CN110288651A - Tolerance visible detection method, device and the calculating equipment of large-size workpiece - Google Patents
Tolerance visible detection method, device and the calculating equipment of large-size workpiece Download PDFInfo
- Publication number
- CN110288651A CN110288651A CN201910542808.5A CN201910542808A CN110288651A CN 110288651 A CN110288651 A CN 110288651A CN 201910542808 A CN201910542808 A CN 201910542808A CN 110288651 A CN110288651 A CN 110288651A
- Authority
- CN
- China
- Prior art keywords
- image
- size
- tolerance
- workpiece
- target site
- 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
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- 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
Abstract
The invention discloses a kind of tolerance visible detection methods of large-size workpiece, suitable for being executed in calculating equipment, the method includes the steps: the image of certain target site in large-size workpiece is obtained, and extracts the interesting target region comprising mounting hole from the image；The sub-pixel edge of target site and target area is extracted respectively, and Contour extraction is carried out to the sub-pixel edge extracted, obtains multiple feature contours；Linear edge and/or oval arc-shaped edge fitting are carried out to multiple feature contours, obtain line segment aggregate and/or oval arc set；At least one characteristic point of line segment aggregate and/or oval arc set is extracted, and calculates the workpiece coordinate of each characteristic point；And target site and the wherein morpheme size and tolerance of each mounting hole are calculated according to the workpiece coordinate of each characteristic point.
Description
Technical field
The present invention relates to the tolerance visible detection method of technical field of vision detection more particularly to a kind of large-size workpiece,
Device and calculating equipment.
Background technique
Size and the geometric tolerance detection of large-size workpiece have higher and higher demand in mechanical manufacturing field.Especially
It is even more important to the position detection of workpiece surface mounting hole.The detection method of mainstream includes artificial and three-coordinates measuring machine at present.
Manual method needs to measure using dedicated detection utensil, and there are at high cost, inefficiency, testing result inaccuracy, nothing
Method realizes the problems such as full inspection.And the price is very expensive for the high three-coordinates measuring machine of measurement accuracy, troublesome maintenance, using having
Limit.
It contains much information since machine vision technique has many advantages, such as non-contact, acquisition, cost performance is high, easy to operate very much
Scholar is applied to size detection field, however at present by and its vision technique be applied to the area research of large scale inspection but very
It is few.The dimensional measurement main stream approach of large-size workpiece is the sequence image that large scale part is shot based on camera, and image is used to spell
The method connect obtains the panorama sketch of large-scale part, finally result and mark according to corresponding to each project that the panorama sketch is demarcated
The size of actual size corresponding to fixed every pixel, obtains the size of large-scale part to be measured.But the detection accuracy of this method is deposited
In cumulative errors, detection accuracy is inadequate, influences the accuracy of testing result.
Accordingly, it is desirable to provide a kind of higher part size detecting method to be measured of detection accuracy.
Summary of the invention
For this purpose, the present invention provides a kind of tolerance visible detection method of large-size workpiece, device and equipment is calculated, with solution
Certainly or at least alleviate above there are the problem of.
According to an aspect of the invention, there is provided a kind of tolerance visible detection method of large-size workpiece, suitable for counting
It calculates and is executed in equipment, the method comprising the steps of: obtaining the image of certain target site in large-size workpiece, and extracted from the image
Interesting target region comprising mounting hole；The sub-pixel edge of target site and target area is extracted respectively, and to extracting
Sub-pixel edge carry out Contour extraction, obtain multiple feature contours；Linear edge and/or ellipse is carried out to multiple feature contours
Circular arc type edge fitting obtains line segment aggregate and/or oval arc set；Extract line segment aggregate and/or oval arc set at least
One characteristic point, and calculate the workpiece coordinate of each characteristic point；And according to the workpiece coordinate of each characteristic point calculate target site and
The wherein morpheme size and tolerance of each mounting hole.
Optionally, in tolerance visible detection method according to the present invention, comprehensive large-size workpiece is further comprised the steps of: not
With the target site and wherein morpheme size and tolerance of each mounting hole, calculates the morpheme size and tolerance of large-size workpiece.
Optionally, in tolerance visible detection method according to the present invention, the mesh comprising mounting hole is extracted from the image
The step of marking region includes: that the image of target site is converted to gray level image, carries out adaptive threshold point to the gray level image
It cuts, and the extracting target from images region after segmentation.
Optionally, in tolerance visible detection method according to the present invention, further comprise the steps of: to the image of target site into
Line distortion correction, and gray level image is filtered and Morphological scale-space.
Optionally, in tolerance visible detection method according to the present invention, profile is carried out to the sub-pixel edge extracted
The step of tracking includes: to carry out Freenman chain code following to the sub-pixel edge extracted, and filter noise edge, is obtained
Multiple feature contours.
Optionally, in tolerance visible detection method according to the present invention, filter noise edge the step of include: to set respectively
Determine area threshold and length threshold, and real area is less than the area threshold or physical length less than the length threshold
Feature contour is set as noise edge.
Optionally, in tolerance visible detection method according to the present invention, setting boundary rectangle length-width ratio is further comprised the steps of:
First threshold and second threshold, and by practical length-width ratio be greater than second threshold feature contour be set as Linear edge, with
And the feature contour that practical length-width ratio is less than first threshold is set as oval arc-shaped edge.
Optionally, in tolerance visible detection method according to the present invention, to multiple feature contours carry out Linear edge/
Or the step of circular line section fitting includes: to carry out Linear edge to the feature contour for belonging to Linear edge to reject coarse mistake
Not good enough least square method fitting, obtains line segment aggregate；And/or elliptic arc is carried out to the feature contour for belonging to oval arc-shaped edge
The least square method fitting of gross error point is rejected at type edge, obtains oval arc set.
Optionally, in tolerance visible detection method according to the present invention, the characteristic point of oval arc set includes elliptical
Central point and each vertex, the characteristic point of line segment aggregate include two endpoints and the midpoint of each line segment in the line segment aggregate.
Optionally, in tolerance visible detection method according to the present invention, certain target site of large-size workpiece is obtained
The step of image includes: the image that target site is acquired from camera, and obtains camera localization machine when shooting the image
The tool coordinates system of device people's measuring head；Wherein, camera is measured by positioning robot according to distance measuring sensor when shooting the image
Range information adjust the operating distance of industrial camera, to guarantee the imaging plane of camera and the face to be detected of large-size workpiece
In parallel.
Optionally, it in tolerance visible detection method according to the present invention, calculates in equipment and is stored with tool coordinates and work
The transformational relation of part coordinate, the step of calculating the workpiece coordinate of each characteristic point include: according to the image coordinate of each characteristic point come really
Determine its tool coordinates, and calculates the workpiece coordinate of each characteristic point according to the transformational relation.
Optionally, in tolerance visible detection method according to the present invention, the origin and image coordinate system of tool coordinates system
Origin be overlapped, and the xOy plane of tool coordinates system is overlapped with the plane where image coordinate system；The transformational relation are as follows:
Ci=R1·(Q·Vi)+T1
Wherein, CiAnd ViIt is the workpiece coordinate and tool coordinates of ith feature point, T respectively1And R1It is to shoot the mesh respectively
For tool coordinates system to the translation matrix and spin matrix of workpiece coordinate system, Q is pixel equivalent matrix, R when marking the image at positionhWith
RvIt is the laterally and longitudinally pixel equivalent of camera respectively.
Optionally, in tolerance vision inspection apparatus according to the present invention, target site and the wherein size of each mounting hole
Morpheme and tolerance include the outer dimension of target site, in target site the location dimension and outer dimension of each mounting hole and
The deviation of each size.
Optionally, in tolerance vision inspection apparatus according to the present invention, outside the outer dimension combination workpiece of target site
The central point of profile line segment is calculated；Each vertex of the outer dimension combination mounting hole of mounting hole is calculated；Mounting hole
The center point coordinate and elliptical center point coordinate of location dimension combination reference data line segment profile are calculated.
Optionally, it in tolerance visible detection method according to the present invention, further comprises the steps of: and is sized measurement parameter
Mark, the mark include workpiece external dimension mark, the location dimension of each mounting hole mark and outer dimension mark, and by each ruler
Very little mark is associated storage with the correspondingly-sized value being calculated.
According to another aspect of the invention, the tolerance visible detection method of another large-size workpiece is provided, suitable for counting
It calculates and is executed in equipment, the method comprising the steps of: obtaining the sequence image of large-size workpiece, which includes large-size workpiece
Different parts image；The tolerance visible detection method of large-size workpiece as described above is respectively adopted to every frame sequence image
Tolerance vision-based detection is carried out, the morpheme size and tolerance of different parts are obtained；And the morpheme size and public affairs of comprehensive all sites
Difference calculates the morpheme size and tolerance of large-size workpiece.
According to another aspect of the invention, a kind of tolerance vision inspection apparatus of large-size workpiece is provided, suitable for residing in
It calculates in equipment, which includes: target area extraction module, suitable for obtaining the image of certain target site in large-size workpiece,
And the interesting target region comprising mounting hole is extracted from the image；Feature contour extraction module, suitable for extracting target respectively
The sub-pixel edge at position and target area, and Contour extraction is carried out to the sub-pixel edge extracted, obtain multiple feature wheels
It is wide；Feature contour fitting module is suitable for carrying out Linear edge/to multiple feature contours or circular line section is fitted, obtains line
Duan Jihe and/or oval arc set；Feature point extraction module, suitable for extracting at least the one of line segment aggregate and/or oval arc set
A characteristic point, and calculate the workpiece coordinate of each characteristic point；And morpheme size computing module, suitable for the workpiece according to each characteristic point
Coordinate calculates target site and the wherein morpheme size and tolerance of each mounting hole.
Optionally, in tolerance vision inspection apparatus according to the present invention, morpheme size computing module is further adapted for comprehensive big
The morpheme size and tolerance of the different target position of dimension workpiece and wherein each mounting hole, to calculate the morpheme ruler of large-size workpiece
Very little and tolerance.
Optionally, in tolerance vision inspection apparatus according to the present invention, target area extraction module is suitable for target portion
The image of position is converted to gray level image, carries out adaptive threshold fuzziness to the gray level image, and should from extracting in image after segmentation
Target area.
Optionally, in tolerance vision inspection apparatus according to the present invention, target area extraction module is further adapted for target
The image at position carries out distortion correction, and is filtered to gray level image and Morphological scale-space.
According to another aspect of the invention, a kind of calculating equipment is provided, comprising: one or more processors；Memory；With
And one or more programs, wherein one or more programs are stored in memory and are configured as by one or more processors
It executes, one or more programs realize the tolerance visible detection method of large-size workpiece as described above when being executed by processor
Step.
According to another aspect of the invention, a kind of computer readable storage medium storing one or more programs is provided,
One or more programs include instruction, which realizes the tolerance of large-size workpiece as described above when executed by a computing apparatus
The step of visible detection method.
According to the technique and scheme of the present invention, it is emerging that the sense comprising mounting hole is extracted from the image of large-size workpiece target site
Interesting target area, and carry out edge fitting by multiple feature contours to target site and target area and obtain line segment aggregate
And/or oval arc set.Later, it is calculated according to the workpiece coordinate of each characteristic point in the line segment aggregate and/or oval arc set
The size morpheme and tolerance of target site and each mounting hole.This method accurately calculates each target site by image procossing
Morpheme size and tolerance.
Moreover, the present invention can also obtain the image-generation sequence image of all target sites of the workpiece, and to every frame sequence
Column image is handled, and morpheme size and tolerance that target site is corresponded in every frame image are obtained.All sequences figure is integrated later
The result of picture obtains the morpheme size and tolerance of the large-size workpiece.The method avoids marked based on spliced panorama sketch
The accumulative precision problem for determining projects method can obtain the accurate morpheme size at workpiece and its each position, and image processing method
Method improves workpiece size detection efficiency.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
To the accomplishment of the foregoing and related purposes, certain illustrative sides are described herein in conjunction with following description and drawings
Face, these aspects indicate the various modes that can practice principles disclosed herein, and all aspects and its equivalent aspect
It is intended to fall in the range of theme claimed.Read following detailed description in conjunction with the accompanying drawings, the disclosure it is above-mentioned
And other purposes, feature and advantage will be apparent.Throughout the disclosure, identical appended drawing reference generally refers to identical
Component or element.
Fig. 1 shows the structure chart of tolerance vision detection system 100 according to an embodiment of the invention；
Fig. 2 shows the structure charts according to an embodiment of the invention for calculating equipment 200；
Fig. 3 shows the stream of the tolerance visible detection method 300 of the large-size workpiece according to an embodiment of the present invention
Cheng Tu；
Fig. 4 a to Fig. 4 d respectively illustrates the sequence image of the multiple target sites of certain large-size workpiece；
Fig. 5 a to Fig. 5 e respectively illustrates the schematic diagram positioned to the mounting hole of target site in Fig. 5 c；
Fig. 6 and Fig. 7 respectively illustrates the tolerance vision-based detection of the large-size workpiece according to a further embodiment of the invention
The flow chart of method 600 and 700；And
Fig. 8 shows the structure of the tolerance vision inspection apparatus 800 of large-size workpiece according to an embodiment of the invention
Figure.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Fig. 1 shows the structure chart of tolerance vision detection system 100 of the invention.As shown in Figure 1, system 100 includes fixed
Position robot 110, acquisition module and calculating equipment.Acquisition module is mounted on positioning robot 110, and acquisition module includes camera
120 and distance measuring sensor, and camera 120 and distance measuring sensor with calculate equipment and be connected.
The drive acquisition module of positioning robot 110 moves to the predetermined position in face to be detected, so that camera 120 is being pre-positioned
The face to be detected set on large-size workpiece is shot, and the image in face to be detected is obtained.According to one embodiment, machine is positioned
People 110 can be mechanical arm, and the acquisition module is fixedly mounted in the end of the mechanical arm.The arm exhibition of mechanical arm can be 1420mm,
It is certainly not limited to this, or other numerical value.
Camera 120 can be industrial camera, such as CCD camera, CMOS camera, be certainly not limited to this.Camera 120 is carrying out
The camera distortion correction that Zhang Zhengyou calibration method can be carried out before Image Acquisition, to avoid stationary lens because of the accuracy of manufacture and assembling work
The introduced lens distortion of the deviation of skill.Distance measuring sensor can be laser range sensor, drive in positioning robot 110
The border movement in lower edge face to be detected, and record camera to face to be detected range data.Positioning robot 110 is according to this distance
Data are adjusted the distance in camera 120 to face to be detected, make the imaging plane of camera 120 and the tested surface of large-size workpiece
In parallel, guarantee to collect the clear image in face to be detected.The Image Acquisition mode of this cooperation laser ranging also can avoid
The perspective distortion problem of " near big and far smaller " is caused because imaging plane and tested surface are not parallel, improves the quality of Image Acquisition.
The tool coordinates system of 120 acquired image of camera and camera 120 when acquiring the image can be obtained by calculating equipment,
And the size morpheme and tolerance of part to be measured are determined according to acquired image and tool coordinates system.Calculating equipment can also be according to survey
The range data measured away from sensor determines the depth of parallelism or verticality of tested surface.Part to be measured generally includes multiple to be detected
Several mounting holes are distributed on each tested surface in face, which can be circular hole, square hole, threaded hole, pilot hole etc., this
The shape and structure of invention device to hole are with no restrictions.The structure size of part to be measured may include outer dimension and location dimension.Positioning rule
It is very little to refer to the size between two structures on part to be measured, such as the size between two holes, thus true according to location dimension
The relative position in the hole on fixed part to be measured.Outer dimension refers to size of structure on part to be measured itself, such as workpiece overall dimensions,
The own dimensions such as diameter, the radius in hole.Geometric tolerance generally includes the features such as straightness, the depth of parallelism, verticality, gradient.
Fig. 2 shows the structural block diagrams according to an embodiment of the invention for calculating equipment 200.In basic configuration 202
In, it calculates equipment 200 and typically comprises system storage 206 and one or more processor 204.Memory bus 208 can
For the communication between processor 204 and system storage 206.
Depending on desired configuration, processor 204 can be any kind of processing, including but not limited to: microprocessor
(μ P), microcontroller (μ C), digital information processor (DSP) or any combination of them.Processor 204 may include such as
The cache of one or more rank of on-chip cache 210 and second level cache 212 etc, processor core
214 and register 216.Exemplary processor core 214 may include arithmetic and logical unit (ALU), floating-point unit (FPU),
Digital signal processing core (DSP core) or any combination of them.Exemplary Memory Controller 218 can be with processor
204 are used together, or in some implementations, and Memory Controller 218 can be an interior section of processor 204.
Depending on desired configuration, system storage 206 can be any type of memory, including but not limited to: easily
The property lost memory (RAM), nonvolatile memory (ROM, flash memory etc.) or any combination of them.System storage
Device 206 may include operating system 220, one or more is using 222 and program data 224.In some embodiments,
It may be arranged to be operated using program data 224 on an operating system using 222.Program data 224 includes instruction, in root
According in calculating equipment 200 of the invention, program data 224 includes the tolerance visible detection method for executing large-size workpiece
300,600 and/or 700 instruction.
Calculating equipment 200 can also include facilitating from various interface equipments (for example, output equipment 242, Peripheral Interface
244 and communication equipment 246) to basic configuration 102 via the communication of bus/interface controller 230 interface bus 240.Example
Output equipment 242 include graphics processing unit 248 and audio treatment unit 250.They can be configured as facilitate via
One or more port A/V 252 is communicated with the various external equipments of such as display or loudspeaker etc.Outside example
If interface 244 may include serial interface controller 254 and parallel interface controller 256, they, which can be configured as, facilitates
Via one or more port I/O 258 and such as input equipment (for example, keyboard, mouse, pen, voice-input device, touch
Input equipment) or the external equipment of other peripheral hardwares (such as printer, scanner etc.) etc communicated.Exemplary communication is set
Standby 246 may include network controller 160, can be arranged to convenient for via one or more communication port 264 and one
A or multiple other calculate communication of the equipment 262 by network communication link.
Network communication link can be an example of communication media.Communication media can be usually presented as in such as carrier wave
Or computer readable instructions, data structure, program module in the modulated data signal of other transmission mechanisms etc, and can
To include any information delivery media." modulated data signal " can such signal, one in its data set or more
It is a or it change can the mode of encoded information in the signal carry out.As unrestricted example, communication media can be with
Wired medium including such as cable network or private line network etc, and it is such as sound, radio frequency (RF), microwave, infrared
(IR) the various wireless mediums or including other wireless mediums.Term computer-readable medium used herein may include depositing
Both storage media and communication media.
Calculating equipment 200 can be implemented as server, such as file server, database server, application program service
Device and WEB server etc. also can be implemented as a part of portable (or mobile) electronic equipment of small size, these electronic equipments
It can be such as cellular phone, personal digital assistant (PDA), personal media player device, wireless network browsing apparatus, individual
Helmet, application specific equipment or may include any of the above function mixing apparatus.Calculating equipment 200 can also be real
It is now the personal computer for including desktop computer and notebook computer configuration.In some embodiments, 200 quilt of equipment is calculated
It is configured to execute the tolerance visible detection method 300,600 and/or 700 of large-size workpiece.
Fig. 3 shows the process of the tolerance visible detection method 300 of large-size workpiece according to an embodiment of the invention
Schematic diagram.Method 300 executes in calculating equipment, such as executes in calculating equipment 200, with the morpheme size to large-size workpiece
It is detected with tolerance.
As shown in figure 3, method 300 starts from step S310.In step s310, certain target site in large-size workpiece is obtained
Image, and from the image extract include mounting hole interesting target region.Mounting hole for example can be threaded hole and dress
Distribution etc..
In practical applications, large-size workpiece can be divided into multiple target sites, obtain the image of each target site
Sequence image is constituted, each target site might have mounting hole.Image procossing is carried out to every frame image respectively, can be obtained each
The size morpheme and tolerance of target site and wherein mounting hole, and integrate all target sites and wherein the size shape of each mounting hole
Position and tolerance, to calculate the size morpheme and tolerance of the large-size workpiece.As 4a to 4d respectively illustrates certain subway shield door left side
The sequence image of lateral brace respectively corresponds four target sites from top to bottom.
In general, camera is when carrying out Image Acquisition, the image at the multiple positions of the workpiece successively can be acquired in position in order, this
The lower edges position at multiple positions can connect just, can also be overlapped certain distance, the invention is not limited in this regard.In addition, to
It surveys part and generally includes multiple tested surfaces, when carrying out Image Acquisition to multiple tested surface, guarantee 110 row of positioning robot as far as possible
The path walked does not repeat (time most short principle) as far as possible, improves Image Acquisition efficiency.It can specifically be selected from all faces to be detected
One datum level, after first being detected to the datum level, then to detect the structure size in remaining face to be detected and its relative to base
The verticality in quasi- face.
According to one embodiment, the image of the target site can be converted to gray level image, and to the gray level image into
After row adaptive threshold fuzziness, from the target area is extracted after the segmentation in image.It further, can also be first to the target portion
The image of position carries out distortion correction, then carries out gradation conversion to the image after distortion correction.Further, it is also possible to the ash after conversion
Degree image is filtered and Morphological scale-space.Such as median filter process, gaussian filtering process is filtered.At morphology
Reason is such as opening operation processing and closed operation processing.Opening operation is used to eliminate the dark stain of workpiece surface, and enhances to be measured
The textural characteristics of threaded hole and assembly bore region.Empty signature grey scale value is bigger than normal, and opening operation can further increase hole region
Gray value, and increase hole region.Closed operation is used to eliminate the grease stain and light spot of the light color of workpiece surface.Pass through opening and closing
The light and shade contrast of image can be remarkably reinforced after calculation process, the adaptive thresholds point such as the big saliva segmentation of OSTO are carried out to image later
It cuts, the approximate region of threaded hole and pilot hole can be obtained, and then the minimum circumscribed rectangle that the region is calculated includes as this
The target area ROI of the mounting hole.
There are a variety of image distortion corrections, gradation conversion, filtering processing, Morphological scale-space, adaptive threshold fuzziness and ROI
The extracting method in interesting target region, the present invention are not only restricted to this, all images that correspondence image processing function may be implemented
Processing method is within the scope of the present invention.
Then, in step s 320, the sub-pixel edge of target site and target area is extracted respectively, and to extracting
Sub-pixel edge carries out Contour extraction, obtains multiple feature contours.
Here, primarily to obtaining the edge contour of workpiece and the profile of multiple mounting holes.Sub-pixel edge extraction can
To realize using any prior art, sub-pixel edge, the invention is not limited in this regard are extracted for example, by using interpolation method.
According to one embodiment, when carrying out Contour extraction, Freenman can be carried out to the sub-pixel edge extracted
Chain code following, and noise edge is filtered, to obtain multiple feature contours.Wherein, Freeman chain code curve starting point
Coordinate and edge direction code are come the method for describing curve or boundary, and common chain code is according to central pixel point adjacent direction
Several differences is divided into 4 connection chain codes and 8 connection chain codes.In addition, when filtering noise edge, can be set separately area threshold and
Length threshold, and real area is less than the area threshold or physical length and is set less than the feature contour of the length threshold
For noise edge.
According to another embodiment, the first threshold and second threshold (the first threshold of boundary rectangle length-width ratio can also be set
Value is less than second threshold), and the feature contour that practical length-width ratio is greater than second threshold is set as Linear edge, and will be real
The feature contour that border length-width ratio is less than first threshold is set as oval arc-shaped edge.Wherein, Linear edge such as workpiece is most
Outer edge and rectangular bore edges etc. (need to obtain when such as surveying the width of side crossbeam and survey crossbeam edge), and oval arc-shaped edge is for example
Ellipse or rounded opening edge etc., (furthermore shield door bottom surface can exist it is some by two straight ways plus two semicircle bend groups
At pilot hole).
Then, in step S330, Linear edge and/or oval arc-shaped edge fitting are carried out to multiple feature contours,
Obtain line segment aggregate and/or oval arc set.
Specifically, can carry out Linear edge to it for the feature contour for belonging to Linear edge and reject coarse mistake
Not good enough least square method fitting, obtains line segment aggregate.For belonging to the feature contour at oval arc-shaped edge, it can be carried out
The least square method fitting of gross error point is rejected at oval arc-shaped edge, obtains oval arc set.Namely carrying out minimum two
Biggish error dot is all eliminated when straight line fitting and the elliptic arc fitting of multiplication, improves the accuracy of lines fitting.
Then, in step S340, at least one characteristic point of line segment aggregate and/or oval arc set is extracted, and is calculated
The workpiece coordinate of each characteristic point.
Wherein, the characteristic point of oval arc set for example may include elliptical central point and each vertex (such as up and down four
Most marginal point on a direction), in order to the elliptical positions and dimensions size of determination.Oval arc set can be independent single hop
Elliptic arc (the semicircle transition arcs of such as workpiece apex angle), being also possible to a complete ellipse, (such as mounting hole is corresponding complete ellipse
Circle).Oval arc set can also be elliptic arc (the corresponding multiple dispersions of such as mounting hole for belonging to several same elliptical dispersions
Elliptic arc), available corresponding ellipse is fitted by the elliptic arc dispersed to these.The characteristic point of line segment aggregate is for example
May include two endpoints and the midpoint of each line segment in the line segment aggregate, according to this feature point can determine each line segment position and
The width of length and workpiece, height etc..
According to one embodiment, the transformational relation for being stored with tool coordinates and workpiece coordinate in equipment is calculated, is determined in this way
The image coordinate V of each characteristic pointiAfter (x, y, 0), so that it may determine its tool coordinates B according to the image coordinatei(x, y, z), in turn
The workpiece coordinate of each characteristic point can be calculated according to the transformational relation of the tool coordinates and workpiece coordinate.
Fig. 1 is labeled with the specific location relationship of tool coordinates system Tool and workpiece coordinate system Base.If workpiece have it is multiple to
Then a workpiece coordinate system and tool coordinates system is arranged for each tested surface in survey face.Tool coordinates system Base can be according to workpiece
It is artificially defined, for determining each point coordinate on workpiece.Tool coordinates system Tool refers to positioning robot's measuring head (i.e. acquisition mould
Block, including industrial camera and distance measuring sensor) coordinate system, initial position is usually overlapped or translated with tool coordinates system
Arrive, specifically can setting means coordinate system by workpiece coordinate system along x-axis translate h unit obtain.Tool coordinates system Tool is with measurement
Head is mobile and moves.In addition, the origin of tool coordinates system is overlapped with the origin of image coordinate system, and the xOy of tool coordinates system is flat
Face is overlapped with the plane where image coordinate system.Large-size workpiece in Fig. 1 is subway shield door, wherein Base coordinate origin
Tool coordinate origin is located at the workpiece upper left corner under the workpiece lower left corner, original state, and two origins differ h in x-axis
Unit, Tool coordinate system is moved with the movement of measuring head, when measuring head is moved to the detection position in Fig. 1, Tool coordinate
It is that origin is moved to the workpiece upper right corner.
According to one embodiment, the transformational relation of tool coordinates and workpiece coordinate are as follows:
Ci=R1·(Q·Vi)+T1
Wherein, CiAnd ViIt is the workpiece coordinate and tool coordinates of ith feature point, T respectively1And R1It is to shoot the mesh respectively
For tool coordinates system to the translation matrix and spin matrix of workpiece coordinate system, Q is pixel equivalent matrix, R when marking the image at positionhWith
RvIt is the laterally and longitudinally pixel equivalent of camera respectively.Here, pixel equivalent is reality corresponding to a pixel on image
Border size can obtain the corresponding pixel equivalent of image by the method for carrying out sizing calibration to standard component at detection scene.Citing
For, the square standard component of a 1*1mm is placed in the visual field of camera 120, and shoot to the square standard component
For image, to the number of pixels calculated after image procossing on image in the region 1*1mm, in this way, size (1mm) and number of pixels
Ratio be pixel equivalent.
Then, in step S350, target site and wherein each mounting hole are calculated according to the workpiece coordinate of each characteristic point
Morpheme size and tolerance.
Wherein, target site and wherein the size morpheme and tolerance of each mounting hole include the outer dimension of target site, mesh
Mark the location dimension of each mounting hole and the deviation of outer dimension and each size in position.Specifically, the shape ruler of target site
The very little central point in conjunction with workpiece outer profile line segment is calculated, such as according to the mid-point computation width of left and right two lines section.Installation
Each vertex of the outer dimension combination mounting hole in hole is calculated, such as according to round two vertex of left and right and central point calculated diameter
Or radius.The center point coordinate and elliptical center point coordinate of the location dimension combination reference data line segment profile of mounting hole calculate
It arrives.The deviation of each size can compare calculating according to the actual size value and preset standard value measured.
Fig. 5 a to 5e respectively illustrates the basic procedure positioned by image procossing to threaded hole, and wherein Fig. 5 a is original
Beginning image, Fig. 5 b are based on the image zooming-out threaded hole ROI region after Morphological scale-space, including three target areas ROI.
Fig. 5 c is that image segmentation is carried out for extracted ROI region, and Fig. 5 d is to carry out circular arc type for extracted sub-pixel edge
The least square method fitting of gross error point is rejected at edge, obtains the ellipse of three fittings.Fig. 5 e is that threaded hole center pixel is sat
Target calculated result, wherein the central coordinate of circle of three threaded holes is respectively A (x1, y1), B (x2, y2), C (x3, y3).It should manage
It solves, the z-axis coordinate of each point is regarded as 0 in image.Furthermore it is also possible to according to the left and right two of this in image section lateral column
The characteristic point coordinate (such as midpoint of two lines section) of line segment is D come the width that this section of lateral column is calculated.
It is also possible to be sized the mark of measurement parameter, which may include workpiece external dimension mark
Know, the location dimension of each mounting hole mark and outer dimension mark, and by each sizing and the correspondingly-sized value that is calculated
It is associated storage.For example, workpiece external dimension mark M_type=0, threaded hole location dimension mark M_type can be defined
=1, pilot hole positioning and outer dimension identify M_type=2.Can determine M_type value according to dimensional measurement type, and with it is corresponding
Workpiece external dimension (E_flag=0), the location dimension (E_flag=1) of threaded hole, pilot hole positioning and outer dimension (E_
Flag=2) associated storage.
Fig. 6 shows the stream of the tolerance visible detection method 600 of large-size workpiece in accordance with another embodiment of the present invention
Journey schematic diagram.Method 600 calculate equipment in execute, such as calculate equipment 200 in execute, with to part to be measured morpheme size with
Tolerance is detected.
As shown in fig. 6, method 600 starts from step S610.In step S610, the sequence image of large-size workpiece is obtained,
The sequence image includes the image of the different parts of the large-size workpiece.
Then, in step S620, the tolerance visible detection method pair such as the large-size workpiece in method 300 is respectively adopted
Every frame sequence image carries out tolerance vision-based detection, obtains the size morpheme and tolerance of different parts.For example, respectively to Fig. 4 a to 4d
The sequence image of this four shield door left side struts carries out tolerance vision-based detection, obtains the outer of counter structure position in every image
Shape size and location dimension, as the endpoint of left and right two lines section and midpoint, every section of pillar width and each mounting hole
Central point and radius etc..
Then, in step S630, the size morpheme and tolerance of comprehensive all sites calculate the size of the large-size workpiece
Morpheme and tolerance.Namely by the size morpheme of line segment structure, pore structure, elliptic arc structure in every image of Fig. 4 a to 4d etc.
It is merged with tolerance, obtains the size morpheme and tolerance of shield door left side strut.
Fig. 7 shows the detailed of the tolerance visible detection method 700 of large-size workpiece according to a further embodiment of the invention
Flow chart executes in calculating equipment, such as executes in calculating equipment 200.
As shown in fig. 7, method 700 starts from step S710.In step S710, acquisition sequence image I0-N, and record each
Corresponding tool coordinates system R when Image Acquisitioni, i=0-N.Wherein, this N sequence images correspond to N number of position of part to be measured, this N
A position collectively forms the part to be measured.
Then, in step S720, for any frame image, successively to the image carry out distortion correction, gradation conversion and
Morphological scale-space creates the target area at least one rectangle ROI of the image.
Then, in step S730, sub- edge pixel detection is carried out to each target area in the image and is based on
The Contour extraction of Freenman chain code obtains multiple feature contours corresponding to each target area.
Then, in step S740, Linear edge is carried out to multiple feature contours of each target area in the image
And/or the judgement of oval arc-shaped edge, and Linear edge and/or oval arc-shaped edge are fitted, it obtains every in the image
The line segment aggregate of a target area and/or oval arc set.
Then, it in step S750, determines the characteristic point of the image middle conductor set and/or oval arc set, calculates each
The image coordinate of characteristic point, and the image coordinate is converted into workpiece coordinate.
Then, in step S760, for other frame images, the behaviour in step S720- step S750 is successively carried out to it
Make, respectively obtains the workpiece coordinate of each characteristic point in other frame images.
Then, in step S770, which is calculated according to the workpiece coordinate of characteristic point each in all sequences image
Size morpheme and tolerance.
It is namely to unify to carry out size again after having obtained the characteristic point workpiece coordinate in all sequences image in method 700
Morpheme and tolerance calculate, wherein specific each image procossing and the details of operation of calculating are detailed in the description based on other accompanying drawings
It is thin open, it is not reinflated here to repeat.
Fig. 8 shows the tolerance vision inspection apparatus 800 of large-size workpiece according to an embodiment of the invention, the device
800 may be embodied in calculating equipment 200 as shown in Figure 2.As shown in figure 8, device 800 includes target area extraction module
810, feature contour extraction module 820, feature contour fitting module 830, feature point extraction module 840 and morpheme size calculate mould
Block 850.
Target area extraction module 810 obtains the image of certain target site in large-size workpiece, and extracts from the image
Interesting target region comprising mounting hole.Target area extraction module 810 can be carried out and be described in step s310 above
The corresponding processing of processing, it is not reinflated here to repeat.
Feature contour extraction module 820 extracts the sub-pixel edge of target site and target area respectively, and to extracting
Sub-pixel edge carry out Contour extraction, obtain multiple feature contours.Feature contour extraction module 820 can carry out and exist above
The corresponding processing of processing, not reinflated here to repeat described in step S320.
Feature contour fitting module 830 carries out Linear edge/to multiple feature contours or circular line section is fitted, and obtains
Line segment aggregate and/or oval arc set.Feature contour fitting module 830 can carry out with above described in the step S330
Corresponding processing is managed, it is not reinflated here to repeat.
Feature point extraction module 840 extracts at least one characteristic point of line segment aggregate and/or oval arc set, and calculates each
The workpiece coordinate of characteristic point.Feature point extraction module 840 can carry out corresponding with the processing described in step S340 above
Processing, it is not reinflated here to repeat.
Morpheme size computing module 850 calculates target site and wherein each mounting hole according to the workpiece coordinate of each characteristic point
Size morpheme and tolerance.Morpheme size computing module 850 can also integrate the different target position and wherein of the large-size workpiece
The size morpheme and tolerance of each mounting hole, to calculate the size morpheme and tolerance of the large-size workpiece.Morpheme size computing module
850 can carry out processing corresponding with the processing described in step S350 above, not reinflated here to repeat.
According to the technique and scheme of the present invention, machine vision and laser range finder is cooperated to carry out big ruler by using robot
Very little measurement establishes based on adaptive thresholding, median filtering, Morphological scale-space, Sub-pixel Edge Detection
Image processing method handles the image of large-size workpiece, and combines Linear edge, the ellipse for rejecting gross error point
Two kinds of shape edge edge fitting algorithm extracts and recognizes the characteristic information of large-size workpiece, final to obtain workpiece items size, meter
It calculates precision and much reaches measurement demand.
A7, the method as described in any one of A1-A6 further comprise the steps of: the first threshold of setting boundary rectangle length-width ratio
And second threshold, and the feature contour that practical length-width ratio is greater than second threshold is set as Linear edge, and by actual (tube) length
Width is set as oval arc-shaped edge than being less than the feature contour of first threshold.A8, the method as described in A7, wherein to described more
The step of a feature contour progress Linear edge/or circular line section are fitted includes: to the feature wheel for belonging to Linear edge
Exterior feature carries out the least square method fitting that Linear edge rejects gross error point, obtains line segment aggregate；And/or to belonging to elliptic arc
The feature contour at type edge carries out the least square method fitting that gross error point is rejected at oval arc-shaped edge, obtains elliptic arc collection
It closes.A9, the method as described in any one of A1-A8, wherein it is described ellipse arc set characteristic point include elliptical central point and
Each vertex, the characteristic point of the line segment aggregate include two endpoints and the midpoint of each line segment in the line segment aggregate.
A10, the method as described in any one of A1-A9, wherein described certain target site for obtaining the large-size workpiece
Image the step of include: the image that target site is obtained from camera, and obtain camera localization machine when shooting the image
The tool coordinates system of device people's measuring head；Wherein, the camera is when shooting the image, by positioning robot according to distance measuring sensor
The range information measured adjusts the operating distance of camera, to guarantee the to be checked of the imaging plane of camera and the large-size workpiece
Survey face is parallel.A11, the method as described in any one of A1-A10, wherein be stored with tool coordinates and work in the calculating equipment
The step of transformational relation of part coordinate, the workpiece coordinate for calculating each characteristic point includes: the image coordinate according to each characteristic point
It determines its tool coordinates, and calculates the workpiece coordinate of each characteristic point according to the transformational relation.A12, the side as described in A11
Method, wherein the origin of tool coordinates system is overlapped with the origin of image coordinate system, and the xOy plane of tool coordinates system and image are sat
Plane where mark system is overlapped；The transformational relation are as follows:
Ci=R1·(Q·Vi)+T1
Wherein, CiAnd ViIt is the workpiece coordinate and tool coordinates of ith feature point, T respectively1And R1It is to shoot the mesh respectively
For tool coordinates system to the translation matrix and spin matrix of workpiece coordinate system, Q is pixel equivalent matrix, R when marking the image at positionhWith
RvIt is the laterally and longitudinally pixel equivalent of camera respectively.
A13, the method as described in any one of A1-A12, wherein the target site and the wherein morpheme of each mounting hole
Size and tolerance include the outer dimension of target site, in target site the location dimension and outer dimension of each mounting hole and
The deviation of each size.A14, the method as described in A13, wherein the outer dimension combination workpiece outer contour of the target site
The central point of section is calculated；Each vertex of the outer dimension combination mounting hole of the mounting hole is calculated；The mounting hole
Location dimension combination reference data line segment profile center point coordinate and elliptical center point coordinate be calculated.A15, such as A13
The method, further comprises the steps of: the mark for being sized measurement parameter, and the mark includes that workpiece external dimension identifies, is each
The location dimension mark and outer dimension mark of mounting hole, and each sizing is closed with the correspondingly-sized value being calculated
Connection storage.
B18, the device as described in B17, the morpheme size computing module are further adapted for integrating the large-size workpiece not
With the target site and wherein morpheme size and tolerance of each mounting hole, to calculate the morpheme size and public affairs of the large-size workpiece
Difference.B19, the device as described in B17, wherein the target area extraction module is suitable for converting the image of the target site
For gray level image, adaptive threshold fuzziness carried out to the gray level image, and from extracting the target area after segmentation in image.
B20, the device as described in B19, the target area extraction module are further adapted for carrying out distortion school to the image of the target site
Just, and to the gray level image it is filtered and Morphological scale-space.
Various technologies described herein are realized together in combination with hardware or software or their combination.To the present invention
Method and apparatus or the process and apparatus of the present invention some aspects or part can take insertion tangible media, such as can
Program code (instructing) in mobile hard disk, USB flash disk, floppy disk, CD-ROM or other any machine readable storage mediums
Form, wherein when program is loaded into the machine of such as computer etc, and when being executed by the machine, the machine becomes to practice
Equipment of the invention.
In the case where program code executes on programmable computers, calculates equipment and generally comprise processor, processor
Readable storage medium (including volatile and non-volatile memory and or memory element), at least one input unit, and extremely
A few output device.Wherein, memory is configured for storage program code；Processor is configured for according to the memory
Instruction in the said program code of middle storage executes the tolerance visible detection method of large-size workpiece of the invention.
By way of example and not limitation, readable medium includes readable storage medium storing program for executing and communication media.Readable storage medium storing program for executing
Store the information such as computer readable instructions, data structure, program module or other data.Communication media is generally such as to carry
The modulated message signals such as wave or other transmission mechanisms embody computer readable instructions, data structure, program module or other
Data, and including any information transmitting medium.Above any combination is also included within the scope of readable medium.
In the instructions provided here, algorithm and display not with any certain computer, virtual system or other
Equipment is inherently related.Various general-purpose systems can also be used together with example of the invention.As described above, it constructs this kind of
Structure required by system is obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can
With using various programming languages realize summary of the invention described herein, and the description that language-specific is done above be for
Disclosure preferred forms of the invention.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, knot is not been shown in detail
Structure and technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims than feature more features expressly recited in each claim.More precisely, as following
As claims reflect, inventive aspect is all features less than single embodiment disclosed above.Therefore, it abides by
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
As a separate embodiment of the present invention.
Those skilled in the art should understand that the module of the equipment in example disclosed herein or unit or groups
Part can be arranged in equipment as depicted in this embodiment, or alternatively can be positioned at and the equipment in the example
In different one or more equipment.Module in aforementioned exemplary can be combined into a module or furthermore be segmented into multiple
Submodule.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
In addition, be described as herein can be by the processor of computer system or by executing by some in the embodiment
The combination of method or method element that other devices of the function are implemented.Therefore, have for implementing the method or method
The processor of the necessary instruction of element forms the device for implementing this method or method element.In addition, Installation practice
Element described in this is the example of following device: the device be used for implement as in order to implement the purpose of the invention element performed by
Function.
As used in this, unless specifically stated, come using ordinal number " first ", " second ", " third " etc.
Description plain objects, which are merely representative of, is related to the different instances of similar object, and is not intended to imply that the object being described in this way must
Must have the time it is upper, spatially, sequence aspect or given sequence in any other manner.
Although the embodiment according to limited quantity describes the present invention, above description, the art are benefited from
It is interior it is clear for the skilled person that in the scope of the present invention thus described, it can be envisaged that other embodiments.Additionally, it should be noted that
Language used in this specification primarily to readable and introduction purpose and select, rather than in order to explain or limit
Determine subject of the present invention and selects.Therefore, without departing from the scope and spirit of the appended claims, for this
Many modifications and changes are obvious for the those of ordinary skill of technical field.For the scope of the present invention, to this
It invents done disclosure to be illustrative and be not restrictive, it is intended that the scope of the present invention be defined by the claims appended hereto.
Claims (10)
1. a kind of tolerance visible detection method of large-size workpiece, suitable for being executed in calculating equipment, the method includes the steps:
The image of certain target site in the large-size workpiece is obtained, and extracts the mesh interested comprising mounting hole from the image
Mark region；
The sub-pixel edge of the target site and target area is extracted respectively, and profile is carried out to the sub-pixel edge extracted
Tracking, obtains multiple feature contours；
Linear edge and/or oval arc-shaped edge fitting are carried out to the multiple feature contour, obtain line segment aggregate and/or ellipse
Circular arc set；
At least one characteristic point of the line segment aggregate and/or oval arc set is extracted, and calculates the workpiece coordinate of each characteristic point；
And
The target site and the wherein morpheme size and tolerance of each mounting hole are calculated according to the workpiece coordinate of each characteristic point.
2. the method as described in claim 1 further comprises the steps of:
The different target position of the comprehensive large-size workpiece and the wherein morpheme size and tolerance of each mounting hole calculate described big
The morpheme size and tolerance of dimension workpiece.
3. the method for claim 1, wherein described the step of extraction includes the target area of mounting hole from the image
Include:
The image of the target site is converted into gray level image, to the gray level image carry out adaptive threshold fuzziness, and from point
It cuts and extracts the target area in rear image.
4. method as claimed in claim 3 further comprises the steps of:
Distortion correction carried out to the image of the target site, and to the gray level image be filtered and morphology at
Reason.
5. such as method of any of claims 1-4, wherein the described pair of sub-pixel edge extracted carry out profile with
The step of track includes:
Freenman chain code following is carried out to the sub-pixel edge extracted, and filters noise edge, obtains multiple feature wheels
It is wide.
6. method as claimed in claim 5, wherein the step of filtering noise edge includes:
Area threshold and length threshold is set separately, and real area is less than less than the area threshold or physical length should
The feature contour of length threshold is set as noise edge.
7. a kind of tolerance visible detection method of large-size workpiece, suitable for being executed in calculating equipment, the method includes the steps:
The sequence image of the large-size workpiece is obtained, the sequence image includes the figure of the different parts of the large-size workpiece
Picture；
It is respectively adopted and tolerance vision-based detection is carried out to every frame sequence image such as method of any of claims 1-6, obtain
To the morpheme size and tolerance of different parts；And
The size morpheme and tolerance of comprehensive all sites, calculate the morpheme size and tolerance of the large-size workpiece.
8. a kind of tolerance vision inspection apparatus of large-size workpiece calculates in equipment suitable for residing in, described device includes:
Target area extraction module suitable for obtaining the image of certain target site in the large-size workpiece, and is mentioned from the image
Take the interesting target region comprising mounting hole；
Feature contour extraction module, suitable for extracting the sub-pixel edge of the target site and target area respectively, and to extraction
The sub-pixel edge arrived carries out Contour extraction, obtains multiple feature contours；
Feature contour fitting module is suitable for carrying out Linear edge/to the multiple feature contour or circular line section is fitted, obtains
To line segment aggregate and/or oval arc set；
Feature point extraction module suitable for extracting at least one characteristic point of the line segment aggregate and/or oval arc set, and calculates
The workpiece coordinate of each characteristic point；And
Morpheme size computing module, suitable for calculating the target site and wherein each mounting hole according to the workpiece coordinate of each characteristic point
Morpheme size and tolerance.
9. a kind of calculating equipment, comprising:
One or more processors；
Memory；And
One or more programs, wherein one or more of programs are stored in the memory and are configured as by described one
A or multiple processors execute, and realize described in any one of claim 1-7 when one or more of programs are executed by processor
Method the step of.
10. a kind of computer readable storage medium for storing one or more programs, one or more of programs include instruction,
Described instruction realizes the step of claim 1-7 described in any item methods when executed by a computing apparatus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910542808.5A CN110288651A (en) | 2019-06-21 | 2019-06-21 | Tolerance visible detection method, device and the calculating equipment of large-size workpiece |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910542808.5A CN110288651A (en) | 2019-06-21 | 2019-06-21 | Tolerance visible detection method, device and the calculating equipment of large-size workpiece |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110288651A true CN110288651A (en) | 2019-09-27 |
Family
ID=68004482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910542808.5A Pending CN110288651A (en) | 2019-06-21 | 2019-06-21 | Tolerance visible detection method, device and the calculating equipment of large-size workpiece |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288651A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111415378A (en) * | 2020-02-27 | 2020-07-14 | 湖南大学 | Image registration method for automobile glass detection and automobile glass detection method |
| CN111539951A (en) * | 2020-05-13 | 2020-08-14 | 西安交通大学 | Visual detection method for outline size of ceramic grinding wheel head |
| CN112132927A (en) * | 2020-09-15 | 2020-12-25 | 成都工具研究所有限公司 | Drawing system and method for generating two-dimensional and three-dimensional models on webpage interface |
| CN112419398A (en) * | 2020-11-25 | 2021-02-26 | 创新奇智(西安)科技有限公司 | Rectangular workpiece dimension measuring method, device, equipment and storage medium |
| CN113267143A (en) * | 2021-06-30 | 2021-08-17 | 三一建筑机器人(西安)研究院有限公司 | Side die identification method |
| CN113932730A (en) * | 2021-09-07 | 2022-01-14 | 华中科技大学 | Detection apparatus for curved surface panel shape |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101387501A (en) * | 2008-10-06 | 2009-03-18 | 天津大学 | Ultra-large workpiece circular section shape and azimuthal measurement apparatus and method |
| CN103499302A (en) * | 2013-09-27 | 2014-01-08 | 吉林大学 | Camshaft diameter online measuring method based on structured light visual imaging system |
| CN109612390A (en) * | 2018-12-17 | 2019-04-12 | 江南大学 | Large-size workpiece automatic measuring system based on machine vision |
-
2019
- 2019-06-21 CN CN201910542808.5A patent/CN110288651A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101387501A (en) * | 2008-10-06 | 2009-03-18 | 天津大学 | Ultra-large workpiece circular section shape and azimuthal measurement apparatus and method |
| CN103499302A (en) * | 2013-09-27 | 2014-01-08 | 吉林大学 | Camshaft diameter online measuring method based on structured light visual imaging system |
| CN109612390A (en) * | 2018-12-17 | 2019-04-12 | 江南大学 | Large-size workpiece automatic measuring system based on machine vision |
Non-Patent Citations (3)
| Title |
|---|
| 何博侠等: "基于序列局部图像的高精度测量", 《光学精密工程》 * |
| 梁晋等: "《3D反求技术》", 31 January 2019, 华中科技大学出版社 * |
| 程敏: "工件圆弧尺寸检测方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111415378A (en) * | 2020-02-27 | 2020-07-14 | 湖南大学 | Image registration method for automobile glass detection and automobile glass detection method |
| CN111415378B (en) * | 2020-02-27 | 2023-11-24 | 湖南大学 | Image registration method for automobile glass detection and automobile glass detection method |
| CN111539951A (en) * | 2020-05-13 | 2020-08-14 | 西安交通大学 | Visual detection method for outline size of ceramic grinding wheel head |
| CN111539951B (en) * | 2020-05-13 | 2022-12-09 | 西安交通大学 | Visual detection method for outline size of ceramic grinding wheel head |
| CN112132927A (en) * | 2020-09-15 | 2020-12-25 | 成都工具研究所有限公司 | Drawing system and method for generating two-dimensional and three-dimensional models on webpage interface |
| CN112132927B (en) * | 2020-09-15 | 2023-10-20 | 成都工具研究所有限公司 | Drawing system and method for generating two-dimensional and three-dimensional models on webpage interface |
| CN112419398A (en) * | 2020-11-25 | 2021-02-26 | 创新奇智(西安)科技有限公司 | Rectangular workpiece dimension measuring method, device, equipment and storage medium |
| CN113267143A (en) * | 2021-06-30 | 2021-08-17 | 三一建筑机器人(西安)研究院有限公司 | Side die identification method |
| CN113267143B (en) * | 2021-06-30 | 2023-08-29 | 三一建筑机器人(西安)研究院有限公司 | Side mold identification method |
| CN113932730A (en) * | 2021-09-07 | 2022-01-14 | 华中科技大学 | Detection apparatus for curved surface panel shape |
| CN113932730B (en) * | 2021-09-07 | 2022-08-02 | 华中科技大学 | Detection apparatus for curved surface panel shape |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288651A (en) | Tolerance visible detection method, device and the calculating equipment of large-size workpiece | |
| Chen et al. | High-accuracy multi-camera reconstruction enhanced by adaptive point cloud correction algorithm | |
| Wöhler | 3D computer vision: efficient methods and applications | |
| CA2961921C (en) | Camera calibration method using a calibration target | |
| CN109612390B (en) | Large-size workpiece automatic measuring system based on machine vision | |
| CN106959078B (en) | A kind of contour measuring method for measuring three-dimensional profile | |
| JP5467404B2 (en) | 3D imaging system | |
| CN102376089B (en) | Target correction method and system | |
| CN109801333B (en) | Volume measurement method, device and system and computing equipment | |
| US8121415B2 (en) | Combining feature boundaries | |
| CN108007388A (en) | A kind of turntable angle high precision online measuring method based on machine vision | |
| CN107229043B (en) | A kind of range sensor external parameters calibration method and system | |
| Karaszewski et al. | Assessment of next-best-view algorithms performance with various 3D scanners and manipulator | |
| CN108458659A (en) | A kind of blade contactless detection device and method | |
| CN110608685A (en) | Object size rapid measurement method based on raspberry pie | |
| CN101720476A (en) | Feature detection apparatus and metod for measuring object distances | |
| CN109343037A (en) | Optical detector installation error detection device, method and terminal device | |
| CN104574357A (en) | System and method for locating fiducials with known shape | |
| JP2017003525A (en) | Three-dimensional measuring device | |
| Wang et al. | Nonmetric camera calibration for underwater laser scanning system | |
| CN109690241A (en) | Three directional measuring device and three-dimensional measurement method | |
| Ali | Reverse engineering of automotive parts applying laser scanning and structured light techniques | |
| Frangione et al. | Multi-step approach for automated scaling of photogrammetric micro-measurements | |
| CN111189413B (en) | Double-camera line structured light measurement system optimization method and terminal equipment | |
| CN113689397A (en) | Workpiece circular hole feature detection method and workpiece circular hole feature detection device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190927 |
|
| RJ01 | Rejection of invention patent application after publication |