CN111476782B - Automobile rear camera extension line terminal image detection system - Google Patents
Automobile rear camera extension line terminal image detection system Download PDFInfo
- Publication number
- CN111476782B CN111476782B CN202010277451.5A CN202010277451A CN111476782B CN 111476782 B CN111476782 B CN 111476782B CN 202010277451 A CN202010277451 A CN 202010277451A CN 111476782 B CN111476782 B CN 111476782B
- Authority
- CN
- China
- Prior art keywords
- image
- module
- area
- reed
- female end
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8861—Determining coordinates of flaws
- G01N2021/8864—Mapping zones of defects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/30164—Workpiece; Machine component
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an automobile rear camera extension line terminal image detection system, which comprises: a module M1: performing mathematical modeling based on a geometric dimension relation between the structural features of the male end and the female end of the product by utilizing a Qt program and an OpenCv computer vision library, and establishing a wire harness feature template; a module M2: collecting image information of a terminal by using an image collecting device; a module M3: and comparing the image information with the mathematical models and the characteristic templates of the male end and the female end of the product to detect the qualification of the terminal. The invention solves the problem of detecting the defects of the male end and the female end of the extension line of the rear camera of the automobile, and carries out mathematical modeling and characteristic template establishment on the askew folding and missing needle-shaped reeds at the male end and the central reed and petal-shaped reeds at the female end respectively based on the geometric dimension relation between the structural characteristics of the male end and the female end of a qualified product, thereby realizing the defect detection of the male end and the female end.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to an image detection system for an extension line terminal of an automobile rear camera.
Background
In the production process of the rear camera of the automobile for extending the line terminal, due to improper operation which possibly occurs, the reeds at the two ends can be lost, and the problems of askew bending and the like can be solved, so that poor contact of the wire harness is caused, and the production progress and the running safety of the automobile are influenced. In a non-automatic wire harness production process, workers mostly observe whether the terminal has defects on a screen through a microscopic camera. On a full-automatic assembly line, a mechanical arm is adopted to clamp a wire harness terminal, and one station detects one terminal defect. In a non-full-automatic production process, subjective factors exist in manual judgment, detection results cannot be effectively recorded, the working efficiency is low, and the product false detection rate is high. In the full-automatic production process, the cost of the mechanical arm is high, and the mechanical arm is not suitable for small automobile wire harness manufacturers in China.
Disclosure of Invention
The invention aims to provide an image detection system for an extension line terminal of a rear camera of an automobile, which is used for establishing a similarity contrast template based on images of a male end and a female end of a qualified product, realizing automatic identification and detection of the male end and the female end and solving the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the utility model provides a camera extension line terminal image detection system behind car, includes:
a module M1: performing mathematical modeling based on a geometric dimension relation between the structural features of the male end and the female end of the product by utilizing a Qt program and an OpenCv computer vision library, and establishing a wire harness feature template;
a module M2: collecting image information of a terminal by using an image collecting device;
a module M3: and comparing the image information with the mathematical models and the characteristic templates of the male end and the female end of the product to detect the qualification of the terminal.
Preferably, the module M1 comprises:
module M1.1: capturing a public end region in the image and storing the public end region as a feature template image A by using a mouse callback function, a region capturing function and an image storing function in OpenCv, and storing coordinates of four vertex coordinates of the feature template image A in an original image by using a function which writes data into an Xml file in OpenCV;
module M1.2: by utilizing OpenCV gray processing, linear filtering, binarization/inverse binarization, contour extraction, a contour drawing function and a mask operation function, firstly extracting the whole contour of a male end, whitewashing the periphery of the contour, then extracting a black area inside a terminal, blacking the outside of the black area, and finally, enabling a bright spot area except a central reed in an image A to be white and enabling the rest parts to be black;
module M1.3: calculating the centroid coordinate of the white area by using a contour function searched in OpenCv, and storing the centroid coordinate into an Xml template file;
module M1.4: utilizing a mouse callback function, an area interception function and an image storage function in OpenCv, intercepting a parent end area in an image and storing the parent end area as a feature template image B, and utilizing a function of writing data into an Xml file in OpenCv to store coordinates of four vertex coordinates of the feature template image B in an original image;
module M1.5: by utilizing color extraction, gray level processing, nonlinear filtering, binarization/inverse binarization, contour extraction, contour drawing functions and mask operation functions in OpenCV, firstly finding out the centroid of the contour at the outermost periphery of a parent end, making a red circle with a specified diameter on a clone image by taking the centroid as the center of circle, whitewashing the part of the original image outside the range of the red solid circle, extracting yellow plastic circle features with black holes in the parent end, turning all the parts except the middle black hole into white, and extracting the features of the central black hole;
module M1.6: changing black into white and changing white into black by using an inverse binarization function in OpenCv, calculating the area of a black hole by using an outline extraction function, and storing the area into an Xml template file;
module M1.7: changing the red area in the module M1.5 into black, processing the picture by utilizing OpenCV gray processing, morphological filtering, linear filtering and binarization processing functions, filtering interference characteristics through area size and shape proportion, extracting bright line characteristics of six petals, calculating the centroid coordinate of each petal by utilizing a contour extraction function, calculating the coordinate difference with the contour centroid at the outermost periphery of the parent end in sequence, and storing the coordinate difference in an Xml template file.
Preferably, when the mass center of the male end central reed is in the middle area of the whole mass center of the terminal, the male end of the product is judged to be qualified; when the mass center of the central reed of the male end does not exist, determining that the male end of the product is missing; and when the mass center of the male end center reed is deviated, determining that the male end of the product is askew folded.
Preferably, when the female end center reed presents two crescent shapes on the image, the product female end is judged to be qualified; when the area between the reeds in the center of the female end is enlarged when a single central reed is absent, or the female end is round when two central reeds are absent, the product female end is judged to be absent; six petal-shaped reeds of the qualified female end are on the same circumference, and when the distance from the center of mass of any one reed to the center of the circle is not within the range, the female end of the product is judged to be askew.
Preferably, in the module M2, the image acquisition device includes that shell, front shroud, back shroud, terminal are pulled out and are inserted mould, annular LED lamp, LED lamp support, industry camera and hexagonal support, the shell is closed black box, the front shroud is located shell one side, the terminal is pulled out and is inserted the mould and locate through the bolt fastening the front shroud outside surface, the back shroud is located the opposite side of shell, annular LED lamp is fixed to be located on the LED lamp support, industry camera below is equipped with the hexagonal support, the industry camera passes through the hexagonal support is installed at LED lamp support rear.
Preferably, the terminal pulling and inserting mold is provided with a male end jack and a female end jack, and the male end jack and the female end jack are symmetrically distributed.
Preferably, the module M3 comprises:
module M3.1: shooting a frame of photo by using an industrial camera, respectively intercepting a male end region and a female end region by utilizing coordinates when a feature template is set in a function reading module M1 for reading data in OpenCV, sequentially carrying out similarity comparison on the intercepted regions and a feature template image A of the male end and a feature template image B of the female end by utilizing a histogram equalization function in OpenCV, and continuously detecting if the similarity is within a certain range;
module M3.2: calculating the area of the brightest pixel in the image by utilizing gray level conversion, linear filtering and binarization functions in OpenCV, and continuously detecting and extracting features when the area is within a certain range;
module M3.3: reading the data information stored in the Xml template file, calculating the coordinate difference between the coordinates of the detection reed and the coordinates of the characteristic template A by the public end, converting the coordinate difference into an offset according to an actual proportion, and determining the detection reed is qualified within a preset range;
module M3.4: the female end calculates the proportion of the area of the black hole of the reed in the detection center to the area of the template, and sequentially calculates the coordinate difference between the centroid of the petal-shaped reed and the centroid of the outermost contour of the female end, and the reed is qualified when the area proportion and each coordinate difference are in a preset range;
module M3.5: and after the judgment is finished, the two-dimensional code information of the wire harness, the shooting time, the terminal image information, the offset of the central reed of the male end, the area ratio of the central reed of the female end, the offset of the petal-shaped reed of the female end and the qualified information are all stored in a database.
Compared with the prior art, the invention has the beneficial effects that:
(1) The invention solves the problem that the acquired terminal image characteristics are not obvious, and the annular colored light source is arranged at the terminal detection position at a certain distance, so that the characteristic to be detected is highlighted.
(2) The invention solves the problem that one station can not detect two terminals simultaneously, establishes a similarity contrast template based on the images of the male terminal and the female terminal of a qualified product, and realizes automatic identification and detection of the male terminal and the female terminal.
(3) The invention solves the problem of detecting the defects of the male end and the female end of the extension line of the rear camera of the automobile, and carries out mathematical modeling and characteristic template establishment on the askew folding and missing needle-shaped reeds at the male end and the central reed and petal-shaped reeds at the female end respectively based on the geometric dimension relation between the structural characteristics of the male end and the female end of a qualified product, thereby realizing the defect detection of the male end and the female end.
(4) The invention solves the problem that the detection result can not be quantitatively stored in the non-full-automatic wire harness production, and the system stores the picture and the data obtained by the picture through the algorithm into the database, thereby being beneficial to the production management of enterprises.
(5) The system in the invention can collect images without interference of external environment light, and can highlight the characteristics to be detected, thereby improving the detection success rate and the detection speed.
(6) The whole system occupies small space, and the male end and the female end can be simultaneously detected at one time by one station, so that the production cost of small enterprises is reduced while the automation degree is improved.
(7) According to the invention, the geometrical size relationship between the structural features of the male end and the female end of the extension line of the rear camera of the automobile is mathematically modeled, the wire harness feature template is established, the features are separately extracted from the picture in the detection process and then processed, and the judgment accuracy is improved.
(8) According to the invention, after the detection is finished, the two-dimensional code information of the wire harness, the acquired image information, the system analysis report and the detection result are stored in the database together, so that the production management of enterprises is facilitated.
Drawings
FIG. 1 is a schematic view of a male end defect of a wiring harness;
FIG. 2 is a schematic view of a wiring harness female end defect;
FIG. 3 is a schematic structural diagram of an image capturing device;
FIG. 4 is a system workflow;
fig. 5 is a general block diagram of the system.
In the figure: 101-the central reed of the male end is intact; 102-bending the central reed at the male end; 103-male end center reed missing; 104-public end shooting effect; 201-the central reed of the female end is intact; 202-the petal-shaped reed at the female end is intact; 203-first female end center reed missing; 204-second female end center reed missing; 205-the first female end petal-shaped reed is bent; 206-the second female end petal-shaped reed is bent; 207-mother end shooting effect; 301-a housing; 302-terminal pulling and inserting mould; 303-ring LED lamp; 304-an LED light fixture; 305-an industrial camera; 306-a front cover plate; 307-rear cover plate; 308-hexagonal pillars; 309-bolt; 3021-male-end jack; 3022-female jack; 401-an acquisition module; 402-detection procedure; 403-detection database.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
The invention provides a technical scheme that: the utility model provides a camera extension line terminal image detection system behind car, includes:
a module M1: performing mathematical modeling based on a geometric dimension relation between the structural features of the male end and the female end of the product by utilizing a Qt program and an OpenCv computer vision library, and establishing a wire harness feature template;
a module M2: collecting image information of a terminal by using an image collecting device;
a module M3: and comparing the image information with the mathematical models and the characteristic templates of the male end and the female end of the product to detect the qualification of the terminal.
As shown in fig. 2, the center of mass of the qualified male end center reed is in the middle area of the overall center of mass of the terminal, for example, the male end center reed is intact 101, and when the reed characteristics do not exist as a defect, for example, the male end center reed is absent 102, the reed center of mass is shifted as a skew, for example, the male end center reed is skewed 102. Utilizing a mouse callback function, an area interception function and an image storage function in OpenCv, intercepting a public end area in an image and storing the public end area as a feature template image A, such as a public end shooting effect 104, and utilizing a function of writing data into an Xml file in OpenCV to store coordinates of four vertex coordinates of the feature template image A in an original image; by utilizing OpenCV gray processing, linear filtering, binarization/inverse binarization, contour extraction, a contour drawing function and a mask operation function, firstly extracting the whole contour of a male end, whitewashing the periphery of the contour, then extracting a black area inside a terminal, blacking the outside of the black area, and finally, enabling a bright spot area except a central reed in an image A to be white and enabling the rest parts to be black; and calculating the centroid coordinate of the white area by using a contour function searched in OpenCv, and storing the centroid coordinate into an Xml template file.
As shown in fig. 3, the qualified female-end center reed shows two crescent shapes on the image, if the female-end center reed is intact 201, the qualified female-end center reed becomes circular in the absence of two center reeds, if the first female-end center reed is absent 203, the area between reeds becomes larger in the absence of a single center reed, if the second female-end center reed is absent 204, the two situations are absent; six petal-shaped reeds at the qualified female end are on the same circumference, and if the petal-shaped reeds at the female end are intact 202; and when the distance from the center of mass to the center of the circle of any reed is not within the range, the reed is distorted, for example, the first female-end petal-shaped reed is distorted 205 or the second female-end petal-shaped reed is distorted 206.
The central reed basically comprises the following steps of utilizing a mouse callback function, an area interception function and an image storage function in OpenCv, intercepting a public end area in an image and storing the public end area in the image as a characteristic template image B, such as a female end shooting effect 207, and utilizing a function which writes data into an Xml file in OpenCV to store coordinates of four vertex coordinates of the characteristic template image B in an original image; by utilizing color extraction, gray processing, nonlinear filtering, binarization/inverse binarization, contour extraction, a contour drawing function and a mask operation function in OpenCV, firstly finding out the centroid of the contour at the outermost periphery of a parent end, making a red circle with a specified diameter on a clone image by taking the centroid as the center of circle, whitewashing the part of the original image outside the range of the red solid circle, extracting yellow plastic circle features with black holes in the parent end, and changing all the parts except the middle black hole into white to extract the features of the central black hole; and changing black into white and changing white into black by using an inverse binarization function in OpenCv, so that the area of a black hole can be calculated by using an outline extraction function and stored in an Xml template file.
The petal-shaped reed basically comprises the following steps of changing the red area in the previous step into black; the method comprises the steps of processing pictures by utilizing OpenCV gray processing, morphological filtering (top hat, black hat, corrosion and expansion), linear filtering and binarization processing functions, and extracting bright line characteristics of six petals by filtering interference characteristics according to area size and shape proportion. And calculating the coordinate of the mass center of each petal by using a contour extraction function, sequentially calculating the coordinate difference with the mass center of the contour at the outermost periphery of the female end, and storing the coordinate difference into an Xml template file.
As shown in fig. 4, when the industrial camera 305 collects image information of a terminal, features to be detected can be highlighted, and interference can be eliminated as much as possible, the housing 301 is a closed black box, the terminal plugging and unplugging mold 302 is fixed on the front cover plate 306 by bolts 309, holes are formed in the rear cover plate 307 for routing, so that it is ensured that the collected terminal image is not influenced by external environment light change, male end jacks 3021 and female end jacks 3022 on the terminal plugging and unplugging mold 302 are symmetrically distributed, the annular LED lamp 303 is fixed on the LED lamp support 304, the ratio of the diameter R of the LED lamp to the distance L from the LED lamp to the front cover plate 306 is adjusted, so that in the collected image, the top end of a reed is obviously reflected, the internal useless features are black, a large difference is formed, the industrial camera 305 is installed behind the LED lamp support 304, and the height is adjusted by the hexagonal support 308, so that the lens and the annular LED lamp 303 are concentric.
As shown in fig. 1, the system takes a geometric dimension relation mathematical model and a feature template between the product male end and female end structural features established in a module M1 as a basis to perform qualified detection of a terminal, and the detection specific steps are as follows, an industrial camera 305 takes a picture, coordinates when the template is set in the module M1 are read by using a function for reading data in OpenCV, the male end region and the female end region are respectively intercepted, the intercepted regions are sequentially compared with the male end template and the female end template by using a histogram equalization function in OpenCV, and the detection is continued if the similarity is within a certain range; calculating the area of the brightest pixel in the image by utilizing gray level conversion, linear filtering and a binarization function in OpenCV, and continuously detecting when the area is within a certain range; the steps of feature extraction are the same as those of feature extraction in the module M1; reading data information stored in an Xml template file, calculating the coordinate difference between the coordinates of the detection reed and the coordinates of the template by the male end, converting the coordinate difference into an offset according to an actual proportion, determining that the detection reed is qualified in a preset range, calculating the proportion between the area of a black hole of the detection center reed and the area of the template by the female end, sequentially calculating the coordinate difference between the centroid of the petal-shaped reed and the centroid of the outermost periphery profile of the female end, and determining that the detection reed is qualified when the area proportion and each coordinate difference are in the preset range; and after the judgment is finished, the two-dimensional code information of the wire harness, the shooting time, the terminal image information, the offset of the central reed of the male end, the area ratio of the central reed of the female end, the offset of the petal-shaped reed of the female end and the qualified information are all stored in a database.
Application method
As shown in fig. 5, the system for detecting the sub-image of the extension line end of the rear camera of the automobile mainly comprises an image acquisition module 401, an image detection program 402 and a detection database 403. A worker inserts a wire harness to be detected into the terminal plugging and unplugging die 302, after a code scanning gun scans a two-dimensional code, a detection program sends a command to the industrial camera 305 of the image acquisition module 401, a frame of image is shot, and the two-dimensional code information, the shooting time, the terminal image information, the offset of the male end center reed, the area ratio of the female end center reed, the offset of the female end petal-shaped reed and qualified information are stored in the detection database 403 after being judged by the image detection program 402.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. The utility model provides a camera extension line terminal image detection system behind car which characterized in that includes:
a module M1: performing mathematical modeling based on a geometric dimension relation between the structural features of the male end and the female end of the product by utilizing a Qt program and an OpenCv computer vision library, and establishing a wire harness feature template;
a module M2: collecting image information of a terminal by using an image collecting device;
a module M3: comparing the image information with mathematical models and characteristic templates of a male end and a female end of a product to perform qualified detection on the terminal;
the module M1 comprises:
module M1.1: capturing a public end region in the image and storing the public end region as a feature template image A by using a mouse callback function, a region capturing function and an image storing function in OpenCv, and storing coordinates of four vertex coordinates of the feature template image A in an original image by using a function which writes data into an Xml file in OpenCV;
module M1.2: by utilizing OpenCV gray processing, linear filtering, binarization/inverse binarization, contour extraction, a contour drawing function and a mask operation function, firstly extracting the whole contour of a male end, whitewashing the periphery of the contour, then extracting a black area inside a terminal, blacking the outside of the black area, and finally, enabling a bright spot area except a central reed in an image A to be white and enabling the rest parts to be black;
module M1.3: calculating the centroid coordinate of the white area by using a contour function searched in OpenCv, and storing the centroid coordinate into an Xml template file;
module M1.4: utilizing a mouse callback function, an area interception function and an image storage function in OpenCv, intercepting a parent end area in an image and storing the parent end area as a feature template image B, and utilizing a function of writing data into an Xml file in OpenCv to store coordinates of four vertex coordinates of the feature template image B in an original image;
module M1.5: by utilizing color extraction, gray level processing, nonlinear filtering, binarization/inverse binarization, contour extraction, contour drawing functions and mask operation functions in OpenCV, firstly finding out the centroid of the contour at the outermost periphery of a parent end, making a red circle with a specified diameter on a clone image by taking the centroid as the center of circle, whitewashing the part of the original image outside the range of the red solid circle, extracting yellow plastic circle features with black holes in the parent end, turning all the parts except the middle black hole into white, and extracting the features of the central black hole;
module M1.6: changing black into white and changing white into black by using an inverse binarization function in OpenCv, calculating the area of a black hole by using an outline extraction function, and storing the area into an Xml template file;
module M1.7: changing the red area in the module M1.5 into black, processing the picture by utilizing OpenCV gray processing, morphological filtering, linear filtering and binarization processing functions, filtering interference characteristics through area size and shape proportion, extracting bright line characteristics of six petals, calculating the centroid coordinate of each petal by utilizing a contour extraction function, calculating the coordinate difference with the contour centroid at the outermost periphery of the parent end in sequence, and storing the coordinate difference in an Xml template file.
2. The system for detecting the image of the extended line terminal of the automobile rear camera according to claim 1, characterized in that: when the mass center of the male end central reed is in the middle area of the whole mass center of the terminal, the product male end is judged to be qualified; when the mass center of the central reed of the male end does not exist, determining that the male end of the product is missing; and when the mass center of the male end center reed is deviated, determining that the male end of the product is askew and folded.
3. The system for detecting the image of the extended line terminal of the automobile rear camera according to claim 1, characterized in that: when the female end center reed shows two crescent shapes on the image, the product female end is judged to be qualified; when the area between the reeds at the center of the female end is increased when a single center reed is absent, or the female end is changed into a circle when two center reeds are absent, the product female end is judged to be absent; six petal-shaped reeds of the qualified female end are on the same circumference, and when the distance from the center of mass of any one reed to the center of the circle is not within the range, the female end of the product is judged to be askew.
4. The system for detecting the image of the extended line terminal of the automobile rear camera according to claim 1, characterized in that: in the module M2, the image acquisition device includes that shell, front shroud, back shroud, terminal are pulled out and are inserted mould, annular LED lamp, LED lamp support, industry camera, hexagonal support and bolt, the shell is closed black box, the front shroud is located shell one side, the terminal is pulled out and is inserted the mould and pass through the bolt fastening and locate front shroud outside surface, the back shroud is located the opposite side of shell, annular LED lamp is fixed to be located on the LED lamp support, industry camera below is equipped with the hexagonal support, the industry camera passes through the hexagonal support is installed at LED lamp support rear.
5. The system for detecting the image of the extended line terminal of the automobile rear camera according to claim 4, characterized in that: the terminal pulling and inserting die is provided with a male end jack and a female end jack, and the male end jack and the female end jack are symmetrically distributed.
6. The system for detecting the image of the extended line terminal of the automobile rear camera according to claim 1, characterized in that: the module M3 comprises:
module M3.1: shooting a frame of photo by using an industrial camera, respectively intercepting a male end region and a female end region by utilizing coordinates when a feature template is set in a function reading module M1 for reading data in OpenCV, sequentially carrying out similarity comparison on the intercepted regions and a feature template image A of the male end and a feature template image B of the female end by utilizing a histogram equalization function in OpenCV, and continuously detecting if the similarity is within a certain range;
module M3.2: calculating the area of the brightest pixel in the image by utilizing gray level conversion, linear filtering and binarization functions in OpenCV, and continuously detecting and extracting features when the area is within a certain range;
module M3.3: reading the data information stored in the Xml template file, calculating the coordinate difference between the coordinates of the detection reed and the coordinates of the characteristic template A by the public end, converting the coordinate difference into an offset according to an actual proportion, and determining the detection reed to be qualified within a preset range;
module M3.4: the female end calculates the proportion of the area of the black hole of the reed in the detection center to the area of the template, and sequentially calculates the coordinate difference between the centroid of the petal-shaped reed and the centroid of the outermost contour of the female end, and the reed is qualified when the area proportion and each coordinate difference are in a preset range;
module M3.5: and after the judgment is finished, the two-dimensional code information of the wire harness, the shooting time, the terminal image information, the offset of the central reed of the male end, the area ratio of the central reed of the female end, the offset of the petal-shaped reed of the female end and the qualified information are all stored in a database.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010277451.5A CN111476782B (en) | 2020-04-10 | 2020-04-10 | Automobile rear camera extension line terminal image detection system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010277451.5A CN111476782B (en) | 2020-04-10 | 2020-04-10 | Automobile rear camera extension line terminal image detection system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111476782A CN111476782A (en) | 2020-07-31 |
CN111476782B true CN111476782B (en) | 2023-04-07 |
Family
ID=71751797
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010277451.5A Active CN111476782B (en) | 2020-04-10 | 2020-04-10 | Automobile rear camera extension line terminal image detection system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111476782B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115330710B (en) * | 2022-08-09 | 2023-03-31 | 湖北安泰汽车电气系统有限公司 | Cloud computing-based automobile wire harness quality inspection system |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105158268A (en) * | 2015-09-21 | 2015-12-16 | 武汉理工大学 | Intelligent online detection method, system and device for defects of fine-blanked parts |
CN106530275B (en) * | 2016-10-11 | 2019-06-11 | 广州视源电子科技股份有限公司 | Element mistake part detection method and system |
CN107886496A (en) * | 2017-09-30 | 2018-04-06 | 北京得华机器人技术研究院有限公司 | A kind of quality determining method of the auto-parts based on form fit |
-
2020
- 2020-04-10 CN CN202010277451.5A patent/CN111476782B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN111476782A (en) | 2020-07-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111951237B (en) | Visual appearance detection method | |
CN113643289B (en) | Fabric surface defect detection method and system based on image processing | |
CN110163853B (en) | Edge defect detection method | |
CN115082419B (en) | Blow-molded luggage production defect detection method | |
CN105894036A (en) | Image feature template matching method being applied to detection of mobile phone screen defects | |
CN106203415B (en) | bank card number automatic identification device based on digital image processing | |
CN105957082A (en) | Printing quality on-line monitoring method based on area-array camera | |
CN104182973A (en) | Image copying and pasting detection method based on circular description operator CSIFT (Colored scale invariant feature transform) | |
CN111476782B (en) | Automobile rear camera extension line terminal image detection system | |
CN110473184A (en) | A kind of pcb board defect inspection method | |
CN113658092A (en) | Aluminum electrolytic capacitor defect detection method based on image processing | |
CN111950654B (en) | Magic cube color block color reduction method based on SVM classification | |
CN106643555A (en) | Connection piece identification method based on structured light three-dimensional measurement system | |
CN115830359A (en) | Workpiece identification and counting method based on target detection and template matching in complex scene | |
CN114387269B (en) | Fiber yarn defect detection method based on laser | |
CN110490924A (en) | A kind of light field image feature point detecting method based on multiple dimensioned Harris | |
WO2022222467A1 (en) | Open circular ring workpiece appearance defect detection method and system, and computer storage medium | |
CN105404900A (en) | Positioning method of paralleled diodes and device | |
CN113538488A (en) | BMS charging port identification method | |
CN112634259A (en) | Automatic modeling and positioning method for keyboard keycaps | |
CN112418210B (en) | Intelligent classification method for tower inspection information | |
CN110866917A (en) | Tablet type and arrangement mode identification method based on machine vision | |
CN109521029B (en) | Method for detecting appearance defects of side surface of lamp holder of bayonet type automobile lamp | |
CN107315392B (en) | Special-shaped workpiece discharging optimization algorithm of automatic feeder of punch press and tolerance algorithm thereof | |
CN115082504A (en) | Light spot identification method for solar photovoltaic panel |
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 |