Tire point cloud construction method, assembly method, control device, and storage medium
By setting reflective marks on the tire and completing them with preset point clouds, the problem of the lack of depth information caused by low tire reflectivity is solved, and the accuracy and completeness of point cloud acquisition is improved, which is suitable for improving the accuracy during vehicle assembly process sex.
Patent Information
- Application Number
- CN202011632909.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-12-31
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2040-12-31
AI Technical Summary
The existing three-dimensional reconstruction technology is missing when acquiring depth information of objects with low reflectivity, resulting in low three-dimensional reconstruction accuracy, especially on tires, which leads to incomplete acquisition of depth information.
Set a reflective mark on the tire, obtain the depth information of the reflective mark through the depth image, and combine the preset tire point cloud to complete the point cloud to build a complete tire point cloud.
The accuracy of point cloud acquisition is improved, the depth information loss caused by tire reflectivity problems is avoided, and the integrity and accuracy of tire point clouds are ensured.
Smart Images

Figure CN112700537B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of vehicle assembly, and in particular to a point cloud construction method, an assembly method, a control device, and a storage medium for a tire. Background Art
[0002] 3D reconstruction technology is to restore the 3D model of an object based on input information data. At present, 3D reconstruction technology is widely used in the field of industrial manufacturing, especially in the field of robotics. It is also a key function of machine vision to achieve high-precision recognition, positioning, reconstruction, scene understanding, etc.
[0003] The input data of the 3D reconstruction technology based on the depth camera is the depth image. The depth image consists of the depth value, that is, the distance value from each point in the scene to the vertical plane where the depth camera is located. However, due to the particularity of the objects in the scene, some objects with low reflectivity, such as black objects, have weak reflected light intensity, resulting in the lack of acquired depth information, which further leads to low 3D reconstruction accuracy. Summary of the invention
[0004] To solve the above problems, the present application provides a point cloud construction method, an assembly method, a control device, and a storage medium for a tire, which can improve the accuracy of point cloud acquisition.
[0005] A technical solution adopted in the present application is: to provide a method for constructing a point cloud of a tire, the method comprising: obtaining a depth image of a target tire; wherein the depth image at least includes depth information of a reflective mark on the target tire; using the depth image to construct a first point cloud of the tire; and using a preset tire point cloud to complete the first point cloud to construct a second point cloud of the target tire.
[0006] Among them, using the depth image to construct the first point cloud of the tire includes: obtaining first depth information of the depth image; wherein the depth image is obtained by taking a depth camera, and the first depth information is determined based on the camera coordinate system of the depth camera; performing coordinate conversion on the first depth information to obtain second depth information; wherein the second depth information is determined based on the spatial coordinate system; and using the second depth information to construct the first point cloud of the tire.
[0007] The step of acquiring the first depth information of the depth image includes: extracting edge feature points of the depth image; and performing affine transformation on the extracted edge feature points to obtain the first depth information of the depth image.
[0008] The first depth information is coordinate-converted to obtain the second depth information, including: obtaining parameters of a depth camera and position information of the depth camera based on a spatial coordinate system; determining first coordinate conversion parameters according to the parameters and the position information; and using the first coordinate conversion parameters to coordinate-convert the first depth information to obtain the second depth information.
[0009] The method uses a preset tire point cloud to complete the first point cloud to construct a second point cloud of the target tire, including: aligning the first point cloud and the preset tire point cloud; and using point information in the preset tire point cloud to complete the missing point information in the first point cloud to construct the second point cloud of the tire.
[0010] Among them, registering the first point cloud and the preset tire point cloud includes: determining matching points in the first point cloud and the preset tire point cloud; using the matching points, determining second coordinate transformation parameters of the first point cloud and the preset tire point cloud; and registering the first point cloud and the preset tire point cloud using the second coordinate transformation parameters.
[0011] The reflectivity of the reflective mark is greater than a set reflection threshold, and the reflective mark is arranged at a key position of a geometric shape of a contour area and / or an axle area of the tire.
[0012] Another technical solution adopted in the present application is: to provide a method for assembling a tire of a vehicle, the method comprising: obtaining a depth image of a scene of assembling a tire to a vehicle; using the depth image to construct a vehicle point cloud of the vehicle and a tire point cloud of the tire; wherein the tire point cloud is constructed using the method as described above; and performing corresponding processing according to the spatial positions of the completed vehicle point cloud and tire point cloud models.
[0013] Among them, corresponding processing is performed according to the spatial positions of the completed vehicle point cloud and tire point cloud models, including: adjusting the running track of the tire according to the spatial positions of the vehicle point cloud and the tire point cloud to assemble the tire to the vehicle.
[0014] Another technical solution adopted in the present application is: to provide a vehicle assembly control device, which includes: a depth camera for collecting depth images of a tire assembly to a vehicle scene; a memory for storing program data; and a controller connected to the depth camera and the memory for executing the program data to implement the method as described above.
[0015] Another technical solution adopted by the present application is: providing a computer-readable storage medium, in which program data is stored, and when the program data is executed by the controller, it is used to implement the above method.
[0016] The tire point cloud construction method provided by the present application includes: obtaining a depth image of the target tire; wherein the depth image at least includes the depth information of the reflective mark on the target tire; using the depth image to construct a first point cloud of the tire; using the preset tire point cloud to complete the first point cloud to construct a second point cloud of the target tire. Through the above method, since the reflective mark is set on the tire, when the depth image is obtained, at least the depth information of the corresponding reflective mark position can be obtained, and then further through point cloud completion, a complete point cloud can be obtained, thereby improving the acquisition accuracy of the point cloud and avoiding the problem of missing depth information due to tire reflectivity problems. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:
[0018] Figure 1 It is a flow chart of an embodiment of a method for constructing a point cloud of a tire provided by the present application;
[0019] Figure 2 is a schematic diagram of the structure of the tire provided by the present application;
[0020] Figure 3 yes Figure 1 Schematic diagram of the process of step 12;
[0021] Figure 4 yes Figure 1 Schematic diagram of the process of step 13;
[0022] Figure 5 It is a flow chart of an embodiment of a vehicle tire assembly method provided by the present application;
[0023] Figure 6 It is a structural schematic diagram of an embodiment of a vehicle assembly control device provided by the present application;
[0024] Figure 7 It is a structural schematic diagram of an embodiment of a computer-readable storage medium provided by the present application. DETAILED DESCRIPTION
[0025] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It will be appreciated that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only some but not all structures related to the present application are shown in the drawings. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the art without making creative work are within the scope of protection of the present application.
[0026] The terms "first", "second", etc. in this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.
[0027] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0028] See also Figure 1 , Figure 1 1 is a flow chart of an embodiment of a method for constructing a point cloud of a tire provided by the present application, the method comprising:
[0029] Step 11: Acquire a depth image of the target tire; wherein the depth image at least includes depth information of the reflective mark on the target tire.
[0030] It is understandable that depth images are generally acquired by taking photos with a depth camera, and then the point cloud is constructed based on the depth information of each pixel in the depth image. Since tires are generally black and have low reflectivity, coupled with the influence of external environmental factors such as light, the depth information of some pixels is missing when the depth image is acquired, affecting the subsequent point cloud construction.
[0031] Therefore, in this embodiment, reflective marks are provided on the tire to increase the reflectivity of the tire, which is beneficial to obtaining tire depth information.
[0032] like Figure 2 As shown, Figure 2It is a structural schematic diagram of the tire provided in the present application. The tire 200 generally includes a support portion (generally called a wheel hub) 210 and a tire body 220. The support portion 210 is generally made of steel material, most of which are silver-white (with a higher reflectivity), and the tire body 220 is generally made of rubber, most of which are black (with a lower reflectivity).
[0033] In one embodiment, the reflective mark can be set on the outer contour of the tire body 220 (such as reflective mark A), the reflective mark can be set on the outer contour of the support portion 210 (such as reflective mark B), or the reflective mark can be set inside the support portion 210 near the center of the shaft (such as reflective mark C). It is worth noting that the position setting of the reflective mark needs to be as close as possible to the key position of the geometric shape of the contour area and / or the shaft area of the tire 200, so that the key feature points of the contour can be extracted when the depth information is extracted.
[0034] Understandably, if Figure 2 The reflective mark shown is block-shaped, and its shape can be set according to actual needs, for example, it can be rectangular, circular, etc. In other embodiments, the reflective mark can be annular around the tire, for example, it can be around the outer contour of the tire body 220, or around the axial area of the support portion 210. Of course, the number of reflective marks is not limited, for example, multiple block-shaped reflective marks can be evenly distributed around the outer contour of the tire body 220.
[0035] The reflective mark can be set on the tire 200 by various methods such as pasting, coating, printing, etc.
[0036] Taking pasting as an example, the reflective logo can be a reflective strip. The reflective strip can be divided into reflective webbing, reflective lattice strips, reflective cloth reflective strips, reflective film, etc. according to different materials. The reflective film is a retro-reflective material that has been made into a film and can be directly applied. It is widely used in transportation. Therefore, in this embodiment, the reflective film can also be pasted on the tire.
[0037] Taking coating as an example, coating materials can be divided into reflective materials and fluorescent materials.
[0038] Reflective materials are mainly materials filled with reflective substances. Reflective materials can quickly reflect the light shining on their surface. Different materials have different wavelength ranges of reflected light. The color of the reflected light depends on what wavelength of light the material absorbs and what wavelength of light it reflects. Therefore, there must be light shining on the surface of the material for the surface of the material to reflect light. Take reflective paint as an example. Reflective paint is a coating made of acrylic resin as the base material, and then mixed with a certain proportion of directional reflective materials in a solvent. It is a new type of reflective paint. The reflective principle of reflective paint is to reflect the light from spotlights, car lights, etc. back to people's sight through microbeads at night or in poor light conditions, forming a reflective effect. The reflective effect is more obvious at night. It has a high reflectivity, can prevent ultraviolet light waves, can resist extremely strong salt spray, prevent color fading and peeling, and has acid and alkali resistance.
[0039] Fluorescent materials absorb light of a certain wavelength and immediately emit light of a different wavelength, which is called fluorescence. When the incident light disappears, the fluorescent material will immediately stop emitting light. More specifically, fluorescence refers to some very bright colors of light that the human eye sees under external light, such as green, orange, and yellow. People often call them neon lights. Specifically, fluorescent powder can be added to the paint and then applied to the tire to form a reflective logo.
[0040] In addition, during the manufacturing process of the tire, reflective markings can be set on the tire by printing, which will not be described in detail here.
[0041] Step 12: Use the depth image to construct the first point cloud of the tire.
[0042] In reverse engineering, the point data set of the product appearance surface obtained by measuring instruments is also called point cloud. Point clouds are divided into sparse point clouds and dense point clouds. Usually, the number of points obtained by using a 3D coordinate measuring machine is relatively small, and the distance between points is relatively large, which is called a sparse point cloud; while the point cloud obtained by using a 3D laser scanner or a photographic scanner has a relatively large number of points and is relatively dense, which is called a dense point cloud.
[0043] In the embodiment of the present application, since the reflectivity of the tire itself is low and a reflective mark is set on the tire, the first point cloud constructed by the depth image in this step at least includes the point cloud of the position of the reflective mark, while the depth information of some areas of the tire with low reflectivity is missing and can be regarded as a sparse point cloud.
[0044] It can be understood that since the setting of the reflective marking in the above step 11 mainly takes into account the key positions of the geometric shape of the tire contour area and / or the axis area, the points in the first point cloud mainly correspond to the key positions of the geometric shape of the tire contour area and / or the axis area.
[0045] Optionally, in one embodiment, see Figure 3 , Figure 3 yes Figure 1 The flowchart of step 12 in FIG. 1 is as follows:
[0046] Step 121: Obtain first depth information of a depth image; wherein the depth image is captured by a depth camera, and the first depth information is determined based on a camera coordinate system of the depth camera.
[0047] Specifically, the first depth information is mainly contour information. The edge feature points of the depth image may be extracted first, and then an affine transformation is performed on the extracted edge feature points to obtain the first depth information of the depth image.
[0048] When performing contour extraction, depth difference detection or gradient difference detection can be used:
[0049] Depth difference detection mainly obtains the difference in depth values between adjacent pixels. If the difference is large, it is considered that the two pixels are discontinuous in three-dimensional space.
[0050] Gradient difference detection mainly obtains the difference in depth gradient values between adjacent pixels. If the difference is large, it is considered that the two points may be located on the contour line of the depth image (ie, not in the same plane).
[0051] After contour extraction, the edge feature points need to be affine transformed. Affine transformation refers to a linear transformation of a vector space followed by a translation in geometry to transform it into another vector space.
[0052] Step 122: performing coordinate transformation on the first depth information to obtain second depth information; wherein the second depth information is determined based on a spatial coordinate system.
[0053] First, the parameters of the depth camera and the position information of the depth camera based on the spatial coordinate system are obtained; and the first coordinate conversion parameters are determined according to the parameters and the position information.
[0054] Among them, the parameters of the depth camera are mainly the camera intrinsic parameters. A camera intrinsic parameter matrix is given below:
[0055]
[0056] Among them, fx and fy are focal lengths, which are generally equal to each other, x0 and y0 are the coordinates of the principal point (relative to the imaging plane), and s is the coordinate axis tilt parameter, which is 0 in an ideal case.
[0057] Among them, the position of the depth camera in the spatial coordinate system, that is, the external parameters of the camera, that is, the position of the camera in space and the rotation parameters relative to each axis.
[0058] Then, using the above external parameters and internal parameters, the first coordinate transformation parameters, that is, the transformation matrix from the camera coordinate system to the space coordinate system, can be obtained. The first coordinate transformation parameters are then used to transform the first depth information to obtain the second depth information.
[0059] For example:
[0060]
[0061] Where [Xc, Yc, Zc] T Represents the camera coordinates, [Xw, Yw, Zw] T It represents the world coordinates of the object, R is the rotation matrix (3 degrees of freedom), T is the translation matrix, and the two form a 3×4 matrix, which is the external parameter matrix of the camera.
[0062] Step 123: construct a first point cloud of the tire using the second depth information.
[0063] The second depth information includes the spatial coordinates of each feature point, that is, a first point cloud including multiple feature points can be constructed.
[0064] Step 13: Use the preset tire point cloud to complete the first point cloud to construct a second point cloud of the target tire.
[0065] Optionally, see Figure 4 , Figure 4 yes Figure 1 The flowchart of step 13 in FIG. 1 is a flowchart of step 13, wherein step 13 may specifically include:
[0066] Step 131: aligning the first point cloud and the preset tire point cloud.
[0067] The main process of registration includes: determining matching points in the first point cloud and the preset tire point cloud; using the matching points, determining the second coordinate transformation parameters of the first point cloud and the preset tire point cloud; and registering the first point cloud and the preset tire point cloud using the second coordinate transformation parameters.
[0068] Specifically, the point cloud registration process is to find a rotation and translation matrix between two point clouds, and transform the source point cloud (the preset tire point cloud) to the same coordinate system as the target point cloud (the first point cloud).
[0069] It can be expressed as the following equation:
[0070] Pt=R×Ps+T;
[0071] Among them, Pt and Ps are a pair of corresponding points in the target power source and source point cloud, and it is necessary to calculate R (rotation matrix) and T (translation matrix).
[0072] In one embodiment, an ICP (Iterative closest point) algorithm may be used:
[0073] (1) Minimize an objective function:
[0074]
[0075] in, It is a pair of corresponding points, with a total of N p For corresponding points. This objective function is actually the sum of the squares of the Euclidean distances between all corresponding points.
[0076] (2) Find corresponding points. In the case of initial values, assume that the source point cloud is transformed using the initial rotation and translation matrix to obtain a transformed point cloud. Then compare this transformed point cloud with the target point cloud. As long as the distance between the two point clouds is less than a certain threshold (this is a parameter in ICP), the two points are considered to be corresponding points. This is also the "nearest neighbor point".
[0077] (3) R and T optimization. With corresponding points, we can use them to estimate the rotation R and translation T. Here, R and T have only 6 degrees of freedom, but the number of corresponding points is huge (there are redundant observations). Therefore, we can use least squares and other methods to solve the optimal rotation and translation matrix.
[0078] (4) Iteration. We optimized and obtained a new R and T, which resulted in changes in the positions of some points after transformation, and some nearest point pairs also changed accordingly. Therefore, we returned to the method of finding the nearest points in step (2). Steps (2) and (3) are iterated continuously until some iteration termination conditions are met, such as the change in R and T is less than a certain value, or the change in the above objective function is less than a certain value, or the nearest point pairs no longer change.
[0079] Through the above method, the first point cloud and the preset point cloud can be aligned.
[0080] Step 132: Use the point information in the preset tire point cloud to complete the missing point information in the first point cloud to construct a second point cloud of the tire.
[0081] Through the above relationship:
[0082] Pt=R×Ps+T;
[0083] Each point in the preset point cloud can be added to the first point cloud to complete the missing points in the first point cloud to form a second point cloud. The second point cloud is a dense point cloud, which is also the final point cloud required.
[0084] Different from the prior art, the tire point cloud construction method provided in this embodiment includes: obtaining a depth image of the target tire; wherein the depth image at least includes the depth information of the reflective mark on the target tire; using the depth image to construct a first point cloud of the tire; using the preset tire point cloud to complete the first point cloud to construct a second point cloud of the target tire. In the above manner, since the reflective mark is set on the tire, when the depth image is obtained, at least the depth information of the corresponding reflective mark position can be obtained, and then further through point cloud completion, a complete point cloud can be obtained, thereby improving the acquisition accuracy of the point cloud and avoiding the problem of missing depth information due to tire reflectivity problems.
[0085] See also Figure 5 , Figure 5 1 is a flow chart of an embodiment of a tire assembly method for a vehicle provided by the present application, the method comprising:
[0086] Step 51: Acquire a depth image of the scene of assembling the tire to the vehicle.
[0087] In one embodiment, vehicle assembly mainly refers to the process in which the vehicle moves on a predetermined track, in which the tire is clamped by a robot and assembled into the trunk of the vehicle (as a spare tire of the vehicle).
[0088] A movable carrier (large board) is arranged in the predetermined track, and the vehicle moves on the carrier as the carrier moves. A depth camera is arranged above the large board, and the photographing range of the depth camera at least covers the vehicle, the manipulator and the tire.
[0089] Step 52: Use the depth image to construct a vehicle point cloud of the vehicle and a tire point cloud of the tire.
[0090] The vehicle point cloud and the tire point cloud can be converted into two different point clouds by performing contour extraction on the depth image. The tire point cloud is constructed by the method provided in the above embodiment.
[0091] Step 53: Perform corresponding processing according to the spatial positions of the completed vehicle point cloud and tire point cloud models.
[0092] In one embodiment, since the vehicle (moving with the carrier) and the tire (moving with the manipulator) are both in motion, it is necessary to obtain the vehicle point cloud and the tire point cloud in real time and perform tracking and judgment during the entire assembly process.
[0093] Optionally, the spatial distance between the vehicle point cloud and the tire point cloud can be obtained in real time, and the two point clouds can be collided. For example, when the spatial distance between the two point clouds is less than a set distance threshold, a response process is performed. The processing method may include: pausing the movement of the vehicle and the tire, or keeping the movement of the vehicle unchanged, adjusting the running track of the tire to prevent the tire from colliding with the vehicle, or issuing an alarm.
[0094] Different from the prior art, the tire assembly method of a vehicle provided in this embodiment includes:
[0095] Acquire a depth image of the scene where the tire is assembled to the vehicle; use the depth image to construct a vehicle point cloud of the vehicle and a tire point cloud of the tire; perform corresponding processing according to the spatial position of the completed vehicle point cloud and tire point cloud models. In the above manner, since a reflective mark is set on the tire, when acquiring the depth image, at least the depth information of the corresponding reflective mark position can be obtained, and then further through point cloud completion, a complete point cloud can be obtained, avoiding the problem of missing depth information due to tire reflectivity problems. Further, when assembling the vehicle tire, a relatively accurate point cloud can be obtained, which improves the efficiency and accuracy of vehicle tire assembly, reduces the failure rate, and effectively reduces the probability of collision between the vehicle and the tire.
[0096] See also Figure 6 , Figure 6 is a schematic structural diagram of an embodiment of a vehicle assembly control device provided in the present application. The vehicle assembly control device 60 includes a depth camera 61 , a memory 62 and a controller 63 .
[0097] The depth camera 61 is installed on the vehicle motion track and is mainly used to collect the depth image of the robot assembling the tire to the vehicle scene; the memory 62 is used to store program data; the controller 63, the depth camera 61 and the memory 62, are used to execute the program data to implement the following method:
[0098] Acquire a depth image of the target tire; wherein the depth image includes at least the depth information of the reflective mark on the target tire; construct a first point cloud of the tire using the depth image; and complete the first point cloud using a preset tire point cloud to construct a second point cloud of the target tire.
[0099] A depth image of a scene in which a tire is assembled to a vehicle is obtained; a vehicle point cloud of the vehicle and a tire point cloud of the tire are constructed using the depth image; and corresponding processing is performed according to the spatial positions of the completed vehicle point cloud and tire point cloud models.
[0100] See also Figure 7 , Figure 71 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present application. The computer-readable storage medium 70 stores program data 71. When the program data 71 is executed by the controller, it is used to implement the following method:
[0101] Acquire a depth image of the target tire; wherein the depth image includes at least the depth information of the reflective mark on the target tire; construct a first point cloud of the tire using the depth image; and complete the first point cloud using a preset tire point cloud to construct a second point cloud of the target tire.
[0102] A depth image of a scene in which a tire is assembled to a vehicle is obtained; a vehicle point cloud of the vehicle and a tire point cloud of the tire are constructed using the depth image; and corresponding processing is performed according to the spatial positions of the completed vehicle point cloud and tire point cloud models.
[0103] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only illustrative, for example, the division of the modules or units is only a logical function division, and 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.
[0104] 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 present embodiment.
[0105] 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.
[0106] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made according to the description and drawings of the present application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A method for constructing a point cloud of a tire, characterized in that: The method comprises: Acquire a depth image of a target tire; wherein the depth image includes at least depth information of a reflective mark on the target tire; Constructing a first point cloud of the tire using the depth image, comprising: acquiring first depth information of the depth image; wherein the depth image is obtained by taking a depth camera, and the first depth information is determined based on a camera coordinate system of the depth camera; performing coordinate conversion on the first depth information to obtain second depth information; wherein the second depth information is determined based on a spatial coordinate system; and constructing a first point cloud of the tire using the second depth information; Using a preset tire point cloud to complete the first point cloud to construct a second point cloud of the target tire; Among them, the obtaining of the first depth information of the depth image includes: extracting edge feature points of the depth image; performing affine transformation on the extracted edge feature points to obtain the first depth information of the depth image; the reflectivity of the reflective mark is greater than a set reflection threshold, and the reflective mark is arranged at a key position of the geometric shape of the contour area and / or the axis area of the tire.
2. The method according to claim 1, characterized in that: The performing coordinate transformation on the first depth information to obtain second depth information includes: Acquire parameters of the depth camera and position information of the depth camera based on the spatial coordinate system; Determine a first coordinate transformation parameter according to the parameter and the position information; The first depth information is coordinate-converted by using the first coordinate conversion parameter to obtain second depth information.
3. The method according to claim 1, characterized in that The method of completing the first point cloud by using the preset tire point cloud to construct a second point cloud of the target tire includes: Registering the first point cloud and the preset tire point cloud; The point information in the preset tire point cloud is used to complete the missing point information in the first point cloud to construct a second point cloud of the tire.
4. The method according to claim 3, characterized in that The registering the first point cloud and the preset tire point cloud comprises: Determining matching points in the first point cloud and the preset tire point cloud; Determine second coordinate transformation parameters of the first point cloud and the preset tire point cloud using the matching points; The first point cloud and the preset tire point cloud are registered using the second coordinate transformation parameters.
5. A method for assembling a tire of a vehicle, characterized in that: The method comprises: Acquire a depth image of a scene where a tire is mounted on a vehicle; Constructing a vehicle point cloud of the vehicle and a tire point cloud of the tire using the depth image; wherein the tire point cloud is constructed using the method according to any one of claims 1 to 4; Corresponding processing is performed according to the spatial positions of the completed vehicle point cloud and tire point cloud models.
6. The method according to claim 5, characterized in that The performing corresponding processing according to the spatial positions of the completed vehicle point cloud and tire point cloud model includes: According to the spatial positions of the vehicle point cloud and the tire point cloud, the running track of the tire is adjusted to assemble the tire to the vehicle.
7. A vehicle assembly control device, characterized in that: The control device comprises: A depth camera for acquiring a depth image of a scene where the tire is assembled to a vehicle; A memory for storing program data; A controller, connected to the depth camera and the memory, configured to execute the program data to implement the method according to any one of claims 1 to 6.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program data, and when the program data is executed by the controller, it is used to implement the method according to any one of claims 1 to 6.
