Vehicle VIN code character carving depth measurement method and system

Abstract

The invention provides a depth measurement method and system for vehicle VIN code character carving, and relates to the technical field of depth measurement. The method comprises the steps of obtaining point cloud data of vehicle VIN code character carving, and obtaining contour depth information of each carved character; respectively carrying out clustering analysis on the contour depth information of each engraved character to correspondingly obtain depth values of a plurality of character contours; and according to the plurality of depth values, obtaining the carving depth of the VIN code character of the vehicle. According to the invention, the problems of high error rate and low precision of the depth measurement result are solved, and the dependence of the vehicle VIN code character engraving depth measurement on the mechanical position of the fixed detection device is reduced to a great extent.

Description

Technical Field

[0001] The present invention relates to the technical field of depth measurement, and in particular to a method and system for measuring the depth of engraving characters in a vehicle VIN code. Background Art

[0002] The vehicle VIN code (Vehicle Identification Number, also known as the frame number) is the unique identification information of the car. Since the engraving of the vehicle VIN code characters is an indispensable part of vehicle production, it contains a lot of important information such as the vehicle manufacturer, year, model, body type and code, engine code and assembly location; therefore, the depth of the VIN code character engraving is one of the important indicators to check whether the VIN code is qualified.

[0003] At present, the depth of the vehicle VIN code characters is mostly measured by a depth dimension detection device, which mainly involves fitting the base of the detection device to the detected surface of the vehicle body, placing a detection component with a movable probe on the base, and then using the probe to detect the depth of the character engraving to determine whether the depth of the character engraving is qualified and effective. This measurement method is limited by the direction and position of the vehicle body, which greatly limits the placement direction and position of the engraved samples. In addition, the probe in the detection device will not only wear out due to long-term use, which will cause a large deviation in the depth measurement accuracy and increase the error rate; the probe needs to measure the depth of each character once, which is very time-consuming.

[0004] In order to solve the problems encountered by the detection device, characters can be jointly determined through two-dimensional recognition and three-dimensional recognition of characters. At the same time, the depth information is measured by the sensor, and the distances of all points from the fitting straight line are calculated; all distance values ​​are traversed and a threshold is set. When the distance value is greater than the threshold, it is considered that a character is engraved and recorded as an inflection point. After this inflection point, 10 pixel positions are taken to obtain the maximum value, which is the depth value of the character.

[0005] However, this depth measurement method will have large errors when fitting a straight line. At the same time, it is also limited by the noise of image acquisition when finding the inflection point, so it is easy to misposition the inflection point, resulting in a high error rate and low accuracy of the depth measurement results. Summary of the invention

[0006] Based on this, it is necessary to provide a depth measurement method and system for engraving vehicle VIN code characters to address the above technical problems, which solves the problems of high error rate and low accuracy of depth measurement results.

[0007] In one aspect, the present invention provides a method for measuring the depth of a vehicle VIN code character engraving, the method comprising: Obtain the point cloud data of the vehicle VIN code characters and obtain the contour depth information of each engraved character; Performing cluster analysis on the contour depth information of each engraved character to obtain depth values ​​of multiple character contours; The depth of engraving the characters of the vehicle VIN code is obtained according to the multiple depth values.

[0008] Furthermore, the contour depth information of each engraved character is obtained by: A plurality of continuous contour depth data are obtained based on the point cloud data; and the continuous contour depth data are segmented according to the engraved characters to obtain contour depth information of each engraved character.

[0009] Furthermore, the method further comprises: A target area is set according to the contour depth data, and cluster analysis is performed on the contour depth information of each engraved character in the target area.

[0010] Furthermore, cluster analysis of the contour depth information of each engraved character includes: Sort all first data points in the profile depth information in ascending order according to depth coordinate values ​​to obtain a second data point set; Constructing a KD tree node for each second data point in the second data point set and creating an index to obtain at least one core object, Starting from any one of the core objects, a cluster is expanded using points within the domain radius of the core object, thereby obtaining a plurality of cluster data points; Sort and filter multiple cluster data points to obtain the depth value of the current engraved character.

[0011] Furthermore, the core object is obtained in the following manner: Set the field radius and the minimum number of points within the field radius; The second data point finds all target points within the domain radius through the KD tree node index. If the target point number is greater than or equal to the minimum point number, it is marked as a core object; otherwise, it is marked as noise.

[0012] Further, the extended cluster includes: Add all points within the core object's sphere radius to the same cluster, and recursively expand the spheres of all points until no new points can be added.

[0013] Further, sorting and filtering multiple cluster data points includes: Sort multiple cluster data points according to the mean values ​​of the cluster data points to obtain multiple first cluster sets; Determine whether the first cluster set is less than or equal to a set value, if so, discard it, otherwise add it to the second cluster set; The second cluster set is calculated to obtain a depth value of the currently engraved character.

[0014] Furthermore, the plurality of depth values ​​are averaged to obtain the depth of engraving of the vehicle VIN code characters.

[0015] Furthermore, the contour depth information of each engraved character includes at least one contour depth map; and each contour depth map includes engraving data points and base material data points.

[0016] On the other hand, the present invention also proposes a vehicle VIN code character engraving depth measurement system, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any one of the above methods.

[0017] In general, the present invention provides a method and system for measuring the depth of vehicle VIN code character engraving, which can achieve the following beneficial effects compared with the prior art: (1) The present invention uses a clustering algorithm to perform cluster analysis on the contour depth information of each engraved character, effectively distinguishing the character engraving data points from the base material data points. On the one hand, it improves the accuracy of character engraving depth measurement, and on the other hand, it can also solve the problem of errors caused by thermal deformation in the character engraving area. This makes the vehicle VIN code character engraving technology more convenient and faster, not only solving the problem of high error rate and low accuracy of depth measurement results, but also greatly reducing the dependence of vehicle VIN code character engraving depth measurement on the mechanical position of the fixed detection device.

[0018] (2) The present invention sets a target area and performs cluster analysis on the contour depth information of each engraved character in the target area, thereby reducing the requirements for scanning accuracy and trajectory teaching accuracy, effectively reducing the difficulty of manual operation, and improving the convenience of implementation; at the same time, by using real-time scanning measurement, the process can be stopped at any time whenever an unqualified engraved character is found, which can effectively ensure welding quality and improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1It is a schematic diagram of the method flow of a vehicle VIN code character engraving depth measurement method and system provided by the present invention; Figure 2 It is a schematic diagram of multiple continuous profile depth data of a vehicle VIN code character engraving depth measurement method and system provided by the present invention; Figure 3 It is a schematic diagram of single profile depth data of a vehicle VIN code character engraving depth measurement method and system provided by the present invention; Figure 4 It is a schematic diagram of a target area of ​​a vehicle VIN code character engraving depth measurement method and system provided by the present invention; Figure 5 It is a schematic diagram of a clustering algorithm analysis of a depth measurement method and system for engraving vehicle VIN code characters provided by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in combination with the drawings and embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0022] It should be noted that, in the description of the embodiments of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a method, step or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such method, step or system. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the method, step or system including the element.

[0023] In order to achieve depth measurement of vehicle VIN code character engraving, the present invention provides a vehicle VIN code character engraving depth measurement method, which collects point cloud data of the character engraving area in real time, and uses an improved clustering algorithm to divide the contour depth information of each identified engraved character into two parts: base material data points and character engraving data points, so as to achieve measurement of the depth data of each character, and then compare the depth data with a preset depth threshold to determine whether the vehicle VIN code engraving depth is qualified, thereby solving the problem of character engraving depth measurement error and accuracy caused by thermal deformation of the scanning area.

[0024] Specifically, if Figure 1 As shown, the method of the present invention comprises: Step 101: Obtain point cloud data of vehicle VIN code character engraving, and obtain contour depth information of each engraved character.

[0025] Point cloud data can be obtained by scanning the vehicle VIN code engraving area in real time using a 3D profiler camera. By using the 3D profiler to scan and measure in real time, unqualified engraved characters can be found in real time and the engraving can be stopped at any time, thus effectively ensuring welding quality and production efficiency.

[0026] However, since directly using point cloud data for point cloud image analysis will affect its analysis efficiency, and there is a large uncertainty in the automatic recognition and analysis of discrete spatial point data, the present invention obtains the contour depth information of each engraved character based on the scanned point cloud data. By analyzing the contour depth information of the engraved characters, the defects of directly processing point cloud data can be greatly avoided.

[0027] As an embodiment, obtaining the contour depth information of each engraved character includes: first obtaining a plurality of continuous contour depth data based on the point cloud data, and then segmenting the continuous contour depth data according to the engraved characters to obtain the contour depth information of each engraved character.

[0028] It should be noted that in order to measure the contour depth information of each engraved character, the contour depth data of each engraved character needs to be segmented, that is, the unengraved contour depth data and the scanned contour depth data are obtained by using point cloud data recognition, such as Figure 2 As shown, when the robot drives the 3D profiler camera to move, the point cloud data collected by the camera includes a plurality of continuous profile depth data, and the profile depth data includes alternating unmarked profile depth data and scanned profile depth data.

[0029] The unmarked contour depth data is contour depth data obtained by scanning the unmarked area between adjacent marked characters; and the scanned contour depth data is contour depth data obtained by scanning the marked characters.

[0030] It should be noted that the contour depth information of each engraved character includes at least one contour depth map; and each contour depth map includes engraving data points and base material data points.

[0031] like Figure 3 As shown, the profile depth information of the engraved character "C" and the engraved character "D" include multiple profile depth maps, wherein the downwardly concave portion of the profile depth map is the engraved data point in a single profile depth map, and the data points other than the engraved data points are the base material data points.

[0032] In addition, the method may further include: setting a target area according to the contour depth data, and performing cluster analysis on the contour depth information of each engraved character in the target area.

[0033] The target area (ROI area) is used to locate the approximate position of a single character in the vehicle VIN code engraving area, which can effectively avoid using the contour data outside the ROI area, thereby reducing the impact of the material near the vehicle VIN code on the engraving depth calculation, making the contour depth information of each engraved character more accurate.

[0034] It should be noted that the setting of the ROI area is related to the marking data points sent in the contour depth map. An ROI area of ​​appropriate size needs to include all the marking data points sent in the contour depth map. Figure 4 As shown in the figure, the internal area defined by the two red dotted lines is the ROI area.

[0035] Step 102: performing cluster analysis on the contour depth information of each engraved character, and obtaining corresponding depth values ​​of multiple character contours.

[0036] In order to accurately calculate the depth value of each engraved character contour, the improved DBSCAN clustering algorithm can be used to perform cluster analysis on the contour depth information of each engraved character. One engraved character gets one depth value, and multiple engraved characters get multiple depth values.

[0037] It should be noted that cluster analysis includes: Step 201: Sort all first data points in the profile depth information in ascending order according to depth coordinate values ​​to obtain a second data point set.

[0038] For example, for each contour depth information, all first data points in the contour depth information are obtained: (x0, z0), (x1, z1), (x2, z2), ..., (x n , z n Then sort all the first data points from small to large according to the z coordinate value to obtain the second data point set: (x -0 , z -0 ), (x -1 , z -1 ), (x -2 , z -2 ),……,(x -n , z -n ).

[0039] Step 202: construct a KD tree node for each second data point in the second data point set, and create an index to obtain at least one core object.

[0040] Since it is necessary to perform distance calculation on each data point in the second data point set, and there are many second data points, it is time-consuming to perform separate distance calculation on each data point. Therefore, the present invention constructs a KD tree (short for k-dimensional tree) node for each second data point and establishes an index, so that each second data point can quickly find all points within its domain radius through the KD tree index, thereby improving the calculation speed.

[0041] The core object is obtained by setting the domain radius (ε) and the minimum number of points within the domain radius (minPts); the second data point finds all target points within the domain radius through the KD tree node index. If the target point number is greater than or equal to the minimum number of points, it is marked as a core object; otherwise, it is marked as noise.

[0042] Step 203: Starting from any core object, the cluster is expanded using points within the domain radius of the core object to obtain multiple cluster data points.

[0043] The cluster expansion may include: adding all points within the domain radius of the core object to the same cluster, and recursively expanding the domains of all points until no new points can be added.

[0044] Step 204: sort and filter the multiple cluster data points to obtain the depth value of the current engraved character.

[0045] As an embodiment, sorting and screening multiple cluster data points includes: sorting multiple cluster data points according to the mean value of the cluster data points to obtain multiple first cluster sets; judging whether the first cluster set is less than or equal to a set value, if so, discarding it, otherwise adding it to the second cluster set; calculating the second cluster set to obtain the depth value of the current engraved character.

[0046] It should be noted that the first cluster set is obtained by sorting the multiple cluster data points according to the size of the cluster data point mean. .

[0047] As an embodiment, it can be directly determined whether the first cluster set includes the engraved character outline. Figure 5 As shown in the figure, if the number of cluster sets is greater than 1, it means that the current contour depth information is the contour depth information of the engraved character (engraving contour depth data). At this time, the cluster set with the largest average value can be directly Discard it and get the second cluster set, which is the engraved character data point If the number of cluster sets is less than or equal to 1, it means that the current contour depth information is the contour depth information of the unengraved character (unengraved contour depth data), which is not included in the calculation of the depth data of the engraved character.

[0048] The purpose of screening is to remove the cluster set of parent material data points and obtain the cluster set of engraved character data points. Since the cluster set value of parent material data points is large, after removing the largest cluster set, the remaining cluster set is the engraved character data point.

[0049] As another embodiment, the mean of each cluster data point can be compared with the set data one by one; if it is greater than, it means that the cluster data point is the parent material data, and the current cluster is discarded; if it is less than, it means that the cluster data point is the engraving data, and finally the second cluster set is obtained. Then, the depth value of the current engraved character is obtained by calculating the second cluster set. .

[0050] Multiple engraved characters correspond to multiple depth values .

[0051] Step 103: Obtain the engraving depth of the vehicle VIN code characters according to the multiple depth values.

[0052] The depth of the vehicle VIN code characters is obtained by averaging the multiple depth values. The depth data of each character can be averaged to obtain the final depth value; or the depth values ​​of all the engraved characters can be obtained and then averaged to obtain the final depth value.

[0053] For example, whenever the depth data of an unengraved character appears, it indicates that the scanning of a single character is completed, and the depth values ​​of all currently engraved characters are counted and calculated. , find the set The mean , the mean This means the depth value of all the engraved characters currently scanned. When the outline of the engraved characters reappears next time, the collection will be re-counted. And calculate the mean , until the entire vehicle VIN code is scanned.

[0054] On the other hand, the present invention provides a vehicle VIN code character engraving depth measurement system, including a memory, a processor and a computer program stored in the memory, the processor executes the computer program to implement the steps of any one of the above methods.

[0055] The technical solution of the system is consistent with the technical solution of the method and will not be described in detail here.

[0056] It should be noted that, for the above-mentioned various embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, and according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0057] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided in this application, it should be understood that the disclosed method or system can be implemented in other ways. For example, the embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0058] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0059] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0060] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

[0061] Those skilled in the art will appreciate that all or part of the various circuits in the above embodiments may be completed by entering a program to instruct related hardware, and the program may be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0062] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0063] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. As long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0064] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for measuring the depth of a vehicle VIN code character engraving, characterized in that: The method comprises: Obtain the point cloud data of the vehicle VIN code characters and obtain the contour depth information of each engraved character; Performing cluster analysis on the contour depth information of each engraved character to obtain depth values ​​of multiple character contours; The depth of engraving the characters of the vehicle VIN code is obtained according to the multiple depth values.

2. A method for measuring the depth of a vehicle VIN code character engraving according to claim 1, characterized in that: The contour depth information of each engraved character is obtained by: A plurality of continuous contour depth data are obtained based on the point cloud data; and the continuous contour depth data are segmented according to the engraved characters to obtain contour depth information of each engraved character.

3. A method for measuring the depth of a vehicle VIN code character engraving according to claim 2, characterized in that: The method further comprises: A target area is set according to the contour depth data, and cluster analysis is performed on the contour depth information of each engraved character in the target area.

4. A method for measuring the depth of a vehicle VIN code character engraving according to claim 1, characterized in that: The cluster analysis of the contour depth information of each engraved character includes: Sort all first data points in the profile depth information from small to large according to depth coordinate values ​​to obtain a second data point set; Constructing a KD tree node for each second data point in the second data point set and creating an index to obtain at least one core object, Starting from any one of the core objects, a cluster is expanded using points within the domain radius of the core object, thereby obtaining a plurality of cluster data points; Sort and filter multiple cluster data points to obtain the depth value of the current engraved character.

5. A method for measuring the depth of a vehicle VIN code character engraving according to claim 4, characterized in that: The core object is obtained by: Set the field radius and the minimum number of points within the field radius; The second data point finds all target points within the domain radius through the KD tree node index. If the target point number is greater than or equal to the minimum point number, it is marked as a core object; otherwise, it is marked as noise.

6. A method for measuring the depth of a vehicle VIN code character engraving according to claim 4, characterized in that: The extended cluster comprises: Add all points within the core object's sphere radius to the same cluster, and recursively expand the spheres of all points until no new points can be added.

7. A method for measuring the depth of a vehicle VIN code character engraving according to claim 4, characterized in that: Sorting and filtering multiple cluster data points includes: Sort multiple cluster data points according to the mean values ​​of the cluster data points to obtain multiple first cluster sets; Determine whether the first cluster set is less than or equal to a set value, if so, discard it, otherwise add it to the second cluster set; The second cluster set is calculated to obtain a depth value of the currently engraved character.

8. A method for measuring the depth of a vehicle VIN code character engraving according to claim 1, characterized in that: The multiple depth values ​​are averaged to obtain the depth of the vehicle VIN code characters.

9. A method for measuring the depth of a vehicle VIN code character engraving according to claim 3, characterized in that: The profile depth information of each engraved character includes at least one profile depth map; and each profile depth map includes engraving data points and base material data points.

10. A vehicle VIN code character engraving depth measurement system, comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes a computer program to implement the steps of the method according to any one of claims 1 to 9.

Images