CN116342539A - Quick construction method, device and medium for machine vision environment - Google Patents

Quick construction method, device and medium for machine vision environment Download PDF

Info

Publication number
CN116342539A
CN116342539A CN202310315419.5A CN202310315419A CN116342539A CN 116342539 A CN116342539 A CN 116342539A CN 202310315419 A CN202310315419 A CN 202310315419A CN 116342539 A CN116342539 A CN 116342539A
Authority
CN
China
Prior art keywords
suspicious
preset
determining
cloud data
point cloud
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
CN202310315419.5A
Other languages
Chinese (zh)
Other versions
CN116342539B (en
Inventor
袁强
吴雍
陈胜进
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.)
Shenzhen Comstar Technology Co ltd
Original Assignee
Shenzhen Comstar Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Comstar Technology Co ltd filed Critical Shenzhen Comstar Technology Co ltd
Priority to CN202310315419.5A priority Critical patent/CN116342539B/en
Publication of CN116342539A publication Critical patent/CN116342539A/en
Application granted granted Critical
Publication of CN116342539B publication Critical patent/CN116342539B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
    • Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The method comprises the steps of obtaining point cloud data of the surface of a material when the occurrence of the material at a preset position on a production line is detected, wherein the preset position is located in the upstream direction of a camera device, comparing the point cloud data with preset point cloud data of standard materials, judging whether a suspicious region exists on the material, determining the position information of the suspicious region if the suspicious region exists, determining a target light source based on the position information, and controlling the target light source to be lightened when the material is detected to move below the camera device. According to the method and the device, a proper shooting environment can be built according to the condition of the surface of the material.

Description

Quick construction method, device and medium for machine vision environment
Technical Field
The present disclosure relates to the field of machine vision, and in particular, to a method, an apparatus, and a medium for quickly constructing a machine vision environment.
Background
Machine vision is widely used in the field of industrial pipelines to detect whether materials on the pipeline are acceptable. When the material moves to the position below the camera device, the camera device shoots the material to judge whether the material is damaged or qualified or not, and the like. However, when the surface of the material is damaged, the shooting environment below the image capturing device may not illuminate the damaged area well, that is, the shooting environment fixed below the image capturing device may not be well adapted to the damaged material, which may further reduce the detection effect. Therefore, how to build a proper shooting environment according to the condition of the material surface becomes a problem.
Disclosure of Invention
In order to realize the establishment of a proper shooting environment according to the condition of the surface of a material, the application provides a quick construction method, a quick construction device and a quick construction medium for a machine vision environment.
In a first aspect, the present application provides a method for quickly constructing a machine vision environment, which adopts the following technical scheme:
a quick construction method of a machine vision environment comprises the following steps:
when detecting that a material appears at a preset position on a production line, acquiring point cloud data of the surface of the material, wherein the preset position is positioned in the upstream direction of a camera device;
comparing the point cloud data with preset point cloud data of standard materials, and judging whether suspicious areas exist on the materials, wherein the suspicious areas are areas which are possibly damaged;
if the suspicious region exists, determining the position information of the suspicious region, wherein the position information is the position information of the suspicious region on a plane perpendicular to the travelling direction of the assembly line;
and determining a target light source based on the position information, and controlling the target light source to be lightened when the material is detected to move below the image pickup device.
Through adopting above-mentioned technical scheme, the assembly line is used for transporting the material, when detecting the material and remove the preset position of camera device upper reaches, obtain the point cloud data on material surface, thereby can learn the condition on material surface through the point cloud data, after obtaining material surface point cloud data, because standard material is the benchmark of contrast, compare the point cloud data of material with the preset point cloud data of standard material, thereby can judge whether the material exists the suspicious region that probably takes place the damage, if there is suspicious region, then confirm the positional information in suspicious region, positional information is the positional information on the plane of perpendicular to assembly line advancing direction, after confirming the positional information in suspicious region, can confirm the target light source that can illuminate suspicious region according to positional information, when detecting the material and remove the camera device below, thereby make suspicious region clear, can be to the characteristics of material itself be fast set up and take the appropriate light source environment of material, camera device can obtain more suspicious region's detail when taking the material image, detection effect has been improved.
In another possible implementation manner, the point cloud data includes three-dimensional coordinates of a plurality of points of the material, the preset point cloud data includes preset three-dimensional coordinates of a plurality of points of a standard material, the comparing the point cloud data with the preset point cloud data of the material, and determining whether a suspicious region exists on the material includes:
determining a contour of the material in a top view direction based on the point cloud data;
performing rotary adjustment on the profile and overlapping the preset profile corresponding to preset point cloud data, wherein the preset profile is the profile of the standard material in the overlooking direction;
comparing the three-dimensional coordinates with the preset three-dimensional coordinates, and judging whether at least two suspicious points with inconsistent three-dimensional coordinates and preset three-dimensional coordinates exist in the point cloud data or not;
if the at least two suspicious points exist, determining all continuous and adjacent suspicious points from the at least two suspicious points, and forming a pending area;
if the number of the suspicious points is greater than the preset number of the pending areas, determining that the suspicious areas exist, and determining the pending areas with the number of the suspicious points greater than the preset number as the suspicious areas;
And if the number of suspicious points is greater than the preset number of the pending areas, determining that the suspicious areas are not present.
By adopting the technical scheme, because the gesture positions of the materials on the assembly line are different, the outline in the overlooking direction of the materials is determined according to the point cloud data of the materials, the outline is rotationally adjusted after the outline is determined, so that the outline is consistent with the gesture position of the outline in the overlooking direction preset by the standard materials and is overlapped, the three-dimensional coordinates are more accurate when compared with the preset three-dimensional coordinates, the suspicious points with inconsistent three-dimensional coordinates are obtained after the comparison, the single suspicious points have higher possibility of errors, the single suspicious points are not considered, the continuous and adjacent suspicious points represent the possibility of breakage of the materials, the continuous and adjacent suspicious point forming area is used as a suspicious area, if the number of the suspicious points in the suspicious area is larger than the preset number, the suspicious area is abnormal, and if the number of the suspicious points is not larger than the preset number of the suspicious area, the suspicious area is less, namely, the probability of breakage of the surface of the materials is indicated, and the suspicious area is not exist, and the continuous and adjacent suspicious points are judged more accurately and comprehensively.
In another possible implementation manner, the determining the location information of the suspicious region includes:
determining center point coordinates of the suspicious region based on three-dimensional coordinates of suspicious points in the suspicious region;
filtering coordinate values consistent with the advancing direction of the assembly line in the coordinates of the central point to obtain two-dimensional coordinates of the central point;
and mapping the two-dimensional coordinates to a preset coordinate system to obtain the position information of the suspicious region, wherein the preset coordinate system is a coordinate system established on a plane perpendicular to the travelling direction of the assembly line.
By adopting the technical scheme, after the suspicious region is determined, the average value of the three-dimensional coordinates of all suspicious points in the suspicious region is calculated, so that the center point coordinate of the suspicious region can be obtained, the center position of the material is represented by the center point coordinate to be accurate, when the material moves below the image pickup device, the center point of the suspicious region of the material and the image pickup device are positioned on the same plane, therefore, the two-dimensional coordinate of the center point can be obtained by filtering the coordinate value consistent with the advancing direction of the assembly line in the center point coordinate, the position information of the suspicious region can be obtained by mapping the two-dimensional coordinate in a preset coordinate system, namely, the position information of the center point of the suspicious region when the image pickup device shoots the material is obtained, and the position information obtained based on the center point coordinate is also accurate because the position of representing the suspicious region by using the center point coordinate is accurate.
In another possible implementation, controlling the target light source to illuminate includes:
determining the depth of the suspicious region based on the three-dimensional coordinates of suspicious points in the suspicious region;
determining a brightness of the target light source based on the depth;
and controlling the target light source to be lightened according to the brightness.
By adopting the technical scheme, the depth of the suspicious region can be determined according to the three-dimensional coordinates of the suspicious points in the suspicious region, the deeper the depth of the suspicious region is, the less easy observation is possible for the situation of the suspicious region, and therefore, the suspicious region is illuminated by light with higher brightness, the detail situation in the suspicious region is obtained more clearly, the brightness of the target light source is determined according to the depth, and the target light source is controlled to be lightened according to the determined brightness, so that the imaging device can shoot the clearer detail situation when detecting materials.
In another possible implementation, the determining the brightness of the target light source based on the depth includes:
determining a preset depth interval in which the depth is located, wherein the preset depth interval corresponds to preset brightness;
and determining the preset brightness corresponding to the preset product interval in which the depth is positioned as the brightness of the target light source.
By adopting the technical scheme, each preset depth interval corresponds to the optimal illumination brightness, namely the preset brightness, and the preset brightness corresponding to the preset depth interval is determined to be the brightness of the target light source more accurately by determining the preset depth interval in which the depth is located.
In another possible implementation, the method further includes:
and controlling the auxiliary image pickup device to rotate based on the position information so that the auxiliary image pickup device faces the suspicious region when the material is detected to move below the image pickup device, and controlling the auxiliary image pickup device to shoot a close-up image of the suspicious region.
Through adopting above-mentioned technical scheme, supplementary camera device is used for shooing the close-up image in the suspicious region of material, and the position information control camera device according to suspicious region rotates to supplementary camera device can shoot the close-up image in suspicious region when making the material remove the camera device below, and then can further know the detail in more suspicious regions.
In another possible implementation, the method further includes:
when the material is detected to move below the image pickup device, controlling the image pickup device to pick up a material image of the material, and controlling the auxiliary image pickup device to pick up a close-up image of the suspicious region;
Determining the corresponding relation between the close-up image and the material image;
and storing the close-up image, the material image and the corresponding relation.
Through adopting above-mentioned technical scheme, confirm the correspondence of material image and close-up image to confirm the material that suspicious region belonged to, store material image, close-up image and correspondence, later stage staff can know the specific circumstances in the general view and suspicious region of material, and then be convenient for the staff to analyze the material better.
In a second aspect, the present application provides a machine vision environment rapid construction apparatus, which adopts the following technical scheme:
a machine vision environment rapid construction apparatus comprising:
the data acquisition module is used for acquiring point cloud data of the surface of the material when the material is detected to appear at a preset position on the assembly line, wherein the preset position is positioned in the upstream direction of the camera device;
the comparison module is used for comparing the point cloud data with preset point cloud data of standard materials and judging whether suspicious areas exist on the materials or not, wherein the suspicious areas are areas which are possibly damaged;
the position determining module is used for determining the position information of the suspicious region when the suspicious region exists, wherein the position information is the position information of the suspicious region on a plane perpendicular to the travelling direction of the pipeline;
And the light source control module is used for determining a target light source based on the position information and controlling the target light source to be lightened when the material is detected to move below the image pickup device.
Through adopting above-mentioned technical scheme, the assembly line is used for transporting the material, when detecting the material and remove the preset position of camera device upper reaches, data acquisition module acquires the point cloud data on material surface, thereby can learn the condition on material surface through the point cloud data, after obtaining material surface point cloud data, because standard material is the benchmark of comparison, contrast module is with the point cloud data of material and the preset point cloud data of standard material, thereby can judge whether there is the suspicious region that probably takes place the damage in the material, if there is suspicious region, then position determination module confirms the positional information in suspicious region, this positional information is the positional information on the plane of perpendicular to assembly line advancing direction, after determining the positional information in suspicious region, the light source control module can confirm the target light source that can lighten suspicious region according to positional information, when detecting the material and remove the camera device below, thereby make suspicious region more clear, can be to the characteristics of material itself and set up the device and shoot the suitable light source environment of material fast, camera device can obtain more suspicious regions when shooting the material image, detection detail effect has been improved.
In another possible implementation manner, the point cloud data includes three-dimensional coordinates of a plurality of points of the material, the preset point cloud data includes preset three-dimensional coordinates of a plurality of points of a standard material, and the comparison module is specifically configured to, when comparing the point cloud data with the preset point cloud data of the material, determine whether a suspicious region exists on the material:
determining a contour of the material in a top view direction based on the point cloud data;
performing rotary adjustment on the profile and overlapping the preset profile corresponding to preset point cloud data, wherein the preset profile is the profile of the standard material in the overlooking direction;
comparing the three-dimensional coordinates with the preset three-dimensional coordinates, and judging whether at least two suspicious points with inconsistent three-dimensional coordinates and preset three-dimensional coordinates exist in the point cloud data or not;
if the at least two suspicious points exist, determining all continuous and adjacent suspicious points from the at least two suspicious points, and forming a pending area;
if the number of the suspicious points is greater than the preset number of the pending areas, determining that the suspicious areas exist, and determining the pending areas with the number of the suspicious points greater than the preset number as the suspicious areas;
And if the number of suspicious points is greater than the preset number of the pending areas, determining that the suspicious areas are not present.
In another possible implementation manner, the location determining module is specifically configured to, when determining the location information of the suspicious region:
determining center point coordinates of the suspicious region based on three-dimensional coordinates of suspicious points in the suspicious region;
filtering coordinate values consistent with the advancing direction of the assembly line in the coordinates of the central point to obtain two-dimensional coordinates of the central point;
and mapping the two-dimensional coordinates to a preset coordinate system to obtain the position information of the suspicious region, wherein the preset coordinate system is a coordinate system established on a plane perpendicular to the travelling direction of the assembly line.
In another possible implementation manner, the light source control module is specifically configured to, when the control target light source is turned on:
determining the depth of the suspicious region based on the three-dimensional coordinates of suspicious points in the suspicious region;
determining a brightness of the target light source based on the depth;
and controlling the target light source to be lightened according to the brightness.
In another possible implementation manner, the light source control module is specifically configured to, when determining the brightness of the target light source based on the depth:
Determining a preset depth interval in which the depth is located, wherein the preset depth interval corresponds to preset brightness;
and determining the preset brightness corresponding to the preset product interval in which the depth is positioned as the brightness of the target light source.
In another possible implementation, the apparatus further includes:
and the rotation control module is used for controlling the auxiliary image pickup device to rotate based on the position information so that the auxiliary image pickup device faces the suspicious region when the material is detected to move below the image pickup device, and controlling the auxiliary image pickup device to shoot a close-up image of the suspicious region.
In another possible implementation, the apparatus further includes:
the shooting control module is used for controlling the image pickup device to shoot a material image of the material when detecting that the material moves below the image pickup device and controlling the auxiliary image pickup device to shoot a close-up image of the suspicious region;
the relation determining module is used for determining the corresponding relation between the close-up image and the material image;
and the storage module is used for storing the close-up image, the material image and the corresponding relation.
In a third aspect, the present application provides an electronic device, which adopts the following technical scheme:
An electronic device, the electronic device comprising:
at least one processor;
a memory;
at least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, the at least one processor configured to: a machine vision environment rapid construction method according to any one of the possible implementations of the first aspect is performed.
In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:
a computer readable storage medium, which when executed in a computer, causes the computer to perform a machine vision environment rapid construction method according to any one of the first aspects.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the production line is used for conveying materials, when the fact that the materials move to the preset position on the upstream of the image pick-up device is detected, point cloud data on the surfaces of the materials are obtained, so that the conditions of the surfaces of the materials can be known through the point cloud data, after the point cloud data on the surfaces of the materials are obtained, the point cloud data of the materials are compared with preset point cloud data of the standard materials as a reference for comparison, so that whether suspicious areas possibly damaged exist in the materials can be judged, if the suspicious areas exist, the position information of the suspicious areas is determined, the position information is the position information on a plane perpendicular to the travelling direction of the production line, after the position information of the suspicious areas is determined, a target light source capable of illuminating the suspicious areas can be determined according to the position information, and when the materials are detected to move to the position below the image pick-up device, the target light source is controlled to be bright, so that the suspicious areas are clearer, namely, the proper light source environment for the materials can be quickly shot by the image pick-up device can be obtained according to the characteristics of the materials, and the detection effect is improved;
2. The depth of the suspicious region can be determined according to the three-dimensional coordinates of the suspicious points in the suspicious region, the deeper the depth of the suspicious region is, the less easy the situation of the suspicious region is to observe, and therefore the suspicious region is illuminated by light with higher brightness, the detail situation in the suspicious region is obtained more clearly, the brightness of the target light source is determined according to the depth, and the target light source is controlled to be lightened according to the determined brightness, so that the imaging device can shoot the clearer detail situation when detecting materials.
Drawings
Fig. 1 is a flow chart of a method for quickly constructing a machine vision environment in an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a machine vision environment rapid construction device in an embodiment of the present application.
Fig. 3 is a schematic structural diagram of a machine vision environment rapid building system according to an embodiment of the present application.
Fig. 4 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
The present application is described in further detail below with reference to the accompanying drawings.
Modifications of the embodiments which do not creatively contribute to the invention may be made by those skilled in the art after reading the present specification, but are protected by patent laws only within the scope of claims of the present application.
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of 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 apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.
Embodiments of the present application are described in further detail below with reference to the drawings attached hereto.
The embodiment of the application provides a quick construction method of a machine vision environment, which is executed by electronic equipment, wherein the electronic equipment can be a server or terminal equipment, and the server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server for providing cloud computing service. The terminal device may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., and the terminal device and the server may be directly or indirectly connected through wired or wireless communication, which is not limited herein, and as shown in fig. 1, the method includes step S101, step S102, step S103, and step S104, where,
S101, when detecting that materials appear at a preset position on a production line, acquiring point cloud data of the surfaces of the materials.
Wherein the preset position is located in an upstream direction of the image pickup device.
For the embodiment of the application, before the material is formally detected, the electronic equipment acquires point cloud data at the preset position at the upstream of the material running line, so that the initial material surface condition is obtained. The infrared transmitting tube and the infrared receiving tube can be arranged on two sides of a preset position on the assembly line respectively, when materials pass through the preset position, the materials cut off infrared rays emitted by the infrared transmitting tube, and the infrared receiving tube cannot receive the infrared rays, so that whether the materials appear at the preset position can be detected. The three-dimensional laser scanner can be arranged above the preset position, and is triggered when the material appears at the preset position, so that the point cloud data of the material is acquired, and the three-dimensional laser scanner can be acquired by the electronic equipment after acquiring the point cloud data of the material.
S102, comparing the point cloud data with preset point cloud data of standard materials, and judging whether suspicious areas exist on the materials.
The suspicious region is a region where breakage may occur.
For the embodiment of the application, preset point cloud data of standard materials are stored in the electronic equipment in advance, the preset point cloud data are used as point cloud data of a reference, and after the electronic equipment acquires the point cloud data of the materials, the point cloud data can be compared with the preset point cloud data, so that whether a suspicious area which is possibly damaged exists on the materials is judged.
S103, if the suspicious region exists, determining the position information of the suspicious region.
The position information is the position information of the suspicious region on a plane perpendicular to the travelling direction of the pipeline.
For the embodiment of the application, when the electronic equipment judges that the suspicious region exists on the material, the electronic equipment determines the position information of the suspicious region, so that the suspicious region can be detected better according to the position information. Specifically, when the material moves to the position right below the image pickup device, the suspicious region and the image pickup device are located on the same vertical plane, namely, a plane perpendicular to the travelling direction of the assembly line, so that the determined position information is the position information of the suspicious region on the plane.
And S104, determining a target light source based on the position information, and controlling the target light source to be lightened when the material is detected to move below the image pickup device.
For the embodiment of the application, the area shot by the camera device on the assembly line is the detection area, the basic light sources are arranged on two sides of the detection area of the assembly line, and the material is illuminated when the material passes through the detection area, so that the camera device detects. The electronic equipment can determine the target light source from the at least one auxiliary light source according to the corresponding relation after determining the position information of the suspicious region, the at least one auxiliary light source can be in a state of being extinguished when no material passes through the detection region, and when the material passes through the detection region, the electronic equipment controls the target light source determined from the at least one auxiliary light source to be lightened, so that a light source environment of the shooting device for shooting the material is built according to the suspicious region of the material, the material can be better detected, and the detection effect is improved.
In one possible implementation manner of this embodiment of the present application, the point cloud data includes three-dimensional coordinates of a plurality of points of the material, the preset point cloud data includes preset three-dimensional coordinates of a plurality of points of the standard material, in step S102, the point cloud data is compared with the preset point cloud data of the material, to determine whether a suspicious region exists on the material, and specifically includes step S1021 (not shown in the figure), step S1022 (not shown in the figure), step S1023 (not shown in the figure), step S1024 (not shown in the figure), step S1025 (not shown in the figure), and step S1026 (not shown in the figure), where,
s1021, determining the outline of the material in the overlooking direction based on the point cloud data.
For this application embodiment, the material on the assembly line is because vibrations of assembly line etc. influence, leads to the gesture position etc. of material different. The electronic equipment determines the outline of the material in the overlooking direction according to the point cloud data, and particularly, the three-dimensional laser scanner can be arranged above a preset position, so that the outline in the overlooking direction represents the gesture position of the material to be more specific, the electronic equipment can determine the outermost peripheral point in the point cloud data, and the area surrounded by the outermost peripheral point is the outline of the material in the overlooking direction.
And S1022, performing rotation adjustment on the outline and overlapping the outline corresponding to the preset point cloud data.
The preset contour is a contour of the standard material in the overlooking direction.
For the embodiment of the application, the preset point cloud data of the standard material also corresponds to the preset outline in the overlook direction, and the electronic equipment carries out rotary adjustment on the outline of the material, so that the gesture position of the material is consistent with the gesture position of the preset outline, and further, the subsequent point cloud data is more accurate when being compared. Specifically, the electronic device can compare with the preset profile in the process of adjusting the rotation of the profile of the material, so as to judge whether the profile coincides with the preset profile.
S1023, comparing the three-dimensional coordinates with preset three-dimensional coordinates, and judging whether at least two suspicious points with inconsistent three-dimensional coordinates and preset three-dimensional coordinates exist in the point cloud data.
For the embodiment of the application, each point in the point cloud data of the material is correspondingly numbered, each point in the preset point cloud data is correspondingly numbered, and the electronic equipment compares the three-dimensional coordinates with the same number with the preset three-dimensional coordinates, so that whether at least two suspicious points with inconsistent three-dimensional coordinates with the preset three-dimensional coordinates exist or not can be judged, and the suspicious points represent positions where damage possibly occurs to the surface of the material.
S1024, if at least two suspicious points exist, determining all continuous and adjacent suspicious points from the at least two suspicious points, and forming a pending area.
For the embodiment of the application, when there is no continuous and adjacent suspicious point around one suspicious point, it is indicated that the suspicious point is more likely to be located within an error range, so that a single suspicious point may be excluded, and if there are at least two suspicious points, it is indicated that the continuous and adjacent suspicious point can form a region, and in order to further determine whether the region belongs to the suspicious region, the electronic device determines the region as a pending region.
S1025, if the number of the suspicious points is greater than the preset number of the pending areas, determining that the suspicious areas exist, and determining the pending areas with the number of the suspicious points greater than the preset number as the suspicious areas.
For the embodiment of the present application, assuming that the preset number is 10, when the electronic device determines that the number of suspicious points in a certain pending area is greater than 10, it indicates that the pending area has a high possibility of belonging to a damaged area, that is, a suspicious area.
And S1026, if the number of suspicious points is not greater than the preset number of the pending areas, determining that the suspicious areas are not present.
For the embodiment of the present application, if the number of suspicious points in the to-be-determined area is smaller than the preset number of 10, it is indicated that the possibility that the to-be-determined area belongs to the damaged area is smaller, so that the electronic device filters the area, that is, when there are no to-be-determined areas with the number of suspicious points greater than 10, it is determined that there are no suspicious areas.
In one possible implementation manner of the embodiment of the present application, the determining the location information of the suspicious region in step S103 specifically includes step S1031 (not shown in the figure), step S1032 (not shown in the figure), and step S1033 (not shown in the figure), where,
s1031, determining the center point coordinates of the suspicious region based on the three-dimensional coordinates of the suspicious points in the suspicious region.
For the embodiment of the application, after the suspicious region is determined, the electronic equipment can know the three-dimensional coordinates of each suspicious point in the suspicious region, the central point coordinates of the suspicious region can be obtained by calculating the average value of the three-dimensional coordinates of all suspicious points, and the positions of the suspicious region in the three-dimensional space are characterized by the central point coordinates to be more accurate.
S1032, filtering coordinate values consistent with the advancing direction of the assembly line in the coordinates of the central point to obtain the two-dimensional coordinates of the central point.
For the embodiment of the application, when the three-dimensional coordinates of the center point of the suspicious region move along the travelling direction of the assembly line, the coordinate values of the upper axis of the center point along the travelling direction of the assembly line change, and the other two coordinate values are unchanged, when the material moves to the lower part of the image pickup device, the suspicious region and the image pickup device are positioned on the same vertical plane, so that the two-dimensional coordinates of the center point can be obtained by filtering the coordinates of the center point by the electronic equipment.
S1033, mapping the two-dimensional coordinates to a preset coordinate system to obtain the position information of the suspicious region, wherein the preset coordinate system is a coordinate system established on a plane perpendicular to the travelling direction of the assembly line.
For the embodiment of the application, after obtaining the two-dimensional coordinates of the center point, the electronic device sets the two-dimensional coordinates in a preset coordinate system and converts the two-dimensional coordinates into coordinates in the preset coordinate system, so that the position information of the suspicious region is obtained, the preset coordinate system is taken as the coordinate system on a plane perpendicular to the travelling direction of the assembly line, and therefore the obtained position information is the position information of the suspicious position when the suspicious position moves below the image pickup device.
In one possible implementation manner of the embodiment of the present application, the step S104 of controlling the illumination of the target light source 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), where,
s1041, determining the depth of the suspicious region based on the three-dimensional coordinates of the suspicious points in the suspicious region.
For the embodiment of the application, after the electronic device determines the suspicious points in the suspicious region, the suspicious points represent the positions of all the points in the suspicious region, so that the depth of the suspicious region can be determined according to the three-dimensional coordinates of the suspicious points. Specifically, the electronic device may extract an axis coordinate of each suspicious point in the vertical direction, and then compare the axis coordinate values in the vertical direction, so as to find a maximum value and a minimum value, where the maximum value and the minimum value represent a range of the suspicious region in the vertical direction, and a difference obtained by subtracting the minimum value from the maximum value is the depth of the suspicious region.
S1042, determining the brightness of the target light source based on the depth.
For the embodiment of the application, the deeper the depth of the suspicious region is, the less easily the details deep in the suspicious region are observed, the more bright light is required to illuminate the suspicious region when the details of the suspicious region are to be observed, namely the depth and the brightness are positively correlated, so that the electronic equipment can determine the brightness of the target light source according to the depth, and the details of the suspicious region can be clearly understood.
S1043, the control target light source is lighted up according to the brightness.
For the embodiment of the application, after the electronic device determines the brightness of the target light source, when the material moves to the detection area below the image pickup device, the electronic device sends a control signal to the target light source, so that the target light source is lightened according to the determined brightness, and the suspicious area on the material is better illuminated.
In one possible implementation manner of the embodiment of the present application, the step S1042 of determining the brightness of the target light source based on the depth specifically includes a step S10421 (not shown in the figure) and a step S10422 (not shown in the figure), where,
s10421, determining a preset depth interval where the depth is located.
The preset depth interval corresponds to preset brightness.
For the embodiment of the application, a plurality of preset depth intervals are prestored in the electronic device, three preset depth intervals (0 mm,5 mm), (5 mm,10 mm) and (10 mm,15 mm) are assumed, preset brightness corresponding to the three preset depth intervals is 30 lumens (lm), 60lm and 90lm respectively, the electronic device can determine that the preset depth interval where the depth is located is (0 mm,5 mm) assuming that the depth of the suspicious region determined by the electronic device is 3 mm.
S10422, determining the preset brightness corresponding to the preset product interval where the depth is located as the brightness of the target light source.
For the embodiment of the present application, taking step S10421 as an example, after the electronic device determines that the section where the suspicious region is located is (0 mm,5 mm), it is sufficient to directly determine the luminance 30lm corresponding to the section as the luminance of the target light source.
In other embodiments, since the depth and the luminance are positively correlated, a positive proportional relation, for example, a linear function relation y=6x+20, where y is the determined luminance, 6 is a proportionality coefficient, x is the depth, and 20 is the initial luminance, may be stored in the electronic device in advance. Substituting the depth into the linear function relation to obtain the brightness required by the target light source.
In one possible implementation manner of the embodiment of the present application, the method further includes step Sa (not shown in the figure), where step Sa may be performed before step S104, or may be performed simultaneously with step S104, where,
the Sa controls the auxiliary imaging device to rotate based on the position information so that the auxiliary imaging device faces the suspicious region when the movement of the material to below the imaging device is detected, and controls the auxiliary imaging device to take a close-up image of the suspicious region.
For the embodiment of the application, the auxiliary image pickup device can change the magnification of the lens of the auxiliary image pickup device and can pick up details of the appointed area on the material. The auxiliary image pick-up device can be arranged above the detection area and can rotate by taking the travelling direction of the assembly line as a central shaft, namely, the auxiliary image pick-up device can rotate on a plane perpendicular to the travelling direction of the assembly line, so that the auxiliary image pick-up device can face the suspicious area at a better angle and shoot a close-up image, and the detail characteristics of the part of the suspicious area of the material can be known by shooting the close-up image through the auxiliary image pick-up device.
In other embodiments, the electronic device may cut the point cloud data of the suspicious region to obtain multiple cross sections of the suspicious region, that is, the electronic device may obtain the point cloud data on the perimeter wall of the suspicious region at the cross section, and the electronic device may connect the three-dimensional coordinates of the central positions of the multiple cross sections according to the three-dimensional coordinates of the central positions of the cross sections of the suspicious region, so as to obtain a depth trend of the suspicious region, and obtain an extension angle of the suspicious region by combining the depth trend with a horizontal plane. The slide way can be arranged above the detection area, the slide way is arranged along the direction perpendicular to the travelling direction of the assembly line, and the light source is arranged on the slide way, so that the slide way can slide and can rotate on a plane perpendicular to the travelling direction of the assembly line. The electronic equipment controls the slide way to move and rotate according to the position information and the extension angle of the suspicious region, so that the auxiliary camera device can emit light parallel to the extension angle at the position corresponding to the suspicious region, and further the suspicious region can be better illuminated, and details in the suspicious region are clearer.
One possible implementation manner of the embodiment of the present application, the method further includes a step S1 (not shown in the figure), a step S2 (not shown in the figure), and a step S3 (not shown in the figure), where the step S1 may be performed simultaneously with the step S104, where,
s1, when the fact that the material moves to the position below the image pickup device is detected, controlling the image pickup device to pick up the material image of the material, and controlling the auxiliary image pickup device to pick up a close-up image of the suspicious region.
Similarly, an infrared transmitting tube and an infrared receiving tube can be respectively arranged on two sides of a detection area on the production line, when materials pass through a preset position, the materials cut off infrared rays emitted by the infrared transmitting tube, and the infrared receiving tube cannot receive the infrared rays, so that whether the materials appear in the detection area can be detected. And a distance measuring sensor can be arranged at one end of the assembly line, and the material is judged to move to the detection area when the specified distance between the sensor and the material is detected. After the electronic equipment detects that the material moves into the detection area, a control signal can be sent to the image pickup device and the auxiliary image pickup device, so that the image pickup device shoots an image of the material to detect the material, and meanwhile, the auxiliary image pickup device shoots a close-up image of the suspicious area, so that the specific details of the suspicious area can be known more clearly.
S2, determining the corresponding relation between the close-up image and the material image.
For the embodiment of the application, after the electronic equipment obtains the close-up image and the material image, the corresponding relation of the two images is determined, so that the close-up image of the material corresponds to the whole material image, and the material of the suspicious region in the close-up image can be more conveniently known.
And S3, storing the close-up image, the material image and the corresponding relation.
For the embodiment of the application, the electronic device may store the close-up image, the material image and the corresponding relationship in a local storage medium, and may also store the close-up image, the material image and the corresponding relationship in a cloud server, so that a subsequent worker may call the image for analysis.
The foregoing embodiments describe a machine vision environment rapid construction method from the viewpoint of a method flow, and the following embodiments describe a machine vision environment rapid construction device from the viewpoint of a virtual module or a virtual unit, specifically the following embodiments.
An embodiment of the present application provides a machine vision environment rapid construction device 20, as shown in fig. 2, the machine vision environment rapid construction device 20 may specifically include:
the data acquisition module 201 is configured to acquire point cloud data of a material surface when a material is detected to appear at a preset position on the assembly line, where the preset position is located in an upstream direction of the camera;
The comparison module 202 is configured to compare the point cloud data with preset point cloud data of a standard material, and determine whether a suspicious region exists on the material, where the suspicious region is a region where damage is possible;
a position determining module 203, configured to determine, when a suspicious region exists, position information of the suspicious region, where the position information is position information of the suspicious region on a plane perpendicular to a traveling direction of the pipeline;
the light source control module 204 is used for determining a target light source based on the position information and controlling the target light source to be lightened when the material is detected to move to the position below the image pickup device.
Through adopting above-mentioned technical scheme, the assembly line is used for transporting the material, when detecting the material and remove the preset position on camera, data acquisition module 201 acquires the point cloud data on material surface, thereby can learn the condition on material surface through the point cloud data, after obtaining material surface point cloud data, because standard material is the benchmark of contrast, contrast module 202 compares the point cloud data of material and the preset point cloud data of standard material, thereby can judge whether there is the suspicious region that probably takes place the damage in the material, if there is suspicious region, then position determination module 203 determines the positional information in suspicious region, this positional information is the positional information on the plane of perpendicular to assembly line advancing direction, after determining the positional information in suspicious region, light source control module 204 can confirm the target light source that can illuminate suspicious region according to the positional information, when detecting the material and remove the camera below, thereby make suspicious region clear, can be to the characteristics of material itself fast build the camera and shoot the suitable light source environment of material, the device can obtain more suspicious regions when the material image, the detection detail effect has been improved.
In one possible implementation manner of this embodiment of the present application, the point cloud data includes three-dimensional coordinates of a plurality of points of the material, the preset point cloud data includes preset three-dimensional coordinates of a plurality of points of the standard material, and the comparison module 202 is specifically configured to, when comparing the point cloud data with the preset point cloud data of the material, determine whether a suspicious region exists on the material:
determining a contour of the material in a top view direction based on the point cloud data;
rotationally adjusting the outline and overlapping the preset outline corresponding to the preset point cloud data, wherein the preset outline is the outline of the standard material in the overlooking direction;
comparing the three-dimensional coordinates with preset three-dimensional coordinates, and judging whether at least two suspicious points with inconsistent three-dimensional coordinates and preset three-dimensional coordinates in the point cloud data exist or not;
if at least two suspicious points exist, determining all continuous and adjacent suspicious points from the at least two suspicious points, and forming a pending area;
if the number of the suspicious points is greater than the preset number of the pending areas, determining that the suspicious areas exist, and determining the pending areas with the number of the suspicious points greater than the preset number as the suspicious areas;
and if the number of suspicious points is greater than the preset number of the pending areas, determining that the suspicious areas are not present.
In one possible implementation manner of the embodiment of the present application, when determining the location information of the suspicious region, the location determining module 203 is specifically configured to:
determining center point coordinates of the suspicious region based on three-dimensional coordinates of suspicious points in the suspicious region;
filtering coordinate values consistent with the advancing direction of the assembly line in the coordinates of the central point to obtain two-dimensional coordinates of the central point;
mapping the two-dimensional coordinates to a preset coordinate system to obtain the position information of the suspicious region, wherein the preset coordinate system is a coordinate system established on a plane perpendicular to the travelling direction of the assembly line.
In one possible implementation manner of the embodiment of the present application, when the control target light source is turned on, the light source control module 204 is specifically configured to:
determining the depth of the suspicious region based on the three-dimensional coordinates of the suspicious points in the suspicious region;
determining a brightness of the target light source based on the depth;
the control target light source is lighted up according to the brightness.
In one possible implementation manner of the embodiment of the present application, when determining the brightness of the target light source based on the depth, the light source control module 204 is specifically configured to:
determining a preset depth interval in which the depth is located, wherein the preset depth interval corresponds to preset brightness;
and determining the preset brightness corresponding to the preset product interval where the depth is located as the brightness of the target light source.
In one possible implementation manner of the embodiment of the present application, the apparatus 20 further includes:
and the rotation control module is used for controlling the auxiliary image pickup device to rotate based on the position information so that the auxiliary image pickup device faces the suspicious region when the material is detected to move below the image pickup device, and controlling the auxiliary image pickup device to shoot a close-up image of the suspicious region.
In one possible implementation manner of the embodiment of the present application, the apparatus 20 further includes:
the shooting control module is used for controlling the image pickup device to shoot a material image of the material when detecting that the material moves to the lower part of the image pickup device and controlling the auxiliary image pickup device to shoot a close-up image of a suspicious region;
the relation determining module is used for determining the corresponding relation between the close-up image and the material image;
and the storage module is used for storing the close-up image, the material image and the corresponding relation.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the machine vision rapid construction device 20 described above may refer to the corresponding process in the foregoing method embodiment, and will not be described herein again.
In the embodiment of the application, a quick construction system for a machine vision environment is provided, as shown in fig. 3, where the system shown in fig. 3 includes a pipeline 31, a three-dimensional laser scanner 32, a basic light source 33, an image capturing device 34, an auxiliary light source 35, and an electronic device (not shown in the figure). In fig. 3, the arrow direction is the traveling direction of the pipeline 31, the position of the pipeline 31 below the three-dimensional laser scanner 32 is a preset position 311, and the area below the imaging device 34 on the pipeline 31 is a detection area 312. The material moves to a preset position 311 on the assembly line 31, infrared transmitting tubes (not shown in the figure) and infrared receiving tubes (not shown in the figure) can be arranged on two sides of the preset position 311 of the assembly line 31, so that whether the material moves to the preset position 311 is detected, the electronic equipment can be connected with the infrared transmitting tubes in a wired or wireless mode, and the electronic equipment can be connected with the infrared receiving tubes in a wired or wireless mode, so that the electronic equipment can know whether the material moves to the preset position. After the material moves to the preset position 311, the three-dimensional laser scanner 32 collects point cloud data of the material, and the electronic device and the three-dimensional laser scanner 32 can be connected through a wire or wirelessly, so that the point cloud data of the material is obtained. After the material continues to move into the detection area 312, the base light source illuminates the monitoring area, and the electronics control the target light source in the auxiliary light source 35 to illuminate, and the camera 34 detects breakage of the material. Further, the system may further include a distance measuring sensor (not shown) at one end of the line 31 for detecting whether the material enters the detection area 312, and the electronic device may be connected to the distance measuring sensor by a wire or wirelessly so that the electronic device knows whether the material enters the detection area.
Referring to fig. 3, an auxiliary image pickup device 36 is further disposed above the detection area 312, and an electronic device is connected with the auxiliary image pickup device 36 in a wired or wireless manner, and controls the auxiliary image pickup device 36 to rotate by an angle such that the auxiliary image pickup device 36 faces the suspicious area of the material, and controls the auxiliary image pickup device 36 to take a close-up image of the suspicious area. In other embodiments, the system further includes a chute (not shown) above the detection zone 312, the auxiliary camera 36 being slidably coupled to the chute and the auxiliary camera 36 being rotatable in a vertical plane perpendicular to the direction of travel of the pipeline.
In the embodiment of the application, as shown in fig. 4, the electronic device shown in fig. 4 may be an electronic device in a machine vision environment rapid construction system in the embodiment of the application. The electronic device 40 shown in fig. 4 includes: a processor 401 and a memory 403. Processor 401 is connected to memory 403, such as via bus 402. Optionally, the electronic device 40 may also include a transceiver 404. It should be noted that, in practical applications, the transceiver 404 is not limited to one, and the structure of the electronic device 40 is not limited to the embodiment of the present application.
The processor 401 may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. Processor 401 may also be a combination that implements computing functionality, such as a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
Bus 402 may include a path to transfer information between the components. Bus 402 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or EISA (Extended Industry Standard Architecture ) bus, among others. Bus 402 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. 4, but not only one bus or type of bus.
The Memory 403 may be, but is not limited to, 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, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, 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.
The memory 403 is used for storing application program codes for executing the present application and is controlled to be executed by the processor 401. The processor 401 is arranged to execute application code stored in the memory 403 for implementing what is shown in the foregoing method embodiments.
Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. But may also be a server or the like. The electronic device shown in fig. 4 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments herein.
The present application provides a computer readable storage medium having a computer program stored thereon, which when run on a computer, causes the computer to perform the corresponding method embodiments described above. Compared with the prior art, the assembly line is used for conveying materials, when the fact that the materials move to the preset position on the upstream of the image pick-up device is detected, point cloud data of the surfaces of the materials are obtained, accordingly, the situation of the surfaces of the materials can be known through the point cloud data, after the point cloud data of the surfaces of the materials are obtained, the point cloud data of the materials are compared with preset point cloud data of the standard materials as a reference for comparison, accordingly, whether suspicious areas possibly damaged exist in the materials can be judged, if the suspicious areas exist, position information of the suspicious areas is determined, the position information is the position information on a plane perpendicular to the travelling direction of the assembly line, a target light source capable of illuminating the suspicious areas can be determined according to the position information, when the fact that the materials move to the lower portion of the image pick-up device is detected, the target light source is controlled to be on, the suspicious areas are clearer, the proper light source environment for the materials can be quickly built to be shot by the image pick-up device, the details of the suspicious areas can be obtained when the image of the materials is shot, and the detection effect is improved.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims (10)

1. The quick construction method of the machine vision environment is characterized by comprising the following steps of:
when detecting that a material appears at a preset position on a production line, acquiring point cloud data of the surface of the material, wherein the preset position is positioned in the upstream direction of a camera device;
Comparing the point cloud data with preset point cloud data of standard materials, and judging whether suspicious areas exist on the materials, wherein the suspicious areas are areas which are possibly damaged;
if the suspicious region exists, determining the position information of the suspicious region, wherein the position information is the position information of the suspicious region on a plane perpendicular to the travelling direction of the assembly line;
and determining a target light source based on the position information, and controlling the target light source to be lightened when the material is detected to move below the image pickup device.
2. The method according to claim 1, wherein the point cloud data includes three-dimensional coordinates of a plurality of points of the material, the preset point cloud data includes preset three-dimensional coordinates of a plurality of points of a standard material, and the comparing the point cloud data with the preset point cloud data of the material includes:
determining a contour of the material in a top view direction based on the point cloud data;
performing rotary adjustment on the profile and overlapping the preset profile corresponding to preset point cloud data, wherein the preset profile is the profile of the standard material in the overlooking direction;
Comparing the three-dimensional coordinates with the preset three-dimensional coordinates, and judging whether at least two suspicious points with inconsistent three-dimensional coordinates and preset three-dimensional coordinates exist in the point cloud data or not;
if the at least two suspicious points exist, determining all continuous and adjacent suspicious points from the at least two suspicious points, and forming a pending area;
if the number of the suspicious points is greater than the preset number of the pending areas, determining that the suspicious areas exist, and determining the pending areas with the number of the suspicious points greater than the preset number as the suspicious areas;
and if the number of suspicious points is greater than the preset number of the pending areas, determining that the suspicious areas are not present.
3. The machine vision environment rapid construction method according to claim 2, wherein the determining the position information of the suspicious region includes:
determining center point coordinates of the suspicious region based on three-dimensional coordinates of suspicious points in the suspicious region;
filtering coordinate values consistent with the advancing direction of the assembly line in the coordinates of the central point to obtain two-dimensional coordinates of the central point;
and mapping the two-dimensional coordinates to a preset coordinate system to obtain the position information of the suspicious region, wherein the preset coordinate system is a coordinate system established on a plane perpendicular to the travelling direction of the assembly line.
4. A machine vision environment rapid construction method according to claim 3, wherein controlling the illumination of the target light source comprises:
determining the depth of the suspicious region based on the three-dimensional coordinates of suspicious points in the suspicious region;
determining a brightness of the target light source based on the depth;
and controlling the target light source to be lightened according to the brightness.
5. The method of claim 4, wherein said determining the brightness of the target light source based on the depth comprises:
determining a preset depth interval in which the depth is located, wherein the preset depth interval corresponds to preset brightness;
and determining the preset brightness corresponding to the preset product interval in which the depth is positioned as the brightness of the target light source.
6. The machine vision environment rapid construction method of claim 1, further comprising:
and controlling the auxiliary image pickup device to rotate based on the position information so that the auxiliary image pickup device faces the suspicious region when the material is detected to move below the image pickup device, and controlling the auxiliary image pickup device to shoot a close-up image of the suspicious region.
7. The machine vision environment rapid construction method of claim 6, further comprising:
when the material is detected to move below the image pickup device, controlling the image pickup device to pick up a material image of the material, and controlling the auxiliary image pickup device to pick up a close-up image of the suspicious region;
determining the corresponding relation between the close-up image and the material image;
and storing the close-up image, the material image and the corresponding relation.
8. A machine vision environment rapid construction apparatus, comprising:
the data acquisition module is used for acquiring point cloud data of the surface of the material when the material is detected to appear at a preset position on the assembly line, wherein the preset position is positioned in the upstream direction of the camera device;
the comparison module is used for comparing the point cloud data with preset point cloud data of standard materials and judging whether suspicious areas exist on the materials or not, wherein the suspicious areas are areas which are possibly damaged;
the position determining module is used for determining the position information of the suspicious region when the suspicious region exists, wherein the position information is the position information of the suspicious region on a plane perpendicular to the travelling direction of the pipeline;
And the light source control module is used for determining a target light source based on the position information and controlling the target light source to be lightened when the material is detected to move below the image pickup device.
9. An electronic device, comprising:
at least one processor;
a memory;
at least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, the at least one application program: for performing a machine vision environment rapid construction method according to any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed in a computer, causes the computer to perform a machine vision environment rapid construction method according to any one of claims 1 to 7.
CN202310315419.5A 2023-03-22 2023-03-22 Quick construction method, device and medium for machine vision environment Active CN116342539B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310315419.5A CN116342539B (en) 2023-03-22 2023-03-22 Quick construction method, device and medium for machine vision environment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310315419.5A CN116342539B (en) 2023-03-22 2023-03-22 Quick construction method, device and medium for machine vision environment

Publications (2)

Publication Number Publication Date
CN116342539A true CN116342539A (en) 2023-06-27
CN116342539B CN116342539B (en) 2023-12-12

Family

ID=86883578

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310315419.5A Active CN116342539B (en) 2023-03-22 2023-03-22 Quick construction method, device and medium for machine vision environment

Country Status (1)

Country Link
CN (1) CN116342539B (en)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000276599A (en) * 1999-03-26 2000-10-06 Suzuki Motor Corp Device for detecting surface fault
CN104913737A (en) * 2015-06-30 2015-09-16 长安大学 Component quality checking device based on line laser three-dimensional measurement and detection method of device
CN107052086A (en) * 2017-06-01 2017-08-18 扬州苏星机器人科技有限公司 Stamping parts surface defect detection apparatus and detection method based on 3D vision
US20180374186A1 (en) * 2017-06-23 2018-12-27 Cloud 9 Perception, LP System and Method for Sensing and Computing of Perceptual Data in Industrial Environments
US20200126208A1 (en) * 2018-10-18 2020-04-23 Wisconsin Alumni Research Foundation Systems, methods, and media for detecting manipulations of point cloud data
CN113607659A (en) * 2021-08-26 2021-11-05 广东省农业科学院设施农业研究所 Conveyor belt type crop phenotype acquisition method, system and device
CN114280073A (en) * 2021-12-27 2022-04-05 南京光衡科技有限公司 Tile defect detection device adopting laser and camera composite detection mode and classification method
CN114359246A (en) * 2022-01-10 2022-04-15 南京中远通科技有限公司 Conveyor belt detection method, device, system, electronic device and medium
CN114414487A (en) * 2022-01-19 2022-04-29 北京科技大学设计研究院有限公司 Two-dimensional and three-dimensional fused round steel surface imaging system
CN114581385A (en) * 2022-02-23 2022-06-03 杭州安脉盛智能技术有限公司 Welding seam defect area mapping algorithm based on circle positioning
CN114596301A (en) * 2022-03-18 2022-06-07 上海宝振自动化工程有限公司 Coating roller surface defect detection system adopting 3D line laser profile technology
CN115526885A (en) * 2022-10-24 2022-12-27 杭州安脉盛智能技术有限公司 Product image defect detection method, system, device and medium
CN115731222A (en) * 2022-12-01 2023-03-03 中网华信科技股份有限公司 Billet surface detection method, device, equipment and computer readable storage medium

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000276599A (en) * 1999-03-26 2000-10-06 Suzuki Motor Corp Device for detecting surface fault
CN104913737A (en) * 2015-06-30 2015-09-16 长安大学 Component quality checking device based on line laser three-dimensional measurement and detection method of device
CN107052086A (en) * 2017-06-01 2017-08-18 扬州苏星机器人科技有限公司 Stamping parts surface defect detection apparatus and detection method based on 3D vision
US20180374186A1 (en) * 2017-06-23 2018-12-27 Cloud 9 Perception, LP System and Method for Sensing and Computing of Perceptual Data in Industrial Environments
US20200126208A1 (en) * 2018-10-18 2020-04-23 Wisconsin Alumni Research Foundation Systems, methods, and media for detecting manipulations of point cloud data
CN113607659A (en) * 2021-08-26 2021-11-05 广东省农业科学院设施农业研究所 Conveyor belt type crop phenotype acquisition method, system and device
CN114280073A (en) * 2021-12-27 2022-04-05 南京光衡科技有限公司 Tile defect detection device adopting laser and camera composite detection mode and classification method
CN114359246A (en) * 2022-01-10 2022-04-15 南京中远通科技有限公司 Conveyor belt detection method, device, system, electronic device and medium
CN114414487A (en) * 2022-01-19 2022-04-29 北京科技大学设计研究院有限公司 Two-dimensional and three-dimensional fused round steel surface imaging system
CN114581385A (en) * 2022-02-23 2022-06-03 杭州安脉盛智能技术有限公司 Welding seam defect area mapping algorithm based on circle positioning
CN114596301A (en) * 2022-03-18 2022-06-07 上海宝振自动化工程有限公司 Coating roller surface defect detection system adopting 3D line laser profile technology
CN115526885A (en) * 2022-10-24 2022-12-27 杭州安脉盛智能技术有限公司 Product image defect detection method, system, device and medium
CN115731222A (en) * 2022-12-01 2023-03-03 中网华信科技股份有限公司 Billet surface detection method, device, equipment and computer readable storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
HONGYAO SHEN等: "Virsual detection of surface defects based on self-feature comparison in robot 3-D printing", 《APPLIED SCIENCES》, vol. 10, no. 01, pages 1 - 11 *
崔融融: "带式输送机故障自动巡检机器人系统设计", 《煤矿机械》, vol. 42, no. 03, pages 15 - 18 *

Also Published As

Publication number Publication date
CN116342539B (en) 2023-12-12

Similar Documents

Publication Publication Date Title
TWI528028B (en) Inspection apparatus, method, and computer program product for machine vision inspection
JP2006266848A (en) Distance measuring device
CN106488115B (en) For tracking and sensing the control device and method of the image sensing apparatus of tracking target
US10841561B2 (en) Apparatus and method for three-dimensional inspection
US20210302529A1 (en) Determining Imperfections in an Imaging Camera for Determining the Orientation of Objects in Space
JPWO2019131155A1 (en) Visual inspection equipment, visual inspection method, program and workpiece manufacturing method
US6807288B2 (en) Image processing apparatus, image processing method, and recording medium recording image processing program
US11663734B2 (en) Systems and methods of measuring an object in a scene of a captured image
CN116342539B (en) Quick construction method, device and medium for machine vision environment
KR101689980B1 (en) Pattern inspection apparatus and pattern inspection method
WO2021186640A1 (en) Deterioration detection device, deterioration detection system, deterioration detection method, and program
CN112233139A (en) System and method for detecting motion during 3D data reconstruction
JP2008241609A (en) Distance measuring system and distance measuring method
US11039114B2 (en) Method for determining distance information from images of a spatial region
CN114494404A (en) Object volume measurement method, system, device and medium
JP6448457B2 (en) Imaging direction variation detection apparatus and imaging direction variation detection method
KR101497396B1 (en) A system for measuring target location and method for measuring target location using the same
CN112788292A (en) Method and device for determining inspection observation point, inspection robot and storage medium
JP2016217872A (en) Inspection device, inspection method, program, and storage media
JP2008164338A (en) Position sensor
US20220414916A1 (en) Systems and methods for assigning a symbol to an object
EP4290480A1 (en) Detection of reflection of objects in a sequence of image frames
CN113674223A (en) Method, device, system and medium for detecting straightness of liquid crystal substrate glass
JP7020074B2 (en) Surface property acquisition device, surface property acquisition system and program
US20200012847A1 (en) Object detection apparatus, control method implemented by object detection apparatus, and non-transitory computer-readable storage medium for storing program

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