CN108507472B - Non-contact visual detection method for size of automobile safety airbag seal - Google Patents
Non-contact visual detection method for size of automobile safety airbag seal Download PDFInfo
- Publication number
- CN108507472B CN108507472B CN201810222752.0A CN201810222752A CN108507472B CN 108507472 B CN108507472 B CN 108507472B CN 201810222752 A CN201810222752 A CN 201810222752A CN 108507472 B CN108507472 B CN 108507472B
- Authority
- CN
- China
- Prior art keywords
- seal
- linear array
- array camera
- distance
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/04—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness specially adapted for measuring length or width of objects while moving
- G01B11/043—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness specially adapted for measuring length or width of objects while moving for measuring length
-
- 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
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/04—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness specially adapted for measuring length or width of objects while moving
- G01B11/046—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness specially adapted for measuring length or width of objects while moving for measuring width
-
- 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
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B5/00—Measuring arrangements characterised by the use of mechanical techniques
- G01B5/0025—Measuring of vehicle parts
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Air Bags (AREA)
Abstract
The invention belongs toThe field of automobile part product detection, and relates to a non-contact visual detection method for the size of an automobile safety airbag seal. Firstly, a linear array camera is adopted to collect images, a system is started, the operation of a torque motor enables an absolute value type incremental encoder to send pulses to a data acquisition card, and then the linear array camera is triggered to scan line by line to obtain complete air bag seal images. After the phase taking is finished, the image acquisition module transmits image information to the upper computer module, the upper computer module performs data processing, and two long-edge straight lines L of the seal are fitted by a least square method1、L2Two wide-edge straight lines L of seal3、L4The adjacent seal broadside L of the spacer seal5Then L is measured by an image processing algorithm1、L2A distance D between1,2，L3、L4A distance D between3,4，L2、L5A distance D between2,5And displaying the detected data result and storing the data. The detection method can realize the non-contact rapid, accurate and automatic detection of the size of the seal of the automobile safety airbag.
Description
Technical Field
The invention belongs to the field of visual detection of automobile part products, and relates to a non-contact visual detection method for the size of an automobile safety airbag seal.
Background
With the rapid development of advanced manufacturing technology in China and the reduction of automobile manufacturing cost, automobiles are widely popularized in daily life of people, and great convenience is brought to daily trips of people.
The production quality of the air bag seal, which is an important component of the air bag, directly affects the safe use of the air bag, and if the length, the width, the interval and other dimensions of the seal exceed the range, the normal ejection of the air bag under emergency can be affected. The traditional dimension measurement of the air bag seal is carried out manually by measuring tools such as a vernier caliper, and the defects of inaccurate detection and low efficiency exist.
Disclosure of Invention
In order to solve the problems, the invention provides a non-contact visual detection method for measuring the size of an air bag seal based on machine vision.
The technical scheme adopted by the invention is as follows:
a non-contact visual detection device for the size of an air bag seal comprises an image acquisition module and a motion control module; the image acquisition module comprises a linear array Camera, a linear array lens, a light source and a data acquisition card, wherein the linear array lens is arranged on the linear array Camera, the installation and irradiation angle of the light source covers the acquisition visual field of the whole linear array Camera, and the linear array Camera is connected to the data acquisition card in a PCI slot of the industrial control computer through a Camera Link communication protocol; the motion control module comprises a torque motor, an encoder, a CMOS photoelectric sensor and a PLC, and the industrial control computer is in communication connection with the PLC through I/O; the torque motor is used for driving the seal belt conveyor belt and the encoder to rotate, the encoder is used for measuring the rotating speed of the motor and sending a corresponding pulse signal to the data acquisition card, and the CMOS photoelectric sensor is connected with the digital quantity input end of the PLC and used for detecting the relative position of the seal belt; the linear array camera finishes image acquisition according to an external trigger signal sent by the PLC and a pulse signal provided by the data acquisition card.
The non-contact visual detection method for the size of the seal of the automobile safety airbag by adopting the device comprises the following steps:
the method comprises the following steps: the air bag seal is attached to the conveyor belt, and the seal belt is fixed on the two torque motors, so that the seal moves according to a fixed position and a track when the conveyor belt runs at a high speed, and the situation that a detection image cannot be used due to the offset of the seal is avoided.
Step two: the linear array camera is adopted to collect images, the system is started, the operation of the torque motor enables the absolute value type incremental encoder to send pulses to the data acquisition card, the linear array camera is triggered to scan line by line to obtain complete airbag seal images, and the airbag seal images are transmitted to an upper computer to be processed.
Step three: after the image is obtained, the sizes of two long sides, two wide sides and adjacent wide sides of the interval seal are measured by a straight line fitting method in sub-pixel measurement, and the specific size detection method is as follows:
(1) fitting two long-edge straight lines L of the seal by a least square method1(Row11,Column11；Row12,Column12)、L2(Row21 Column 21; Row22 Column22) and two straight broadside lines L of seal3(Row31,Column31；Row32,Column32)、L4(Row41, Column 41; Row42, Column42), spacer seal immediately adjacent seal broadside L5(Row51,Column51；Row52,Column52)。
(2) L is measured by an image processing algorithm1、L2A distance D between1,2，L3、L4A distance D between3,4，L2、L5A distance D between2,5。
Calibrating and calibrating the linear array camera, and selecting a checkerboard calibration plate with a grid of 0.5mm by 0.5 mm; straight lines are fitted in the corresponding edge areas of the seal to obtain 5 straight lines L in total1(Row11,Column11；Row12,Column12)、L2(Row21,Column21；Row22,Column22)、L3(Row31,Column31；Row32,Column32)、L4(Row41,Column41；Row42,Column42)、L5(Row51, Column 51; Row52, Column 52). Measure L1、L2A distance D between1,2，L3、L4A distance D between3,4，L2、L5A distance D between2,5Coordinates of 5 straight lines are in accordance with the following relations:
calibrating and calibrating the image acquired by the linear array camera, correcting perspective distortion, radial distortion and plane linear distortion by adopting a nonlinear correction mode, and selecting invariant feature points of the seal for matching and positioning to obtain the position information of the matched image.
The light source adopts a Dome lamp, and the back is polished in a polishing mode.
The encoder adopts an absolute value encoder.
The non-contact visual detection method for the size of the seal of the automobile safety airbag adopts non-contact detection, has high automation degree and strong operability, saves a large amount of labor cost, improves the measurement precision and reliability, and has wide market application prospect.
Drawings
FIG. 1 is a schematic structural diagram of a non-contact visual inspection device for the size of an airbag seal of an automobile.
Figure 2 is a schematic view of an airbag seal test (containing 5 straight lines and 3 length measurements to be fitted).
FIG. 3 is a flow chart of the detection method of the present invention.
In fig. 1: 1, a line scan camera; 2, linear array lens; 3, conveying a belt; 4, a torque motor; 5, PLC; 6, displaying a screen; 7 an industrial control computer; 8CMOS sensors; 9 an encoder; 10 light source.
Detailed Description
The following detailed description of specific embodiments of the present invention is provided in connection with the accompanying drawings.
(1) When the detection is started, firstly, the air bag seal is installed in place, the positions of the torque motor and the acrylic plate are fixed, and the speeds of the first torque motor and the second torque motor are respectively adjusted. After formal starting, the torque motor drives the seal conveyor belt to rotate, and 5000 pulses are transmitted to the data acquisition card by each circle of rotation of the absolute value type incremental encoder under the traction of the seal conveyor belt, so that the linear array camera is triggered to shoot a complete image.
(2) Obtaining image post-processing, calibrating and calibrating the linear array camera, selecting a checkerboard calibration board with the specification of 300mm multiplied by 300mm, and correcting perspective distortion and plane distortion by adopting a nonlinear correction mode; the method comprises the following specific steps: the method comprises the steps of collecting images containing a calibration plate, taking images from different angles, generating a calibration file through analysis of the collected images, and loading information of the calibration file into an upper computer template.
(3) And acquiring an image, searching to obtain a template, positioning, and searching to obtain coordinate information of the edge of the seal by adopting the edge characteristic of the offline safety airbag seal of the positioning function according to the corresponding relation between the template and the matched image.
(4) Image processing, fitting the short edge of the seal by adopting a least square method in the corresponding edge area of the short edge to obtain the characteristics of a short edge pair, and measuring the edge pair distance D by using an edge pair distance measurement function1,2(ii) a Fitting the long edge of the seal by adopting a least square method in the corresponding edge area of the long edge to obtain the characteristics of a long edge pair, and measuring the edge pair distance D by using the edge pair distance measurement function again3,4(ii) a Fitting the wide edge of one seal to obtain a straight line, fitting the adjacent wide edge of the interval seal again to obtain another straight line, and calculating the distance D between two sub-pixel edge pairs after fitting2,5。
Because non-contact detection equipment has some artificial deviation, so in first round debugging test, need fix baffle, gyro wheel, moment motor mechanical device installation, guarantee moment motor when high-speed operation, the air bag strip of paper used for sealing can not take place to vibrate because of air resistance, squint. The upper computer can display images and size data acquired by the camera in real time and generate reports of the data for subsequent inquiry and retrieval.
Claims (2)
1. A non-contact visual detection method for the size of an automobile safety air bag seal is characterized in that a non-contact visual detection device for the size of the safety air bag seal adopted by the non-contact visual detection method comprises an image acquisition module and a motion control module; the image acquisition module comprises a linear array Camera, a linear array lens, a light source and a data acquisition card, wherein the linear array lens is arranged on the linear array Camera, the installation and irradiation angle of the light source covers the acquisition visual field of the whole linear array Camera, and the linear array Camera is connected to the data acquisition card in a PCI slot of the industrial control computer through a Camera Link communication protocol; the motion control module comprises a torque motor, an encoder, a CMOS photoelectric sensor and a PLC, and the industrial control computer is in communication connection with the PLC through I/O; the torque motor is used for driving the seal belt conveyor belt and the encoder to rotate, the encoder is used for measuring the rotating speed of the motor and sending a corresponding pulse signal to the data acquisition card, and the CMOS photoelectric sensor is connected with the digital quantity input end of the PLC and used for detecting the relative position of the seal belt; the linear array camera finishes image acquisition according to an external trigger signal sent by the PLC and a pulse signal provided by the data acquisition card;
the encoder adopts an absolute value encoder;
the non-contact visual detection method for the size of the seal of the automobile safety airbag by adopting the device comprises the following specific steps:
the method comprises the following steps: the air bag seal is attached to the conveyor belt, and the seal belt is fixed on the two torque motors, so that the seal moves according to a fixed position and a track when the conveyor belt runs at a high speed, and the situation that a detection image cannot be used due to the offset of the seal is avoided;
step two: the linear array camera is adopted to collect images, the system is started, the operation of the torque motor enables the absolute value type incremental encoder to send pulses to the data acquisition card, the linear array camera is triggered to scan line by line to obtain complete airbag seal images, and the airbag seal images are transmitted to an upper computer to be processed;
step three: after the image is obtained, the sizes of two long sides, two wide sides and adjacent wide sides of the interval seal are measured by a straight line fitting method in sub-pixel measurement, and the specific size detection method is as follows:
(1) fitting two long-edge straight lines L of the seal by a least square method1(Row11,Column11；Row12,Column12)、L2(Row21 Column 21; Row22 Column22) and two straight broadside lines L of seal3(Row31,Column31；Row32,Column32)、L4(Row41, Column 41; Row42, Column42), spacer seal immediately adjacent seal broadside L5(Row51,Column51；Row52,Column52)；
(2) L is measured by an image processing algorithm1、L2A distance D between1,2，L3、L4A distance D between3,4，L2、L5A distance D between2,5；
Calibrating and calibrating the linear array camera, and selecting a checkerboard calibration plate with a grid of 0.5mm by 0.5 mm; fitting straight lines in the corresponding edge regions of the sealGo out straight lines to obtain 5 straight lines L in total1(Row11,Column11；Row12,Column12)、L2(Row21,Column21；Row22,Column22)、L3(Row31,Column31；Row32,Column32)、L4(Row41,Column41；Row42,Column42)、L5(Row51, Column 51; Row52, Column 52); measure L1、L2A distance D between1,2，L3、L4A distance D between3,4，L2、L5A distance D between2,5Coordinates of 5 straight lines are in accordance with the following relations:
calibrating and calibrating the image acquired by the linear array camera, correcting perspective distortion, radial distortion and plane linear distortion by adopting a nonlinear correction mode, and selecting invariant feature points of the seal for matching and positioning to obtain the position information of the matched image.
2. The method of claim 1, wherein the light source is a Dome lamp and the back is illuminated by a light.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810222752.0A CN108507472B (en) | 2018-03-19 | 2018-03-19 | Non-contact visual detection method for size of automobile safety airbag seal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810222752.0A CN108507472B (en) | 2018-03-19 | 2018-03-19 | Non-contact visual detection method for size of automobile safety airbag seal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108507472A CN108507472A (en) | 2018-09-07 |
| CN108507472B true CN108507472B (en) | 2020-09-15 |
Family
ID=63375867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810222752.0A Active CN108507472B (en) | 2018-03-19 | 2018-03-19 | Non-contact visual detection method for size of automobile safety airbag seal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108507472B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109202903B (en) * | 2018-09-13 | 2021-05-28 | 河南机电职业学院 | Method for calibrating countsPerMeter parameter and base standard system of sorting robot workstation conveying chain |
| CN109631764B (en) * | 2018-11-22 | 2020-12-04 | 南京理工大学 | Dimension measuring system and method based on RealSense camera |
| CN116907360B (en) * | 2023-08-03 | 2024-03-12 | 苏州苏瑞膜纳米科技有限公司 | RO (reverse osmosis) membrane gel line width detection system and detection method based on machine vision |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101365144A (en) * | 2008-10-14 | 2009-02-11 | 北京信息科技大学 | Regulating and calibrating method for linear array CCD scanning detection system |
| CN101806586A (en) * | 2010-04-21 | 2010-08-18 | 上海交通大学 | Method and device for measuring section contour of sealing strip of vehicle based on image matching |
| CN102305793A (en) * | 2011-05-11 | 2012-01-04 | 苏州天准精密技术有限公司 | Method and equipment for detecting appearance quality of product |
| CN204881536U (en) * | 2015-07-08 | 2015-12-16 | 华东交通大学 | Size measurement device |
| CN106323474A (en) * | 2016-08-22 | 2017-01-11 | 沈阳建筑大学 | Detecting device for stone surface color difference and control system thereof |
| CN106969706A (en) * | 2017-04-02 | 2017-07-21 | 聊城大学 | Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201107639Y (en) * | 2007-11-30 | 2008-08-27 | 华南理工大学 | Large-sized producing workpiece geometric measuring apparatus using machine vision |
| CN102538705B (en) * | 2012-01-12 | 2014-11-05 | 杭州浙达精益机电技术股份有限公司 | Secondary-projection-algorithm-based on-line non-contact contour detection system and method of intermediate-thick plate |
| CN104913722B (en) * | 2015-07-01 | 2017-08-22 | 江南大学 | A kind of car body controller connector pin normotopia degree detection method |
| CN204705323U (en) * | 2015-07-01 | 2015-10-14 | 江南大学 | A kind of car body controller connector pin normotopia degree pick-up unit |
| CN105571501A (en) * | 2016-02-02 | 2016-05-11 | 北京铁道工程机电技术研究所有限公司 | Brake-shoe detection system and method |
| CN107767371B (en) * | 2017-09-30 | 2021-02-05 | 电子科技大学 | High-precision rectangular magnetic material size detection method based on sub-pixels |
-
2018
- 2018-03-19 CN CN201810222752.0A patent/CN108507472B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101365144A (en) * | 2008-10-14 | 2009-02-11 | 北京信息科技大学 | Regulating and calibrating method for linear array CCD scanning detection system |
| CN101806586A (en) * | 2010-04-21 | 2010-08-18 | 上海交通大学 | Method and device for measuring section contour of sealing strip of vehicle based on image matching |
| CN102305793A (en) * | 2011-05-11 | 2012-01-04 | 苏州天准精密技术有限公司 | Method and equipment for detecting appearance quality of product |
| CN204881536U (en) * | 2015-07-08 | 2015-12-16 | 华东交通大学 | Size measurement device |
| CN106323474A (en) * | 2016-08-22 | 2017-01-11 | 沈阳建筑大学 | Detecting device for stone surface color difference and control system thereof |
| CN106969706A (en) * | 2017-04-02 | 2017-07-21 | 聊城大学 | Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108507472A (en) | 2018-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109682826B (en) | Machine vision system and detection method for cambered surface appearance detection | |
| CN106017325B (en) | Improved non-contact optical measurement method for complex surface and irregular object volume | |
| CN108507472B (en) | Non-contact visual detection method for size of automobile safety airbag seal | |
| CN107121093A (en) | A kind of gear measurement device and measuring method based on active vision | |
| US11478219B2 (en) | Handheld three-dimensional ultrasound imaging system and method | |
| CN104833317A (en) | Medium or heavy steel plate morphology detection system based on controllable symmetrical double-line laser angle and method thereof | |
| EP3100266A1 (en) | Positioning device for an optical triangulation sensor | |
| CN103674963A (en) | Tunnel detection device based on digital panoramic photography and detection method thereof | |
| CN106382886A (en) | Online detection device and online detection method for indexable cutter machining | |
| CN113251926A (en) | Method and device for measuring size of irregular object | |
| CN110455378B (en) | Water meter small flow verification method based on machine vision | |
| CN108188835B (en) | Machine vision-based numerical control machine tool spindle thermal elongation testing device and testing method | |
| CN110470247B (en) | Device and method for detecting coaxiality of inner and outer circular surfaces of part | |
| US6590221B2 (en) | On-line measuring system for measuring substrate thickness and the method thereof | |
| CN109187373A (en) | A kind of Tomato Quality detection system and detection method based on machine vision | |
| CN104034259A (en) | Method for correcting image measurement instrument | |
| CN109642820B (en) | Optical sensing device, detection system and detection method | |
| CN214583088U (en) | Workpiece roundness measuring device | |
| CN204730813U (en) | A kind of medium plate Shap feature detection system controlled based on symmetric double line laser angle | |
| CN106767654B (en) | Method and system for detecting horizontal deflection angle of camera | |
| CN108225175B (en) | Device and method for acquiring tooth surface contact mark data of bevel gear of tractor transmission system | |
| CN110702936A (en) | Device and method for measuring rotating speed of air preheater based on laser image recognition | |
| CN207850305U (en) | A kind of safe automobile air bag strip of paper used for sealing size non-contact vision detection device | |
| CN205607332U (en) | Measuring device is striden to bridge crane crane span structure based on machine vision | |
| CN109654993B (en) | Motor terminal form and position tolerance detection device and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |