CN106323167A - Intelligent scanning online measurement system and intelligent scanning online measurement method based on image identification - Google Patents
Intelligent scanning online measurement system and intelligent scanning online measurement method based on image identification Download PDFInfo
- Publication number
- CN106323167A CN106323167A CN201610704368.5A CN201610704368A CN106323167A CN 106323167 A CN106323167 A CN 106323167A CN 201610704368 A CN201610704368 A CN 201610704368A CN 106323167 A CN106323167 A CN 106323167A
- Authority
- CN
- China
- Prior art keywords
- measurement
- scanning
- robot
- ecu
- ccd camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
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
- G01B11/005—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates coordinate measuring machines
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an intelligent scanning online measurement system based on image identification, wherein the system relates to the field of industrial automation. The intelligent scanning online measurement system comprises an image identification positioning module, a six-freedom robot laser scanning measurement module and a measurement control module, wherein the image identification positioning module comprises a CCD camera triggering switch, a CCD camera, a CCD camera bracket, and a CCD camera electronic control unit (ECU). The measurement control module comprises a central processing unit, a measurement system controller, a measurement robot pose ECU and a measuring head ECU. The six-freedom robot laser scanning measurement module comprises a six-freedom measurement robot, a measurement robot pose sensor, a measurement robot joint motor, a laser scanning measuring head and a measurement triggering switch. The invention further discloses an intelligent scanning online measurement method based on image identification. The intelligent scanning online measurement method comprises the steps of establishing an intelligent scanning strategy database; performing image identification and initial positioning; performing adaptive scanning measurement; performing accurate secondary positioning in the measurement process; and updating a scanning strategy in the scanning measurement process.
Description
Technical field
The present invention relates to scan-type On-line Measuring Method, refer in particular to a kind of intelligent scanning on-line measurement based on image recognition
System and measuring method.
Background technology
Along with the continuous appearance of novel sensor, theoretical the most perfect of non-cpntact measurement so that use non-cpntact measurement
Technology realizes the on-line measurement of free form surface and is possibly realized.Compared with measuring technology, CMM technology with traditional model, noncontact swashs
Photoscanning detection technique has contactless, the detection advantages such as speed is fast, data volume is big, in reverse-engineering, quality testing, virtual existing
The field tools such as reality have great advantage, and are widely deployed in producing and in life.
Along with industry 4.0 and the Internet+etc. the proposition of concept, mass customization (OEM) produces and is overturning thousand one
The homogeneous product of rule, factory also becomes fewer and feweri peopleization, unmanned, automatization and intellectuality.And the gentle life of Automated water
The raising producing efficiency directly translates into the raising of production line beat, and the quality testing how realizing product under fast beat would is that the present
The key issue of rear a period of time.
Current automotive industry and parts manufacturer mainly use cubing and CMM sampling Detection for the quality management of product
Method, or use on-line checking robotic gripper's laser feeler, get measurement for key point online ready, and be aided with
The mode of CMM timing sampling observation carries out quality management.The method using cubing and CMM sampling Detection is required to for each part to be measured
Make special cubing, not only increase the cost of quality management, and detection efficiency is low, it is impossible to realize on-line checking；Online
Measuring robots key point on-line checking mode, can be only done the detection of some key point, it is impossible to meet the comprehensive quality of product
Management requirement, especially for parts produce, cannot comprehensively reflect part situation for finding critical point detection, with
Time measure and special CMM measures system and drastically increases production cost owing to introducing robot, thus significantly limit
The application in parts produce of the robot on-line checking.
Therefore, those skilled in the art is devoted to develop a kind of intelligent scanning on-line measurement system based on image recognition
And measuring method, it is achieved for multi items, the online inspection of the parts automated production of fast beat, in high volume personalized customization
Survey.
Summary of the invention
Because the drawbacks described above of prior art, the technical problem to be solved is how for multi items, fast
The on-line checking of the parts automated production of beat, in high volume personalized customization, it is achieved based on part feature and measurement requirement
Self adaptation laser scanning measurement, simplify measurement equipment, improve and measure efficiency and comprehensive.
For achieving the above object, the invention provides a kind of intelligent scanning on-line measurement system based on image recognition, bag
Including image recognition locating module, six-DOF robot laser scanning measurement module, measure control module, wherein said image is known
Other locating module includes that CCD camera triggers switch, CCD camera, CCD camera support, CCD camera electronic control unit ECU；Described
Measure control module to include central processing unit, measure system controller, robot measurement pose ECU, measurement head ECU；Described six
Degree of freedom robot laser scanning measurement module includes that six degree of freedom measures robotic arm, robot measurement Position and attitude sensor, measurement
Joint of robot motor, laser scanning measuring head, measurement trigger switch.
Further, described CCD camera triggers switch and is positioned on production line, is positioned at the described CCD camera on production line side
Described CCD camera is supported in above production line by support.
Further, described robot measurement pose ECU and described measurement head ECU is gathered by described measurement system controller
Pose data and measurement data be sent to described central processing unit, the control command of described central processing unit is sent to simultaneously
Described robot measurement pose ECU and described measurement head ECU.
Further, described triggering switch of measuring is positioned at production line measurement station, and described laser scanning head is positioned at described
Six degree of freedom measures the end of robotic arm, and described robot measurement joint motor and described robot measurement Position and attitude sensor are positioned at
Six degree of freedom measures each joint of robotic arm.
Present invention also offers a kind of intelligent scanning On-line Measuring Method based on image recognition, comprise the following steps:
Step 1, set up intelligent scanning policy database；
Step 2, image recognition also carry out initial alignment；
Step 3, adaptively scanning survey；
Accurate second positioning during step 4, scanning survey；
Scanning strategy during step 5, scanning survey updates.
Further, in step 1, also include
Step 1.1, by production line all kinds of online production three-dimensional part model import central processing unit；
Step 1.2, central processing unit will be treated according to the aspect of model and the measurement requirement of the threedimensional model of each part to be measured
The threedimensional model surveying part is converted to the target measurement point cloud of gridding domain type；
Step 1.3, foundation target measurement point cloud make the adaptive scanning strategy meeting the aspect of model and measurement requirement.
Further, in step 2, also include
Step 2.1, weld during rearward measurement station moves when part, when CCD camera triggers switch,
CCD camera triggers switch and is triggered to CCD camera transmission CCD camera triggering signal, and then part is clapped by control CCD camera
Take the photograph；
The three-dimensional part image of the part of acquisition is passed to CCD camera ECU, CCD camera ECU warp by step 2.2, CCD camera
Cross process, three-dimensional part image is converted to the part 3-dimensional digital signal of band coordinate position and passes to central processing unit；
Step 2.3, central processing unit according to the feature identification of part 3-dimensional digital signal go out corresponding part and with import
Corresponding three-dimensional part model is corresponding, and identifies the coordinate information that this three-dimensional part model elements of fix is corresponding, it is achieved image is known
Other function；
Elements of fix corresponding for the part 3-dimensional digital signal obtained by image information is sat by step 2.4, central processing unit
Mark information, in conjunction with robot measurement initial coordinate position, and part arrives the initial coordinate measuring position, obtains measuring machine
Device people is for the measurement coordinate of part to be measured；
Step 2.5, elements of fix coordinate information corresponding for part 3-dimensional digital signal is corresponding with target measurement point cloud
Key element coordinate information carries out optimal fitting, thus realizes image initial positioning function, and Robot Scanning is measured coordinate and model
Target measurement point cloud coordinate unification, provides the basis reference of scanning for follow-up adaptive scanning.
Further, in step 3, also include
Step 3.1, when the retinue platform loading part arrives and measures station, be positioned at and measure the measurement at station and trigger and open
Close and will be triggered, send measurement to measurement system controller and trigger signal, after measurement system controller receives measurement triggering signal
Start process of measurement；
Step 3.2, measure the adaptive scanning strategy that sends according to central processing unit of system controller and measure machine
The robot pose feedback signal that people pose ECU sends generates robot Pose Control signal and passes to robot measurement pose ECU,
The pose signal that robot measurement pose ECU is surveyed according to robot Pose Control signal and robot measurement Position and attitude sensor
Generate joint of robot motor control signal, thus control the pose of robot measurement joint motor, make laser scanning head arrive
Scan position；
Step 3.3, when laser scanning head arrive scan position time, measure system controller will receive from robot measurement
The robot pose feedback signal that pose ECU sends, measures system controller and sends scan control signal extremely measurement head ECU, by
Measure head ECU and generate scanning signal, thus control laser scanning head and complete scanning；
Laser signal from laser scanning head is converted to position digital signal and passes to measurement by step 3.4, measurement head ECU
System controller, measures system controller and generates measurement pointcloud number according to position digital signal and robot pose feedback signal
According to passing central processing unit back；
Step 3.5, central processing unit are by the target measurement point of measurement pointcloud data with the threedimensional model conversion of workpiece for measurement
Measurement result is presented by cloud the most in real time.
Further, in step 4, also include
Step 4.1, startup measurement after measurement system controller receives the measurement triggering signal that measurement triggering switch sends
Program, measurement system controller first controls measurement system and completes the elements of fix scanning that three-dimensional part model is corresponding, and central authorities process
After device receives the scanning survey cloud data of initial alignment key element, by scanning survey cloud data and the target of initial alignment key element
In measurement pointcloud, corresponding key element coordinate information carries out quadratic fit；
Step 4.2, Robot Scanning is measured coordinate accurately it is directed at simulated target measurement pointcloud coordinate, for follow-up adaptive
The exact references benchmark that scanning is provided should be scanned.
Further, in steps of 5, also include
After step 5.1, central processing unit receive measurement pointcloud data, threedimensional model and target in conjunction with part to be measured are surveyed
Amount point cloud, calculates the target measurement point cloud to be measured made new advances, formulates the adaptive scanning strategy made new advances and pass to measurement system controller；
Step 5.2, measurement system controller measure according to new adaptive scanning strategy thus realize scanning strategy
With the dynamic adjustment of scanning process, until completing the measurement of part to be measured；
Step 5.3, robot measurement return initial position.
Intelligent scanning type on-line measurement system based on image recognition of the present invention, as it is shown in figure 1, include that image is known
Other locating module, six-DOF robot laser scanning measurement module, measurement control module, also include welding and assembling production lines, be positioned at
Retinue platform on welding and assembling production lines, the pallet pallet being positioned on retinue platform, fixture on pallet pallet and
Part on fixture, wherein image recognition locating module is triggered switch, CCD camera, CCD camera support, CCD phase by CCD camera
Organic electronic control unit (ECU) forms, and CCD camera triggers switch and is positioned on production line, and the CCD camera being positioned at production line side is propped up
CCD camera is supported in above production line by frame；Six-DOF robot laser scanning measurement module is measured machine by six degree of freedom
Arm, robot measurement Position and attitude sensor, robot measurement joint motor, laser scanning measuring head, measurement trigger switch, measure and touch
Sending out switch to be positioned at production line measurement station, laser scanning head is positioned at six degree of freedom and measures the end of robotic arm, robot measurement
Joint motor and robot measurement Position and attitude sensor are positioned at six degree of freedom and measure each joint of robotic arm；Measure control module by
Central processing unit, measurement system controller, robot measurement pose ECU, measurement head ECU composition.
Intelligent scanning type on-line measurement system intelligent scanning based on image recognition of the present invention detection control method:
1) setting up intelligent scanning policy database, process is: first by production line the zero of all kinds of online production
Part threedimensional model imports central processing unit, and central processing unit is according to the aspect of model of the threedimensional model of each part to be measured and measurement
Require to be converted to the threedimensional model of part to be measured the target measurement point cloud of gridding domain type, and then according to target measurement point cloud
Make the adaptive scanning strategy meeting the aspect of model and measurement requirement.
2) image recognition carry out initial alignment, process is: when part has welded the process that rearward measurement station moves
In, when CCD camera triggers switch, CCD camera triggers switch and is triggered to CCD camera transmission CCD camera triggering signal, enters
And control CCD camera and part is shot, the three-dimensional part image of the part of acquisition is passed to CCD camera by CCD camera subsequently
ECU, three-dimensional part image, through processing, is converted to the part 3-dimensional digital signal of band coordinate position and passes by CCD camera ECU
To central processing unit, central processing unit is according to the part 3-dimensional digital signal of band coordinate position, three-dimensional part model, first basis
The feature identification of part 3-dimensional digital signal goes out corresponding part corresponding to the corresponding three-dimensional part model imported, and identifies this
The coordinate information that three-dimensional part model elements of fix is corresponding, it is achieved image identification function；Then zero will obtained by image information
The elements of fix coordinate information that part 3-dimensional digital signal is corresponding, in conjunction with robot measurement initial coordinate position, and part arrives
Measure the initial coordinate of position, obtain the robot measurement measurement coordinate for part to be measured；Last again by part three dimension
The elements of fix coordinate information that word signal is corresponding carries out optimal fitting with corresponding key element coordinate information in target measurement point cloud, thus
Realize image initial positioning function, Robot Scanning is measured coordinate and simulated target measurement pointcloud coordinate unification, for follow-up
Adaptive scanning provides the basis reference of scanning.
3) scanning survey adaptively, process is: when the retinue platform loading part arrives and measures station, be positioned at measurement
Measurement at station triggers switch and will be triggered, and sends measurement triggering signal to measuring system controller, measures system controller
Receive after measurement triggers signal and start process of measurement, measure the adaptive scanning plan that system controller sends according to central processing unit
The robot pose feedback signal that summary and robot measurement pose ECU send generates robot Pose Control signal and passes to measurement
Robot pose ECU, robot measurement pose ECU is according to robot Pose Control signal and robot measurement Position and attitude sensor
The pose signal surveyed generates joint of robot motor control signal, thus controls the pose of robot measurement joint motor, makes
Laser scanning head arrives scan position；When laser scanning head arrives scan position, measurement system controller will receive tests oneself
The robot pose feedback signal that amount robot pose ECU sends, then measures system controller and sends scan control signal extremely
Measure head ECU, generated scanning signal by measuring head ECU, thus control laser scanning head and complete scanning；Measuring head ECU will be from
The laser signal of laser scanning head is converted to position digital signal and passes to measurement system controller, measures system controller according to position
Putting digital signal and robot pose feedback signal generates measurement pointcloud data and passes central processing unit back, central processing unit will be surveyed
Present together with the target measurement point cloud that amount cloud data is changed with the threedimensional model of workpiece for measurement, thus in real time by measurement result
Present, it is achieved the adaptive scanning to workpiece for measurement.
4) the accurate second positioning process during scanning survey is: when measuring beginning, receives when measuring system controller
Measurement starts process of measurement after triggering the measurement triggering signal that switch sends, and measurement system controller first controls measurement system to be completed
The elements of fix scanning that three-dimensional part model is corresponding, central processing unit receives the scanning survey cloud data of initial alignment key element
After, the scanning survey cloud data of initial alignment key element is carried out secondary plan with corresponding key element coordinate information in target measurement point cloud
Close, thus realize laser scanning secondary precise locating function, Robot Scanning is measured coordinate and sits with simulated target measurement pointcloud
Mark accurately alignment, thus the exact references benchmark of scanning is provided for follow-up adaptive scanning.
5) the scanning strategy renewal process during scanning survey is: after central processing unit receives measurement pointcloud data, knot
Close threedimensional model and the target measurement point cloud of part to be measured, calculate the target measurement point cloud to be measured made new advances, formulate make new advances from
Adapt to scanning strategy and pass to measurement system controller, measure system controller and measure according to new adaptive scanning strategy,
Thus realize the scanning strategy dynamic adjustment with scanning process, until completing the measurement of part to be measured, robot measurement is returned subsequently
Return initial position.
Beneficial effects of the present invention is as follows:
1, the present invention use six degree of freedom robot measurement complete online parts be welded produce measurement, be possible not only to reality
Now the most quick scanning survey, improves detection efficiency, simultaneously because scanning survey completes online, it is not necessary to make special inspection
The fixing measured workpiece of tool carries out measuring under line, greatly extends the scope of application of scanning survey, and the resource decreasing measurement disappears
Consumption.
2, the present invention uses identification based on image procossing and initial alignment function, by measuring basis and impact point before measuring
Cloud carries out coordinate alignment, it is possible to achieve the com-parison and analysis during measurement, can formulate according to impact point cloud direct-on-line and measure
Strategy, and dynamic tracking measurement；Image recognition is used to make measurement system be adapted to the weldering of multi items welding production line multi items
The detection of pipe fitting is measured.
3, the present invention according to the aspect of model of workpiece for measurement threedimensional model and measurement requirement by the threedimensional model of workpiece for measurement
Be converted to the target measurement point cloud of gridding domain type, and by the secondary of initial alignment based on image procossing with laser scanning
Precise positioning, it is achieved target measurement point cloud coordinate and the registration of measurement pointcloud coordinate, can make and meet workpiece for measurement model spy
The optimum scanning strategy of measurement requirement of seeking peace, and realization measurement adjustment real-time during measuring, it is achieved to workpiece for measurement
Three-dimensional adaptive scanning survey, makes measurement more fit and measures object and measurement requirement.
Below with reference to accompanying drawing, the technique effect of design, concrete structure and the generation of the present invention is described further, with
It is fully understood from the purpose of the present invention, feature and effect.
Accompanying drawing explanation
Fig. 1 is the structural representation of a preferred embodiment of the present invention；
Fig. 2 is the method flow diagram of a preferred embodiment of the present invention；
In figure: 1 triggers switch for CCD camera, and 2 is CCD camera, and 3 is CCD camera support, 4 measure machine for six degree of freedom
Arm, 5 is robot measurement Position and attitude sensor, and 6 is robot measurement joint motor, and 7 is laser scanning measuring head, and 8 is flat for retinue
Platform, 9 is pallet pallet, and 10 is fixture, and 11 is part, and 12 is welding and assembling production lines, and 13 is CCD camera electronic control unit
(ECU), 14 is central processing unit, and 15 for measuring system controller, and 16 is robot measurement pose ECU, and 17 for measuring head ECU,
18 trigger signal for CCD camera, and 19 is part image, and 20 is part 3-dimensional digital signal, and 21 is three-dimensional part model, and 22 for surveying
Amount triggers signal, and 23 is adaptive scanning strategy, and 24 is measurement pointcloud data, and 25 is robot Pose Control signal, and 26 is machine
Device people's pose feedback signal, 17 is joint of robot motor control signal, and 28 is joint of robot motor feedback signals, and 29 is position
Appearance signal, 30 is scan control signal, and 31 is position digital signal, and 32 is scanning signal, and 33 is laser signal, and 34 touch for measuring
Send out switch.
Detailed description of the invention
Below in conjunction with the accompanying drawings the invention is described in further details.
As it is shown in figure 1, intelligent scanning type on-line measurement system based on image recognition of the present invention, know including image
Other locating module, six-DOF robot laser scanning measurement module, measurement control module, also include welding and assembling production lines 12, position
On retinue platform 8 on welding and assembling production lines 12, the pallet pallet 9 being positioned on retinue platform 8, pallet pallet 9
Part 11 on fixture 10 and fixture 10, wherein image recognition locating module by CCD camera trigger switch 1, CCD camera 2,
CCD camera support 3, CCD camera electronic control unit (ECU) 13 form, and CCD camera triggers switch 1 and is positioned on production line, is positioned at
CCD camera 2 is supported in above production line by the CCD camera support 3 on production line side；Six-DOF robot laser scanning measurement
Module is measured robotic arm 4, robot measurement Position and attitude sensor 5, robot measurement joint motor 6, laser scanning by six degree of freedom
Measurement 7, measurement triggering switch 34, measurement triggering switchs 34 and is positioned at production line measurement station, and laser scanning head 7 is positioned at six certainly
Measured the end of robotic arm 1 by degree, robot measurement joint motor 6 and robot measurement Position and attitude sensor 7 are positioned at six degree of freedom
Measure each joint of robotic arm 1；Measure control module by central processing unit 14, measurement system controller 15, robot measurement
Pose ECU16, measurement head ECU17 composition.
As in figure 2 it is shown, intelligent scanning type on-line measurement system intelligent scanning based on image recognition of the present invention inspection
Survey control method:
1) setting up intelligent scanning policy database, process is: first by production line the zero of all kinds of online production
Part threedimensional model 21 imports central processing unit 14, and central processing unit 14 is special according to the model of the threedimensional model 21 of each part to be measured
The threedimensional model 21 of part to be measured is converted to the target measurement point cloud of gridding domain type by measurement requirement of seeking peace, and then according to mesh
Mark measurement pointcloud makes the adaptive scanning strategy 23 meeting the aspect of model and measurement requirement；
2) image recognition carry out initial alignment, process is: when part 11 has welded the mistake that rearward measurement station moves
Cheng Zhong, when CCD camera triggers switch 1, CCD camera triggering switch 1 is triggered and sends CCD camera triggering letter to CCD camera 2
Numbers 18, and then control CCD camera 2 part 11 is shot, the three-dimensional part drawing of part 11 that CCD camera 2 will obtain subsequently
As 19 pass to CCD camera ECU13, three-dimensional part image 19, through processing, is converted to band coordinate position by CCD camera ECU13
Part 3-dimensional digital signal 20 and pass to central processing unit 14, central processing unit 14 is according to part three dimension of band coordinate position
Word signal 20, three-dimensional part model 21, first according to the feature identification of part 3-dimensional digital signal 20 go out corresponding part and with lead
The corresponding three-dimensional part model 21 entered is corresponding, and identifies the coordinate information that this three-dimensional part model 21 elements of fix is corresponding, real
Existing image identification function；Then the elements of fix coordinate of part 3-dimensional digital signal 20 correspondence obtained by image information is believed
Breath, in conjunction with robot measurement initial coordinate position, and part 11 arrives the initial coordinate measuring position, obtains measuring machine
People is for the measurement coordinate of part 11 to be measured；Last the most again by the elements of fix coordinate information of part 3-dimensional digital signal 20 correspondence with
In target measurement point cloud, corresponding key element coordinate information carries out optimal fitting, thus realizes image initial positioning function, by robot
Scanning survey coordinate and simulated target measurement pointcloud coordinate unification, thus the initial ginseng of scanning is provided for follow-up adaptive scanning
Examine benchmark.
3) scanning survey adaptively, process is: when the retinue platform loading part 11 arrives and measures station, be positioned at survey
Measurement at amount station triggers switch 34 and will be triggered, and sends measurement to measurement system controller 15 and triggers signal 22, measures system
System controller 15 receives after measurement triggers signal 22 and starts process of measurement, measures system controller 15 according to central processing unit 14
The robot pose feedback signal 26 that the adaptive scanning strategy 23 gone out and robot measurement pose ECU16 send generates machine
People's Pose Control signal 25 passes to robot measurement pose ECU16, and robot measurement pose ECU16 is according to robot Pose Control
The pose signal 29 that signal 25 and robot measurement Position and attitude sensor 5 are surveyed generates joint of robot motor control signal 27,
Thus control the pose of robot measurement joint motor 6, make laser scanning head 7 arrive scan position；When laser scanning head 7 arrives
During scan position, measuring system controller 15 will receive from the robot pose feedback that robot measurement pose ECU16 sends
Signal 26, then measure system controller 15 send scan control signal 30 to measure head ECU17, by measure head ECU17 generate
Scanning signal 32, thus control laser scanning head 7 and implement scanning；Measure head ECU17 by the laser signal from laser scanning head 7
33 are converted to position digital signal 31 passes to measurement system controller 15, measures system controller 15 according to position digital signal 31
And robot pose feedback signal 26 generates measurement pointcloud data 24 and passes central processing unit 14 back, central processing unit 14 will be measured
Present together with the target measurement point cloud that cloud data 24 is changed with the threedimensional model 20 of workpiece for measurement, thus in real time measurement is tied
Fruit presents, it is achieved the adaptive scanning to workpiece for measurement.
4) the accurate second positioning process during scanning survey is: when measuring beginning, receives when measuring system controller 15
Start process of measurement to measuring to trigger to switch after 34 measurements sent trigger signal 22, measure system controller 15 and first control to measure
System completes the elements of fix scanning of three-dimensional part model 21 correspondence, and central processing unit 14 receives the scanning of initial alignment key element and surveys
After amount cloud data 24, by the scanning survey cloud data 24 of initial alignment key element and corresponding key element coordinate in target measurement point cloud
Information carries out quadratic fit, thus realizes laser scanning secondary precise locating function, and Robot Scanning is measured coordinate and model
Target measurement point cloud coordinate is accurately directed at, thus provides the exact references benchmark of scanning for follow-up adaptive scanning.
5) the scanning strategy renewal process during scanning survey is: central processing unit 14 receives measurement pointcloud data 24
After, in conjunction with threedimensional model 21 and the target measurement point cloud of part 11 to be measured, calculate the target measurement point cloud to be measured made new advances, formulate
The adaptive scanning strategy 23 made new advances passes to measurement system controller 15, measures system controller 15 according to new adaptive scanning
Strategy 23 measures, thus realizes the scanning strategy 23 dynamic adjustment with scanning process, until completing the survey of part 11 to be measured
Amount, robot measurement returns initial position subsequently.
The preferred embodiment of the present invention described in detail above.Should be appreciated that the ordinary skill of this area is without wound
The property made work just can make many modifications and variations according to the design of the present invention.Therefore, all technical staff in the art
The most on the basis of existing technology by the available technology of logical analysis, reasoning, or a limited experiment
Scheme, all should be in the protection domain being defined in the patent claims.
Claims (10)
1. an intelligent scanning on-line measurement system based on image recognition, it is characterised in that include image recognition locating module,
Six-DOF robot laser scanning measurement module, measurement control module, wherein said image recognition locating module includes CCD phase
Machine triggers switch, CCD camera, CCD camera support, CCD camera electronic control unit ECU；During described measurement control module includes
Central processor, measurement system controller, robot measurement pose ECU, measurement head ECU；Described six-DOF robot laser is swept
Retouch measurement module and include that six degree of freedom measures robotic arm, robot measurement Position and attitude sensor, robot measurement joint motor, laser
Scanning survey head, measurement trigger switch.
2. intelligent scanning on-line measurement system based on image recognition as claimed in claim 1, it is characterised in that described CCD
Camera triggers switch and is positioned on production line, and described CCD camera is supported in life by the described CCD camera support being positioned at production line side
Produce above line.
3. intelligent scanning on-line measurement system based on image recognition as claimed in claim 1, it is characterised in that described measurement
Pose data and measurement data that described robot measurement pose ECU and described measurement head ECU is gathered by system controller send
To described central processing unit, the control command of described central processing unit is sent to simultaneously described robot measurement pose ECU and
Described measurement head ECU.
4. intelligent scanning on-line measurement system based on image recognition as claimed in claim 1, it is characterised in that described measurement
Triggering switch to be positioned at production line measurement station, described laser scanning head is positioned at described six degree of freedom and measures the end of robotic arm,
Described robot measurement joint motor and described robot measurement Position and attitude sensor are positioned at six degree of freedom and measure each pass of robotic arm
At joint.
5. an intelligent scanning On-line Measuring Method based on image recognition, it is characterised in that comprise the following steps:
Step 1, set up intelligent scanning policy database；
Step 2, image recognition also carry out initial alignment；
Step 3, adaptively scanning survey；
Accurate second positioning during step 4, scanning survey；
Scanning strategy during step 5, scanning survey updates.
6. intelligent scanning On-line Measuring Method based on image recognition as claimed in claim 5, it is characterised in that in step 1
In, also include
Step 1.1, by production line all kinds of online production three-dimensional part model import central processing unit；
Step 1.2, central processing unit according to the aspect of model of the threedimensional model of each part to be measured and measurement requirement by be measured zero
The threedimensional model of part is converted to the target measurement point cloud of gridding domain type；
Step 1.3, foundation target measurement point cloud make the adaptive scanning strategy meeting the aspect of model and measurement requirement.
7. intelligent scanning On-line Measuring Method based on image recognition as claimed in claim 5, it is characterised in that in step 2
In, also include
Step 2.1, weld during rearward measurement station moves when part, when CCD camera triggers switch, CCD
Camera triggers switch and is triggered to CCD camera transmission CCD camera triggering signal, and then part is shot by control CCD camera；
The three-dimensional part image of the part of acquisition is passed to CCD camera ECU by step 2.2, CCD camera, at CCD camera ECU process
Reason, is converted to the part 3-dimensional digital signal of band coordinate position by three-dimensional part image and passes to central processing unit；
Step 2.3, central processing unit go out corresponding part corresponding to import according to the feature identification of part 3-dimensional digital signal
Three-dimensional part model is corresponding, and identifies the coordinate information that this three-dimensional part model elements of fix is corresponding, it is achieved image recognition merit
Energy；
Elements of fix coordinate corresponding for the part 3-dimensional digital signal obtained by image information is believed by step 2.4, central processing unit
Breath, in conjunction with robot measurement initial coordinate position, and part arrives the initial coordinate measuring position, obtains robot measurement
Measurement coordinate for part to be measured；
Step 2.5, by elements of fix coordinate information corresponding for part 3-dimensional digital signal and corresponding key element in target measurement point cloud
Coordinate information carries out optimal fitting, thus realizes image initial positioning function, and Robot Scanning is measured coordinate and simulated target
Measurement pointcloud coordinate unification, provides the basis reference of scanning for follow-up adaptive scanning.
8. intelligent scanning On-line Measuring Method based on image recognition as claimed in claim 5, it is characterised in that in step 3
In, also include
Step 3.1, when the retinue platform loading part arrives and measures station, be positioned at measure the measurement at station trigger switch will
Being triggered, send measurement triggering signal to measuring system controller, measurement system controller receives after measurement triggers signal and starts
Process of measurement；
Step 3.2, measure the adaptive scanning strategy that sends according to central processing unit of system controller and robot measurement position
The robot pose feedback signal that appearance ECU is sent generates robot Pose Control signal and passes to robot measurement pose ECU, measures
The pose signal that robot pose ECU is surveyed according to robot Pose Control signal and robot measurement Position and attitude sensor generates
Joint of robot motor control signal, thus control the pose of robot measurement joint motor, make laser scanning head arrive scanning
Position；
Step 3.3, when laser scanning head arrive scan position time, measure system controller will receive from robot measurement pose
The robot pose feedback signal that ECU sends, measures system controller and sends scan control signal extremely measurement head ECU, by measuring
Head ECU generates scanning signal, thus controls laser scanning head and complete scanning；
Laser signal from laser scanning head is converted to position digital signal and passes to measurement system by step 3.4, measurement head ECU
Controller, measures system controller and generates measurement pointcloud data biography according to position digital signal and robot pose feedback signal
Return central processing unit；
Step 3.5, central processing unit are by the target measurement point cloud one of measurement pointcloud data with the threedimensional model conversion of workpiece for measurement
Rise and in real time measurement result is presented.
9. intelligent scanning On-line Measuring Method based on image recognition as claimed in claim 5, it is characterised in that in step 4
In, also include
Step 4.1, receive to measure to trigger after the measurement that sends of switch triggers signal and start process of measurement when measuring system controller,
Measurement system controller first controls measurement system and completes the elements of fix scanning that three-dimensional part model is corresponding, and central processing unit receives
After the scanning survey cloud data of initial alignment key element, by the scanning survey cloud data of initial alignment key element and target measurement point
In cloud, corresponding key element coordinate information carries out quadratic fit；
Step 4.2, Robot Scanning is measured coordinate accurately it is directed at simulated target measurement pointcloud coordinate, sweep for follow-up self adaptation
Retouch the exact references benchmark that scanning is provided.
10. intelligent scanning On-line Measuring Method based on image recognition as claimed in claim 5, it is characterised in that in step 5
In, also include
After step 5.1, central processing unit receive measurement pointcloud data, in conjunction with threedimensional model and the target measurement point of part to be measured
Cloud, calculates the target measurement point cloud to be measured made new advances, and formulates the adaptive scanning strategy made new advances and passes to measurement system controller；
Step 5.2, measurement system controller measure according to new adaptive scanning strategy thus realize scanning strategy with sweeping
Retouch the dynamic adjustment of process, until completing the measurement of part to be measured；
Step 5.3, robot measurement return initial position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610704368.5A CN106323167B (en) | 2016-08-22 | 2016-08-22 | A kind of intelligent scanning on-line measurement system and measurement method based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610704368.5A CN106323167B (en) | 2016-08-22 | 2016-08-22 | A kind of intelligent scanning on-line measurement system and measurement method based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106323167A true CN106323167A (en) | 2017-01-11 |
| CN106323167B CN106323167B (en) | 2019-06-07 |
Family
ID=57741858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610704368.5A Active CN106323167B (en) | 2016-08-22 | 2016-08-22 | A kind of intelligent scanning on-line measurement system and measurement method based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106323167B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106705847A (en) * | 2017-01-18 | 2017-05-24 | 重庆市计量质量检测研究院 | Geometric size measuring method and device for slit inside free-form surface |
| CN106767517A (en) * | 2017-01-18 | 2017-05-31 | 重庆市计量质量检测研究院 | Trailing edge slot pattern automatic acquiring method and harvester in a kind of free form surface |
| CN107144236A (en) * | 2017-05-25 | 2017-09-08 | 西安交通大学苏州研究院 | A kind of robot automatic scanner and scan method |
| CN107270833A (en) * | 2017-08-09 | 2017-10-20 | 武汉智诺维科技有限公司 | A kind of complex curved surface parts three-dimension measuring system and method |
| CN107576503A (en) * | 2017-09-01 | 2018-01-12 | 西北工业大学 | Aero-engine high accuracy assembly quality detector device people's system |
| CN107598775A (en) * | 2017-07-27 | 2018-01-19 | 芜湖微云机器人有限公司 | It is a kind of by laser detect the method that simultaneously multi-axis robot is polished |
| CN108274302A (en) * | 2017-12-25 | 2018-07-13 | 重庆达德机械制造有限公司 | A kind of intelligence tuber |
| CN108274092A (en) * | 2017-12-12 | 2018-07-13 | 北京石油化工学院 | Groove automatic cutting system and cutting method based on 3D vision and Model Matching |
| CN108362223A (en) * | 2017-11-24 | 2018-08-03 | 广东康云多维视觉智能科技有限公司 | A kind of portable 3D scanners, scanning system and scan method |
| CN108489361A (en) * | 2018-03-02 | 2018-09-04 | 昆山艾尔发计量科技有限公司 | A kind of logical only detecting system of workpiece with hole |
| CN109839075A (en) * | 2017-11-29 | 2019-06-04 | 沈阳新松机器人自动化股份有限公司 | A kind of robot automatic measurement system and measurement method |
| CN110006361A (en) * | 2019-03-12 | 2019-07-12 | 精诚工科汽车系统有限公司 | Part automated detection method and system based on industrial robot |
| CN110174346A (en) * | 2019-05-06 | 2019-08-27 | 江苏耀群工业技术有限公司 | Autoregistration strainer scan method and device |
| CN110207619A (en) * | 2019-04-10 | 2019-09-06 | 北京航星机器制造有限公司 | The measuring system and method for cooperation mechanical arm are carried based on omni-directional moving platform |
| CN110244653A (en) * | 2019-06-13 | 2019-09-17 | 深圳市腾浩科技有限公司 | The Toolpath Generation method of workpiece |
| CN111397507A (en) * | 2019-12-30 | 2020-07-10 | 宁波大正工业机器人技术有限公司 | Disc part laser calibration method |
| CN113379905A (en) * | 2021-07-16 | 2021-09-10 | 秦皇岛信能能源设备有限公司 | Wheel hub is 3D vision intelligent identification and control system for production line |
| CN113959352A (en) * | 2021-10-19 | 2022-01-21 | 上海交通大学 | Flexible point location direction identification system and method |
| CN115717868A (en) * | 2022-10-08 | 2023-02-28 | 北京航天计量测试技术研究所 | Real-time online three-dimensional automatic scanning measurement system |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI821027B (en) * | 2022-11-17 | 2023-11-01 | 英業達股份有限公司 | Component matching and reporting method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101044505A (en) * | 2004-07-23 | 2007-09-26 | 3形状股份有限公司 | Adaptiv 3d scanning |
| CN101236660A (en) * | 2008-03-06 | 2008-08-06 | 张利群 | Three-dimensional scanners and its three-dimensional model reconfiguration method |
| CN102663810A (en) * | 2012-03-09 | 2012-09-12 | 北京航空航天大学 | Full-automatic modeling approach of three dimensional faces based on phase deviation scanning |
| CN202523112U (en) * | 2012-04-09 | 2012-11-07 | 北京拓博尔机器人科技有限公司 | System for reconstructing three-dimensional model by robot carrying laser scanner |
| CN104036546A (en) * | 2014-06-30 | 2014-09-10 | 清华大学 | Method for carrying out face three-dimensional reconstruction at any viewing angle on basis of self-adaptive deformable model |
| US20150030253A1 (en) * | 2013-07-24 | 2015-01-29 | Fu Tai Hua Industry (Shenzhen) Co., Ltd. | Electronic device and method for measuring point cloud of an object |
-
2016
- 2016-08-22 CN CN201610704368.5A patent/CN106323167B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101044505A (en) * | 2004-07-23 | 2007-09-26 | 3形状股份有限公司 | Adaptiv 3d scanning |
| CN101236660A (en) * | 2008-03-06 | 2008-08-06 | 张利群 | Three-dimensional scanners and its three-dimensional model reconfiguration method |
| CN102663810A (en) * | 2012-03-09 | 2012-09-12 | 北京航空航天大学 | Full-automatic modeling approach of three dimensional faces based on phase deviation scanning |
| CN202523112U (en) * | 2012-04-09 | 2012-11-07 | 北京拓博尔机器人科技有限公司 | System for reconstructing three-dimensional model by robot carrying laser scanner |
| US20150030253A1 (en) * | 2013-07-24 | 2015-01-29 | Fu Tai Hua Industry (Shenzhen) Co., Ltd. | Electronic device and method for measuring point cloud of an object |
| CN104036546A (en) * | 2014-06-30 | 2014-09-10 | 清华大学 | Method for carrying out face three-dimensional reconstruction at any viewing angle on basis of self-adaptive deformable model |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106705847B (en) * | 2017-01-18 | 2019-04-05 | 重庆市计量质量检测研究院 | Gap geometric dimension measurement method and device in a kind of free form surface |
| CN106767517A (en) * | 2017-01-18 | 2017-05-31 | 重庆市计量质量检测研究院 | Trailing edge slot pattern automatic acquiring method and harvester in a kind of free form surface |
| CN106705847A (en) * | 2017-01-18 | 2017-05-24 | 重庆市计量质量检测研究院 | Geometric size measuring method and device for slit inside free-form surface |
| CN106767517B (en) * | 2017-01-18 | 2019-03-01 | 重庆市计量质量检测研究院 | Trailing edge slot pattern automatic acquiring method and acquisition device in a kind of free form surface |
| CN107144236A (en) * | 2017-05-25 | 2017-09-08 | 西安交通大学苏州研究院 | A kind of robot automatic scanner and scan method |
| CN107598775A (en) * | 2017-07-27 | 2018-01-19 | 芜湖微云机器人有限公司 | It is a kind of by laser detect the method that simultaneously multi-axis robot is polished |
| CN107270833A (en) * | 2017-08-09 | 2017-10-20 | 武汉智诺维科技有限公司 | A kind of complex curved surface parts three-dimension measuring system and method |
| CN107576503A (en) * | 2017-09-01 | 2018-01-12 | 西北工业大学 | Aero-engine high accuracy assembly quality detector device people's system |
| CN108362223A (en) * | 2017-11-24 | 2018-08-03 | 广东康云多维视觉智能科技有限公司 | A kind of portable 3D scanners, scanning system and scan method |
| CN109839075A (en) * | 2017-11-29 | 2019-06-04 | 沈阳新松机器人自动化股份有限公司 | A kind of robot automatic measurement system and measurement method |
| CN108274092A (en) * | 2017-12-12 | 2018-07-13 | 北京石油化工学院 | Groove automatic cutting system and cutting method based on 3D vision and Model Matching |
| CN108274302A (en) * | 2017-12-25 | 2018-07-13 | 重庆达德机械制造有限公司 | A kind of intelligence tuber |
| CN108489361A (en) * | 2018-03-02 | 2018-09-04 | 昆山艾尔发计量科技有限公司 | A kind of logical only detecting system of workpiece with hole |
| CN110006361A (en) * | 2019-03-12 | 2019-07-12 | 精诚工科汽车系统有限公司 | Part automated detection method and system based on industrial robot |
| CN110207619A (en) * | 2019-04-10 | 2019-09-06 | 北京航星机器制造有限公司 | The measuring system and method for cooperation mechanical arm are carried based on omni-directional moving platform |
| CN110174346A (en) * | 2019-05-06 | 2019-08-27 | 江苏耀群工业技术有限公司 | Autoregistration strainer scan method and device |
| CN110244653A (en) * | 2019-06-13 | 2019-09-17 | 深圳市腾浩科技有限公司 | The Toolpath Generation method of workpiece |
| CN110244653B (en) * | 2019-06-13 | 2020-10-09 | 深圳市腾浩科技有限公司 | Method for planning machining trajectory of workpiece |
| CN111397507A (en) * | 2019-12-30 | 2020-07-10 | 宁波大正工业机器人技术有限公司 | Disc part laser calibration method |
| CN111397507B (en) * | 2019-12-30 | 2021-10-01 | 宁波大正工业机器人技术有限公司 | Disc part laser calibration method |
| CN113379905A (en) * | 2021-07-16 | 2021-09-10 | 秦皇岛信能能源设备有限公司 | Wheel hub is 3D vision intelligent identification and control system for production line |
| CN113959352A (en) * | 2021-10-19 | 2022-01-21 | 上海交通大学 | Flexible point location direction identification system and method |
| CN115717868A (en) * | 2022-10-08 | 2023-02-28 | 北京航天计量测试技术研究所 | Real-time online three-dimensional automatic scanning measurement system |
| CN115717868B (en) * | 2022-10-08 | 2023-11-07 | 北京航天计量测试技术研究所 | Real-time online three-dimensional automatic scanning measurement system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106323167B (en) | 2019-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106323167A (en) | Intelligent scanning online measurement system and intelligent scanning online measurement method based on image identification | |
| CN106091931A (en) | A kind of adaptive scanning based on threedimensional model measures system and control method thereof | |
| CN106163771B (en) | Method and system for robot 3D printing | |
| Mineo et al. | Robotic path planning for non-destructive testing–A custom MATLAB toolbox approach | |
| EP1043126B1 (en) | Teaching model generating method | |
| CN102825602B (en) | PSD (Position Sensitive Detector)-based industrial robot self-calibration method and device | |
| CN106064377B (en) | A kind of excitation track optimizing method of robot for space dynamic parameters identification | |
| US20190193268A1 (en) | Robotic arm processing system and method, and non-transitory computer-readable storage medium therefor | |
| CN111595949B (en) | Laser ultrasonic imaging detection system and detection method for self-adaptive irregular surface | |
| Mineo et al. | Flexible integration of robotics, ultrasonics and metrology for the inspection of aerospace components | |
| CN106600681A (en) | A method for polishing a curved surface having obstacles | |
| CN205748263U (en) | The online detection unit of artificial intelligence's sheet metal component production system | |
| CN105699487A (en) | Manipulator detection device and method for residual stress of complex component | |
| CN103759635A (en) | Scanning measurement robot detection method allowing precision to be irrelevant to robot | |
| CN104502456A (en) | Single-manipulator ultrasonic non-destructive testing device and single-manipulator ultrasonic non-destructive testing method | |
| CN205734940U (en) | A kind of online fast calibration device of TCP being applied to industrial robot | |
| CN110196231A (en) | A kind of laser-ultrasound off-line detection device and method increasing material product | |
| CN108982664A (en) | A kind of double-manipulator supersonic detection method | |
| CN114295728A (en) | Ultrasonic three-dimensional tomography method for internal defects of complex curved surface workpiece | |
| Rémy et al. | Hand-eye calibration | |
| CN206825428U (en) | A kind of real-time acquisition device of three-dimensional point cloud | |
| CN113850280A (en) | Intelligent airplane part code spraying identification method and device, storage medium and equipment | |
| CN1987344A (en) | Flexible three dimension holographic measuring system | |
| CN106291919A (en) | Optical probe and the equipment of measurement | |
| Riise et al. | Adapting robot paths for automated NDT of complex structures using ultrasonic alignment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |