CN111612014A - Windshield glass identification error-proofing method in gluing process - Google Patents
Windshield glass identification error-proofing method in gluing process Download PDFInfo
- Publication number
- CN111612014A CN111612014A CN202010340805.6A CN202010340805A CN111612014A CN 111612014 A CN111612014 A CN 111612014A CN 202010340805 A CN202010340805 A CN 202010340805A CN 111612014 A CN111612014 A CN 111612014A
- Authority
- CN
- China
- Prior art keywords
- windshield glass
- actual
- windshield
- gray values
- identifying
- 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
- 239000011521 glass Substances 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000004026 adhesive bonding Methods 0.000 title claims abstract description 18
- 239000003292 glue Substances 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 3
- 230000007547 defect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Abstract
The invention discloses a windshield glass identification error-proofing method in a gluing process. The method comprises the steps of moving the windshield glass to be glued to a standard position, shooting an actual image of the windshield glass, obtaining actual gray values of a plurality of characteristic element points corresponding to the positions of the characteristic points on the windshield glass with the correct model from the actual image, and identifying whether the windshield glass to be glued is the windshield glass with the correct model according to the actual gray values. The invention improves the accuracy of the automobile windshield glass identification, greatly saves the working hours, reduces the repair working hours, improves the labor productivity of the assembly workshop and effectively solves the problem of identification errors.
Description
Technical Field
The invention belongs to the technical field of automobiles, and particularly relates to a windshield glass identification mistake-proofing method in a gluing process.
Background
In the prior art, when the automobile windshield glass is coated with glue, impulse type signal identification or two-dimensional X \ Y-direction length and width dimension identification is generally adopted to identify whether the windshield glass is the correct type, but the two modes are easy to identify errors when a correct target gluing program is called for the windshield glass with the similar length and width dimension, so that the windshield glass of one automobile type is easy to identify into another automobile type, the wrong gluing program is called, the gluing track is wrong, and the water leakage condition is caused because the glass glue is not attached to the automobile body due to the fact that the glass glue is coated eccentrically or the glass glue is installed on the automobile body.
Disclosure of Invention
The invention aims to solve the defects of the background technology and provide a windshield glass identification mistake-proofing method in the gluing process.
The technical scheme adopted by the invention is as follows: a windshield glass to be glued is moved to a standard position, an actual image of the windshield glass is shot, actual gray values of a plurality of characteristic element points corresponding to the positions of the characteristic points on the windshield glass with the correct model are obtained from the actual image, and whether the windshield glass to be glued is the windshield glass with the correct model is identified according to the actual gray values.
Further, when the center of the windshield glass is coincident with the positioning origin of the gluing device, the windshield glass is moved to the standard position.
Further, the characteristic points comprise a specific mark with identifiability on the edge profile and/or the middle of the windscreen.
And further, comparing all the actual gray values with the standard gray values corresponding to the standard images of the windshield glass with the correct model respectively, and if the absolute values of the difference values of all the actual gray values and the standard gray values are less than or equal to a first set value, identifying the windshield glass to be glued as the windshield glass with the correct model.
Furthermore, the actual contour of the windshield glass to be glued is obtained according to the colors corresponding to all the actual gray values, the actual contour is compared with the standard contour of the windshield glass with the correct model, and if the similarity between the actual contour and the standard contour is larger than or equal to a second set value, the windshield glass to be glued is identified as the windshield glass with the correct model.
According to the invention, the size and specific position information of the current physical windshield are obtained in an image recognition mode, the size and specific position information are compared with standard information, the rapid and accurate matching is realized, and whether the current physical windshield is in the correct model can be confirmed in a high-accuracy matching manner, so that a target vehicle type gluing program is automatically obtained, the accuracy of automobile windshield recognition is improved, the operation time is greatly saved, the repair time is reduced, the labor productivity of a general assembly workshop is improved, and the problem of recognition errors is effectively solved.
Drawings
FIG. 1 is a flow chart of the recognition process of the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the drawings. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in fig. 1, the invention provides a method for identifying and preventing errors of windshield glass in a gluing process, the windshield glass to be glued is moved into gluing equipment through a conveyor belt until the center of the windshield glass coincides with a positioning origin of the equipment, so as to realize primary windshield centering identification, the center of the windshield glass is a windshield centering identification point which can be definitely the geometric center of the windshield or can be determined through a clamping tool, namely the central point determined in the left, right, front and back directions. Then, the high-definition camera arranged above the windshield glass on the gluing equipment or other equipment shoots the windshield glass to be glued to obtain a high-definition actual image of the windshield glass, the high-definition image is transmitted to the gluing host, the gluing host obtains actual gray values [0,255] of a plurality of characteristic element points corresponding to the positions of the characteristic points on the windshield glass with the correct model from the actual image, and whether the windshield glass to be glued is the windshield glass with the correct model can be identified in a plurality of ways according to the actual gray values and the standard gray values corresponding to the windshield glass with the correct model.
In the above solution, the characteristic points include specific marks having identifiability in the edge profile and/or the middle of the windshield, the characteristic points are actually one or more continuous profile lines, and the corresponding characteristic element points are discrete points capable of forming the profile line.
In the above scheme, one way of identifying whether the windshield to be glued is the windshield of the correct model is as follows: and comparing all the actual gray values with the standard gray values corresponding to the standard images of the windshield glass with the correct model respectively, and if the absolute values of the difference values of all the actual gray values and the standard gray values are less than or equal to a first set value, identifying the windshield glass to be coated with glue as the windshield glass with the correct model, otherwise, identifying unsuccessfully.
In the above scheme, another way of identifying whether the windshield to be glued is the windshield of the correct model is as follows: and acquiring the actual contour of the windshield glass to be glued according to the colors corresponding to all the actual gray values (the actual contour comprises the length and width of the windshield glass main body, edge line characteristics, middle specific marks and the like), comparing the actual contour with the standard contour of the windshield glass with the correct model, and if the similarity between the actual contour and the standard contour is more than or equal to a second set value, such as 95%, identifying the windshield glass to be glued as the windshield glass with the correct model, otherwise, identifying unsuccessfully.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Those not described in detail in this specification are within the skill of the art.
Claims (5)
1. A windshield glass identification error-proofing method in a gluing process is characterized in that: moving the windshield glass to be glued to a standard position, shooting an actual image of the windshield glass, obtaining actual gray values of a plurality of characteristic element points corresponding to the positions of the characteristic points on the windshield glass with the correct model from the actual image, and identifying whether the windshield glass to be glued is the windshield glass with the correct model according to the actual gray values.
2. The method for identifying and preventing the mistake of the windshield glass in the gluing process according to claim 1, which is characterized in that: when the center of the windshield glass is superposed with the positioning origin of the gluing equipment, the windshield glass is moved to the standard position.
3. The method for identifying and preventing the mistake of the windshield glass in the gluing process according to claim 1, which is characterized in that: the characteristic points comprise specific marks which can be identified on the edge profile of the windshield and/or in the middle of the windshield.
4. The method for identifying and preventing the mistake of the windshield glass in the gluing process according to claim 1, which is characterized in that: and comparing all the actual gray values with the standard gray values corresponding to the standard images of the windshield glass with the correct model respectively, and if the absolute values of the difference values of all the actual gray values and the standard gray values are less than or equal to a first set value, identifying the windshield glass to be coated with glue as the windshield glass with the correct model.
5. The method for identifying and preventing the mistake of the windshield glass in the gluing process according to claim 1, which is characterized in that: and acquiring the actual contour of the windshield glass to be glued according to the colors corresponding to all the actual gray values, comparing the actual contour with the standard contour of the windshield glass with the correct model, and identifying the windshield glass to be glued as the windshield glass with the correct model if the similarity between the actual contour and the standard contour is greater than or equal to a second set value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010340805.6A CN111612014A (en) | 2020-04-26 | 2020-04-26 | Windshield glass identification error-proofing method in gluing process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010340805.6A CN111612014A (en) | 2020-04-26 | 2020-04-26 | Windshield glass identification error-proofing method in gluing process |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111612014A true CN111612014A (en) | 2020-09-01 |
Family
ID=72204386
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010340805.6A Pending CN111612014A (en) | 2020-04-26 | 2020-04-26 | Windshield glass identification error-proofing method in gluing process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111612014A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113191444A (en) * | 2021-05-15 | 2021-07-30 | 北京北科麦思科自动化工程技术有限公司 | Method for identifying automobile windshield glass |
CN113223029A (en) * | 2021-04-20 | 2021-08-06 | 梅卡曼德(北京)机器人科技有限公司 | Glass gluing method, glass gluing device, electronic equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101169657A (en) * | 2007-11-28 | 2008-04-30 | 安徽江淮自动化装备有限公司 | Automobile wind shield glass mounting method based on automatic glue application and artificial mounting |
CN102004898A (en) * | 2010-11-03 | 2011-04-06 | 天津工业大学 | Target tracking method based on template matching |
CN102847667A (en) * | 2012-09-27 | 2013-01-02 | 天津博信汽车零部件有限公司 | Automobile windshield glass rubber coating device |
CN102880877A (en) * | 2012-09-28 | 2013-01-16 | 中科院成都信息技术有限公司 | Target identification method based on contour features |
CN106295649A (en) * | 2015-05-15 | 2017-01-04 | 中云智慧(北京)科技有限公司 | Target identification method based on contour features |
US9691161B1 (en) * | 2015-09-25 | 2017-06-27 | A9.Com, Inc. | Material recognition for object identification |
CN107016362A (en) * | 2017-03-30 | 2017-08-04 | 华中科技大学 | Vehicle based on vehicle front windshield sticking sign recognition methods and system again |
-
2020
- 2020-04-26 CN CN202010340805.6A patent/CN111612014A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101169657A (en) * | 2007-11-28 | 2008-04-30 | 安徽江淮自动化装备有限公司 | Automobile wind shield glass mounting method based on automatic glue application and artificial mounting |
CN102004898A (en) * | 2010-11-03 | 2011-04-06 | 天津工业大学 | Target tracking method based on template matching |
CN102847667A (en) * | 2012-09-27 | 2013-01-02 | 天津博信汽车零部件有限公司 | Automobile windshield glass rubber coating device |
CN102880877A (en) * | 2012-09-28 | 2013-01-16 | 中科院成都信息技术有限公司 | Target identification method based on contour features |
CN106295649A (en) * | 2015-05-15 | 2017-01-04 | 中云智慧(北京)科技有限公司 | Target identification method based on contour features |
US9691161B1 (en) * | 2015-09-25 | 2017-06-27 | A9.Com, Inc. | Material recognition for object identification |
CN107016362A (en) * | 2017-03-30 | 2017-08-04 | 华中科技大学 | Vehicle based on vehicle front windshield sticking sign recognition methods and system again |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113223029A (en) * | 2021-04-20 | 2021-08-06 | 梅卡曼德(北京)机器人科技有限公司 | Glass gluing method, glass gluing device, electronic equipment and storage medium |
CN113191444A (en) * | 2021-05-15 | 2021-07-30 | 北京北科麦思科自动化工程技术有限公司 | Method for identifying automobile windshield glass |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111612014A (en) | Windshield glass identification error-proofing method in gluing process | |
CN109724615B (en) | Method and system for verifying lane line identification result | |
CN108388641B (en) | Traffic facility map generation method and system based on deep learning | |
US8582091B2 (en) | Vision-based headlamp aiming | |
CN105118300A (en) | Method of correcting license plate number automatically recognized in traffic snapshot | |
CN108927805B (en) | Robot automatic nail inserting method based on visual compensation | |
CN113640778A (en) | Multi-laser radar combined calibration method based on non-overlapping view field | |
CN111507130A (en) | Lane level positioning method and system, computer equipment, vehicle and storage medium | |
CN101743524B (en) | Method for machining a contour on at least one workpiece by means of a robot | |
CN109859206A (en) | A kind of extracting method of circular hole feature | |
CN109945782A (en) | Overlength white body key position detection method | |
CN109991917A (en) | Composite and flexible windscreen recognition methods | |
CN110120081B (en) | Method, device and storage equipment for generating lane markings of electronic map | |
CN105046686A (en) | Positioning method and apparatus | |
CN115055964A (en) | Intelligent assembling method and system based on fuel injection pump | |
CN111626995A (en) | Intelligent insert detection method and device for workpiece | |
CN108254776A (en) | Tunnel placement system and method based on curb fluorescent reflection and binocular camera | |
CN215526103U (en) | Vehicle-mounted radar calibration system | |
CN101661669A (en) | Road vehicle type identification method and system thereof | |
CN110254477B (en) | Automatic train benchmarking method and system based on satellite differential positioning | |
CN102446275A (en) | Identification method and device for Arabic character | |
CN108520533B (en) | Workpiece positioning-oriented multi-dimensional feature registration method | |
CN108569280B (en) | Method and device for automatic parking, intelligent automobile and computer storage medium | |
CN115893294A (en) | Robot automatic filling method based on 2D camera | |
CN110955983B (en) | Simulation calculation method for automobile chassis assembly success rate |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200901 |