CN118112005A - Industrial visual detection method and system - Google Patents
Industrial visual detection method and system Download PDFInfo
- Publication number
- CN118112005A CN118112005A CN202410246055.4A CN202410246055A CN118112005A CN 118112005 A CN118112005 A CN 118112005A CN 202410246055 A CN202410246055 A CN 202410246055A CN 118112005 A CN118112005 A CN 118112005A
- Authority
- CN
- China
- Prior art keywords
- workpiece
- visual
- detected
- defect
- defect area
- 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.)
- Pending
Links
Classifications
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an industrial visual detection method and system, wherein each defective area is marked on a three-dimensional model corresponding to a workpiece to be detected, and the visual grade of each defective area relative to the three-dimensional model is judged; if the visual grade of each defect area relative to the three-dimensional model is lower than the preset visual grade, regulating and controlling the repair route butted by the multidirectional track according to the visual grade; in the repairing route, an attitude adjustment sequence is constructed based on a plurality of defect areas of the workpiece to be detected, corresponding repairing is carried out when the attitude is adjusted each time, at this time, the corresponding defect areas are defined according to the identification of a plurality of corner images, so that the rapid investigation of the defect areas is realized, the investigation is not comprehensive, the corner characteristics of corners are conveniently utilized, and meanwhile, the repairing route butted by the multidirectional rail is regulated and controlled according to the visual grade, so that the corresponding repairing is carried out on the plurality of defect areas of the workpiece to be detected, and the detection efficiency and the repairing efficiency of the workpiece to be detected are improved.
Description
Technical Field
The invention relates to the technical field of industrial visual detection, in particular to an industrial visual detection method and system.
Background
Along with development of science and technology, the visual inspection of the workpiece to be detected is gradually and widely performed in industry, at this time, the workpiece to be detected can measure length, thickness or defects in the visual inspection, in the prior art, the workpiece to be detected is used for defect identification, shooting is required to be performed on the workpiece to be detected, and corresponding images are acquired, at this time, the images need to be inspected layer by layer or region by region, for example, the images are provided with a plurality of regions, and each region needs to be inspected independently so as to perform comprehensive inspection, however, the comprehensive inspection influences the detection efficiency of the workpiece to be detected.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides an industrial visual detection method and system, which are used for determining corners based on visual images of a workpiece to be detected, and carrying out subsequent processing on a plurality of corner images so as to define corresponding defect areas according to the identification of the plurality of corner images, thereby realizing rapid investigation but not comprehensive investigation of the defect areas, so that the corner characteristics of the corners are utilized, simultaneously, in order to further manage the defect areas, the visual grade of each defect area relative to a three-dimensional model is introduced, and the repair route butted by a multidirectional rail is regulated according to the visual grade, so that corresponding repair is carried out on the plurality of defect areas of the workpiece to be detected, the repair of the corresponding defect areas of the workpiece to be detected under the corresponding postures is ensured, and the detection efficiency and the repair efficiency of the workpiece to be detected are improved.
In order to solve the technical problems, the embodiment of the invention provides an industrial visual detection method which is applied to visual detection scenes;
the industrial visual inspection method comprises the following steps:
detecting a workpiece to be detected on a multidirectional track, and collecting a visual image of the workpiece to be detected;
Determining corners based on visual images of the workpiece to be detected, and forming a plurality of corner images;
Defining a corresponding defect area according to the identification of the plurality of corner images;
marking each defect area on a three-dimensional model corresponding to the workpiece to be detected, and judging the visual grade of each defect area relative to the three-dimensional model;
if the visual grade of each defect area relative to the three-dimensional model is lower than the preset visual grade, regulating and controlling the repair route butted by the multidirectional track according to the visual grade;
In the repairing route, an attitude adjustment sequence is constructed based on a plurality of defect areas of the workpiece to be detected, and corresponding repairing is carried out when the attitude is adjusted each time.
Optionally, the detecting the workpiece to be detected on the multidirectional track and collecting the visual image of the workpiece to be detected includes:
when a workpiece to be detected enters a multi-directional track, acquiring an in-place signal output by the multi-directional track;
triggering the multi-directional track to measure the weight of the workpiece to be measured according to the in-place signal, and determining the weight information of the workpiece to be measured;
Matching a weight speed table based on weight information of a workpiece to be detected so as to determine the running speed of the multidirectional rail;
In the running process of the multidirectional rail, shooting a workpiece to be detected based on a plurality of cameras, and collecting images of the workpiece to be detected at a plurality of different angles;
A visual image of the workpiece to be measured is determined based on a combination of the plurality of images at different angles, wherein the visual image of the workpiece to be measured contains images of different sides of the workpiece to be measured.
Optionally, the determining the corner based on the visual image of the workpiece to be measured and forming a plurality of corner images includes:
Acquiring a visual image of a workpiece to be measured;
Traversing the visual image of the workpiece to be detected, and highlighting the outline of the visual image of the workpiece to be detected;
Determining a serpentine segment based on the investigation of the outer contour and determining a corner based on the serpentine segment;
The extending direction of the serpentine segment is captured and a plurality of corner images are formed along the extending direction of the serpentine segment.
Optionally, the determining the corner based on the visual image of the workpiece to be measured, and forming a plurality of corner images, further includes:
obtaining a snake-shaped line segment;
Traversing the snake line segment and collecting a plurality of segmentation distances in the snake line segment;
determining a segmentation level based on the plurality of segmentation distances;
Matching corresponding image learning models according to the segmentation level;
corresponding corner images are formed based on the image learning model and the serpentine segments.
Optionally, the defining the corresponding defect area according to the identification of the plurality of corner images includes:
collecting a plurality of corner images and defining the priority of the corner images;
Sequentially sequencing the plurality of corner images according to the priority level, and forming a corner image set;
Integral identification is carried out according to the corner image set, and the mixing part corresponding to each corner image is determined;
the mixed part in the corner image is defined as a defect part, and a corresponding defect area is formed according to the plurality of defect parts.
Optionally, marking each defect area on the stereoscopic model corresponding to the workpiece to be measured, and judging the visual grade of each defect area relative to the stereoscopic model, including:
forming three-dimensional characteristics based on dynamic scanning of the workpiece to be detected;
Type optimization is carried out on the three-dimensional characteristics, and a three-dimensional model is formed under the optimization;
Collecting each defect area and defining the space coordinates of each defect area relative to the three-dimensional model;
each defective region is marked on the stereoscopic model based on its spatial coordinates relative to the stereoscopic model.
Optionally, marking each defect area on the stereoscopic model corresponding to the workpiece to be measured, and judging the visual grade of each defect area relative to the stereoscopic model, and further including:
In the stereoscopic model, each defective area is subjected to dark treatment so as to reduce the brightness of each defective area;
And when the brightness of each defect area accords with the preset brightness, carrying out visual identification on each defect area after the dark treatment so as to define the visual grade of each defect area relative to the stereoscopic model.
Optionally, if the visual grade of each defect area relative to the stereoscopic model is lower than a preset visual grade, regulating and controlling the repair route docked by the multidirectional track according to the visual grade includes:
Collecting the visual grade of each defect area relative to the stereoscopic model;
comparing the visual grade of each defect area relative to the stereoscopic model with a preset visual grade;
if the visual grade of each defect area relative to the stereoscopic model is lower than the preset visual grade, constructing a virtual scene for each defect area, and observing each defect area in the virtual scene;
defining a perception coefficient of each defect region based on a presentation area of each defect region relative to the virtual scene;
and associating the perception coefficient with the multidirectional track, and triggering the direction change of the multidirectional track to regulate and control the repair route which is butted by the multidirectional track.
Optionally, in the repairing route, an attitude adjustment sequence is constructed based on a plurality of defect areas of the workpiece to be detected, and corresponding repairing is performed when the adjusted attitude is performed each time, including:
In the repairing route, a plurality of defect areas of the workpiece to be tested are fixed;
Collecting space positions among a plurality of defect areas, and defining adjustment priorities for defect areas in the defect areas;
sequencing according to the adjustment priority to stop the gesture adjustment sequence of the workpiece to be tested, and presenting a corresponding defect area in the corresponding gesture;
Checking the orientation of the defect area and adjusting the defect area along the upward direction;
at each adjusted pose, the multiple defective areas are repaired in sequence.
In addition, the embodiment of the invention also provides an industrial visual detection system, which comprises:
the acquisition module is used for detecting the workpiece to be detected on the multidirectional track and acquiring a visual image of the workpiece to be detected;
the corner image module is used for determining corners based on visual images of the workpiece to be detected and forming a plurality of corner images;
A defect area module for defining a corresponding defect area according to the identification of the plurality of corner images;
the visual grade module is used for marking each defect area on the three-dimensional model corresponding to the workpiece to be detected and judging the visual grade of each defect area relative to the three-dimensional model;
The repair route module is used for regulating and controlling the repair route which is butted by the multidirectional track according to the visual grade if the visual grade of each defect area relative to the stereoscopic model is lower than the preset visual grade;
And the repair module is used for constructing an attitude adjustment sequence based on a plurality of defect areas of the workpiece to be detected in the repair route and carrying out corresponding repair when the attitude is adjusted each time.
In the embodiment of the invention, the method in the embodiment of the invention detects the workpiece to be detected on the multidirectional track and acquires the visual image of the workpiece to be detected; determining corners based on visual images of the workpiece to be detected, and forming a plurality of corner images; defining a corresponding defect area according to the identification of the plurality of corner images; marking each defect area on a three-dimensional model corresponding to the workpiece to be detected, and judging the visual grade of each defect area relative to the three-dimensional model; if the visual grade of each defect area relative to the three-dimensional model is lower than the preset visual grade, regulating and controlling the repair route butted by the multidirectional track according to the visual grade; in the repairing route, an attitude adjustment sequence is constructed based on a plurality of defect areas of the workpiece to be detected, corresponding repairing is carried out when the attitude is adjusted each time, at this time, corners are determined based on visual images of the workpiece to be detected, and subsequent processing is carried out through a plurality of corner images, so that the corresponding defect areas are defined according to the identification of the plurality of corner images, and therefore rapid investigation but not comprehensive investigation of the defect areas is realized, so that the corner characteristics of the corners are utilized, meanwhile, in order to further manage the defect areas, the visual grade of each defect area relative to a three-dimensional model is introduced, and the repairing route butted by the multidirectional tracks is regulated according to the visual grade, so that corresponding repairing is carried out on the plurality of defect areas of the workpiece to be detected, the repairing of the corresponding defect areas of the workpiece to be detected under the corresponding attitude is guaranteed, and the detecting efficiency and the repairing efficiency of the workpiece to be detected are improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an industrial visual inspection method in an embodiment of the invention;
FIG. 2 is a schematic flow diagram of S11 in an industrial visual inspection method in an embodiment of the invention;
FIG. 3 is a schematic flow diagram of S12 in an industrial visual inspection method in an embodiment of the invention;
FIG. 4 is a schematic flow diagram of S13 in an industrial visual inspection method in an embodiment of the invention;
FIG. 5 is a schematic flow chart of S14 in an industrial visual inspection method in an embodiment of the invention;
FIG. 6 is a schematic flow diagram of S15 in an industrial visual inspection method in an embodiment of the invention;
FIG. 7 is a schematic diagram of the structural composition of an industrial visual inspection system in an embodiment of the present invention;
Fig. 8 is a hardware diagram of an electronic device, according to an example embodiment.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
Referring to fig. 1 to 8, an industrial visual inspection method is applied to a visual inspection scene; the industrial visual inspection method comprises the following steps:
Step S11: detecting a workpiece to be detected on a multidirectional track, and collecting a visual image of the workpiece to be detected;
step S12: determining corners based on visual images of the workpiece to be detected, and forming a plurality of corner images;
Step S13: defining a corresponding defect area according to the identification of the plurality of corner images;
Step S14: marking each defect area on a three-dimensional model corresponding to the workpiece to be detected, and judging the visual grade of each defect area relative to the three-dimensional model;
step S15: if the visual grade of each defect area relative to the three-dimensional model is lower than the preset visual grade, regulating and controlling the repair route butted by the multidirectional track according to the visual grade;
Step S16: in the repairing route, an attitude adjustment sequence is constructed based on a plurality of defect areas of the workpiece to be detected, and corresponding repairing is carried out when the attitude is adjusted each time.
According to the method, the corners are determined based on the visual images of the workpiece to be detected, the subsequent processing is carried out on the plurality of corner images, so that the corresponding defect areas are defined according to the identification of the plurality of corner images, the rapid investigation of the defect areas is realized, the corner features at the corners are not comprehensively investigated, the visual grade of each defect area relative to the three-dimensional model is introduced for further managing and controlling the defect areas, the repair route butted by the multidirectional tracks is regulated and controlled according to the visual grade, the corresponding repair is carried out on the plurality of defect areas of the workpiece to be detected, the repair of the corresponding defect areas of the workpiece to be detected under the corresponding postures is guaranteed, and the detection efficiency and the repair efficiency of the workpiece to be detected are improved.
In step S11, detecting a workpiece to be detected on a multidirectional track, and collecting a visual image of the workpiece to be detected;
in the embodiment of the application, the workpiece to be detected is conveyed by adopting the multidirectional rail, and simultaneously, the workpiece to be detected is shot under the conveying of the multidirectional rail so as to conveniently detect the workpiece to be detected on the multidirectional rail, so that the workpiece to be detected is dynamically detected, the visual image of the workpiece to be detected is conveniently collected, and the visual image of the workpiece to be detected is further processed.
In the implementation process of the invention, the specific steps can be as follows:
s111: when a workpiece to be detected enters a multi-directional track, acquiring an in-place signal output by the multi-directional track;
S112: triggering the multi-directional track to measure the weight of the workpiece to be measured according to the in-place signal, and determining the weight information of the workpiece to be measured;
In the embodiment of the application, when the workpiece to be detected enters the multidirectional rail, the workpiece to be detected abuts against the multidirectional rail by means of self gravity, so that in-place detection of the workpiece to be detected is realized, the downward pressing action of the workpiece to be detected on the multidirectional rail is fully utilized, meanwhile, in-place signals output by the multidirectional rail are collected, the weight measurement of the workpiece to be detected by the multidirectional rail is triggered according to the in-place signals, the weight information of the workpiece to be detected is determined, and then the weight information of the workpiece to be detected is introduced.
S113: matching a weight speed table based on weight information of a workpiece to be detected so as to determine the running speed of the multidirectional rail;
S114: in the running process of the multidirectional rail, shooting a workpiece to be detected based on a plurality of cameras, and collecting images of the workpiece to be detected at a plurality of different angles;
S115: determining a visual image of the workpiece to be measured based on the synthesis of a plurality of images at different angles, wherein the visual image of the workpiece to be measured contains images of different sides of the workpiece to be measured;
In the embodiment of the application, the weight information of the workpiece to be detected is introduced so as to be convenient for matching the weight speed meter based on the weight information of the workpiece to be detected, thereby adjusting the conveying speed of the multi-directional track according to different weights and further determining the running speed of the multi-directional track.
At this time, in the running process of the multidirectional rail, the workpiece to be detected is shot based on a plurality of cameras, and a plurality of images of different angles of the workpiece to be detected are collected so that different angle pictures of the workpiece to be detected can be displayed through the plurality of images, and further visual images of the workpiece to be detected can be determined based on the synthesis of the plurality of images of different angles, wherein the visual images of the workpiece to be detected contain images of different sides of the workpiece to be detected.
In step S12, corners are determined based on the visual image of the workpiece to be measured, and a plurality of corner images are formed;
In the embodiment of the application, the visual image of the workpiece to be detected is introduced so as to determine the corners in the visual image of the workpiece to be detected, so that the corners are rapidly screened out, and further, the corresponding images are acquired based on the positioning of the corners, so that a plurality of corner images are formed, and the corners images are rapidly processed.
In the implementation process of the invention, the specific steps can be as follows:
s121: acquiring a visual image of a workpiece to be measured;
s122: traversing the visual image of the workpiece to be detected, and highlighting the outline of the visual image of the workpiece to be detected;
S123: determining a serpentine segment based on the investigation of the outer contour and determining a corner based on the serpentine segment;
s124: the extending direction of the serpentine segment is captured and a plurality of corner images are formed along the extending direction of the serpentine segment.
In the embodiment of the application, the visual image of the workpiece to be measured is obtained and is further processed, at the moment, the visual image of the workpiece to be measured is traversed, the outline of the visual image of the workpiece to be measured is highlighted, the outline of the visual image of the workpiece to be measured is fully utilized, the snake line segment is determined based on the investigation of the outline, the corner is determined based on the snake line segment, and therefore, the quick positioning of the corner is realized through the snake line segment, and at the moment, the corner can be understood as a bent part of the workpiece to be measured and possibly a defect part.
Further, determining a serpentine segment based on the investigation of the outer contour and determining a corner based on the serpentine segment; the extending direction of the snake-shaped line segment is captured, and a plurality of corner images are formed along the extending direction of the snake-shaped line segment, so that the corner images are clear, and the subsequent control based on the corner images is facilitated.
In addition, the method for determining the corners based on the visual images of the workpiece to be detected, forming a plurality of corner images, and further comprises the following steps: obtaining a snake-shaped line segment; traversing the snake line segment and collecting a plurality of segmentation distances in the snake line segment; determining a segmentation level based on the plurality of segmentation distances; matching corresponding image learning models according to the segmentation level; corresponding corner images are formed based on the image learning model and the serpentine segments.
At this time, the snake line segment is further processed, a plurality of segmentation distances in the snake line segment are collected, the segmentation distances are utilized for operation, the optimal segmentation distance is defined based on the segmentation distances, so that the segmentation level is determined based on the optimal segmentation distance, the segmentation level is conveniently introduced, the mixing degree of the corner image is displayed, and the corresponding corner image is formed based on the image learning model and the snake line segment.
In step S13, defining a corresponding defect area according to the identification of the plurality of corner images;
In the embodiment of the application, the corners are determined based on the visual images of the workpiece to be detected, and the subsequent processing is carried out by using a plurality of corner images, so that the corresponding defect areas are defined according to the identification of the plurality of corner images, the rapid investigation of the defect areas is realized, the incomplete investigation is not realized, the corner characteristics of the corners are conveniently utilized, and meanwhile, the defect areas are further controlled.
In the implementation process of the invention, the specific steps can be as follows:
S131: collecting a plurality of corner images and defining the priority of the corner images;
s132: sequentially sequencing the plurality of corner images according to the priority level, and forming a corner image set;
In the embodiment of the application, a plurality of corner images are acquired, priority ranking is performed on the plurality of corner images, so that the plurality of corner images are ranked, the plurality of corner images are ranked in sequence according to the priority, and a corner image set is formed.
S133: integral identification is carried out according to the corner image set, and the mixing part corresponding to each corner image is determined;
s134: the mixed part in the corner image is defined as a defect part, and a corresponding defect area is formed according to the plurality of defect parts.
The method comprises the steps of carrying out integral identification on a corner image set so as to synchronously identify a plurality of corner images in the corner image set, avoiding omission of the corner images, further determining a mixed part corresponding to each corner image in the identification process, defining a defect part by the mixed part in the corner image, and forming a corresponding defect area according to the defect parts, so that the corresponding defect area is defined according to identification of the corner images, and quick investigation, but not comprehensive investigation, of the defect area is realized, and corner features at corners are conveniently utilized.
S14: marking each defect area on a three-dimensional model corresponding to the workpiece to be detected, and judging the visual grade of each defect area relative to the three-dimensional model;
In the embodiment of the application, each defect area is fixed in a grid, and each defect area is marked on a three-dimensional model corresponding to a workpiece to be detected, so that each defect area is integrally displayed in the three-dimensional model, the three-dimensional display of each defect area is ensured, the visual grade of each defect area relative to the three-dimensional model is further judged, at the moment, the visual grade is introduced, the influence of each defect area relative to the appearance is limited, and the fault tolerance of partial defects is carried out.
In the implementation process of the invention, the specific steps can be as follows:
S141: forming three-dimensional characteristics based on dynamic scanning of the workpiece to be detected;
s142: type optimization is carried out on the three-dimensional characteristics, and a three-dimensional model is formed under the optimization;
In the embodiment of the application, the workpiece to be detected is dynamically scanned so as to form the three-dimensional feature based on the dynamic scanning of the workpiece to be detected, further, the three-dimensional feature is optimized in type, a three-dimensional model is formed under the optimization, the three-dimensional feature is optimized through the introduction of the type, and the further improvement of the three-dimensional model is ensured.
S143: collecting each defect area and defining the space coordinates of each defect area relative to the three-dimensional model;
s144: marking each defective region on the stereoscopic model based on spatial coordinates of each defective region relative to the stereoscopic model;
S145: in the stereoscopic model, each defective area is subjected to dark treatment so as to reduce the brightness of each defective area;
s146: and when the brightness of each defect area accords with the preset brightness, carrying out visual identification on each defect area after the dark treatment so as to define the visual grade of each defect area relative to the stereoscopic model.
In the embodiment of the application, the spatial coordinates of each defect area relative to the stereoscopic model are positioned, so that each defect area is positioned, the spatial coordinates of each defect area relative to the stereoscopic model are utilized, and each defect area is marked on the stereoscopic model based on the spatial coordinates of each defect area relative to the stereoscopic model, so that stereoscopic presentation is performed on each defect area.
Further, in the stereoscopic model, each defective area is subjected to dark treatment so as to reduce the brightness of each defective area; when the brightness of each defect area accords with the preset brightness, carrying out visual identification on each defect area after the dark treatment to define the visual grade of each defect area relative to the stereoscopic model, at the moment, introducing the visual grade, thereby limiting the influence of each defect area relative to the appearance, and carrying out fault tolerance on part of defects.
S15: if the visual grade of each defect area relative to the three-dimensional model is lower than the preset visual grade, regulating and controlling the repair route butted by the multidirectional track according to the visual grade;
in the implementation process of the invention, the specific steps can be as follows:
s151: collecting the visual grade of each defect area relative to the stereoscopic model;
S152: comparing the visual grade of each defect area relative to the stereoscopic model with a preset visual grade;
s153: if the visual grade of each defect area relative to the stereoscopic model is lower than the preset visual grade, constructing a virtual scene for each defect area, and observing each defect area in the virtual scene;
s154: defining a perception coefficient of each defect region based on a presentation area of each defect region relative to the virtual scene;
S155: associating the perception coefficient with the multidirectional track, and triggering the direction change of the multidirectional track to regulate and control the repair route which is butted by the multidirectional track;
In the embodiment of the application, the visual grade of each defect area relative to the stereoscopic model is acquired, and the visual grade is compared with the preset visual grade, so that the control is further carried out according to the comparison result between the visual grade and the preset visual grade.
Further, if the visual grade of each defect area relative to the stereoscopic model is lower than a preset visual grade, constructing a virtual scene for each defect area, and observing each defect area in the virtual scene; at the moment, a virtual scene is introduced, so that each defect area is conveniently observed in the virtual scene, and the visual test of each defect area is realized.
At this time, a perception coefficient of each defective area is defined based on a presentation area of each defective area with respect to the virtual scene; the perceived difficulty is presented on the side of the perceived coefficient, so that the perceived coefficient is related to the multidirectional track, and the direction change of the multidirectional track is triggered to regulate and control the repair route which the multidirectional track is butted with.
S16: in the repairing route, constructing an attitude adjustment sequence based on a plurality of defect areas of the workpiece to be detected, and carrying out corresponding repairing when the attitude is adjusted each time;
At this time, in the repair route, a plurality of defect areas of the workpiece to be tested are fixed; collecting space positions among a plurality of defect areas, and defining adjustment priorities for defect areas in the defect areas; sequencing according to the adjustment priority to stop the gesture adjustment sequence of the workpiece to be tested, and presenting a corresponding defect area in the corresponding gesture; checking the orientation of the defect area and adjusting the defect area along the upward direction; at each adjusted pose, multiple defective regions are repaired in turn .
According to the method, the corners are determined based on the visual images of the workpiece to be detected, the subsequent processing is carried out on the plurality of corner images, so that the corresponding defect areas are defined according to the identification of the plurality of corner images, the rapid investigation of the defect areas is realized, the corner features at the corners are not comprehensively investigated, the visual grade of each defect area relative to the three-dimensional model is introduced for further managing and controlling the defect areas, the repair route butted by the multidirectional tracks is regulated and controlled according to the visual grade, the corresponding repair is carried out on the plurality of defect areas of the workpiece to be detected, the repair of the corresponding defect areas of the workpiece to be detected under the corresponding postures is guaranteed, and the detection efficiency and the repair efficiency of the workpiece to be detected are improved.
Examples
Referring to fig. 7, fig. 7 is a schematic structural diagram of an industrial visual inspection system according to an embodiment of the invention.
As shown in fig. 7, an industrial visual inspection system, comprising:
The acquisition module 21 is used for detecting the workpiece to be detected on the multidirectional track and acquiring a visual image of the workpiece to be detected;
A corner image module 22 for determining corners based on visual images of the workpiece to be measured and forming a plurality of corner images;
a defect area module 23 for defining a corresponding defect area according to the identification of the plurality of corner images;
the visual grade module 24 is used for marking each defect area on the three-dimensional model corresponding to the workpiece to be detected and judging the visual grade of each defect area relative to the three-dimensional model;
the repair route module 25 is configured to adjust and control a repair route to which the multidirectional rail is docked according to the visual grade if the visual grade of each defective area relative to the stereoscopic model is lower than a preset visual grade;
And the repairing module 26 is used for constructing an attitude adjustment sequence based on a plurality of defect areas of the workpiece to be detected in the repairing route and carrying out corresponding repairing when the attitude is adjusted each time.
Examples
Referring to fig. 8, an electronic device 40 according to this embodiment of the present invention is described below with reference to fig. 8. The electronic device 40 shown in fig. 8 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 8, the electronic device 40 is in the form of a general purpose computing device. Components of electronic device 40 may include, but are not limited to: the at least one processing unit 41, the at least one memory unit 42, a bus 43 connecting the different system components, including the memory unit 42 and the processing unit 41.
Wherein the storage unit stores program code that is executable by the processing unit 41 such that the processing unit 41 performs the steps according to various exemplary embodiments of the present invention described in the above-described "example methods" section of the present specification.
The memory unit 42 may include readable media in the form of volatile memory units, such as Random Access Memory (RAM) 421 and/or cache memory 422, and may further include Read Only Memory (ROM) 423.
The storage unit 42 may also include a program/utility 424 having a set (at least one) of program modules 425, such program modules 425 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
The bus 43 may be one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
Electronic device 40 may also communicate with one or more external devices (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 40, and/or any device (e.g., router, modem, etc.) that enables electronic device 40 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 44. Also, electronic device 40 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, via network adapter 45. As shown in fig. 8, the network adapter 45 communicates with other modules of the electronic device 40 over the bus 43. It should be appreciated that although not shown in fig. 8, other hardware and/or software modules may be used in connection with electronic device 40, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup planning systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access Memory (RAM, randomAccess Memory), magnetic disk or optical disk, and the like. And which stores computer program instructions which, when executed by a computer, cause the computer to perform a method according to the above.
In addition, the industrial visual inspection method and system provided by the embodiments of the present invention are described in detail, and specific examples should be adopted to illustrate the principles and embodiments of the present invention, and the description of the above examples is only used to help understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. An industrial visual inspection method is characterized by being applied to visual inspection scenes;
the industrial visual inspection method comprises the following steps:
detecting a workpiece to be detected on a multidirectional track, and collecting a visual image of the workpiece to be detected;
Determining corners based on visual images of the workpiece to be detected, and forming a plurality of corner images;
Defining a corresponding defect area according to the identification of the plurality of corner images;
marking each defect area on a three-dimensional model corresponding to the workpiece to be detected, and judging the visual grade of each defect area relative to the three-dimensional model;
if the visual grade of each defect area relative to the three-dimensional model is lower than the preset visual grade, regulating and controlling the repair route butted by the multidirectional track according to the visual grade;
In the repairing route, an attitude adjustment sequence is constructed based on a plurality of defect areas of the workpiece to be detected, and corresponding repairing is carried out when the attitude is adjusted each time.
2. The industrial vision inspection method of claim 1, wherein the inspecting the workpiece to be inspected on the multi-directional track and collecting the visual image of the workpiece to be inspected comprises:
when a workpiece to be detected enters a multi-directional track, acquiring an in-place signal output by the multi-directional track;
triggering the multi-directional track to measure the weight of the workpiece to be measured according to the in-place signal, and determining the weight information of the workpiece to be measured;
Matching a weight speed table based on weight information of a workpiece to be detected so as to determine the running speed of the multidirectional rail;
In the running process of the multidirectional rail, shooting a workpiece to be detected based on a plurality of cameras, and collecting images of the workpiece to be detected at a plurality of different angles;
A visual image of the workpiece to be measured is determined based on a combination of the plurality of images at different angles, wherein the visual image of the workpiece to be measured contains images of different sides of the workpiece to be measured.
3. The method of claim 1, wherein the determining the corners based on the visual image of the workpiece to be inspected and forming a plurality of corner images comprises:
Acquiring a visual image of a workpiece to be measured;
Traversing the visual image of the workpiece to be detected, and highlighting the outline of the visual image of the workpiece to be detected;
Determining a serpentine segment based on the investigation of the outer contour and determining a corner based on the serpentine segment;
The extending direction of the serpentine segment is captured and a plurality of corner images are formed along the extending direction of the serpentine segment.
4. The industrial vision inspection method of claim 3, wherein the determining the corners based on the visual image of the workpiece to be inspected and forming a plurality of corner images further comprises:
obtaining a snake-shaped line segment;
Traversing the snake line segment and collecting a plurality of segmentation distances in the snake line segment;
determining a segmentation level based on the plurality of segmentation distances;
Matching corresponding image learning models according to the segmentation level;
corresponding corner images are formed based on the image learning model and the serpentine segments.
5. The method of claim 4, wherein defining the corresponding defect area based on the identification of the plurality of corner images comprises:
collecting a plurality of corner images and defining the priority of the corner images;
Sequentially sequencing the plurality of corner images according to the priority level, and forming a corner image set;
Integral identification is carried out according to the corner image set, and the mixing part corresponding to each corner image is determined;
the mixed part in the corner image is defined as a defect part, and a corresponding defect area is formed according to the plurality of defect parts.
6. The method for visual inspection of an industrial object according to claim 5, wherein marking each defective area on the stereoscopic model corresponding to the workpiece to be inspected and judging the visual grade of each defective area with respect to the stereoscopic model comprises:
forming three-dimensional characteristics based on dynamic scanning of the workpiece to be detected;
Type optimization is carried out on the three-dimensional characteristics, and a three-dimensional model is formed under the optimization;
Collecting each defect area and defining the space coordinates of each defect area relative to the three-dimensional model;
each defective region is marked on the stereoscopic model based on its spatial coordinates relative to the stereoscopic model.
7. The method for visual inspection of an industrial object according to claim 6, wherein marking each defective area on a stereoscopic model corresponding to the workpiece to be inspected and judging a visual grade of each defective area with respect to the stereoscopic model, further comprises:
In the stereoscopic model, each defective area is subjected to dark treatment so as to reduce the brightness of each defective area;
And when the brightness of each defect area accords with the preset brightness, carrying out visual identification on each defect area after the dark treatment so as to define the visual grade of each defect area relative to the stereoscopic model.
8. The method according to claim 7, wherein if the visibility level of each defective area with respect to the stereoscopic model is lower than a preset visibility level, adjusting the repair route to which the multi-directional track is docked according to the visibility level, comprising:
Collecting the visual grade of each defect area relative to the stereoscopic model;
comparing the visual grade of each defect area relative to the stereoscopic model with a preset visual grade;
if the visual grade of each defect area relative to the stereoscopic model is lower than the preset visual grade, constructing a virtual scene for each defect area, and observing each defect area in the virtual scene;
defining a perception coefficient of each defect region based on a presentation area of each defect region relative to the virtual scene;
and associating the perception coefficient with the multidirectional track, and triggering the direction change of the multidirectional track to regulate and control the repair route which is butted by the multidirectional track.
9. The industrial vision inspection method according to claim 8, wherein in the repair route, an attitude adjustment sequence is constructed based on a plurality of defective areas of the workpiece to be inspected, and corresponding repairs are performed at each adjusted attitude, comprising:
In the repairing route, a plurality of defect areas of the workpiece to be tested are fixed;
Collecting space positions among a plurality of defect areas, and defining adjustment priorities for defect areas in the defect areas;
sequencing according to the adjustment priority to stop the gesture adjustment sequence of the workpiece to be tested, and presenting a corresponding defect area in the corresponding gesture;
Checking the orientation of the defect area and adjusting the defect area along the upward direction;
at each adjusted pose, the multiple defective areas are repaired in sequence.
10. An industrial visual inspection system for use in an industrial visual inspection method according to any one of claims 1 to 9, the industrial visual inspection system comprising:
the acquisition module is used for detecting the workpiece to be detected on the multidirectional track and acquiring a visual image of the workpiece to be detected;
the corner image module is used for determining corners based on visual images of the workpiece to be detected and forming a plurality of corner images;
A defect area module for defining a corresponding defect area according to the identification of the plurality of corner images;
the visual grade module is used for marking each defect area on the three-dimensional model corresponding to the workpiece to be detected and judging the visual grade of each defect area relative to the three-dimensional model;
The repair route module is used for regulating and controlling the repair route which is butted by the multidirectional track according to the visual grade if the visual grade of each defect area relative to the stereoscopic model is lower than the preset visual grade;
And the repair module is used for constructing an attitude adjustment sequence based on a plurality of defect areas of the workpiece to be detected in the repair route and carrying out corresponding repair when the attitude is adjusted each time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410246055.4A CN118112005A (en) | 2024-03-05 | 2024-03-05 | Industrial visual detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410246055.4A CN118112005A (en) | 2024-03-05 | 2024-03-05 | Industrial visual detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118112005A true CN118112005A (en) | 2024-05-31 |
Family
ID=91213814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410246055.4A Pending CN118112005A (en) | 2024-03-05 | 2024-03-05 | Industrial visual detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118112005A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118967664A (en) * | 2024-10-12 | 2024-11-15 | 广东力创信息技术有限公司 | Defect detection method and system for urban pipe network |
| CN119260721A (en) * | 2024-10-29 | 2025-01-07 | 北京和崎精密科技有限公司 | A vibration sensor-based manipulator mis-collision control method and system |
-
2024
- 2024-03-05 CN CN202410246055.4A patent/CN118112005A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118967664A (en) * | 2024-10-12 | 2024-11-15 | 广东力创信息技术有限公司 | Defect detection method and system for urban pipe network |
| CN118967664B (en) * | 2024-10-12 | 2024-12-10 | 广东力创信息技术有限公司 | Defect detection method and system for urban pipe network |
| CN119260721A (en) * | 2024-10-29 | 2025-01-07 | 北京和崎精密科技有限公司 | A vibration sensor-based manipulator mis-collision control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109949305B (en) | Product surface defect detection method and device and computer equipment | |
| CN118112005A (en) | Industrial visual detection method and system | |
| CN109871895B (en) | Method and device for detecting defects of circuit board | |
| CN115578326A (en) | Road disease identification method, system, equipment and storage medium | |
| CN113838044B (en) | Panel defect detection method and system based on machine vision | |
| JP2001256480A (en) | Automatic image classification method and apparatus | |
| CN118014779B (en) | Acceptance method and device for assembled building, electronic equipment and storage medium | |
| JP2008175549A (en) | Defect detection device and method | |
| CN111428374A (en) | Part defect detection method, device, equipment and storage medium | |
| CN112884743B (en) | Detection method and device, detection equipment and storage medium | |
| CN115937147A (en) | Defect detection parameter determination method, device, equipment and storage medium | |
| CN119125167A (en) | A photovoltaic aluminum frame surface defect detection system | |
| CN115035092A (en) | Image-based bottle detection method, device, equipment and storage medium | |
| CN116465315A (en) | Automatic screen quality detection method and system | |
| US7538750B2 (en) | Method of inspecting a flat panel display | |
| JP2002140694A (en) | Image processor, its method and recording medium with recorded image processing program | |
| CN105572133A (en) | Flaw detection method and device | |
| Tang et al. | Multidamage identification in high-resolution concrete bridge component imagery based on deep learning | |
| CN114627093A (en) | Quality inspection method and device, quality inspection system, electronic equipment, readable medium | |
| CN117788444A (en) | SMT patch offset detection method, SMT patch offset detection device and SMT patch offset detection system | |
| CN118096712A (en) | Defect identification method and system based on visual processing | |
| CN117495846A (en) | Image detection method, device, electronic equipment and storage medium | |
| JP2006292615A (en) | Appearance inspection apparatus, appearance inspection method, program for causing computer to function as appearance inspection apparatus, and recording medium | |
| CN115222669A (en) | Method for auxiliary judgment of product grade by automatic defect area calculation of ADC (analog to digital converter) system | |
| TWI807854B (en) | Method for detecting defects, computer device and storage medium |
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 |