CN115661045A - Quality 3D visual holographic detection method, device, equipment and medium of automobile tires - Google Patents

Abstract

The invention relates to the field of three-dimensional images, and discloses a 3D visual holographic detection method, a device, equipment and a medium for the quality of an automobile tire, wherein the method comprises the following steps: acquiring three-dimensional contour data of an automobile tire, performing three-dimensional shape reconstruction on the automobile tire to obtain a three-dimensional reconstruction image, and dividing a depth detection area and a width detection area of the three-dimensional reconstruction image; sampling a depth vision point set in a depth detection area, calculating the average gravity center of the point set of the depth vision point set, performing plane fitting on the average gravity center of the point set to obtain a fitted vision plane of the depth vision point set, and calculating the tire detection depth of an automobile tire; detecting edge vision points of the width detection area, performing edge line fitting on the edge vision points to obtain a fitted vision line, and calculating the tire detection width of the automobile tire; and determining a three-dimensional visual quality detection result of the automobile tire according to the tire detection depth and the tire detection width. The invention can improve the defect detection comprehensiveness of the automobile tire.

Description

Quality 3D visual holographic detection method, device, equipment and medium of automobile tires

technical field

The invention relates to the field of three-dimensional images, in particular to a quality 3D visual holographic detection method, device, equipment and medium of automobile tires.

Background technique

The 3D visual holographic inspection of the quality of automobile tires refers to the inspection of three-dimensional vision of automobile tires to detect whether there are quality problems in automobile tires.

At present, for a long time, the tires are only considered to be inspected when the car is punctured and air leaked, but only the leaked places are tested, and the entire tire is not fully inspected in terms of tread depth, width, and wear. Scientific and quantifiable detection; the inspection process of automobile tires is as follows: after the vehicle is driven to the detection area, the overall appearance of the tire is first manually inspected by the naked eye, and then some parts of the tire are randomly selected by calipers or tread depth detectors. Inspection, from which it can be concluded whether the tire needs to be replaced and maintained. On the one hand, the defect of this inspection method is that there are measurement errors and inaccurate measurement in manual inspection; There are two common detection methods: one is to manually use calipers to randomly check the tread width and depth at any position of the tire, and use these values as a reference It is an indicator to judge whether the tire is excessively worn and whether it needs to be replaced. However, in the actual use of the tire, when a certain part encounters a sharp foreign object, the wear at that part is often more likely to be worn than other parts of the tire. Manual sampling often leads to Missed inspections cause traffic safety risks during the operation of the car; in addition to manual inspection through calipers, the other is hand-held tire inspection equipment, which is also a current tire inspection technology. The ranging sensor measures the tread depth in real time. Although the efficiency and detection accuracy of this solution are improved compared with the manual method, it still cannot detect the quality of the entire tire surface well. If a full tire inspection is required, it will cost A large number of laborers inspect the tires one by one. Through the above analysis, the shortcomings of the current automobile tire inspection technology lie in the low efficiency of manual inspection, the unreliable inspection process, and the limited inspection area of the tires, which makes it possible to miss inspection with a high probability. These problems lead to the quality of automobile tires. Detection is flawed. Therefore, the comprehensiveness of automobile tire quality inspection is insufficient.

Contents of the invention

In order to solve the above problems, the present invention provides a quality 3D visual holographic detection method, device, equipment and medium of automobile tires, which can improve the comprehensiveness of defect detection of automobile tires.

In a first aspect, the present invention provides a quality 3D visual holographic detection method for automobile tires, comprising:

Collecting three-dimensional contour data of automobile tires, performing three-dimensional shape reconstruction on the automobile tires according to the three-dimensional contour data, obtaining a three-dimensional reconstruction image, and dividing a depth detection area and a width detection area of the three-dimensional reconstruction image;

Sampling the depth vision point set in the depth detection area, calculating the average center of gravity of the point set of the depth vision point set, and performing plane fitting on the average center of gravity of the point set, to obtain the fitting visual plane of the depth vision point set , calculating the tire detection depth of the automobile tire according to the average center of gravity of the point set and the fitting visual plane;

Detecting the edge visual points of the width detection area, performing edge line fitting on the edge visual points to obtain a fitted visual line, and calculating the tire size of the automobile tire according to the edge visual points and the fitted visual line detection width;

According to the tire detection depth and the tire detection width, the three-dimensional visual quality detection result of the automobile tire is determined.

In a possible implementation manner of the first aspect, the collecting three-dimensional profile data of automobile tires includes:

Using a three-dimensional vision sensor and a motor encoder to configure the rotation detection platform of the automobile tire;

In the rotation detection platform, the following formula is used to calculate the rotation encoding signal of the motor encoder:

Wherein, E represents the rotary encoding signal, C represents the tire circumference of the automobile tire, and n represents the contour spacing;

Constructing the emitted laser signal of the automobile tire and its corresponding reflected laser signal by using the three-dimensional vision sensor according to the rotary encoding signal;

According to the emitted laser signal and its corresponding reflected laser signal, the three-dimensional profile data of the automobile tire is determined.

It can be seen that in the embodiment of the present invention, the 3D point cloud data of the entire 3D tire surface and side can be obtained by using the 3D vision sensor and the motor encoder to configure the rotation detection platform of the car tire to collect the 3D profile data of the car tire.

In a possible implementation manner of the first aspect, the three-dimensional shape reconstruction of the automobile tire according to the three-dimensional contour data to obtain a three-dimensional reconstruction image includes:

determining a two-dimensional depth image corresponding to the three-dimensional contour data;

The depth translation coordinates of the two-dimensional depth image are calculated using the following formula:

P(x',0,z')=P(x,y,z+r)

Wherein, P(x', 0, z') represents the depth translation coordinates of the two-dimensional depth image, r represents the tire radius of the automobile tire, and x, y, z represent the collected values in the two-dimensional depth image Coordinates of car tire point cloud data points;

According to the depth translation coordinates, the following formula is used to perform three-dimensional reconstruction on the two-dimensional depth image to obtain a three-dimensional reconstructed image:

θ＝360°÷N

x'=x

y'=cosα*y-sinα*z

z'=cosα*y+sinα*z

P(x", y", z")=P(x', 0, z')→P(x, cosα*y-sinα*z, cosα*y+sinα*z)

Wherein, P (x ", y ", z ") represents the point cloud data in the described three-dimensional reconstructed image, x ", y ", z " represents the coordinate of described point cloud data in the described three-dimensional reconstructed image, i Represents the serial number of the contour line in the two-dimensional depth image, the range is [0, N], x, y, z represent the coordinates of the car tire point cloud data points collected in the two-dimensional depth image, P(x' , 0, z') represent the depth translation coordinates of the two-dimensional depth image.

It can be seen that in the embodiment of the present invention, the 2D depth image of the surface of the automobile tire can be converted into a three-dimensional 3D model image of the automobile tire by performing 3D shape reconstruction on the 2D depth image.

In a possible implementation manner of the first aspect, the dividing the depth detection area and the width detection area of the 3D reconstructed image includes:

Querying the tread profile of the automobile tire in the three-dimensional reconstructed image;

The contour line area corresponding to the tread contour line is used as a depth detection area and a width detection area of the three-dimensional reconstructed image.

It can be seen that in the embodiment of the present invention, the contour area corresponding to the tread contour line is used as the depth detection area and width detection area of the three-dimensional reconstruction image to detect the concave depth and tread width of the tread pattern.

In a possible implementation manner of the first aspect, the calculating the point set average center of gravity of the depth vision point set includes:

Utilize the following formula to calculate the point set average center of gravity of the depth vision point set:

Wherein, P _i represents the point set average center of gravity of the depth vision point set, i represents the sequence number in the depth vision point set, j represents the sequence number of the depth vision point in the depth vision point set, x _j , y _j , z _j represents the three-dimensional coordinates of the depth vision point whose sequence number is j in the depth vision point set, and m represents the total number of depth vision points in the depth vision point set.

It can be seen that in the embodiment of the present invention, the average value of the visual points in the depth visual point set is calculated to select the central point of the visual point in the deep visual point set.

In a possible implementation manner of the first aspect, performing plane fitting on the average center of gravity of the point set to obtain a fitted visual plane of the depth vision point set includes:

Utilize the following formula to determine the plane fitting surface parameters of the mean center of gravity of the point set:

Wherein, a, b, c represent the plane fitting surface parameters of the average center of gravity of the point set, x _i , y _i , z _i represent the coordinates of the average center of gravity of the point set, and n represents the number of point sets of the depth vision point set;

According to the plane fitting surface parameters, the following formula is used to construct the fitting vision plane of the depth vision point set:

z=ax+by+c

Wherein, z=ax+by+c represents the fitting visual plane of described depth vision point set, and z, x, y represent the variable of plane function, and a represents fitting in the plane fitting surface parameter of described point set mean center of gravity The parameter of the variable x of the visual plane function, b represents the parameter of the variable y of the fitting visual plane function in the plane fitting surface parameters of the average center of gravity of the point set, and c represents the plane fitting surface parameter of the average center of gravity of the point set Constant for fitting the visual plane function.

It can be seen that, in the embodiment of the present invention, the fitting visual plane of the depth visual point set is constructed to construct the plane function relationship among the visual points in the depth visual point set.

In a possible implementation manner of the first aspect, the calculating the tire detection depth of the automobile tire according to the average center of gravity of the point set and the fitted visual plane includes:

Utilize following formula to calculate the tire detection depth of described automobile tire:

Wherein, _di represents the tire detection depth of the automobile tire, a represents the parameter of the variable x of the fitting visual plane function in the plane fitting surface parameters of the average center of gravity of the point set, and b represents the plane of the average center of gravity of the point set The parameter of the variable y of the fitting visual plane function in the fitting surface parameter, c represents the constant of the fitting visual plane function in the plane fitting surface parameter of the mean center of gravity of the point set, and d represents the variable z of the fitting visual plane function The parameters, x _i , y _i , _zi represent the coordinates of the mean center of gravity of the point set.

It can be seen that the embodiment of the present invention calculates the tire inspection depth of the automobile tire to detect whether the inspection depth deviates from the standard depth, so as to detect whether there is a defect in the automobile tire.

In a possible implementation manner of the first aspect, the detecting the edge vision point of the width detection area includes:

The binarization operation is performed on the width detection area by using the following formula to obtain the binarization area:

Wherein, p _i (xi _, y _i ) represents the coordinate value of the point cloud data in the binarized region, xi _, y _i , z _i represent the coordinates of the average center of gravity of the point set, and k represents the preset Image pixel parameters;

The edge point gradient of the binarized region is calculated using the following formula:

表示所述二值化区域中像素的一阶导数差分；Among them, |G(x, y)| represents the edge point gradient of the binarized region, sprt represents the square root calculation, f(x+1, y), f(x, y), f(x, y+1 ) represents the pixel function of the binarized region,

Representing the first-order derivative difference of pixels in the binarized region;

Determine the edge visual point of the width detection area according to the gradient of the edge point.

It can be seen that in the embodiment of the present invention, by calculating the edge point gradient of the binarized region, it is used to find a point with a larger pixel gradient transformation in the binarized region as the width of the defect detection edge line point.

In a possible implementation manner of the first aspect, the performing edge line fitting on the edge visual point to obtain the fitted visual line includes:

Utilize following formula to calculate the fitting line parameter of described edge vision point:

Wherein, A, B represent the fitting line parameter of described edge vision point, x _j , y _j represent the jth edge vision point, M represents the quantity of described edge vision point;

Use following formula to carry out edge line fitting to described edge visual point, obtain fitting visual line:

Y=AX+B

Wherein, Y=AX+B represents the fitting visual line, A, B represent the fitting line parameters of the peripheral vision point, Y, X represent the independent variable of the straight line function.

It can be seen that, in the embodiment of the present invention, edge line fitting is performed on the edge visual point, so as to identify the edge part of the width-related area in the width detection area by the edge line.

In a second aspect, the present invention provides a quality 3D visual holographic detection device for automobile tires, said device comprising:

The detection area division module is used to collect the three-dimensional contour data of the automobile tire, perform three-dimensional shape reconstruction on the automobile tire according to the three-dimensional contour data, obtain a three-dimensional reconstruction image, and divide the depth detection area and width of the three-dimensional reconstruction image Detection area;

The detection depth calculation module is used to sample the depth vision point set in the depth detection area, calculate the point set average center of gravity of the depth vision point set, and perform plane fitting on the point set average center of gravity to obtain the depth vision point set A fitting visual plane of the point set, calculating the tire detection depth of the automobile tire according to the average center of gravity of the point set and the fitting visual plane;

The detection width calculation module is used to detect the edge visual point of the width detection area, and perform edge line fitting on the edge visual point to obtain a fitted visual line. According to the edge visual point and the fitted visual line, Calculate the tire detection width of the automobile tire;

The detection result determining module is used to determine the three-dimensional visual quality detection result of the automobile tire according to the tire detection depth and the tire detection width.

In a third aspect, the present invention provides an electronic device, comprising:

at least one processor; and a memory communicatively coupled to the at least one processor;

Wherein, the memory stores a computer program that can be executed by the at least one processor, so that the at least one processor can perform the quality 3D visual holographic inspection of automobile tires as described in any one of the first aspects above. method.

In a fourth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the 3D visual holographic detection of the quality of automobile tires as described in any one of the above-mentioned first aspects is realized. method.

Compared with the existing technology, the technical principle and beneficial effect of this scheme are:

In the embodiment of the present invention, firstly, the three-dimensional profile data of the automobile tire is collected for 3D visual holographic detection of the tire defect of the automobile tire. The three-dimensional shape reconstruction of the tire is used to construct the three-dimensional virtual model of the automobile tire, and the three-dimensional virtual model including the shape characteristics of the automobile tire realizes the comprehensive detection of the automobile tire. Further, the embodiment of the present invention adopts dividing the depth detection area and the width detection area of the three-dimensional reconstruction image, so as to detect the depth and width of the tire tread in the corresponding area;

Furthermore, in the embodiment of the present invention, the depth vision point set in the depth detection area is sampled to integrate the point cloud data in the depth detection area to achieve comprehensive detection of the depth detection area. Further, this The embodiment of the invention calculates the average center of gravity of the point set of the depth vision point set to determine the center of the point in the depth vision point set. combined to obtain the functional relationship of conforming data, determine the connection between point cloud data, improve the feature representation ability of the point cloud data, and ensure a unified standard detection process for automobile tire defect detection. Further, this The embodiment of the invention calculates the tire inspection depth of the automobile tire according to the average center of gravity of the point set and the fitting visual plane, so as to determine whether there is a defect in the surface tread depression of the automobile tire;

Furthermore, the embodiment of the present invention detects the edge vision points in the width detection area to identify points with obvious brightness changes in the digital image. Further, the embodiment of the present invention performs edge line simulation on the edge vision points. to determine the functional relationship between each point in the peripheral vision points and other points by using a straight line function. Further, the embodiment of the present invention calculates the The tire detection width of automobile tires is used to detect tire defects by inquiring whether there is a deviation in the width;

Further, in the embodiment of the present invention, the three-dimensional visual quality inspection result of the automobile tire is determined according to the tire inspection depth and the tire inspection width, so as to use the detected depth and width data to determine the automobile tire whether there are defects on the surface.

Therefore, the 3D visual holographic inspection method, device, electronic equipment, and storage medium for the quality of automobile tires proposed by the embodiments of the present invention can improve the comprehensiveness of defect detection of automobile tires.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description serve to explain the principles of the invention.

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, In other words, other drawings can also be obtained from these drawings without paying creative labor.

Fig. 1 is a schematic flow diagram of a 3D visual holographic detection method for the quality of automobile tires provided by an embodiment of the present invention;

Fig. 2-Fig. 5 are schematic diagrams of acquisition of three-dimensional profile data provided in an embodiment of the present invention;

6-7 are schematic diagrams of three-dimensional shape reconstruction of automobile tires in an embodiment of the present invention;

Fig. 8 is a block diagram of a 3D visual holographic detection device for the quality of automobile tires provided by an embodiment of the present invention;

FIG. 9 is a schematic diagram of the internal structure of an electronic device implementing a 3D visual holographic inspection method for the quality of automobile tires provided by an embodiment of the present invention.

Detailed ways

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

An embodiment of the present invention provides a 3D visual holographic detection method for the quality of automobile tires. The execution subject of the 3D visual holographic detection method for automobile tires includes but is not limited to a server, a terminal, etc., which can be configured to execute the method provided by the embodiment of the present invention. At least one of the electronic devices of the method. In other words, the 3D visual holographic inspection method for the quality of automobile tires can be implemented by software or hardware installed on terminal equipment or server equipment, and the software can be a blockchain platform. The server includes but is not limited to: single server, server cluster, cloud server or cloud server cluster, etc. The server can be an independent server, or it can provide cloud services, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content delivery network (Content Delivery Network, CDN), and cloud servers for basic cloud computing services such as big data and artificial intelligence platforms.

Referring to FIG. 1 , it is a schematic flowchart of a 3D visual holographic inspection method for the quality of automobile tires provided by an embodiment of the present invention. Wherein, the quality 3D vision holographic detection method of automobile tire described in Fig. 1 comprises:

S1. Collect the 3D contour data of the automobile tire, reconstruct the 3D shape of the automobile tire according to the 3D contour data, obtain a 3D reconstruction image, and divide the depth detection area and the width detection area of the 3D reconstruction image.

In the embodiment of the present invention, the three-dimensional profile data of the automobile tires are collected for 3D visual holographic detection of the tire defects of the automobile tires. Among them, the three-dimensional contour data refers to the 3D point cloud contour data of the automobile tire surface collected by the 3D visual sensor. The 3D visual sensor mainly uses the principle of laser triangulation to measure the three-dimensional data. After the receiving end of the visual sensor receives the laser beam reflected from the tire surface, it can obtain the single contour data of the current tire surface.

In one embodiment of the present invention, collecting three-dimensional profile data of automobile tires includes: using a three-dimensional vision sensor and a motor encoder to configure a rotation detection platform for automobile tires; on the rotation detection platform, using the following formula to calculate the rotation of the motor encoder Coded signal:

Among them, E represents the rotary encoding signal, C represents the tire circumference of the automobile tire, and n represents the contour spacing;

According to the rotary encoding signal, the emitted laser signal and the corresponding reflected laser signal of the automobile tire are constructed by using the three-dimensional vision sensor; the three-dimensional contour data of the automobile tire is determined according to the emitted laser signal and the corresponding reflected laser signal.

For example, three 3D vision sensors are equipped to scan and detect the whole car tire from three angles. When the tire is in a rolling state, the positions of the three 3D vision sensors are directly above the tire and on the left and right sides respectively, and the tire rotates After one lap, the three 3D vision sensors can collect the profile data of the entire tire crown surface and the profile data of the two tires. During detection, the rotation of the tire is driven by the external servo motor to rotate passively. After the tire is removed, wear The connecting rod is installed to the tire detection device, and the other end of the connecting rod is connected to the servo motor. The rotation of the servo motor drives the tire to rotate. When the servo motor drives the tire to rotate a circle, the encoder in the servo motor also generates a corresponding circle of 3D tire contour lines. The time sequence of the signal, the present invention uses the A-phase signal in the encoder signal as the trigger signal, when the servo motor rotates so that the A-phase pulse is a rising edge, the 3D vision sensor will trigger to obtain the contour line of the current position.

In order to further understand the acquisition process of three-dimensional contour data, please refer to Figures 2-5, which are schematic diagrams of acquisition of three-dimensional contour data provided by an embodiment of the present invention, wherein Figure 2 is used to represent the principle of emitting laser signals from a three-dimensional vision sensor , wherein the height of the emitted laser signal emitted by the three-dimensional vision sensor to the surface of the automobile tire is represented by the z-axis, the emitted laser signal along the rolling direction of the tire is represented by the y-axis, and the emitted laser signal in the lateral direction of the tire is represented by the x-axis, and the corresponding The reflected laser signal is reflected from the tire surface to the three-dimensional vision sensor. After the tire rotates one circle, the 3D point cloud data of the entire surface contour of the tire can be obtained; Figure 3 is used to indicate the placement position of the three-dimensional vision sensor built in the rotation detection platform , the three-dimensional vision sensors are respectively placed on the top of the car tire and on both sides of the tire. Figure 4 is used to represent the rotation detection platform including the motor encoder. The servo motor on the left represents the motor encoder. During detection, the rotation of the tire is determined by The external servo motor drives the tire to rotate passively. After the tire is removed, it is installed on the tire detection device through the connecting rod. The other end of the connecting rod is connected to the servo motor. The rotation of the servo motor drives the tire to rotate. When the servo motor drives the tire to rotate one circle, The encoder in the servo motor also produces a time sequence of signals corresponding to a circle of 3D tire contour lines; Fig. 5 is used to indicate that the rotation encoding signal triggers the three-dimensional vision sensor to collect the three-dimensional contour data, and the present invention adopts the A-phase signal in the encoder signal As a trigger signal, when the servo motor rotates so that the phase A pulse is a rising edge, the 3D vision sensor will trigger to obtain the contour line of the current position. The trigger method can be considered to be triggered once by one pulse, or once by multiple pulses, or when needed A more precise trigger signal is realized by combining the encoder A+, A-, B+, and B- four signal differentials.

Further, the embodiment of the present invention reconstructs the three-dimensional shape of the automobile tire according to the three-dimensional contour data, so as to construct the three-dimensional virtual model of the automobile tire, and the three-dimensional virtual model including the morphological characteristics of the automobile tire realizes the comprehensive detection of the automobile tire . Wherein, the 3D reconstructed image refers to a 3D stereoscopic image obtained by converting a 2D depth image originally composed of a 2D image of the surface of the tire and the depth of the tire depression, that is, a structural diagram of a 3D virtual model of the tire.

In one embodiment of the present invention, according to the three-dimensional contour data, the automobile tire is reconstructed in three-dimensional form to obtain the three-dimensional reconstructed image, including: determining the two-dimensional depth image corresponding to the three-dimensional contour data; using the following formula to calculate the depth of the two-dimensional depth image Translation coordinates:

P(x',0,z')=P(x,y,z+r)

Among them, P(x′, 0, z′) represents the depth translation coordinates of the 2D depth image, r represents the tire radius of the car tire, and x, y, z represent the point cloud data points of the car tire collected in the 2D depth image coordinate of;

According to the depth translation coordinates, the following formula is used to reconstruct the 3D shape of the 2D depth image to obtain a 3D reconstructed image:

θ＝360°÷N

x'=x

y'=cosα*y-sinα*z

z'=cosα*y+sinα*z

P(x", y", z")=P(x', 0, z')→P(x, cosα*y-sinα*z, cosα*y+sinα*z)

Among them, P(x", y", z") represents the point cloud data in the 3D reconstruction image, x", y", z" represents the coordinates of the point cloud data in the 3D reconstruction image, and i represents the point cloud data in the 2D depth image The serial number of the contour line, the range is [0, N], x, y, z represent the coordinates of the car tire point cloud data points collected in the two-dimensional depth image, P(x', 0, z') represents the two-dimensional depth The depth translation coordinates of the image.

y_i∈(0，N*n)，z_i∈(-l，l)，l属于3D视觉传感器的量程，由于系统坐标系原点在轮胎中心，所以空间点x坐标和z坐标值范围在正负区间中，图7用于表示三维重建图像，原始获取到深度图在XOY平面上，将平面上的若干条轮廓线先平移，再通过沿X轴方向旋转坐标变换后，达到对轮胎数据进行重构，实现对轮胎3D形态的还原。In order to further understand the process of reconstructing the three-dimensional shape of automobile tires, please refer to Figures 6-7, which are schematic diagrams of three-dimensional reconstruction of automobile tires provided by an embodiment of the present invention, wherein Figure 6 is used to represent the three-dimensional contour The two-dimensional depth image corresponding to the data, assuming that the number of contours generated by scanning the entire tire surface is N, the distance between each contour is n (unit: mm), and each contour line is composed of M spatial points. The spacing is m (unit: mm). In three-dimensional space, the Y direction is the perimeter direction of the contour line, and the X direction is the point direction of a single contour line. The 3D vision sensor provides height data in the Z direction for each point, so that The contour line is "stretched" along the XOY projection plane to form a 2D height map with height information, and the pixel information of each image P=( _xi , _y , zi ₎ is the coordinate value of the tire relative to the camera coordinate system , z _i is the height value from the tire surface to the camera coordinate system, and

y _i ∈ (0, N*n), z _i ∈ (-l, l), l belongs to the range of the 3D vision sensor, since the origin of the system coordinate system is at the center of the tire, the range of the x coordinate and z coordinate values of the space point is positive In the negative interval, Figure 7 is used to represent the 3D reconstruction image. The original obtained depth map is on the XOY plane, and several contour lines on the plane are first translated, and then rotated along the X-axis direction to achieve the tire data. Reconstruction to restore the 3D shape of the tire.

Further, the embodiment of the present invention divides the depth detection area and the width detection area of the three-dimensional reconstructed image, so as to detect the depth and width of the tire tread in the corresponding area. Wherein, the depth detection area refers to the area where the concave depth of the tread of the tire needs to be calculated, and the width detection area refers to the area where the width of the tire tread needs to be calculated.

In an embodiment of the present invention, dividing the depth detection area and the width detection area of the three-dimensional reconstruction image includes: querying the tread contour line of the automobile tire in the three-dimensional reconstruction image; taking the contour line area corresponding to the tread contour line as the three-dimensional reconstruction The depth detection area and width detection area of the image.

Exemplarily, the tread outline refers to the tread lines perpendicular to the rolling direction in the rolling surface of the automobile tire in the three-dimensional image.

S2. Sampling the depth vision point set in the depth detection area, calculating the average center of gravity of the point set of the depth vision point set, and performing plane fitting on the average center of gravity of the point set to obtain the fitting visual plane of the depth vision point set, according to the average center of gravity of the point set Compute the tire detection depth of a car tire with the fitted visual plane.

In the embodiment of the present invention, the depth vision point set in the depth detection area is sampled to integrate the point cloud data in the depth detection area to achieve comprehensive detection of the depth detection area. Wherein, the depth vision point set refers to a set of data points of the point cloud data in the depth detection area.

In an embodiment of the present invention, sampling the depth vision point set in the depth detection area includes: collecting the depth vision point coordinates in the depth detection area; and using the coordinate set corresponding to the depth vision point coordinates as the depth vision point set.

Further, in the embodiment of the present invention, the point set average center of gravity of the depth vision point set is calculated to determine the center of the points in the depth vision point set. Wherein, the average center of gravity of the point set refers to the point where the resultant force of the earth's gravitational force on each tiny part of the object acts, and in the present invention represents the center of the concentrated point of the depth vision point.

In one embodiment of the present invention, the point set average center of gravity of the depth vision point set is calculated using the following formula:

Among them, P _i represents the average center of gravity of the point set of the depth vision point set, i represents the sequence number of the depth vision point set, j represents the sequence number of the depth vision point in the depth vision point set, x _j , y _j , z _j represent the depth vision point Set the three-dimensional coordinates of the depth vision point whose serial number is j, and m represents the total number of depth vision points in the depth vision point set.

Further, the embodiment of the present invention performs plane fitting on the average center of gravity of the point set to obtain the functional relationship conforming to the data, determine the connection between the point cloud data, improve the feature representation ability of the point cloud data, and ensure the accuracy of the vehicle. A unified standard inspection process for tire defect detection. Wherein, the fitting visual plane refers to a set of depth visual points represented by a plane function.

In an embodiment of the present invention, the plane fitting is carried out to the average center of gravity of the point set to obtain the fitted visual plane of the depth vision point set, including: using the following formula to determine the plane fitting surface parameters of the average center of gravity of the point set:

Among them, a, b, c represent the plane fitting surface parameters of the average center of gravity of the point set, x _i , y _i , z _i represent the coordinates of the average center of gravity of the point set, and n represents the number of point sets of the depth vision point set;

According to the parameters of the plane fitting surface, use the following formula to construct the fitting vision plane of the depth vision point set:

z=ax+by+c

Wherein, z=ax+by+c represents the fitting vision plane of depth vision point set, z, x, y represents the variable of plane function, and a represents the value of fitting vision plane function in the plane fitting surface parameter of point set mean center of gravity The parameter of the variable x, b represents the parameter of the variable y of the fitting visual plane function in the plane fitting surface parameters of the average center of gravity of the point set, and c represents the constant of the fitting visual plane function in the plane fitting surface parameters of the average center of gravity of the point set.

Further, the embodiment of the present invention calculates the tire inspection depth of the automobile tire according to the average center of gravity of the point set and the fitted visual plane, so as to determine whether there is a defect in the surface tread depression of the automobile tire. Wherein, the tire detection depth refers to the degree of depression of the tread pattern on the tire surface.

In one embodiment of the present invention, according to the average center of gravity of the point set and the fitting visual plane, the tire detection depth of the automobile tire is calculated using the following formula:

Among them, d _i represents the tire detection depth of the car tire, a represents the parameter of the variable x of the fitting visual plane function in the plane fitting surface parameters of the average center of gravity of the point set, and b represents the parameter of the plane fitting surface parameter of the average center of gravity of the point set The parameter of the variable y that fits the visual plane function, c represents the constant of the fitting visual plane function in the plane fitting surface parameters of the average center of gravity of the point set, and d represents the parameter of the variable z that fits the visual plane function, x _i , y _i , z _i represent the coordinates of the mean center of gravity of the point set.

S3. Detecting the edge visual points of the width detection area, performing edge line fitting on the edge visual points to obtain a fitted visual line, and calculating the tire detection width of the automobile tire according to the edge visual points and the fitted visual line.

In the embodiment of the present invention, the edge vision points in the width detection area are detected to identify the points with obvious brightness changes in the digital image. Wherein, the edge visual point refers to the edge point in the width detection area.

In an embodiment of the present invention, detecting the edge vision point of the width detection area includes: using the following formula to perform a binarization operation on the width detection area to obtain a binarized area:

Among them, p _i (xi _, y _i ) represents the coordinate value of the point cloud data in the binarization area, xi _, y _i , z _i represent the coordinates of the average center of gravity of the point set, and k represents the preset image pixel parameters;

Use the following formula to calculate the edge point gradient of the binarized region:

表示二值化区域中像素的一阶导数差分；Among them, |G(x,y)|represents the edge point gradient of the binarized area, sprt represents the square root calculation, f(x+1,y), f(x,y), f(x,y+1) represents The pixel function of the binarized region,

Represents the first-order derivative difference of pixels in the binarized region;

Determine the edge vision point of the width detection area according to the gradient of the edge point.

Optionally, according to the gradient of the edge point, determining the edge visual point of the width detection area can be performed by comparing the gradient of the edge point with a preset threshold, if the gradient of the edge point is greater than the preset threshold, it means that the gradient changes greatly, and the point corresponding to the gradient for the edge points.

Further, in the embodiment of the present invention, edge line fitting is performed on the edge vision points, so as to use a straight line function to determine the functional relationship between each point in the edge vision points and other points. Wherein, the fitting visual line is represented by a straight line function.

In an embodiment of the present invention, performing edge line fitting on the edge visual point to obtain the fitted visual line includes: calculating the fitted line parameters of the edge visual point by using the following formula:

Wherein, A, B represent the fitting line parameter of edge vision point, x _j , y _j represent the jth edge vision point, M represents the quantity of edge vision point;

Use the following formula to fit the edge line to the edge vision point to get the fitted vision line:

Y=AX+B

Among them, Y=AX+B represents the fitting visual line, A and B represent the fitting line parameters of the edge visual points, and Y and X represent the independent variables of the straight line function.

Further, the embodiment of the present invention calculates the tire detection width of the automobile tire according to the edge visual point and the fitted visual line, so as to achieve the purpose of tire defect detection by querying whether there is a deviation in the width. Wherein, the tire detection width refers to the tire tread width.

In one embodiment of the present invention, according to the edge vision point and the fitted vision line, the tire detection width of the automobile tire is calculated using the following formula:

Among them, W represents the tire detection width of the car tire, x, y represent the edge point P(x, y) to be obtained, and A, B represent the fitting line parameters of the edge visual point.

S4. Determine the three-dimensional visual quality inspection result of the automobile tire according to the tire inspection depth and the tire inspection width.

The embodiment of the present invention determines the three-dimensional visual quality inspection result of the automobile tire according to the tire inspection depth and the tire inspection width, so as to use the detected depth and width data to determine whether there is a defect on the surface of the automobile tire. Wherein, the three-dimensional visual quality detection result refers to a combination of tire detection depth and tire detection width.

It can be seen that the embodiment of the present invention first collects the three-dimensional contour data of the automobile tires for 3D visual holographic detection of the tire defects of the automobile tires. Further, the embodiment of the present invention uses the three-dimensional contour data to Reconstructing the three-dimensional shape of the automobile tire to construct a three-dimensional virtual model of the automobile tire, the three-dimensional virtual model including the shape characteristics of the automobile tire realizes the comprehensive detection of the automobile tire, further, this The embodiment of the invention divides the depth detection area and the width detection area of the three-dimensional reconstruction image to detect the depth and width of the tire tread in the corresponding area;

Furthermore, in the embodiment of the present invention, the depth vision point set in the depth detection area is sampled to integrate the point cloud data in the depth detection area to achieve comprehensive detection of the depth detection area. Further, this The embodiment of the invention calculates the average center of gravity of the point set of the depth vision point set to determine the center of the point in the depth vision point set. combined to obtain the functional relationship of conforming data, determine the connection between point cloud data, improve the feature representation ability of the point cloud data, and ensure a unified standard detection process for automobile tire defect detection. Further, this The embodiment of the invention calculates the tire inspection depth of the automobile tire according to the average center of gravity of the point set and the fitting visual plane, so as to determine whether there is a defect in the surface tread depression of the automobile tire;

Furthermore, the embodiment of the present invention detects the edge vision points in the width detection area to identify points with obvious brightness changes in the digital image. Further, the embodiment of the present invention performs edge line simulation on the edge vision points. to determine the functional relationship between each point in the peripheral vision points and other points by using a straight line function. Further, the embodiment of the present invention calculates the The tire detection width of automobile tires is used to detect tire defects by inquiring whether there is a deviation in the width;

Further, in the embodiment of the present invention, the three-dimensional visual quality inspection result of the automobile tire is determined according to the tire inspection depth and the tire inspection width, so as to use the detected depth and width data to determine the automobile tire whether there are defects on the surface.

Therefore, the 3D visual holographic inspection method for the quality of automobile tires proposed by the embodiment of the present invention can improve the comprehensiveness of defect detection of automobile tires.

As shown in FIG. 8 , it is a functional block diagram of the 3D visual holographic detection device for the quality of automobile tires of the present invention.

The 3D visual holographic detection device 800 for the quality of automobile tires of the present invention can be installed in electronic equipment. According to the realized functions, the quality 3D visual holographic detection device for automobile tires may include a detection area division module 801 , a detection depth calculation module 802 , a detection width calculation module 803 and a detection result determination module 804 . The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of the electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

In the embodiment of the present invention, the functions of each module/unit are as follows:

The detection area division module 801 is used to collect the three-dimensional contour data of the automobile tire, perform three-dimensional shape reconstruction on the automobile tire according to the three-dimensional contour data, obtain a three-dimensional reconstruction image, and divide the depth detection area and the width detection area of the three-dimensional reconstruction image;

The detection depth calculation module 802 is used to sample the depth vision point set in the depth detection area, calculate the average center of gravity of the point set of the depth vision point set, and perform plane fitting on the average center of gravity of the point set to obtain the fitted vision plane of the depth vision point set , calculate the tire detection depth of the car tire according to the average center of gravity of the point set and the fitted visual plane;

The detection width calculation module 803 is used to detect the edge visual points of the width detection area, and perform edge line fitting on the edge visual points to obtain the fitted visual line, and calculate the tire detection width of the automobile tire according to the edge visual points and the fitted visual line ;

The detection result determining module 804 is configured to determine the three-dimensional visual quality detection result of the automobile tire according to the tire detection depth and the tire detection width.

In detail, each module in the 3D visual holographic detection device 800 for car tire quality in the embodiment of the present invention adopts the same technical means as the above-mentioned 3D visual holographic test method for car tire quality in FIGS. 1 to 7 , And can produce the same technical effect, and will not repeat them here. As shown in FIG. 9 , it is a schematic structural diagram of an electronic device implementing a 3D visual holographic detection method for the quality of automobile tires according to the present invention.

The electronic device may include a processor 90, a memory 91, a communication bus 92, and a communication interface 93, and may also include a computer program stored in the memory 91 and operable on the processor 90, such as a 3D visual holographic inspection program for the quality of automobile tires.

Wherein, the processor 90 may be composed of integrated circuits in some embodiments, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same function or different functions packaged, including one or more Combination of central processing unit (Central Processing unit, CPU), microprocessor, digital processing chip, graphics processor and various control chips, etc. The processor 90 is the control core (Control Unit) of the electronic equipment. It uses various interfaces and lines to connect the various components of the entire electronic equipment, and runs or executes programs or modules stored in the memory 91 (for example, the quality 3D vision of automobile tires is executed). holographic detection program, etc.), and call the data stored in the memory 91 to execute various functions of the electronic device and process data.

The memory 91 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a memory card (for example: SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 91 may be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 91 may also be an external storage device of the electronic device, such as a plug-in mobile hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card , Flash Card (Flash Card), etc. Further, the memory 91 may also include both an internal storage unit of the electronic device and an external storage device. The memory 91 can not only be used to store application software and various data installed in electronic equipment, such as codes of database configuration connection programs, etc., but also can be used to temporarily store data that has been output or will be output.

The communication bus 92 may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (EISA for short) bus or the like. The bus can be divided into address bus, data bus, control bus and so on. The bus is set to realize connection communication between the memory 91 and at least one processor 90 and the like.

The communication interface 93 is used for communication between the electronic device 9 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display) or an input unit (such as a keyboard (Keyboard)). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, Organic Light-Emitting Diode) touch panel, and the like. Wherein, the display may also be properly referred to as a display screen or a display unit, and is used for displaying information processed in the electronic device and for displaying a visualized user interface.

FIG. 9 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. Combining certain parts, or different arrangements of parts.

For example, although not shown, the electronic device may also include a power supply (such as a battery) for supplying power to various components. Preferably, the power supply may be logically connected to at least one processor 90 through a power management device, thereby implementing charging management, discharge management, and power management functions. The power supply may also include one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components. The electronic device may also include various sensors, bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

It should be understood that the embodiment is only for illustration, and is not limited by the structure in the scope of the patented invention.

The database configuration connection program stored in the memory 91 in the electronic device is a combination of multiple computer programs. When running in the processor 90, it can realize:

Collect the 3D profile data of the car tires, reconstruct the 3D shape of the car tires according to the 3D profile data, obtain the 3D reconstructed image, and divide the depth detection area and width detection area of the 3D reconstruction image;

Sample the depth vision point set in the depth detection area, calculate the point set average center of gravity of the depth vision point set, and perform plane fitting on the point set average center of gravity to obtain the fitted visual plane of the depth vision point set. Combined with the visual plane, calculate the tire detection depth of the car tire;

Detecting the edge visual points of the width detection area, performing edge line fitting on the edge visual points to obtain the fitted visual lines, and calculating the tire detection width of the automobile tires according to the edge visual points and the fitted visual lines;

According to the tire detection depth and tire detection width, the 3D visual quality detection results of automobile tires are determined.

Specifically, for a specific implementation method of the above computer program by the processor 90, reference may be made to the description of relevant steps in the embodiment corresponding to FIG. 1 , and details are not repeated here.

Furthermore, if the integrated module/unit of the electronic device is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium. Storage media can be either volatile or nonvolatile. For example, a computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, removable hard disk, magnetic disk, optical disk, computer memory, and read-only memory (ROM, Read-Only Memory).

The present invention also provides a storage medium. The readable storage medium stores a computer program. When the computer program is executed by the processor of the electronic device, it can realize:

Collect the 3D profile data of the car tires, reconstruct the 3D shape of the car tires according to the 3D profile data, obtain the 3D reconstructed image, and divide the depth detection area and width detection area of the 3D reconstruction image;

Sample the depth vision point set in the depth detection area, calculate the point set average center of gravity of the depth vision point set, and perform plane fitting on the point set average center of gravity to obtain the fitted visual plane of the depth vision point set. Combined with the visual plane, calculate the tire detection depth of the car tire;

Detecting the edge visual points of the width detection area, performing edge line fitting on the edge visual points to obtain the fitted visual lines, and calculating the tire detection width of the automobile tires according to the edge visual points and the fitted visual lines;

According to the tire detection depth and tire detection width, the 3D visual quality detection results of automobile tires are determined.

In the several embodiments provided by the present invention, it should be understood that the disclosed devices, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

A module described as a separate component may or may not be physically separated, and a component shown as a module may or may not be a physical unit, that is, it may be located in one place, or may also be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each unit may physically exist separately, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software function modules.

It will be apparent to those skilled in the art that the invention is not limited to the details of the above-described exemplary embodiments, but that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention.

Accordingly, the embodiments should be regarded in all points of view as exemplary and not restrictive, the scope of the invention being defined by the appended claims rather than the foregoing description, and it is therefore intended that the scope of the invention be defined by the appended claims rather than by the foregoing description. All changes within the meaning and range of equivalents of the elements are embraced in the present invention. Any reference sign in a claim should not be construed as limiting the claim concerned.

It should be noted that in this article, relative terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these No such actual relationship or order exists between entities or operations. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or device. 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 apparatus that includes the element.

The above are only specific embodiments of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention will not be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims (12)

1. a quality 3D visual holographic detection method of automobile tire, is characterized in that, described method comprises: Collecting three-dimensional contour data of automobile tires, performing three-dimensional shape reconstruction on the automobile tires according to the three-dimensional contour data, obtaining a three-dimensional reconstruction image, and dividing a depth detection area and a width detection area of the three-dimensional reconstruction image; Sampling the depth vision point set in the depth detection area, calculating the average center of gravity of the point set of the depth vision point set, and performing plane fitting on the average center of gravity of the point set, to obtain the fitting visual plane of the depth vision point set , calculating the tire detection depth of the automobile tire according to the average center of gravity of the point set and the fitting visual plane; Detecting the edge visual points of the width detection area, performing edge line fitting on the edge visual points to obtain a fitted visual line, and calculating the tire size of the automobile tire according to the edge visual points and the fitted visual line detection width; According to the tire detection depth and the tire detection width, the three-dimensional visual quality detection result of the automobile tire is determined. 2. The method according to claim 1, wherein the three-dimensional profile data of said collection of automobile tires comprises: Using a three-dimensional vision sensor and a motor encoder to configure the rotation detection platform of the automobile tire; In the rotation detection platform, the following formula is used to calculate the rotation encoding signal of the motor encoder:

Wherein, E represents the rotary encoding signal, C represents the tire circumference of the automobile tire, and n represents the contour spacing; Constructing the emitted laser signal of the automobile tire and its corresponding reflected laser signal by using the three-dimensional vision sensor according to the rotary encoding signal; According to the emitted laser signal and its corresponding reflected laser signal, the three-dimensional profile data of the automobile tire is determined. 3. The method according to claim 1, wherein, according to the three-dimensional profile data, performing three-dimensional shape reconstruction on the automobile tire to obtain a three-dimensional reconstructed image comprises: determining a two-dimensional depth image corresponding to the three-dimensional contour data; The depth translation coordinates of the two-dimensional depth image are calculated using the following formula: P(x',0,z')=P(x,y,z+r) Wherein, P(x', 0, z') represents the depth translation coordinates of the two-dimensional depth image, r represents the tire radius of the automobile tire, and x, y, z represent the collected values in the two-dimensional depth image Coordinates of car tire point cloud data points; According to the depth translation coordinates, the following formula is used to perform three-dimensional reconstruction on the two-dimensional depth image to obtain a three-dimensional reconstructed image: θ＝360°÷N

x'=x y'=cosα*y-sinα*z z'=cosα*y+sinα*z P(x", y", z")=P(x', 0, z')→P(x, cosα*y-sinα*z, cosα*y+sinα*z) Wherein, P (x ", y ", z ") represents the point cloud data in the described three-dimensional reconstructed image, x ", y ", z " represents the coordinate of described point cloud data in the described three-dimensional reconstructed image, i Represents the serial number of the contour line in the two-dimensional depth image, the range is [0, N], x, y, z represent the coordinates of the car tire point cloud data points collected in the two-dimensional depth image, P(x' , 0, z') represent the depth translation coordinates of the two-dimensional depth image. 4. The method according to claim 1, wherein said dividing the depth detection area and the width detection area of the three-dimensional reconstructed image comprises: Querying the tread profile of the automobile tire in the three-dimensional reconstructed image; The contour line area corresponding to the tread contour line is used as a depth detection area and a width detection area of the three-dimensional reconstructed image. 5. The method according to claim 1, wherein said calculating the point set average center of gravity of said depth vision point set comprises: Utilize the following formula to calculate the point set average center of gravity of the depth vision point set:

Wherein, P _i represents the point set average center of gravity of the depth vision point set, i represents the sequence number in the depth vision point set, j represents the sequence number of the depth vision point in the depth vision point set, x _j , y _j , z _j represents the three-dimensional coordinates of the depth vision point whose sequence number is j in the depth vision point set, and m represents the total number of depth vision points in the depth vision point set. 6. The method according to claim 1, wherein the said point set mean center of gravity is carried out to plane fitting to obtain the fitting visual plane of the depth vision point set, comprising: Utilize the following formula to determine the plane fitting surface parameters of the mean center of gravity of the point set:

Wherein, a, b, c represent the plane fitting surface parameters of the average center of gravity of the point set, x _i , y _i , z _i represent the coordinates of the average center of gravity of the point set, and n represents the number of point sets of the depth vision point set; According to the plane fitting surface parameters, the following formula is used to construct the fitting vision plane of the depth vision point set: z=ax+by+c Wherein, z=ax+by+c represents the fitting visual plane of described depth vision point set, and z, x, y represent the variable of plane function, and a represents fitting in the plane fitting surface parameter of described point set mean center of gravity The parameter of the variable x of the visual plane function, b represents the parameter of the variable y of the fitting visual plane function in the plane fitting surface parameters of the average center of gravity of the point set, and c represents the plane fitting surface parameter of the average center of gravity of the point set Constant for fitting the visual plane function. 7. The method according to claim 1, wherein the calculation of the tire detection depth of the automobile tire according to the average center of gravity of the point set and the fitting visual plane comprises: Utilize following formula to calculate the tire detection depth of described automobile tire:

Wherein, _di represents the tire detection depth of the automobile tire, a represents the parameter of the variable x of the fitting visual plane function in the plane fitting surface parameters of the average center of gravity of the point set, and b represents the plane of the average center of gravity of the point set The parameter of the variable y of the fitting visual plane function in the fitting surface parameter, c represents the constant of the fitting visual plane function in the plane fitting surface parameter of the mean center of gravity of the point set, and d represents the variable z of the fitting visual plane function The parameters, x _i , y _i , _zi represent the coordinates of the mean center of gravity of the point set. 8. The method according to claim 1, wherein the detecting the edge visual point of the width detection area comprises: The binarization operation is performed on the width detection area by using the following formula to obtain the binarization area:

Wherein, p _i (xi _, y _i ) represents the coordinate value of the point cloud data in the binarized region, xi _, y _i , z _i represent the coordinates of the average center of gravity of the point set, and k represents the preset Image pixel parameters; The edge point gradient of the binarized region is calculated using the following formula:

Among them, |G(x, y)| represents the edge point gradient of the binarized region, sprt represents the square root calculation, f(x+1, y), f(x, y), f(x, y+1 ) represents the pixel function of the binarized region,

Representing the first-order derivative difference of pixels in the binarized region; Determine the edge visual point of the width detection area according to the gradient of the edge point. 9. The method according to claim 1, wherein said performing edge line fitting on said edge visual point to obtain a fitted visual line comprises: Utilize following formula to calculate the fitting line parameter of described edge vision point:

Wherein, A, B represent the fitting line parameter of described edge vision point, x _j , y _j represent the jth edge vision point, M represents the quantity of described edge vision point; Use following formula to carry out edge line fitting to described edge visual point, obtain fitting visual line: Y=AX+B Wherein, Y=AX+B represents the fitting visual line, A, B represent the fitting line parameters of the peripheral vision point, Y, X represent the independent variable of the straight line function. 10. A quality 3D visual holographic detection device for automobile tires, characterized in that the device comprises: The detection area division module is used to collect the three-dimensional contour data of the automobile tire, perform three-dimensional shape reconstruction on the automobile tire according to the three-dimensional contour data, obtain a three-dimensional reconstruction image, and divide the depth detection area and width of the three-dimensional reconstruction image Detection area; The detection depth calculation module is used to sample the depth vision point set in the depth detection area, calculate the point set average center of gravity of the depth vision point set, and perform plane fitting on the point set average center of gravity to obtain the depth vision point set A fitting visual plane of the point set, calculating the tire detection depth of the automobile tire according to the average center of gravity of the point set and the fitting visual plane; The detection width calculation module is used to detect the edge visual point of the width detection area, and perform edge line fitting on the edge visual point to obtain a fitted visual line. According to the edge visual point and the fitted visual line, Calculate the tire detection width of the automobile tire; The detection result determination module is used to determine the three-dimensional visual quality detection result of the automobile tire according to the tire detection depth and the tire detection width. 11. An electronic device, characterized in that the electronic device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, the computer program is executed by the at least one processor, so that the at least one processor can perform any one of claims 1 to 9 The quality 3D visual holographic detection method of the automobile tire described in the item. 12. A computer-readable storage medium, storing a computer program, characterized in that, when the computer program is executed by a processor, the quality 3D visual holographic detection of automobile tires according to any one of claims 1 to 9 is realized method.

Images