CN114821589A

CN114821589A - Vehicle VIN code detection method and device

Info

Publication number: CN114821589A
Application number: CN202210437987.8A
Authority: CN
Inventors: 李斌; 程思; 陈文效; 张仕磊; 陈以诺
Original assignee: Wuhan Xinnaishi Intelligent Technology Co ltd
Current assignee: Wuhan Xinnaishi Intelligent Technology Co ltd
Priority date: 2022-04-25
Filing date: 2022-04-25
Publication date: 2022-07-29

Abstract

The invention provides a vehicle VIN code detection method and a device, wherein the method comprises the following steps: scanning a VIN code engraving area, acquiring a corresponding surface topography characteristic curve, and generating a two-dimensional depth image of the corresponding area; acquiring the character height and the total character length of the VIN code, and judging whether the height and the length of the VIN code are qualified or not; the two-dimensional depth image is segmented, each character of the segmented VIN code is identified and combined to obtain the VIN code, and whether the VIN code is the same as a standard value or not is judged; extracting the feature points of each character based on a preset character feature library, thereby realizing the analysis of the feature points of each individual character, avoiding missing the engraving defect of a single character and realizing the complete detection of the VIN code; the invention also provides a vehicle VIN code detection device, and the scanning module is detachably arranged on the robot, so that the detection device can adapt to various working angles, and the automation of the detection process is convenient to realize.

Description

Vehicle VIN code detection method and device

Technical Field

The invention relates to the technical field of automobile production, in particular to a vehicle VIN code detection method and device.

Background

A Vehicle Identification Number (VIN), which is called VIN for short, is composed of 17 digits or letters, and can be used to identify information such as the country of automobile production, manufacturer, and engine model, which is equivalent to the Identification Number of a Vehicle, so Identification of the VIN is particularly important. At present, the VIN code has strict requirements on the engraving morphology, the engraving depth and the like, and according to the regulations of national standards (GB 16735 and 2019), the engraving code word height of automobiles and trailers is greater than or equal to 7.0mm, and the engraving depth is greater than or equal to 0.3 mm; for passenger cars and closed trucks with the total mass less than or equal to 3500kg, the marking depth is greater than or equal to 0.2mm, and the marking total length is less than or equal to 200 mm.

The traditional VIN code is engraved by a mechanical engraving method, the engraving head is easy to wear, and the engraving effect is not ideal when facing high-hardness materials, so that the laser processing mode is gradually applied to vehicle VIN code engraving by the advantages of high speed, high power, long service life and the like. However, since laser processing belongs to thermal processing, if abnormality occurs in the processing process, irreversible influence is generated on the engraving result, batch scrapping of the whole vehicle is easy to occur, and serious consequences can be caused. Meanwhile, the VIN code is easy to be etched to a depth insufficient due to factors such as workpiece surface pollution. Therefore, the conventional two-dimensional character defect detection cannot completely judge the engraving quality, and the engraving result needs to be subjected to three-dimensional depth detection in real time so as to find all problems in time and take measures to solve the problems as early as possible.

At present, VIN (vehicle identification number) codes are recognized and detected mainly by photographing an engraved area, training a model by using a deep learning method or analyzing pictures by using an image processing method, and performing simple defect detection, but the detection methods are only stopped at two-dimensional detection, cannot detect depth conditions at the same time, and do not meet the detection requirement of laser processing VIN codes; the VIN code quality can be checked by a contact detection method, and the depth data is read by using a special depth measuring device and a detection needle and a dial indicator, so that the detection precision is low, the detection method is very dependent on the technical level of detection personnel, and the detection method has human errors, system errors and observation errors, and is difficult to obtain a correct detection result.

Disclosure of Invention

The invention provides a vehicle VIN code detection method and device, which are used for solving the problems that in the prior art, the detection on the VIN code cannot be completed in one step, the detection on the character shape, the engraving depth and the engraving width is easy to miss a single character, and the detection efficiency is low, realizing the real-time scanning and detection on the VIN code, improving the automation level of the VIN code detection, realizing the detection on the single character, avoiding the omission and improving the detection accuracy.

The invention provides a vehicle VIN code detection method, which comprises the following steps:

s1, scanning a VIN code marking area to obtain a plurality of surface topography characteristic curves;

s2, generating a two-dimensional depth image of a corresponding area based on the surface topography characteristic curve;

s3, acquiring the character height and the character total length of the VIN code according to the two-dimensional depth image, comparing the character height and the character total length with corresponding standard ranges respectively, if the character height and the character total length accord with the standard ranges, further segmenting each character of the VIN code, otherwise, judging that the VIN code is unqualified;

identifying each character of the segmented VIN code, combining to obtain the VIN code, comparing the VIN code with an actual value of the VIN code, and if the VIN code is the same as the actual value of the VIN code, judging that the character identification is correct;

s4, extracting feature points of each character based on a preset character feature library, calculating the engraving depth and the character stroke width of each character, comparing the engraving depth and the character stroke width of each character with the corresponding standard ranges, and if the comparison result of each character is in accordance with the corresponding standard ranges, judging that the VIN code is qualified.

According to the VIN code detection method for the vehicle provided by the invention, the step S1 specifically includes:

and calibrating the initial position and the end position of scanning in the VIN code marking area, and scanning the VIN code marking area from the initial position to the end position through a 3D camera so as to obtain the surface topography feature data.

According to the VIN code detection method for the vehicle provided by the invention, the step S3 specifically includes:

establishing a coordinate system on the two-dimensional depth image, wherein any corner point is taken as a coordinate origin, the horizontal direction at the origin is an X axis, and the vertical direction is a Y axis;

performing binarization processing on the two-dimensional depth image, respectively projecting characters to an X axis and a Y axis, wherein the positions with the projected characters are 1, and the rest positions are 0;

acquiring the positions of the leftmost end and the rightmost end of the projection character in the X-axis direction, acquiring the difference value of the horizontal coordinates of the end point positions of the two ends, and acquiring the total length of the character;

and acquiring the positions of the topmost and bottommost ends of the projected character in the Y-axis direction, acquiring the difference value of the vertical coordinates of the end points of the two corresponding ends, and acquiring the height of the character.

According to the VIN code detection method for the vehicle provided by the invention, in the step S3, each character of the VIN code is segmented, and the method specifically includes the steps of:

acquiring a plurality of jumping points which are changed from 0 to 1 according to the projection characters on the X axis based on the two-dimensional depth image after the binarization processing;

and segmenting the original two-dimensional depth image at each jumping point to obtain 17 independent characters.

According to the vehicle VIN code detection method provided by the invention, the step S3 specifically includes the steps of:

after each individual character is obtained, comparing the character with the standard character of the VIN code, and judging whether the stroke of each character has defects;

the defects at least comprise stroke errors and stroke deletions; and if the defects exist, judging that the VIN code is unqualified to be engraved.

According to the vehicle VIN code detection method provided by the invention, the step S4 includes:

establishing a corresponding character feature library based on all the usable characters of the VIN code;

extracting characteristic points of each individual character based on the character characteristic library, acquiring coordinates of each characteristic point, and acquiring a surface appearance characteristic curve corresponding to the coordinates of each characteristic point based on the resolution of the surface appearance characteristic curve and the scanning rate of the surface appearance characteristic curve;

taking the region with jumping height on the surface topography characteristic curve as a character engraving region to obtain the engraving depth of the corresponding characteristic point;

and acquiring the distance between two end points of the character engraving area, and acquiring the character stroke width of the corresponding characteristic point through angle conversion.

Optionally, since the numbers and alphabetical characters allowed to be used by the VIN code are fixed, the numbers and alphabetical characters of a fixed number can be analyzed to obtain corresponding character feature points; including but not limited to: for each different usable character, adding stroke end points of the character and intersection points among the strokes as feature points of the corresponding character into the character feature library; adding the defect point positions in the historical detection data into the character feature library as feature points of corresponding characters;

according to the method for detecting the VIN code of the vehicle provided by the invention, the step S4 includes:

calculating the average engraving depth and the average character stroke width of all feature points detected by a single VIN code, and counting the variation trend of the average engraving depth and the average character stroke width;

and if the variation trend of the average engraving depth and/or the average character stroke width is higher than a preset threshold value, judging that the VIN code is unqualified.

On the other hand, the invention also provides a vehicle VIN code detection device, which comprises a robot, a scanning module and an analysis module:

the scanning module is arranged on the robot and used for scanning a VIN code marking area to obtain a corresponding surface topography characteristic curve;

the analysis module generates a two-dimensional depth image of a corresponding area based on the surface topography characteristic curve;

the analysis module is further used for obtaining the character height and the character total length of the VIN code according to the two-dimensional depth image, comparing the character height and the character total length with corresponding standard ranges respectively, if the character height and the character total length accord with the standard ranges, further segmenting each character of the VIN code, and otherwise, judging that the VIN code is unqualified;

and extracting feature points of each character based on a preset character feature library, calculating the engraving depth and the character stroke width of each character, comparing the engraving depth and the character stroke width of each character with the corresponding standard ranges, and judging that the VIN code is qualified if the comparison result of each character conforms to the corresponding standard ranges.

The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the vehicle VIN code detection method.

The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program that, when executed by a processor, implements the steps of the vehicle VIN code detection method as described in any one of the above.

According to the method and the device for detecting the VIN code of the vehicle, provided by the invention, multiple groups of surface morphology characteristic curves of the VIN code in the longitudinal direction are obtained by scanning the VIN code engraving area and are combined to generate the corresponding two-dimensional depth image, so that the surface morphology characteristics of the VIN code engraving area are more accurately reflected; carrying out binarization coordinate processing on the two-dimensional depth image so as to accurately obtain the character height and the total length of the character of the VIN code; by further segmenting each character of the VIN code, the single character is identified and then combined to obtain the complete VIN code, which is beneficial to improving the identification accuracy; further analyzing the feature points of each individual character according to a preset character feature library, thereby avoiding missing the engraving defect of a single character and realizing the complete detection of the VIN code; according to the vehicle VIN code detection device provided by the invention, the scanning module is detachably arranged on the robot, so that the device is easily detached according to the actual vehicle type to be detected, the detection device can adapt to various working angles through the robot, and the automation of the detection process is convenient to realize.

Drawings

In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.

FIG. 1 is a schematic flow chart of a vehicle VIN code detection method provided by the present invention;

FIG. 2 is a schematic diagram of a surface topography characteristic curve of the VIN code detection method for a vehicle according to the present invention;

fig. 3 is a schematic diagram of a two-dimensional depth image obtained by the vehicle VIN code detection method provided by the invention;

fig. 4 is a schematic diagram of calculating the width and depth of the vehicle VIN code detection method provided by the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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 terms "first," "second," "third," and the like in the description and claims of this application and in the foregoing drawings are used for distinguishing between different elements and not for describing a particular sequential order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

In one embodiment, the invention provides a vehicle VIN code detection method, which specifically includes the steps of:

Further, the step S1 includes:

calibrating an initial position and an end position of scanning in the VIN code marking area, and scanning the VIN code marking area from the initial position to the end position through a 3D camera to obtain the surface topography feature data;

it should be noted that the initial position and the end position may be set as the left end and the right end of the VIN code stamping area, the scanning direction may be from left to right or from right to left, as long as the surface topography feature information in the VIN code stamping area is obtained; the invention does not further limit the scanning direction; when transverse scanning is carried out, a plurality of longitudinal surface topography characteristic curves in a VIN code marking area are obtained;

the initial position and the terminal position can also be set as the upper end and the lower end of the VIN code stamping area, and can be scanned from top to bottom or from bottom to top; because from last to down or from the bottom up when carrying out longitudinal scanning, what obtain is that VIN sign indicating number beats a plurality of horizontal surface topography characteristic curve in the district of carving, the character number of VIN sign indicating number is more, and horizontal surface topography characteristic curve can be more complicated, is unfavorable for carrying out analysis and segmentation to the character, consequently from the top down or from the bottom up carry out longitudinal scanning's efficiency not in from left to right or from right to left scanning mode.

Specifically, after scanning the VIN code engraving region, the obtained surface topography characteristic curve is as shown in fig. 2, and the letters "a", "B", and "C" are scanned, and when the letter B is located, the obtained longitudinal surface topography characteristic curve has three valley sections, and the three valley sections correspond to regions with jump height in the character B, that is, the engraving region of the character B;

integrating a plurality of longitudinal surface topography characteristic curves scanned and obtained by letters A, B and C to obtain a two-dimensional gray image, marking a flat wave band by a light color, and marking a highly jumped wave valley band by a dark color, namely obtaining a corresponding depth image;

optionally, the device for scanning may be a 3D camera and a laser capable of emitting ray structured light, and the specific scanning device is not limited in the present invention;

by way of example, as shown in FIG. 3 of the drawings, a two-dimensional depth image is obtained by integrating a plurality of surface topography profiles;

further, according to the obtained two-dimensional depth image of the complete VIN code engraving area, the font height and the total character length of the VIN code are calculated, and the step S3 includes:

establishing a coordinate system on the two-dimensional depth image, wherein any one corner point is taken as a coordinate origin, the horizontal right of the origin is an X axis, and the vertical downward is a Y axis;

acquiring the positions of the topmost and bottommost ends of the projected character in the Y-axis direction, acquiring the difference value of the vertical coordinates of the end points of the two corresponding ends, and acquiring the height of the character;

specifically, a planar rectangular coordinate system is established by taking a fixed point of any one angle of the two-dimensional depth image as an origin, and the two-dimensional depth image is subjected to binarization processing;

when a character is projected to an X axis, as long as a surface topography characteristic curve corresponding to one row of pixels has a height jump area, the row of pixels is indicated to belong to a character imprinting area, and the projection at the position is set to be 1; similarly, when projecting to the Y axis, if the pixel corresponding to the row belongs to the character imprinting area, the corresponding projection value is set to "1";

therefore, the total projection on the X axis and the Y axis is measured, and the length value in the X axis direction and the height value in the Y axis direction are obtained, namely the total length of the character and the height of the character.

Specifically, in an embodiment, in the step S3, the dividing each character of the VIN code specifically includes the steps of:

Specifically, since the VIN code has 17 bits in total, it means that 16 blank areas without imprinted traces exist in the middle of 17 characters of the VIN code; then when the image is segmented, there are 16 regions with a projection value of 0 based on the character projection on the X-axis acquired in the above step;

optionally, a jumping point at which the projection numerical value is changed from "1" to "0" for the first time is selected as a dividing point, and one of the jumping points in the blank area may also be selected as the dividing point according to the actual situation, which is not limited in the present invention;

optionally, after the character is segmented, the segmented image is subjected to binarization processing again, and projection to the Y axis is calculated, so that the word height of a single character is calculated, and whether the word height of each character meets the relevant standard is checked;

further, the step S3 further includes:

if the VIN code has defects, the VIN code is judged to be unqualified in engraving.

Optionally, recognizing the character in each segmented region by using an OCR technology, and judging whether the stroke of each character has defects, wherein the types of the defects include but are not limited to stroke missing, stroke error, character error, uneven stroke and the like, and the character is indicated to be unqualified in imprinting; if the characters are difficult to recognize, the characters may be recognized incorrectly or may be marked incorrectly.

In one embodiment, the step S4 further includes:

extracting feature points of each individual character based on the character feature library, and acquiring coordinates of each feature point;

acquiring a surface topography characteristic curve corresponding to the coordinates of each characteristic point based on the resolution and the scanning speed of the two-dimensional depth image;

The VIN code allows the use of fixed numbers and fixed alphabetic characters, so that the fixed numbers of the numbers and the fixed alphabetic characters can be analyzed to obtain corresponding character feature points; including but not limited to: for each different usable character, adding stroke end points of the character and intersection points among strokes as feature points of the corresponding character into the character feature library;

optionally, in the process of detecting the inscription of the VIN code for multiple times, collecting historical data of multiple detections, and adding an area with high defect frequency of each character in the historical detection data as a feature point of a corresponding character into the character feature library;

therefore, the computational power consumption of each detection is saved, the feature points are directly detected, and the depth of the corresponding character is fed back through the average depth of the feature points.

Specifically, the schematic diagram of obtaining the depth and width of the engraved stroke is shown in fig. 4, a single character after segmentation is obtained, a detected feature point is selected according to the feature point position library, the position of a pixel is determined according to the resolution of a picture, and a surface topography characteristic curve corresponding to the position is obtained according to the scanning speed of a sensor;

optionally, on the extracted surface topography characteristic curve, linear filtering is used to make the curve smooth, so as to prevent external disturbance from influencing the detection result in the detection process;

further, as shown in fig. 4, according to the extracted surface topography characteristic curve, marking a region where height jump occurs on the curve, fitting line segments corresponding to non-engraved regions into a straight line, and calculating a height difference from the straight line to a trough, namely, the engraving depth of the characteristic point;

taking the front end point and the rear end point of the height jump area, taking the distance between the two end points as the initial stroke width, and converting the obtained initial stroke width according to the angle because part of strokes have an angle with the vertical direction so as to obtain the width of the engraved stroke;

and for a single character, calculating the average value of the engraving depths and the average value of the stroke widths of all the characteristic points, comparing the average values with the range of the standard requirements of the VIN code, and if the engraving depth or the engraving width of any character does not meet the standard requirements, determining that the VIN code on the surface is unqualified.

On the other hand, in an embodiment, the present invention further provides a vehicle VIN code detection apparatus, where the detection apparatus described below and the detection method described above may be referred to in correspondence, and specifically includes a robot, a scanning module, and an analysis module:

the scanning module is detachably arranged on the robot and is used for scanning a VIN code marking area to obtain a corresponding surface topography characteristic curve;

Preferably, the robot is a six-axis robot; the robot can use a clamping jaw or a pneumatic sucking disc to grab the detection device; the detection device includes, but is not limited to, a 3D camera and a laser capable of emitting line-structured light, which is not limited to the invention.

The present invention also provides an electronic device, which may include: the system comprises a processor (processor), a communication interface (communication interface), a memory (memory) and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus. The processor may invoke logic instructions in the memory to perform the vehicle VIN code detection method described above.

In addition, the logic instructions in the memory may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the vehicle VIN code detection method provided above.

In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform the vehicle VIN code detection method described above.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A vehicle VIN code detection method is characterized by comprising the following steps:

s2, generating a two-dimensional depth image of the corresponding area based on the surface topography characteristic curve;

2. The vehicle VIN code detection method according to claim 1, wherein said step S1 includes:

3. The vehicle VIN code detection method according to claim 1, wherein said step S3 includes:

establishing a coordinate system on the two-dimensional depth image, taking any one corner point as a coordinate origin, taking the horizontal direction at the origin as an X axis, and taking the vertical direction as a Y axis;

acquiring the positions of the leftmost end and the rightmost end of the projection character in the X-axis direction, acquiring the difference value of the abscissa of the end point positions of the two ends, and acquiring the total length of the character;

4. The method for detecting a vehicle VIN code according to claim 3, wherein in the step S3, each character of the VIN code is segmented, specifically comprising the steps of:

5. The vehicle VIN code detection method as claimed in claim 4, wherein the step S3 comprises:

6. The vehicle VIN code detection method as claimed in any one of claims 3 to 5, wherein the step S4 comprises:

acquiring a surface topography characteristic curve corresponding to the coordinates of each characteristic point based on the resolution of the surface topography characteristic curve and the scanning speed of the surface topography characteristic curve;

7. The vehicle VIN code detection method as claimed in claim 6, wherein the step S4 comprises:

8. The vehicle VIN code detection device is characterized by comprising a robot, a scanning module and an analysis module:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 7 are implemented when the processor executes the program.

10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.