CN113191444A - Method for identifying automobile windshield glass - Google Patents

Method for identifying automobile windshield glass Download PDF

Info

Publication number
CN113191444A
CN113191444A CN202110530909.8A CN202110530909A CN113191444A CN 113191444 A CN113191444 A CN 113191444A CN 202110530909 A CN202110530909 A CN 202110530909A CN 113191444 A CN113191444 A CN 113191444A
Authority
CN
China
Prior art keywords
glass
characteristic
operated
standard
type
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
Application number
CN202110530909.8A
Other languages
Chinese (zh)
Inventor
葛良松
刘文广
王长松
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Beike Masic Automation Engineering Ltd
Original Assignee
Beijing Beike Masic Automation Engineering Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Beike Masic Automation Engineering Ltd filed Critical Beijing Beike Masic Automation Engineering Ltd
Priority to CN202110530909.8A priority Critical patent/CN113191444A/en
Publication of CN113191444A publication Critical patent/CN113191444A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Library & Information Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Geometry (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The application relates to a method for identifying automobile windshield glass, which comprises the following steps: establishing a standard characteristic database; measuring the actual size of the glass to be operated; calculating a first feature threshold; acquiring gray values of a plurality of characteristic points corresponding to characteristic positions in all standard types of glass and glass to be operated; calculating the absolute value of the difference value of the gray value at the characteristic point corresponding to the characteristic position in the glass to be operated and the gray value at the characteristic point corresponding to the characteristic position in all standard types of glass one by one; and determining the type of the glass to be operated. According to the invention, the appearance characteristics of the glass to be operated and the pre-obtained standard type glass are compared, so that the type of the glass to be operated can be preliminarily obtained. Meanwhile, the comparison is carried out according to the similarity degree of the glass to be operated and the standard type glass at the characteristic position, the comparison result is comprehensively analyzed with the type of the glass to be operated determined according to the appearance characteristics, and the category of the glass to be operated can be determined more accurately.

Description

Method for identifying automobile windshield glass
Technical Field
The application relates to the technical field of automobiles, in particular to a method for identifying automobile windshield glass.
Background
The installation of the automobile windshield glass is an important process of an automobile assembly, the installation quality of the windshield glass directly influences the sealing property and the safety of the whole automobile, and the installation quality of the windshield glass is an important index of the automobile quality. Simultaneously in order to adapt to intellectualization and flexibility of automobile production, several types of automobile models can be assembled simultaneously on the same assembly line, and glass of several different types is installed on the same type of automobile, and new glass types are added when a new type of automobile is on line. In the prior art, the length and width of the windshield glass in the two-dimensional X/Y direction are generally adopted to identify whether the model of the windshield glass is the correct model. However, in this way, for windshields with similar length and width dimensions, errors are easily identified when a correct target gluing program is called, so that windshields of one vehicle type are easily identified as windshields of another vehicle type, a wrong gluing program is called, a gluing track is wrong, and water leakage occurs because glass glue is applied unevenly or is installed on a vehicle body and the glass glue is not attached to the vehicle body.
Thus, there is a need for a method of accurately identifying the type of windshield to be operated.
Disclosure of Invention
In order to solve the above technical problem or at least partially solve the above technical problem, the present application provides a method of identifying a windshield of an automobile.
The application provides a method for identifying automobile windshield glass, which comprises the following specific contents:
step S1, establishing a standard characteristic database;
according to the profile characteristics (L) of standard types of glassi、Wi、Hi) Establishing a standard characteristic database of all standard types of glass needing to be operated on a workstation; wherein the parameter LiDenotes the length, parameter W, of the i-th standard type glassiWidth of i standard types of glass is shown, and parameter is HiThickness of standard type glass, i 1, 2, N is the type number of the standard type glass;
step S2, moving the glass to be operated to a standard position, and measuring the actual size (L) of the glass to be operatedreal、Wreal、Hreal) Wherein L isrealRepresents the actual length, W, of the glass to be handledrealRepresents the actual width of the glass to be handled, HrealRepresenting the actual thickness of the glass to be operated;
step S3, calculating a first characteristic threshold value according to the following formula
Figure RE-GDA0003111011010000021
Obtaining a first set of characteristic thresholds α ═ α1、α2、α3、...、αN}；
Presetting a first threshold beta1Selecting from the first set of characteristic threshold values a the first threshold value β1Nearest first characteristic threshold value alphajWherein j is 1, 2.. times.n;
calculating the first characteristic threshold value alphajAnd the first threshold value beta1Ratio of (2)1；
Step S4, pre-selecting a characteristic position, pre-selecting a plurality of characteristic points at the characteristic position, and acquiring gray values of the characteristic points corresponding to the characteristic position in all standard types of glass;
shooting an actual image corresponding to the position of the characteristic position in the glass to be operated in a perspective mode;
performing graying processing on the actual image to obtain a grayed image;
step S5, obtaining the gray value at the characteristic point corresponding to the characteristic position in the glass to be operated from the gray image;
step S6, presetting second threshold β2；
Calculating the absolute value of the difference value between the gray value at the characteristic point corresponding to the characteristic position in the glass to be operated and the gray value at the characteristic point corresponding to the characteristic position in all standard types of glass one by one;
for each standard type glass, counting the sum of absolute values of differences of the gray values at the characteristic points corresponding to the characteristic positions in the standard type glass and the gray values at the characteristic points corresponding to the characteristic positions in the glass to be operated to obtain the sum of m absolute values;
selecting the absolute value sum with the minimum value from the m absolute value sums, and calculating the absolute value sum with the minimum value and the second threshold value beta2Ratio of (2)2；
Step S7, according to the ratio1And the ratio2And determining the type of the glass to be operated.
Preferably, the capturing an actual image of the glass to be operated corresponding to the position of the characteristic position in the step S4 specifically includes:
horizontally placing the glass to be operated, arranging a light source under the glass to be operated, and fixing the light source;
arranging a high-definition camera right above the glass to be operated;
and starting a light source, and shooting an actual image corresponding to the position of the characteristic position in the glass to be operated by utilizing the high-definition camera.
Preferably, the characteristic position in step S4 is a lace position of the glass to be operated.
Preferably, the high-definition camera is a wide-angle camera.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
according to the invention, the appearance characteristics of the glass to be operated and the pre-obtained standard type glass are compared, so that the type of the glass to be operated can be preliminarily obtained. Meanwhile, the comparison is carried out according to the similarity degree of the glass to be operated and the standard type glass at the characteristic position, and the comparison result and the type of the glass to be operated determined according to the appearance characteristic are comprehensively analyzed, so that the category of the glass to be operated can be more accurately determined.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The installation of the automobile windshield glass is an important process of an automobile assembly, the installation quality of the windshield glass directly influences the sealing property and the safety of the whole automobile, and the installation quality of the windshield glass is an important index of the automobile quality. Simultaneously in order to adapt to intellectualization and flexibility of automobile production, several types of automobile models can be assembled simultaneously on the same assembly line, and glass of several different types is installed on the same type of automobile, and new glass types are added when a new type of automobile is on line. In the prior art, the length and width of the windshield glass in the two-dimensional X/Y direction are generally adopted to identify whether the model of the windshield glass is the correct model. However, in this way, for windshields with similar length and width dimensions, errors are easily identified when a correct target gluing program is called, so that windshields of one vehicle type are easily identified as windshields of another vehicle type, a wrong gluing program is called, a gluing track is wrong, and water leakage occurs because glass glue is applied unevenly or is installed on a vehicle body and the glass glue is not attached to the vehicle body.
The embodiment of the specification provides a method for identifying automobile windshield glass, which can accurately identify the type of the windshield glass to be operated, and the technical scheme provided by each embodiment of the application is described in detail below.
From the viewpoint of a program, the main body of the flow according to the present invention may be a program installed in an application server or an application terminal.
The process may include the steps of:
step S1, establishing a standard characteristic database;
according to the profile characteristics (L) of standard types of glassi、Wi、Hi) Establishing a standard characteristic database of all standard types of glass needing to be operated on a workstation; wherein the parameter LiDenotes the length, parameter W, of the i-th standard type glassiWidth of i standard types of glass is shown, and parameter is HiThickness of standard type glass, i 1, 2.
In order to adapt to intellectualization and flexibility of automobile production, several automobile models can be assembled simultaneously on the same assembly line, and windshield glass of several different models can be installed on the same automobile model. The types of all kinds of standard types of glass to be installed on the assembly line are known in advance, and the external shape characteristics of these standard types of glass are also known in advance. The purpose of the step is to establish an appearance characteristic database of the standard type glass of different types in advance, so that the subsequent steps are compared one by one according to the actual size of the glass to be operated and the appearance characteristics of the standard type glass of different types, the standard type glass closest to the actual size of the glass to be operated is selected from the database, and the glass to be operated is set as the type of the standard type glass closest to the actual size of the glass to be operated according to the preset confidence coefficient.
Step S2, moving the glass to be operated to a standard position, and measuring the actual size (L) of the glass to be operatedreal、Wreal、Hreal) Wherein L isrealRepresents the actual length, W, of the glass to be handledrealRepresents the actual width of the glass to be handled, HrealRepresenting the actual thickness of the glass to be worked.
The purpose of this step is to obtain the actual physical dimensions of the glass to be worked, and the embodiments of the present invention are not particularly limited.
Step S3, calculating a first characteristic threshold value according to the following formula
Figure RE-GDA0003111011010000051
Obtaining a first set of characteristic thresholds α ═ α1、α2、α3、...、αN}；
Presetting a first threshold beta1Selecting from the first set of characteristic threshold values a the first threshold value β1Nearest first characteristic threshold value alphajWherein j ═1，2，...，N；
Calculating the first characteristic threshold value alphajAnd the first threshold value beta1Ratio of (2)1。
First threshold value beta in this step1The square root of the sum of the absolute values of the differences of the length, the width and the thickness among different glasses in the same type of glass can be counted in advance according to historical records.
Step S4, pre-selecting a characteristic position, pre-selecting a plurality of characteristic points at the characteristic position, and acquiring gray values of the characteristic points corresponding to the characteristic position in all standard types of glass;
shooting an actual image corresponding to the position of the characteristic position in the glass to be operated in a perspective mode;
and carrying out graying processing on the actual image to obtain a grayed image after graying processing.
The technical idea of this step is that the windshield glass has a characteristic position during production and manufacturing, the characteristic of the characteristic position is stable, and the characteristics of different types of windshield glass at the characteristic position are obviously different, so that the characteristic at the characteristic position can be used as the type mark of the windshield glass, and the specific type of the glass to be operated can be identified by using the characteristic at the characteristic position when the windshield glass is installed. For example, the lines in the corners of the glass can be selected as feature positions, and since the lines of each type of windshield glass are different, the features of the glass to be operated at the feature positions can be identified by using a machine vision technology, and the specific type of the glass to be operated can be identified. Specifically, several feature points are selected at the feature position, for example, 100 feature points may be selected at the feature position.
The specific machine vision technology selected in the technical scheme of the embodiment is a robot image recognition technology, and gray values at all feature points in the feature positions of all standard types of glass need to be collected in advance. That is, for the first standard type of glass, the first standard type of glass is collected in advanceGray values { Data 'at all feature points of the feature position of (1)'11、Data’12、...、Data’1m}; for the second standard type of glass, the gray values { Data 'at all characteristic points of the characteristic positions of the second standard type of glass are acquired in advance'21、Data’22、...、Data’2mFor the Nth standard type of glass, gray values { Data 'at all characteristic points of characteristic positions of the second standard type of glass are acquired in advance'N1、Data’N2、...、Data’NmWhere the parameter m represents the number of feature points.
Simultaneously, shooting an actual image corresponding to the position of the characteristic position in the glass to be operated in a perspective mode; and carrying out graying processing on the actual image to obtain a grayed image after graying processing. The shooting of the actual image corresponding to the position of the characteristic position in the glass to be operated specifically comprises: horizontally placing the glass to be operated, arranging a light source under the glass to be operated, and fixing the light source; arranging a high-definition camera right above the glass to be operated; and starting a light source, and shooting an actual image corresponding to the position of the characteristic position in the glass to be operated by utilizing the high-definition camera. The purpose of this is to obtain reliable picture characteristics by illuminating the glass with a light source, taking into account that the glass is a transparent object.
And step S5, obtaining the gray value at the characteristic point corresponding to the characteristic position in the glass to be operated from the gray image.
The aim of the step is to collect the gray values at the characteristic points corresponding to the characteristic positions of the glass to be operated, namely to collect the gray values { Data at m characteristic points of the glass to be operated1、Data2、...、DatamAnd S5, so as to compare the gray values at all the characteristic points of the characteristic positions of the standard type glass collected in the step S5.
Step S6, presetting second threshold β2；
Calculating the absolute value of the difference value between the gray value at the characteristic point corresponding to the characteristic position in the glass to be operated and the gray value at the characteristic point corresponding to the characteristic position in all standard types of glass one by one;
for each standard type glass, counting the sum of absolute values of differences of the gray values at the characteristic points corresponding to the characteristic positions in the standard type glass and the gray values at the characteristic points corresponding to the characteristic positions in the glass to be operated to obtain the sum of m absolute values;
selecting the absolute value sum with the minimum value from the m absolute value sums, and calculating the absolute value sum with the minimum value and the second threshold value beta2Ratio of (2)2。
The gradation values { Data at the m feature points of the glass to be operated { Data } have been obtained in step S61、Data2、...、DatamThe purpose of this step is to calculate the value (i.e. the sum of the difference values of the gray values at the corresponding points): SUMi＝|Data’i1-Data1|+|Data’i2-Data2|+...+|Data’im-DatamI 1, 2.. N, so that a total of m SUM values can be calculated, from which the SUM value with the smallest value is selectedjAnd calculates SUMjAnd the second threshold value beta2Ratio of (2)2. Second threshold value beta in this step2The selection of (2) is also critical and can be set according to a history.
Step S7, according to the ratio1And the ratio2And determining the type of the glass to be operated.
If the ratio1And the ratio2All are less than 1, the type of the glass corresponding to the minimum sum of absolute values is taken as the type of the glass to be operated.
If the ratio1Less than or equal to 1 and the ratio2And if the external shape feature is larger than 1, determining the type of the glass to be operated determined according to the external shape feature as the type of the glass to be operated.
If the ratio1Greater than 1 and the ratio2And if the absolute value is less than 1, the glass type corresponding to the small sum of the absolute values is taken as the type of the glass to be operated.
If the ratio1And the ratio2If the absolute value is more than 1, the type of the glass corresponding to the minimum sum of the absolute values is taken as the type of the glass to be operated.
According to the invention, the appearance characteristics of the glass to be operated and the pre-obtained standard type glass are compared, so that the type of the glass to be operated can be preliminarily obtained. Meanwhile, the comparison is carried out according to the similarity degree of the glass to be operated and the standard type glass at the characteristic position, and the comparison result and the type of the glass to be operated determined according to the appearance characteristic are comprehensively analyzed, so that the category of the glass to be operated can be more accurately determined.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (4)

1. A method of identifying a vehicle windshield, the method comprising:
step S1, establishing a standard characteristic database;
according to the profile characteristics (L) of standard types of glassi、Wi、Hi) Establishing a standard characteristic database of all standard types of glass needing to be operated on a workstation; wherein the parameter LiDenotes the length, parameter W, of the i-th standard type glassiWidth of i standard types of glass is shown, and parameter is HiThickness of standard type glass, i 1, 2, N is the type number of the standard type glass;
step S2, moving the glass to be operated to a standard position, and measuring the actual size (L) of the glass to be operatedreal、Wreal、Hreal) Wherein L isrealRepresents the actual length, W, of the glass to be handledrealRepresents the actual width of the glass to be handled, HrealRepresenting the actual thickness of the glass to be operated;
step S3, calculating a first characteristic threshold value according to the following formula
Figure RE-FDA0003110973000000011
Obtaining a first set of characteristic thresholds α ═ α1、α2、α3、...、αN}；
Presetting a first threshold beta1Selecting from the first set of characteristic threshold values a the first threshold value β1Nearest first characteristic threshold value alphajWherein j is 1, 2.. times.n;
calculating the first characteristic threshold value alphajAnd the first threshold value beta1Ratio of (2)1；
Step S4, pre-selecting a characteristic position, pre-selecting a plurality of characteristic points at the characteristic position, and acquiring gray values of the characteristic points corresponding to the characteristic position in all standard types of glass;
shooting an actual image corresponding to the position of the characteristic position in the glass to be operated in a perspective mode;
performing graying processing on the actual image to obtain a grayed image;
step S5, obtaining the gray value at the characteristic point corresponding to the characteristic position in the glass to be operated from the gray image;
step S6, presetting second threshold β2；
Calculating the absolute value of the difference value between the gray value at the characteristic point corresponding to the characteristic position in the glass to be operated and the gray value at the characteristic point corresponding to the characteristic position in all standard types of glass one by one;
for each standard type glass, counting the sum of absolute values of differences of the gray values at the characteristic points corresponding to the characteristic positions in the standard type glass and the gray values at the characteristic points corresponding to the characteristic positions in the glass to be operated to obtain the sum of m absolute values;
selecting the absolute value sum with the minimum value from the m absolute value sums, and calculating the absolute value sum with the minimum value and the second threshold value beta2Ratio of (2)2；
Step S7, according to the ratio1And the ratio2And determining the type of the glass to be operated.
2. The method for identifying a windshield of an automobile as recited in claim 1, wherein said step S4 of capturing an actual image of the glass to be operated corresponding to the position of the characteristic position specifically comprises:
horizontally placing the glass to be operated, arranging a light source under the glass to be operated, and fixing the light source;
arranging a high-definition camera right above the glass to be operated;
and starting a light source, and shooting an actual image corresponding to the position of the characteristic position in the glass to be operated by utilizing the high-definition camera.
3. The method for identifying a windshield glass of an automobile as recited in claim 2, wherein the characteristic position in the step S4 is a lace position of the glass to be operated.
4. A method of identifying a vehicle windscreen according to claim 2 wherein said high definition camera is a wide angle camera.
CN202110530909.8A 2021-05-15 2021-05-15 Method for identifying automobile windshield glass Pending CN113191444A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110530909.8A CN113191444A (en) 2021-05-15 2021-05-15 Method for identifying automobile windshield glass

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110530909.8A CN113191444A (en) 2021-05-15 2021-05-15 Method for identifying automobile windshield glass

Publications (1)

Publication Number Publication Date
CN113191444A true CN113191444A (en) 2021-07-30

Family

ID=76982055

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110530909.8A Pending CN113191444A (en) 2021-05-15 2021-05-15 Method for identifying automobile windshield glass

Country Status (1)

Country Link
CN (1) CN113191444A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101109935A (en) * 2007-07-10 2008-01-23 安徽江淮自动化装备有限公司 Automatic glass recognition method for windshield robot coating system
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
JP2016142611A (en) * 2015-02-02 2016-08-08 マツダ株式会社 Inspection method and device of vehicle window glass
CN109991917A (en) * 2019-04-09 2019-07-09 东风汽车集团有限公司 Composite and flexible windscreen recognition methods
CN111612014A (en) * 2020-04-26 2020-09-01 东风汽车集团有限公司 Windshield glass identification error-proofing method in gluing process

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101109935A (en) * 2007-07-10 2008-01-23 安徽江淮自动化装备有限公司 Automatic glass recognition method for windshield robot coating system
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
JP2016142611A (en) * 2015-02-02 2016-08-08 マツダ株式会社 Inspection method and device of vehicle window glass
CN109991917A (en) * 2019-04-09 2019-07-09 东风汽车集团有限公司 Composite and flexible windscreen recognition methods
CN111612014A (en) * 2020-04-26 2020-09-01 东风汽车集团有限公司 Windshield glass identification error-proofing method in gluing process

Similar Documents

Publication Publication Date Title
CN110427937B (en) Inclined license plate correction and indefinite-length license plate identification method based on deep learning
CN106504248B (en) Vehicle damage judging method based on computer vision
CN116740070B (en) Plastic pipeline appearance defect detection method based on machine vision
KR102118173B1 (en) System and method for image correction based estimation of distortion parameters
CN116030060B (en) Plastic particle quality detection method
CN109543753B (en) License plate recognition method based on self-adaptive fuzzy repair mechanism
CN116402808B (en) Intelligent detection method for manufacturing cable clamp plate die
CN116385434B (en) Intelligent detection method for precast beam cracks
CN112330646A (en) Motor car bottom abnormity detection method based on two-dimensional image
CN113191444A (en) Method for identifying automobile windshield glass
CN113155057A (en) Line structured light plane calibration method using non-purpose-made target
CN111126371B (en) Coarse pointer dial reading method based on image processing
CN114943738A (en) Sensor packaging curing adhesive defect identification method based on visual identification
CN109493316B (en) Intelligent detection method for cigarette packet missing strip of carton sealing machine based on similarity analysis and feature increment learning
CN116721096A (en) New energy harness quality online detection method based on artificial intelligence
CN111862080A (en) Deep learning defect identification method based on multi-feature fusion
CN116664494A (en) Surface defect detection method based on template comparison
CN116843618A (en) Method for detecting shallow apparent appearance defects of metal parts
CN115546716A (en) Binocular vision-based method for positioning fire source around power transmission line
CN112562008B (en) Target point matching method in local binocular vision measurement
CN115273219A (en) Yoga action evaluation method and system, storage medium and electronic equipment
CN114548250A (en) Mobile phone appearance detection method and device based on data analysis
CN113570524A (en) Restoration method for high-reflection noise depth image
CN117372422B (en) Material bending degree detection method for part production
CN117058130B (en) Visual inspection method for coating quality of optical fiber drawing surface

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