection point into the region for combination, and determining each intersection point positioned in the region for combination as each scanning repair point.
5. The stone repair scanning method according to claim 1, wherein,
Performing a qualification check based on the first check item, including:
generating a comparison contour surrounding the restoration contour by extending a preset distance outwards along the restoration contour in the acquired image, and determining a region between the comparison contour and the restoration contour as a comparison region;
Determining the horizontal comparison length and the vertical comparison length of the comparison area in the horizontal direction and the vertical direction respectively, and determining the direction corresponding to the highest length of the horizontal comparison length and the vertical comparison length as the dividing direction;
performing equidistant region division on the comparison region based on the division direction to obtain each comparison sub-region;
respectively acquiring any sub-region pixel point in each contrast sub-region, and determining each sub-region pixel point as each contrast pixel point;
Respectively carrying out difference calculation on the regional pixel values and the contrast pixel values of each contrast pixel point to obtain each first absolute difference value, and calling a first preset difference value interval;
If all the first absolute difference values are located in the first preset difference value interval, determining that the inspection result of the first inspection item is qualified;
And if at least one of the first absolute differences is not located in the first preset difference interval, determining that the inspection result of the first inspection item is unqualified.
6. The stone repair scanning method according to claim 1, wherein,
Performing a qualification check based on the second check item, including:
generating a comparison contour surrounding the restoration contour by extending a preset distance outwards along the restoration contour in the acquired image, and determining a region between the comparison contour and the restoration contour as a comparison region;
Determining the horizontal comparison length and the vertical comparison length of the comparison area in the horizontal direction and the vertical direction respectively, and determining the direction corresponding to the highest length of the horizontal comparison length and the vertical comparison length as the dividing direction;
performing equidistant region division on the comparison region based on the division direction to obtain each comparison sub-region;
Respectively acquiring any sub-region pixel point in each contrast sub-region, and determining each sub-region pixel point as each scanning contrast point;
Controlling the machine end to scan each scanning comparison point, obtaining each comparison depth corresponding to each scanning comparison point, and carrying out mean value calculation based on each comparison depth to obtain a depth mean value;
respectively carrying out difference calculation on each inspection depth and the depth mean value to obtain each second absolute difference value, and calling a second preset difference value interval;
If the second absolute differences are all located in the second preset difference interval, determining that the inspection result of the second inspection item is qualified;
And if at least one of the second absolute differences is not located in the second preset difference interval, determining that the inspection result of the second inspection item is unqualified.
7. A stone repair scanning system, comprising:
The determining module is configured to control the machine end to scan each stone in the site to be repaired, determine the stone as the stone to be repaired in response to the scanning result of the machine end on any stone as a determined flaw, and acquire a scanning image of the stone to be repaired;
the identification module is configured to carry out image identification on the scanned image, determine a flaw outline in the scanned image and determine each scanning repair point positioned in the flaw outline;
the volume acquisition module is configured to acquire each repair depth corresponding to each scanning repair point and determine the area volume of the flaw area in the flaw outline according to each repair depth;
the repairing module is configured to control the machine end to fill the repairing material into the defect area in the stone to be repaired to obtain repaired stone comprising the repairing area under the condition that the material volume of the repairing material carried by the machine end is not smaller than the area volume;
The inspection module is configured to respond to the repair completion signal sent by the machine end and control the machine end to perform multi-dimensional repair condition inspection on the repair area in the repaired stone;
The method for identifying the scanning image, determining the flaw outline in the scanning image and determining each scanning repair point in the flaw outline comprises the following steps:
Inputting the scanning image into a pre-trained contour recognition model, and determining the flaw contour in the scanning image;
Determining a flaw center point located in the flaw profile, and establishing a flaw coordinate system based on the flaw center point;
Based on the flaw coordinate system, acquiring a flaw coordinate set formed by flaw coordinate points in the flaw outline, and determining an abscissa maximum absolute value and an ordinate maximum absolute value in the flaw coordinate set;
determining a first interval and a second interval based on the abscissa maximum absolute value and the ordinate maximum absolute value respectively;
generating first dividing lines with first intervals and second dividing lines with second intervals respectively on the basis of two sides of a Y axis and two sides of an X axis of the flaw coordinate system;
Acquiring the coordinates of each point corresponding to each intersection point between the first dividing lines and the second dividing lines, and determining each intersection point corresponding to each point coordinate in the flaw coordinate set as each scanning repair point;
wherein determining the area volume of the flaw area in the flaw profile according to each repair depth comprises:
establishing a virtual blank model and a virtual clone model which is the same as the virtual blank model;
Determining a corresponding relation between a model center point of the virtual blank model and the flaw center point, and respectively generating virtual point positions corresponding to the scanning repair points in the virtual blank model based on the corresponding relation;
according to the repair depths corresponding to the scanning repair points, performing model updating based on the virtual point positions on the virtual blank model to obtain a virtual defect model comprising a virtual defect area;
respectively carrying out model change based on the same regular shape on the virtual flaw model and the virtual clone model to obtain a first model and a second model;
determining a volume difference between the first model and the second model, and determining the volume difference as the region volume;
Wherein, control the machine end to carry out multidimensional restoration condition inspection to the stone material that has been repaired, include:
Controlling the machine end to acquire an acquired image of the repaired stone, and determining a repair contour corresponding to the flaw contour in the acquired image based on a comparison result of the acquired image and the scanning image;
Acquiring region pixel points of a repair region in the repair contour, and determining a region pixel value corresponding to the region pixel points as a first inspection item;
Determining scanning check points which are positioned in the repair area and correspond to the scanning repair points respectively, controlling the machine end to scan the scanning check points, acquiring the inspection depths corresponding to the scanning check points respectively, and determining the inspection depths as second inspection items;
And performing qualification inspection based on the first inspection item and the second inspection item respectively, and filling inspection results into a pre-established inspection list.
CN202410502565.3A 2024-04-25 2024-04-25 Stone repairing and scanning method and system Active CN118096602B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410502565.3A CN118096602B (en) 2024-04-25 2024-04-25 Stone repairing and scanning method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410502565.3A CN118096602B (en) 2024-04-25 2024-04-25 Stone repairing and scanning method and system

Publications (2)

Publication Number Publication Date
CN118096602A CN118096602A (en) 2024-05-28
CN118096602B true CN118096602B (en) 2024-06-21

Family

ID=91160114

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410502565.3A Active CN118096602B (en) 2024-04-25 2024-04-25 Stone repairing and scanning method and system

Country Status (1)

Country Link
CN (1) CN118096602B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102892021A (en) * 2012-10-15 2013-01-23 浙江大学 New method for synthesizing virtual viewpoint image
CN110596134A (en) * 2018-05-25 2019-12-20 上海翌视信息技术有限公司 Sheet glass edge flaw detection method based on image acquisition

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102008048383A1 (en) * 2008-09-22 2010-03-25 Baumer Inspection Gmbh Automatic patching of wood panels with aesthetic reconstruction
CN113414819B (en) * 2021-08-24 2021-11-26 航天云网数据研究院(广东)有限公司 Substrate material processing method and system, electronic device and storage medium
CN117523307B (en) * 2023-11-24 2024-04-19 佛山众陶联供应链服务有限公司 Tile sorting method and system based on opc and tile surface flaw identification model

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102892021A (en) * 2012-10-15 2013-01-23 浙江大学 New method for synthesizing virtual viewpoint image
CN110596134A (en) * 2018-05-25 2019-12-20 上海翌视信息技术有限公司 Sheet glass edge flaw detection method based on image acquisition

Also Published As

Publication number Publication date
CN118096602A (en) 2024-05-28

Similar Documents

Publication Publication Date Title
CN110383038B (en) System and method for automated analysis of air samples
KR101782542B1 (en) System and method for inspecting painted surface of automobile
JP6029870B2 (en) Method and apparatus for detecting deformation of concrete surface
EP3007022B1 (en) System and method for inspecting a composite part during manufacture
JP5894012B2 (en) Method for detecting linear deformation on concrete surface
CN113658325B (en) Intelligent identification and early warning method for uncertain objects of production line in digital twin environment
US20040073411A1 (en) System, method and computer program product for maintaining a structure
Lin et al. Applications of computer vision on tile alignment inspection
CN113362276B (en) Visual detection method and system for plates
CN103245671A (en) Surface defect detection device and method for stamping piece
WO2020079694A1 (en) Optimizing defect detection in an automatic visual inspection process
US10788434B2 (en) Method for inspecting an object optically
CN118096602B (en) Stone repairing and scanning method and system
CN117437220A (en) Building engineering quality detection method and system based on big data
CN108760755A (en) A kind of dust granule detection method and device
US12018442B2 (en) Ground information detection method, ground information detection system, ground information detection program, and profile
JP2023171889A (en) Altitude difference detection method, altitude difference detection system, and altitude difference detection program
CN115494659A (en) Liquid crystal panel detection method and system
Paterson et al. Building inspection: can computer vision help?
CN118351099A (en) Automatic repair and positioning method and system for flaw stone
CN115790400B (en) Machine vision target calibration method applied to bridge-tunnel structure safety
KR20230130890A (en) Device and method of controlling vehicle body inspection
CN109612400A (en) A kind of the material deformation degree dynamic measurement method and system of view-based access control model tracking
CN118357788A (en) Automatic marble polishing and repairing method and system
CN116740470A (en) Sorting system and method based on image recognition

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