CN116358856A - Buckle detection method, device, equipment and storage medium - Google Patents

Abstract

The invention belongs to the technical field of vehicle design, and discloses a buckle detection method, a buckle detection device, buckle detection equipment and a storage medium. The method comprises the steps of constructing a detection template corresponding to a virtual buckle to be detected; moving the detection template to enable the pose of the detection template to be matched with the virtual buckle to be detected; identifying a buckle mounting plate corresponding to the virtual buckle to be detected based on the detection template; establishing an installation coordinate system on the buckle installation plate; and carrying out installation normalization detection on the virtual buckle to be detected based on the installation coordinate system and the detection template. Because the detection template corresponding to the virtual buckle to be detected can be moved, the detection template is matched with the virtual buckle to be detected, the buckle installation plate can be correctly identified, parameters such as the size and the thickness of the buckle installation plate can be correctly measured according to the installation coordinate system established on the buckle installation plate and the detection template, and whether other parts interfering with the buckle exist or not is determined, so that whether the automatic detection buckle accords with installation standardization or not is realized.

Description

Buckle detection method, device, equipment and storage medium

technical field

The present invention relates to the technical field of vehicle design, in particular to a buckle detection method, device, equipment and storage medium.

Background technique

In order to avoid the mismatch of various hardware of the vehicle when it is actually put into production, before the vehicle is put into production, a corresponding vehicle design model is generally built for the vehicle to simulate the actual effect of various hardware, and a large number of buckles are generally set in the vehicle. To avoid installation difficulties or too loose buckles during the actual vehicle assembly process, it is necessary to conduct normative testing on the buckle parameters used in the vehicle design model.

At present, the standard detection of buckles is generally carried out by manual confirmation. However, there are a large number of buckles in the vehicle, and manual confirmation has high labor costs, low timeliness, and is prone to missed inspections.

The above content is only used to assist in understanding the technical solution of the present invention, and does not mean that the above content is admitted as prior art.

Contents of the invention

The main purpose of the present invention is to provide a buckle detection method, device, equipment and storage medium, aiming to solve the technical problem that the prior art cannot automatically perform standardized detection of buckle.

In order to achieve the above object, the present invention provides a buckle detection method, the method comprising the following steps:

Build a detection template corresponding to the virtual buckle to be detected;

moving the detection template so that the detection template matches the virtual buckle to be detected;

Identifying the buckle installation plate corresponding to the virtual buckle to be detected based on the detection template;

Establishing an installation coordinate system on the buckle installation plate;

Based on the installation coordinate system and the detection template, an installation normative detection is performed on the virtual buckle to be detected.

Optionally, before the step of constructing the detection template corresponding to the virtual buckle to be detected, it also includes:

When receiving the search keyword, match the search keyword with the keyword in the configuration table to determine the type of virtual buckle to be detected;

Correspondingly, the step of constructing a detection template corresponding to the virtual buckle to be detected includes:

Obtain the buckle type corresponding to the virtual buckle to be detected;

Searching for a detection template corresponding to the virtual buckle to be detected according to the buckle type.

Optionally, the step of moving the detection template so that the detection template matches the virtual buckle to be detected includes:

Simulating moving the detection template, and performing model registration through a local consistency registration algorithm;

When the registration is successful through the local consistency registration algorithm, record the current template pose information of the detection template;

The detection template is moved according to the template pose information, so that the detection template is matched with the virtual buckle to be detected.

Optionally, after the step of simulating moving the detection template and performing model registration through a local consistency registration algorithm, it also includes:

If the registration fails through the local consistency registration algorithm, then perform model registration through the local similarity registration algorithm;

When the registration is successful through the local similarity registration algorithm, record the current template pose information of the detection template;

The detection template is moved according to the template pose information, so that the detection template is matched with the virtual buckle to be detected.

Optionally, the step of identifying the buckle installation plate corresponding to the virtual buckle to be detected based on the detection template includes:

determining the minimum containment box corresponding to the virtual buckle to be detected according to the detection template;

Match the minimum containment box with the minimum containment boxes of other parts in the assembly to determine the suspected mounting plate;

Calculating the minimum distance between each suspected mounting plate and the template end of the detection template;

According to the minimum distance, a buckle installation board is selected from the suspected installation boards.

Optionally, the step of establishing an installation coordinate system on the snap-fit installation plate includes:

Obtain the point cloud of the installation hole corresponding to the buckle installation plate, and fit the installation plane through the point cloud of the installation hole;

Obtaining the normal vector corresponding to the installation plane, and determining an approximate center point according to the point cloud of the installation hole;

determining an interference point in the installation hole point cloud according to the approximate center point, and removing the interference point from the installation hole point cloud;

Calculate the approximate center point according to the installation hole point cloud after removing the interference point, and obtain the reference center point;

An installation coordinate system is constructed based on the reference center point and the normal vector.

Optionally, the step of performing installation normative inspection on the virtual buckle to be inspected based on the installation coordinate system and the inspection template includes:

Determining the thickness of the plate corresponding to the buckle mounting plate and the size of the mounting hole based on the installation coordinate system;

determining a target part that interferes with the detection template;

Calculating the minimum distance between the target part and the end preset feature in the detection template one by one;

The installation normative detection result of the virtual buckle to be detected is determined according to the thickness of the board, the size of the installation hole and the minimum distance.

In addition, in order to achieve the above purpose, the present invention also proposes a buckle detection device, which includes the following modules:

Template construction module, used to construct the detection template corresponding to the virtual buckle to be detected;

a template matching module, configured to move the detection template, so that the detection template matches the virtual buckle to be detected;

A plate identification module, configured to identify the buckle installation plate corresponding to the virtual buckle to be detected based on the detection template;

A coordinate building module, used to establish an installation coordinate system on the buckle installation plate;

A buckle detection module, configured to perform installation normative detection on the virtual buckle to be detected based on the installation coordinate system and the detection template.

In addition, in order to achieve the above object, the present invention also proposes a buckle detection device, which includes: a processor, a memory, and a buckle detection device stored in the memory and operable on the processor. A program, when the buckle detection program is executed by the processor, the steps of the above buckle detection method are implemented.

In addition, in order to achieve the above object, the present invention also proposes a computer-readable storage medium, the computer-readable storage medium stores a buckle detection program, and when the buckle detection program is executed, the above-mentioned buckle detection is realized. method steps.

The present invention constructs the detection template corresponding to the virtual buckle to be detected; moves the detection template so that the detection template matches the virtual buckle to be detected; identifies the buckle installation plate corresponding to the virtual buckle to be detected based on the detection template; The installation coordinate system is established on the installation board; based on the installation coordinate system and the detection template, the installation normative inspection is carried out for the virtual buckle to be detected. Since the detection template corresponding to the virtual buckle to be detected will be moved, the detection template will match the virtual buckle to be detected to ensure that the buckle installation plate can be correctly identified, and then according to the installation coordinate system established on the buckle installation plate and the detection The template can correctly measure the size, thickness and other parameters of the buckle installation plate, and determine whether there are other parts that interfere with the buckle, so as to realize the automatic detection of whether the buckle conforms to the installation specification.

Description of drawings

Fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment involved in the solution of an embodiment of the present invention;

Fig. 2 is a schematic flow chart of the first embodiment of the buckle detection method of the present invention;

3 is a schematic structural diagram of a detection template according to an embodiment of the present invention;

Fig. 4 is a schematic flow chart of the second embodiment of the buckle detection method of the present invention;

Fig. 5 is a schematic diagram of local features of an embodiment of the present invention;

Fig. 6 is a schematic diagram of triangular subdivision according to an embodiment of the present invention;

Fig. 7 is a schematic diagram of corner features according to an embodiment of the present invention;

Fig. 8 is a schematic flow chart of the third embodiment of the buckle detection method of the present invention;

Fig. 9 is a schematic diagram of a point cloud of an installation hole according to an embodiment of the present invention;

Fig. 10 is a schematic diagram of a coordinate system construction point according to an embodiment of the present invention;

Fig. 11 is a structural block diagram of the first embodiment of the buckle detection device of the present invention.

The realization of the purpose of the present invention, functional characteristics and advantages will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

Detailed ways

It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

Referring to FIG. 1 , FIG. 1 is a schematic structural diagram of a buckle detection device in a hardware operating environment involved in the solution of an embodiment of the present invention.

As shown in FIG. 1 , the electronic device may include: a processor 1001 , such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002 , a user interface 1003 , a network interface 1004 , and a memory 1005 . Wherein, the communication bus 1002 is used to realize connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wireless-Fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .

Those skilled in the art can understand that the structure shown in FIG. 1 does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine some components, or arrange different components.

As shown in FIG. 1 , the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a buckle detection program.

In the electronic device shown in Figure 1, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in In the buckle detection device, the electronic device calls the buckle detection program stored in the memory 1005 through the processor 1001, and executes the buckle detection method provided by the embodiment of the present invention.

An embodiment of the present invention provides a buckle detection method. Referring to FIG. 2 , FIG. 2 is a schematic flowchart of a first embodiment of a buckle detection method according to the present invention.

In this embodiment, the buckle detection method includes the following steps:

Step S10: Construct a detection template corresponding to the virtual buckle to be detected.

It should be noted that the execution subject of this embodiment may be the buckle detection device, and the buckle detection device may be a device capable of building and testing vehicle design models, such as electronic devices such as personal computers, tablet computers, or servers. , it can also be other devices that can realize the same or similar functions, which is not limited in this embodiment. In this embodiment and the following embodiments, the buckle detection method of the present application is described by taking the buckle detection device as an example. Be explained.

It should be noted that the virtual buckle to be detected may be a virtual buckle designated in the vehicle design model for normative detection, and the virtual buckle to be detected may be designated by the management personnel of the buckle detection device according to actual needs. The detection template can include a registration body and a measurement body. The registration body is used for registration with the buckle to be detected, and the measurement body is marked with preset features for the detection of the buckle, such as the preset features of the hole , end preset features, etc. During the registration process, if the registration body is rotated or translated, the measuring body will also follow the registration body to perform operations such as rotation and translation.

In order to facilitate understanding, it will now be described in conjunction with Figure 3. Figure 3 is a schematic structural diagram of the detection template of this embodiment. As shown in Figure 3, the detection template includes a registration body and a measurement body, and the measurement body is marked with preset features of the hole. , End Position, and End Preset Features.

Further, in order to facilitate the user to select the virtual buckle to be detected, before step S10 described in this embodiment, it may also include:

When receiving the search keyword, match the search keyword with the keyword in the configuration table to determine the virtual buckle to be detected;

Correspondingly, the step S10 may include:

Obtain the buckle type corresponding to the virtual buckle to be detected;

Searching for a detection template corresponding to the virtual buckle to be detected according to the buckle type.

It should be noted that when a car is designed, it will use a variety of buckles, and may use a variety of different types of buckles. In order to distinguish the buckles used, "position + part type + "type + number" to distinguish multiple buckles used in the vehicle design model, so that users can select virtual buckles to be detected by inputting search keywords. At this time, when the buckle detection device receives the search keywords, it will Match the search keyword with the keyword in the configuration table to determine the virtual buckle to be detected. Wherein, the configuration table may store the relationship between the position of each buckle in the vehicle design model and the unique identification of the buckle, and the keyword may be the unique identification of each buckle.

For example: Suppose there are four buckles in the vehicle design model, and the unique identifiers of the corresponding buckles are "head-Buckle-type1-1", "head-Buckle-type2-2", "body-Buckle-type1- 1", "body-Buckle-type1-2", where "head" indicates that the buckle is used for the front part of the car, "body" indicates that the buckle is used for the body part, and "Buckle" indicates that the part type is a buckle, "type1" and "type2" indicate the type of buckle. At this time, if the search keyword entered by the user is "head-Buckle", the unique identifier of the buckle is "head-Buckle-type1-1" and "head-Buckle" respectively. The two buckles of Buckle-type2-2" will be used as virtual buckles to be detected; and if the search keyword entered by the user is "type1", the unique identifiers of the buckles are "head-Buckle-type1-1" and The two buckles of "body-Buckle-type1-1" will be used as virtual buckles to be detected.

It is understandable that since a large number of buckles may be installed in the vehicle, setting up a detection template for each buckle requires a huge amount of work, and the actual use effect is also poor, but the vehicle is actually equipped with many different types (different size, different specifications), the buckle parameters of the same type of buckle are actually the same, and the same detection template can be used for the detection of the same type of buckle. Therefore, the corresponding detection can be set in advance according to the buckle type Template to improve the reuse rate of the detection template. At this time, when detection is required, the corresponding detection template is searched according to the buckle type of the virtual buckle to be detected.

Step S20: moving the detection template to match the detection template with the virtual buckle to be detected.

It should be noted that moving the detection template to match the detection template with the virtual buckle to be detected may be to move the registration body in the detection template through operations such as rotation and translation, so that the installation direction and posture information of the registration body are consistent with the virtual buckle to be detected. The detection of virtual snaps remains consistent.

Step S30: Identify the buckle installation plate corresponding to the virtual buckle to be detected based on the detection template.

It should be noted that the buckle installation plate may be a plate that the buckle should clamp when the buckle is installed. Identifying the buckle mounting plate corresponding to the virtual buckle to be detected based on the detection template may be to screen each part in the vehicle design model according to the detection template, and determine the plate clamped by the virtual buckle to be detected in the vehicle design model.

In a specific implementation, in order to accurately identify the buckle installation plate corresponding to the virtual buckle to be detected, step S30 in this embodiment may include:

determining the minimum containment box corresponding to the virtual buckle to be detected according to the detection template;

Match the minimum containment box with the minimum containment boxes of other parts in the assembly to determine the suspected mounting plate;

Calculating the minimum distance between each suspected mounting plate and the template end of the detection template;

According to the minimum distance, a buckle installation board is selected from the suspected installation boards.

It should be noted that the determination of the minimum containment box corresponding to the virtual buckle to be detected according to the detection template may be the minimum containment box containing the detection template determined according to the spatial position of the component in the detection template. The assembly can be a vehicle design model, matching the minimum containing box to the minimum containing boxes of other parts in the assembly, identifying suspected mounting panels can be comparing the minimum containing box to the minimum containing boxes of other parts in the assembly, the Parts in the minimum containment box that may interfere with the minimum containment box corresponding to the virtual buckle to be detected are used as suspected mounting plates.

In a specific implementation, judging whether two minimum containing boxes interfere can be determined by comparing the maximum and minimum points of the two minimum containing boxes.

For example: Suppose the smallest point of the smallest containing box A is (x11, y11, z11), and the largest point is (x12, y12, z12); the smallest point of the smallest containing box B is (x21, y21, z21), and the largest point is ( x22,y22,z22);

If A interferes with B, then there are ((x21<x11<x22) and (y21<y11<y22) and (z21<z11<z22)) or ((x21<x12<x22) and (y21<y12<y22) and (z21<z12<z22)) or ((x11<x21<x12) and (y11<y21<y12) and (z11<z21<z12)) or ((x11<x22<x12) and (y11<y22< y12) and (z11<z22<z12)).

In actual use, if the minimum distance between each suspected mounting plate and the template end of the detection template is not 0, then the suspected mounting plate with the smallest corresponding minimum distance can be used as the snap-fit mounting plate; and If the minimum distance between only one suspected mounting plate and the template end of the detection template is 0, the corresponding suspected mounting plate with the minimum distance of 0 can be used as the snap-fit mounting plate.

Wherein, if there are two or more suspected installation panels and the minimum distance between the template end of the detection template is 0, it can be determined that the virtual buckle to be detected interferes with other parts except the panel, and this It can be judged that the buckle status is abnormal.

Step S40: establishing an installation coordinate system on the buckle installation board.

It should be noted that when carrying out standard installation inspections on the buckle, it is necessary to check whether the distance between other parts that interfere with the end of the buckle and the end of the buckle, and the size of the mounting hole of the buckle meet the specifications. And parameters such as the thickness of the mounting plate, and in order to facilitate the detection of the size of the mounting hole on the snap mounting plate and the thickness of the snap mounting plate, it is necessary to establish an installation coordinate system on the snap mounting plate.

Step S50: Perform installation normative inspection on the virtual buckle to be inspected based on the installation coordinate system and the inspection template.

It should be noted that, based on the installation coordinate system and the detection template, the installation normative detection of the virtual buckle to be detected can be based on the installation coordinate system to determine the installation hole size and thickness of the buckle installation plate corresponding to the virtual buckle to be detected, and according to The detection template determines whether there are other parts that may contact or interfere with the buckle to be detected in the vehicle design model, so as to determine whether the virtual buckle to be detected conforms to the installation specification.

In this embodiment, the detection template corresponding to the virtual buckle to be detected is constructed; the detection template is moved to match the detection template with the virtual buckle to be detected; the buckle installation plate corresponding to the virtual buckle to be detected is identified based on the detection template; The installation coordinate system is established on the buckle installation plate; the installation normative inspection is carried out based on the installation coordinate system and the detection template of the virtual buckle to be detected. Since the detection template corresponding to the virtual buckle to be detected will be moved, the detection template will match the virtual buckle to be detected to ensure that the buckle installation plate can be correctly identified, and then according to the installation coordinate system established on the buckle installation plate and the detection The template can correctly measure the size, thickness and other parameters of the buckle installation plate, and determine whether there are other parts that interfere with the buckle, so as to realize the automatic detection of whether the buckle conforms to the installation specification.

Referring to FIG. 4 , FIG. 4 is a schematic flowchart of a second embodiment of a buckle detection method according to the present invention.

Based on the first embodiment above, the step S20 of the buckle detection method in this embodiment includes:

Step S201: Simulate moving the detection template, and perform model registration through a local consistency registration algorithm.

In actual use, simulating a moving detection template and performing model registration through a local consistency registration algorithm can be:

①Simulate the moving detection template in the memory, and calculate the characteristic description value of each triangular surface of the moving detection template and the virtual buckle to be detected, and round up each characteristic matching value;

② Construct histograms of the feature matching values of the virtual buckle to be detected and the detection template respectively;

③ Find a pair of triangular surfaces with the same feature matching value and frequency of 1 in the histogram for matching;

④ If the virtual buckle to be detected and the detection template are still not registered, continue to simulate the mobile detection template, and repeat ③ until the registration is successful;

⑤If all moving possibilities have been moved and the registration has not been realized in step ④, it is determined that the registration fails.

For ease of understanding, description is now made in conjunction with FIG. 5 , but this solution is not limited. Figure 5 is a schematic diagram of the local features of this embodiment, as shown in Figure 5, the three vertices of the triangular face i are A, B, C, respectively, and the lengths of the three sides are respectively a, b, and c; the normal of i and its adjacent surface The included angles of the normal direction of i are k1, k2, k3 respectively; the sum of the distances between the vertex i and the center point of the adjoining surface of the vertex is d1, d2, d3 respectively; then the feature descriptor of triangular surface i is: (a,b ,c,k1,k2,k3,d1,d2,d3), the feature matching value of triangle i is: a*k1*d1+b*k2*d2+c*k3*d3.

In a specific implementation, before step S201 is executed, the matching score between the detection template and the virtual buckle to be detected and the detection template can also be calculated. If the matching score is less than the preset matching threshold, the detection template and the virtual buckle to be detected can be directly determined. match, no subsequent moving steps need to be performed; and if the matching score is greater than or equal to a preset matching threshold. Wherein, the preset matching threshold can be set in advance by the manager of the buckle detection device, for example, the preset matching threshold is set to 0.05.

Step S202: When the registration is successful through the local consistency registration algorithm, record the current template pose information of the detection template.

It can be understood that if the registration is successful through the local consistency registration algorithm, the detection template can be moved according to the current template pose information of the detection template at this time, so as to ensure that the detection template matches the virtual buckle to be detected. Wherein, the pose information of the template may include the installation direction and pose information of the detection template.

Step S203: Moving the detection template according to the pose information of the template, so that the detection template matches the virtual buckle to be detected.

In a specific implementation, the mobile detection template can be a mobile detection template according to the template pose information, so that the installation direction and posture information of the registration body in the detection template are consistent with those recorded in the template pose information, so that the detection template is consistent with the to-be-detected Virtual snap matching.

In the specific implementation, the local consistency registration algorithm is an algorithm that calculates the transformation matrix from the template feature translation and rotation to the target feature by finding two local features on the matching target. The overall execution speed of the algorithm is fast, but the matching target The requirements are high, and consistent local features need to be matched on the target. Although the registration speed of this method is fast, the requirements are too strict, and there is a certain possibility of registration failure. , it can still be ensured that the detection template can be matched with the virtual buckle to be detected. After step S201 described in this embodiment, it can also include:

If the registration fails through the local consistency registration algorithm, then perform model registration through the local similarity registration algorithm;

When the registration is successful through the local similarity registration algorithm, record the current template pose information of the detection template;

The detection template is moved according to the template pose information, so that the detection template is matched with the virtual buckle to be detected.

It should be noted that if the registration fails through the local consistency registration algorithm, it means that the virtual buckle to be detected may not be suitable for the more stringent local consistency registration algorithm at this time, so you can try to use local similarity Similarly, if the registration is successful through the local similarity registration algorithm, the detection template can still be moved according to the current template pose information of the detection template, so that the detection template matches the virtual buckle to be detected .

For ease of understanding, description is now made in conjunction with FIGS. 6 and 7 , but this solution is not limited. FIG. 6 is a schematic diagram of triangular subdivision in this embodiment, and FIG. 7 is a schematic diagram of corner features. Model registration through the local similarity registration algorithm can be subdivided for each triangular surface on the virtual buckle to be detected and the detection template. The maximum side length of a single small plane is 0.5mm (the purpose of subdivision is to obtain evenly distributed The triangular surface makes the local similarity between the target and the template higher, and the maximum side length can be adjusted according to actual needs), as shown in Figure 6; The center point and normal vector of a triangular surface; calculate the angular characteristics α, β, γ between every two center points within the range of 20mm of each center point, as shown in Figure 7, each pair of center points (P _s and P _t ) between: α=v×n _t , β=u×(P _t -P _s )/d, γ=arctan(w×n _t ,u×n _t ); the quaternion of each central point The feature values (α, β, γ, d,) are boxed into a histogram, and similar features are aligned according to the histogram, and the current template pose information of the detection template is recorded during alignment.

In this embodiment, the detection template is moved by simulation, and the model registration is performed through the local consistency registration algorithm; when the registration is successful through the local consistency registration algorithm, the current template pose information of the detection template is recorded ; Moving the detection template according to the pose information of the template, so that the detection template matches the virtual buckle to be detected. Because it simulates the moving detection template, and quickly calculates whether the registration is completed through the preset registration algorithm, the detection template is actually moved after the registration is completed, so that the detection template matches the virtual buckle to be detected, reducing the need for vehicle design The adjustment of the model speeds up the overall execution efficiency.

Referring to FIG. 8 , FIG. 8 is a schematic flowchart of a third embodiment of a buckle detection method according to the present invention.

Based on the first embodiment above, the step S40 of the buckle detection method in this embodiment includes:

Step S401: Obtain the point cloud of the installation hole corresponding to the snap-on installation plate, and fit the installation plane through the point cloud of the installation hole.

It should be noted that obtaining the point cloud of the mounting hole corresponding to the buckle mounting plate may be to obtain the point cloud of the plate on the buckle mounting plate within the preset feature range of the hole, that is, the point cloud of the mounting hole, wherein the mounting hole Edge points of mounting holes as well as interference points can be included in the point cloud. Fitting the installation plane through the point cloud of the installation hole may be fitting an installation plane through the point cloud of the installation hole by the least square method.

Step S402: Obtain the normal vector corresponding to the installation plane, and determine an approximate center point according to the point cloud of the installation hole.

It should be noted that determining the approximate center point according to the point cloud of the installation hole may be calculating an average value of the coordinates of each point contained in the point cloud of the installation hole, so as to obtain the approximate center point.

Step S403: Determine an interference point in the installation hole point cloud according to the approximate center point, and remove the interference point from the installation hole point cloud.

It should be noted that the interference points can be divided into interference points on the installation plane and outer edge interference points. According to the approximate center point, the interference points on the installation plane in the installation hole point cloud can be determined by any point in the installation hole point cloud C A is translated to the approximate center point o ₁ by a preset distance to obtain point A ₂ , and the line segment A is respectively drawn in the direction of +n (the positive direction of the normal vector corresponding to the installation plane) and -n (the negative direction of the normal vector corresponding to the installation plane) ₂ B, A ₂ C, if the distance between A ₂ B or A ₂ C and the plate is 0, A is called the interference point;

Determine the interference point on the outer edge of the point cloud of the installation hole based on the approximate center point, which can be obtained by shifting the preset distance from any point A in C to the opposite direction of the approximate center point o ₁ to obtain point A ₃ , and use point A ₃ and o ₁ as endpoints to make a line segment L, if the shortest distance between L and the plate is 0, then A is called the interference point.

Wherein, the preset distance can be set in advance by the manager of the buckle detection device according to actual needs, for example, the preset distance is set to 0.5 mm.

Step S404: Calculate an approximate center point according to the point cloud of the installation hole after removing the interference point, and obtain a reference center point.

It should be noted that after the interference points are removed, the remaining points in the point cloud of the installation hole are the edge points of the installation hole. At this time, the average value of the coordinates of each point in the point cloud of the installation hole after removing the interference points can be calculated , to obtain the approximate center point, and use the approximate center point obtained at this time as the reference center point for subsequent calculations. Wherein, the reference center point is closer to the real installation hole center than the approximate center point obtained in the above step S402.

For ease of understanding, description is now made in conjunction with FIG. 9 , but this solution is not limited. Fig. 9 is a schematic diagram of the installation hole point cloud of this embodiment, as shown in Fig. 9, O1 in Fig. 9 is an approximate center point, O2 is a reference center point, and the light-colored points in Fig. 9 are interference points to be screened out, The remaining dark points are the rest of the mounting hole point cloud.

Step S405: Construct an installation coordinate system based on the reference center point and the normal vector.

In order to facilitate understanding, it is now described in conjunction with Fig. 10. Fig. 10 is a schematic diagram of the coordinate system construction point of this embodiment. The construction of the installation coordinate system based on the reference center point and the normal vector can be based on the reference center point o ₂ as the starting point, respectively with +n (the positive direction of the normal vector) and -n (the negative direction of the normal vector) are used as directions to translate the preset translation distance to obtain points A and B, and a line segment L ₂ is made with A and B as endpoints. For each point of C, draw a vertical line perpendicular to _L2 , and the intersection of the vertical line and _L2 constitutes the mapping point set P, and take the farthest mapping point in the +n direction of the mapping point set as the origin o of the coordinate system (as shown in Figure 10, Map all the edge points of the installation holes on the line segment AB, take the farthest mapping point on AB in the +n direction as the origin o of the coordinate system, and o is the point on the installation plane), and then use the Euclidean distance clustering method to calculate P Clustering, the mapping points with similar distances are grouped into one category, then the edge points of the installation holes corresponding to the same type of mapping points are called edge points of the same layer; the minimum circumscribed rectangle is calculated for the edge points of the same layer corresponding to o, and the long direction of the rectangle is called Y, the width direction is X, then o is the origin of the installation coordinate system, n is the z axis, the Y direction is the y axis, and the X direction is the x axis to construct the installation coordinate system. Wherein, the preset translation distance can be set in advance by the manager of the buckle detection device according to actual needs, for example, the preset translation distance is set to 20mm.

In a specific implementation, in order to reasonably determine whether the virtual buckle to be detected conforms to the installation specification, in this embodiment, the step S50 may include:

Determining the thickness of the plate corresponding to the buckle mounting plate and the size of the mounting hole based on the installation coordinate system;

determining a target part that interferes with the detection template;

Calculating the minimum distance between the target part and the end preset feature in the detection template one by one;

The installation normative detection result of the virtual buckle to be detected is determined according to the thickness of the board, the size of the installation hole and the minimum distance.

It should be noted that, based on the installation coordinate system, the size of the installation hole corresponding to the buckle installation plate can be determined based on the origin o of the installation hole coordinate system, and the points A and B are obtained by moving 20mm in the direction of +n and -n respectively, and then A and B are endpoints and draw a line segment L. Make a vertical line perpendicular to L ₂ for each point in the point cloud C of the installation hole, and the intersection point of the vertical line and L ₂ constitutes the mapping point set P; use Euclidean clustering to segment P to obtain the hierarchical point cloud set of C; through Calculate the maximum inner diameter value of different layers, find the minimum inner diameter layer of C, and then use the arc method and the four-point method to calculate the measured value (the measured value includes the length and width of the installation hole), the measured value calculated by the two methods Select the measured value of the mounting hole size close to the buckle specification parameters as the mounting hole size.

Among them, the step of using the arc method to calculate the measured value may include: according to the point cloud of the minimum inner diameter of the installation hole and the coordinate system of the installation hole, respectively take three points in the one-sided point set to fit the circle, then the centers of the circles on both sides are o1, o2, diameter are d1 and d2, and the center distance is L; then the length of the installation hole is L+d1/2+d2/2, and the width is (d1+d2)/2;

The steps of using the four-point method to calculate the measured value may include: according to the point cloud of the minimum inner diameter of the installation hole and the coordinate system of the installation hole, after creating a vertical line segment at the origin, translate to a point close to the end point of the installation hole, and calculate the minimum distance point between the sheet metal and the line segment , then this point is the endpoint of the mounting hole; the length and width of the mounting hole can be calculated by calculating the distance between two pairs of endpoints.

In a specific implementation, the determination of the plate thickness corresponding to the buckle mounting plate based on the installation coordinate system can be based on the installation coordinate system, using the AABB enclosing box algorithm (also known as the AABB bounding box algorithm) for the edge point cloud of the mounting hole to calculate Minimum containment box; the length of the side parallel to the z-axis of the minimum containment box is the thickness of the plate. Of course, if there is a plate thickness parameter in the feature attribute of the mounting sheet metal of the snap-fit mounting plate, the plate thickness can also be directly extracted from the feature attribute.

In actual use, according to the thickness of the board, the size of the installation hole and the minimum distance, the installation normative detection result of the virtual buckle to be detected can be determined as whether there is a minimum distance between the predetermined feature of the end in the detection template and the detection template is less than or a target part equal to 0, if it exists, it can be directly determined that the installation normative detection result of the virtual buckle to be detected does not meet the normative conditions for buckle installation; if it does not exist, it can continue to determine the thickness of the plate or the size of the installation hole Whether it is within the range of installation normative standards, if not, it can be determined that the installation normative detection result of the virtual buckle to be detected does not meet the normative conditions for buckle installation.

In the specific implementation, in order to facilitate the user to view the inspection results of installation norms, a UI interface can also be set up to display the vehicle design model and the result output area in the UI interface. In the result output area in the UI interface, each The installation normative detection results of the virtual buckle, each test result item records the thickness of the board corresponding to the buckle, the size of the installation hole and the interference result (that is, whether there are interfering parts). Among them, if the item in the UI interface is clicked , then the view can be adjusted to the position of the buckle corresponding to the item, and the value of the inspection result is marked in the view. Specifically, in order to further improve visibility, buckles that do not meet installation normative requirements can also be highlighted on the UI interface (for example, marked with a red circle).

In this embodiment, by obtaining the point cloud of the installation hole corresponding to the buckle installation plate, and fitting the installation plane through the point cloud of the installation hole; obtaining the normal vector corresponding to the installation plane, and according to the point cloud of the installation hole Determine the approximate center point; determine the interference point in the installation hole point cloud according to the approximate center point, and remove the interference point from the installation hole point cloud; according to the installation hole point after removing the interference point Approximate the center point by cloud computing to obtain a reference center point; construct an installation coordinate system based on the reference center point and the normal vector. Since the interference points in the installation hole point cloud will be removed by calculating the approximate center point when constructing the coordinate system, it is ensured that the constructed coordinate system will not be affected by the interference points, thereby ensuring the accuracy of subsequent size and plate thickness calculations sex.

In addition, an embodiment of the present invention also proposes a storage medium, on which a buckle detection program is stored, and when the buckle detection program is executed by a processor, the steps of the buckle detection method as described above are implemented.

Referring to FIG. 11 , FIG. 11 is a structural block diagram of the first embodiment of the buckle detection device of the present invention.

As shown in Figure 11, the buckle detection device proposed by the embodiment of the present invention includes:

Template construction module 10, for constructing the detection template corresponding to the virtual buckle to be detected;

Template matching module 20, configured to move the detection template, so that the detection template matches the virtual buckle to be detected;

A plate identification module 30, configured to identify the buckle installation plate corresponding to the virtual buckle to be detected based on the detection template;

A coordinate construction module 40, configured to establish an installation coordinate system on the buckle installation plate;

The buckle detection module 50 is configured to perform installation normative detection on the virtual buckle to be detected based on the installation coordinate system and the detection template.

In this embodiment, the detection template corresponding to the virtual buckle to be detected is constructed; the detection template is moved to match the detection template with the virtual buckle to be detected; the buckle installation plate corresponding to the virtual buckle to be detected is identified based on the detection template; The installation coordinate system is established on the buckle installation plate; the installation normative inspection is carried out based on the installation coordinate system and the detection template of the virtual buckle to be detected. Since the detection template corresponding to the virtual buckle to be detected will be moved, the detection template will match the virtual buckle to be detected to ensure that the buckle installation plate can be correctly identified, and then according to the installation coordinate system established on the buckle installation plate and the detection The template can correctly measure the size, thickness and other parameters of the buckle installation plate, and determine whether there are other parts that interfere with the buckle, so as to realize the automatic detection of whether the buckle conforms to the installation specification.

Further, the template construction module 10 is also configured to match the search keyword with keywords in the configuration table when receiving the search keyword, to determine the virtual buckle to be detected;

The template construction module 10 is further configured to obtain the buckle type corresponding to the virtual buckle to be detected; and search for the detection template corresponding to the virtual buckle to be detected according to the buckle type.

Further, the template matching module 20 is also used to simulate moving the detection template, and perform model registration through the local consistency registration algorithm; when the registration is successful through the local consistency registration algorithm, record the The current template pose information of the detection template; the detection template is moved according to the template pose information, so that the detection template matches the virtual buckle to be detected.

Further, the template matching module 20 is also used to perform model registration through the local similarity registration algorithm if the registration fails through the local similarity registration algorithm; When the registration is successful, record the current template pose information of the detection template; move the detection template according to the template pose information, so that the detection template matches the virtual buckle to be detected.

Further, the panel identification module 30 is also used to determine the minimum containment box corresponding to the virtual buckle to be detected according to the detection template; compare the minimum containment box with the minimum containment boxes of other parts in the assembly Matching, determining the suspected installation boards; calculating the minimum distance between each suspected installation board and the template end of the detection template; selecting a buckle installation board from the suspected installation boards according to the minimum distance.

Further, the coordinate construction module 40 is also used to obtain the installation hole point cloud corresponding to the buckle installation plate, and fit the installation plane through the installation hole point cloud; obtain the normal vector corresponding to the installation plane , and determine the approximate center point according to the point cloud of the installation hole; determine the interference point in the point cloud of the installation hole according to the approximate center point, and remove the interference point from the point cloud of the installation hole; according to The point cloud of the installation hole after removing the interference point calculates an approximate center point to obtain a reference center point; an installation coordinate system is constructed based on the reference center point and the normal vector.

Further, the buckle detection module 50 is also used to determine the board thickness and installation hole size corresponding to the buckle installation board based on the installation coordinate system; determine the target part that interferes with the detection template; Calculate the minimum distance between the target part and the end preset feature in the detection template one by one; determine the installation of the virtual buckle to be detected according to the thickness of the plate, the size of the installation hole and the minimum distance Normative test results.

It should be understood that the above is only an example, and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings according to needs, and the present invention is not limited thereto.

It should be noted that the workflow described above is only illustrative and does not limit the protection scope of the present invention. In practical applications, those skilled in the art can select part or all of them to implement according to actual needs. The purpose of the scheme of this embodiment is not limited here.

In addition, for technical details not described in detail in this embodiment, reference may be made to the buckle detection method provided in any embodiment of the present invention, which will not be repeated here.

Furthermore, it should be noted that in this document, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or system comprising a set of elements includes not only those elements, but also other elements not expressly listed, or elements inherent in such a process, method, article, or system. Without further limitations, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article or system comprising that element.

The serial numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as a read-only memory (Read Only Memory) , ROM)/RAM, magnetic disk, optical disk), including several instructions to make a terminal device (which can be a mobile phone, computer, server, or network device, etc.) execute the methods described in various embodiments of the present invention.

The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process conversion made by using the description of the present invention and the contents of the accompanying drawings, or directly or indirectly used in other related technical fields , are all included in the scope of patent protection of the present invention in the same way.

Claims (10)

1. The buckle detection method is characterized by comprising the following steps of:

constructing a detection template corresponding to the virtual buckle to be detected;

moving the detection template to enable the detection template to be matched with the virtual buckle to be detected;

identifying a buckle installation plate corresponding to the virtual buckle to be detected based on the detection template;

establishing an installation coordinate system on the buckle installation plate;

and carrying out installation normalization detection on the virtual buckle to be detected based on the installation coordinate system and the detection template.

2. The method for detecting a buckle according to claim 1, wherein before the step of constructing the detection template corresponding to the virtual buckle to be detected, the method further comprises:

when a search keyword is received, matching the search keyword with keywords in a configuration table, and determining a virtual buckle to be detected;

correspondingly, the step of constructing the detection template corresponding to the virtual buckle to be detected comprises the following steps:

obtaining a buckle type corresponding to the virtual buckle to be detected;

and searching a detection template corresponding to the virtual buckle to be detected according to the buckle type.

3. The method of claim 1, wherein the step of moving the detection template to match the detection template with the virtual buckle to be detected comprises:

The detection template is moved in a simulation mode, and model registration is carried out through a local consistency registration algorithm;

recording current template pose information of the detection template when the registration is successful through the local consistency registration algorithm;

and moving the detection template according to the template pose information so as to enable the detection template to be matched with the virtual buckle to be detected.

4. The method of claim 3, wherein after the step of modeling the movement of the detection template and model registration by a local consistency registration algorithm, further comprising:

if the registration by the local consistency registration algorithm fails, carrying out model registration by the local similarity registration algorithm;

recording current template pose information of the detection template when the registration by the local similarity registration algorithm is successful;

and moving the detection template according to the template pose information so as to enable the detection template to be matched with the virtual buckle to be detected.

5. The clip detecting method according to claim 1, wherein the step of identifying the clip mounting plate corresponding to the virtual clip to be detected based on the detecting template includes:

Determining a minimum containing box corresponding to the virtual buckle to be detected according to the detection template;

matching the minimum containing box with the minimum containing boxes of other parts in the assembly body to determine suspected mounting plates;

calculating the minimum distance between each suspected installation plate and the template end part of the detection template;

and selecting a buckle mounting plate from the suspected mounting plates according to the minimum distance.

6. The clip detection method of claim 1, wherein the step of establishing a mounting coordinate system on the clip mounting plate comprises:

acquiring corresponding installation Kong Dianyun of the buckle installation plate, and fitting an installation plane through the installation Kong Dianyun;

acquiring a normal vector corresponding to the installation plane, and determining an approximate center point according to the installation Kong Dianyun;

determining an interference point in the installation Kong Dian cloud from the approximate center point and removing the interference point from the installation Kong Dianyun;

calculating an approximate center point according to the installation Kong Dianyun after the interference point is removed, and obtaining a reference center point;

and constructing an installation coordinate system based on the reference center point and the normal vector.

7. The method for detecting a buckle according to any one of claims 1 to 6, wherein the step of performing installation normalization detection on the virtual buckle to be detected based on the installation coordinate system and the detection template includes:

Determining the thickness of the plate corresponding to the buckle mounting plate and the size of the mounting hole based on the mounting coordinate system;

determining a target part interfering with the detection template;

calculating the minimum distance between the target part and the preset end characteristic in the detection template one by one;

and determining the installation standardization detection result of the virtual buckle to be detected according to the thickness of the plate, the size of the installation hole and the minimum distance.

8. The buckle detection device is characterized by comprising the following modules:

the template construction module is used for constructing a detection template corresponding to the virtual buckle to be detected;

the template matching module is used for moving the detection template so as to match the detection template with the virtual buckle to be detected;

the plate identifying module is used for identifying the buckle installation plate corresponding to the virtual buckle to be detected based on the detection template;

the coordinate construction module is used for establishing an installation coordinate system on the buckle installation plate;

and the buckle detection module is used for carrying out installation normalization detection on the virtual buckle to be detected based on the installation coordinate system and the detection template.

9. A buckle detection apparatus, characterized in that the buckle detection apparatus comprises: a processor, a memory and a buckle detection program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the buckle detection method according to any one of claims 1-7.

10. A computer-readable storage medium, wherein a buckle detection program is stored on the computer-readable storage medium, which when executed implements the steps of the buckle detection method according to any one of claims 1 to 7.

Images