Vehicle chassis comprehensive detection system and method based on visual detection method

Abstract

The invention discloses a vehicle chassis comprehensive detection system and method based on a visual detection method. The system comprises a Bluetooth sensor and a signal receiver to realize wheel positioning, an inclination angle sensor and a weight measuring instrument compensate angle inclination and center-of-gravity shift caused by ground inclination, parameters of a wheel toe-in angle, a camber angle, a kingpin inclination angle and a kingpin caster angle in a static state of a vehicle are visually detected, and accurate wheel positioning parameters are obtained after correction and compensation. The system does not need frame type shooting, wheel positioning measurement can be independently completed, the system structure is simple, the equipment cost is remarkably reduced, complex environmental factors such as uneven ground and dynamic inclination of a vehicle can be effectively handled, a stable and accurate positioning solution is provided, and the system is widely applied to positioning of most wheels.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile maintenance and detection, and in particular to a vehicle chassis comprehensive detection system and method based on a visual detection method. Background Art

[0002] Wheel alignment is the precise adjustment of the wheels of a car so that their angles meet the requirements of the vehicle manufacturer. This adjustment mainly involves the contact angle between the tire and the ground, as well as the relationship between the tires. The purpose is to ensure that the tires wear evenly when the vehicle is driving, to ensure handling performance, driving stability, comfort, and to extend the service life of the tires.

[0003] At present, there are two methods for wheel alignment: the traditional instrument uses mechanical relationship to determine the position, and the traditional instrument is combined with electronic equipment for positioning. For the combination of electronic equipment and traditional instruments, the more typical one is the three-dimensional detection method. Its structure consists of a crane, front and rear multiple poles, and multiple poles combined with industrial cameras. The camera is used to take pictures of the tires, and the image is processed. Combined with the weight meter on the flip board, the various angles and center of gravity positions are calculated to determine whether the wheel is abnormal. This method has the disadvantages of large space and complex operation, and requires a simpler and equally accurate wheel alignment system. Summary of the invention

[0004] Purpose of the invention: In view of the above problems, the present invention proposes a vehicle chassis comprehensive detection system and method based on visual detection method.

[0005] Technical solution:

[0006] The present invention provides a vehicle chassis comprehensive detection system based on a visual detection method, the system comprising: a Bluetooth sensor module, wherein four Bluetooth sensors supporting AoA broadcasting are fixed at the wheel axis position, and two receivers supporting AoA are deployed at fixed positions around the vehicle to obtain the coordinates of the wheels;

[0007] The tilt sensor detects the ground tilt angle. The tilt sensor measures the top view and roll angle of each wheel in the vehicle coordinate system and records ; The top view is the forward and backward tilt of the rotation around the Y axis The roll angle is the left-right tilt around the X axis. ; Use the rotation matrix to correct, , and then through Inverse transformation compensation to wheel alignment parameters;

[0008] The load cell detects the center of gravity deviation. There are four load cells in each flip board, evenly distributed in the four corners of the rectangular flip board. The wheel load is compensated according to the ground inclination to obtain the real pressure. , calculate the center of gravity coordinates according to the moment balance; compensate the wheel alignment parameters according to the offset of the center of gravity coordinates;

[0009] Visual inspection uses industrial cameras for camera calibration and PC for image preprocessing to obtain wheel posture parameters through visual inspection.

[0010] Wheel alignment parameter correction and compensation: angle correction and compensation are performed on the wheel posture parameters obtained by visual inspection according to the ground inclination angle and center of gravity offset to obtain accurate wheel alignment parameters.

[0011] Preferably, the wheel load is compensated according to the ground inclination to obtain the real pressure Includes: Correction of each weighing instrument data:

[0012] , i=1, 2, 3, 4…4n, n is the number of wheels;

[0013] The compensation of wheel alignment parameters according to the offset of the center of gravity coordinates includes: calculating the center of gravity correction compensation angles of the camber angle, toe angle, caster angle and kingpin inclination angle according to the center of gravity coordinates.

[0014] Preferably, the angle correction compensation of the wheel posture parameters obtained by visual detection according to the ground inclination angle and the center of gravity offset includes: detecting the ground inclination angle according to the inclination sensor; the weighing instrument cooperates with the inclination sensor to correct the center of gravity offset, and calculates the center of gravity correction compensation angle of camber angle, toe angle, kingpin castor angle and kingpin inclination angle; visually detecting the wheel posture parameters of camber angle, toe angle, kingpin castor angle and kingpin inclination angle in a static state; and combining the above three to obtain accurate wheel alignment parameters.

[0015] Preferably, the ground inclination angle detected by the inclination sensor needs to be corrected using a rotation matrix, and the rotation matrix is:

[0016] , ;

[0017] in and are respectively the top angle and roll angle measured by the tilt sensor; The inverse transformation is compensated into the parameters of the wheel alignment.

[0018] Preferably, the inclination sensor is installed at the center of the flip plate and is compared and verified using a level meter.

[0019] Preferably, the Bluetooth sensor module adopts Bluetooth 5.1 communication protocol, supports SPP protocol, and has a baud rate of 0.92M bps; adopts a one-master-multiple-slave Bluetooth network configuration, with the master device being a PC and a dual-mode Bluetooth module, to control the slave device, receive AoA data, execute the MUSIC angle estimation algorithm, and calculate coordinates; the slave device is a wheel sensor, to broadcast AoA signals and respond to SPP instructions.

[0020] The present invention also provides a vehicle chassis comprehensive detection method based on a visual detection method, comprising the following steps:

[0021] S1: A Bluetooth sensor supporting AoA broadcasting is installed at the center of each wheel, and two AoA-supported receivers are deployed at fixed positions around the vehicle; the PC is connected via Bluetooth; the PC sends wheel position positioning operation instructions to perform wheel position positioning.

[0022] S2: The PC sends a command to start the tilt sensor and level to measure the pitch and roll angles and record them. ; The top view is the forward and backward tilt of the rotation around the Y axis The roll angle is the left-right tilt around the X axis. ; Use the rotation matrix to correct, , and then through Inverse transformation compensation to wheel alignment parameters;

[0023] S3: The PC sends a command to start the load cell to measure the load of each wheel, and compensates the wheel load according to the ground inclination to obtain the actual pressure. , calculate the center of gravity coordinates according to the moment balance; compensate the wheel alignment parameters according to the offset of the center of gravity coordinates;

[0024] S4: PC starts industrial camera detection to visually detect the camber angle, toe angle, caster angle, and kingpin inclination angle of the wheel;

[0025] S5: According to the ground inclination angle and the center of gravity offset, the visually detected camber angle, toe angle, caster angle and kingpin inclination angle are corrected and compensated to obtain accurate wheel alignment parameters.

[0026] Preferably, the specific method of step S1 is as follows:

[0027] S1.1 puts the car body in a straight position and then installs a Bluetooth sensor with AoA broadcast support on each wheel;

[0028] S1.2 adopts a "one master and multiple slaves" Bluetooth network architecture: the PC is the master device, and multiple wheel Bluetooth sensors are slave devices; the Bluetooth module supports the SPP protocol and sets the baud rate to 0.92 M bps to match the data transmission requirements;

[0029] S1.3 constructs the vehicle body coordinate system, track width W, wheelbase L, sets a wheel slave range, the PC sends a signal through the communication channel, the sensor receives the command and determines the tire center position, and stores and returns its coordinate value to the main device PC for range matching to determine the tire position.

[0030] Preferably, the specific method of step S3 includes:

[0031] S3.1 The PC sends a start command to the weighing instrument. Each flip board has four weighing instruments, which are distributed at the four corners of the flip board. The weighing instruments measure the weight of each tire at the four corners. , where i=1, 2, 3…16;

[0032] S3.2 For each Perform tilt compensation and obtain ;

[0033] S3.3 The center of gravity solution equation is established based on the moment balance to deduce the center of gravity coordinates; the wheel alignment parameters are compensated based on the offset of the center of gravity coordinates to deduce the center of gravity correction compensation angles of the camber angle, toe angle, caster angle, and kingpin inclination angle.

[0034] Preferably, the specific method of step S5 is: detecting the ground inclination angle according to the inclination sensor; performing gravity center offset correction with the load cell in cooperation with the inclination sensor to deduce the gravity center correction compensation angles of the camber angle, toe angle, kingpin castor angle, and kingpin inclination angle; visually detecting the wheel posture parameters of the camber angle, toe angle, kingpin castor angle, and kingpin inclination angle in a stationary state; and obtaining accurate wheel alignment parameters by combining the three.

[0035] Compared with the prior art, the present invention has the following beneficial effects: the present invention adopts a combination of an inclination sensor and a level to obtain the ground inclination angle; for compensation of center of gravity offset, due to the different degrees of ground inclination, each flip plate corresponds to a tire, and there are four weighing instruments in a flip plate, which are distributed on the four corners of the flip plate, and multi-point compensation of wheel load-bearing is adopted to obtain a more accurate load-bearing capacity; thereby obtaining compensation of wheel alignment parameters; Bluetooth positioning is adopted to lock the wheel, and the visual detection method cooperates with the inclination sensor and the weighing instrument to correct the wheel alignment parameters, making the positioning more accurate; through multi-sensor fusion and image processing technology, efficient and accurate wheel alignment is achieved. Compared with traditional detection equipment and industrial frame measurement methods, the present invention simplifies the equipment and reduces the cost while ensuring accuracy, and concentrates the measurement part on the flip plate to complete it independently, reducing the measurement footprint. Both R&D expenses and usage scenarios have been improved and optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1is a flow chart of the vehicle chassis comprehensive detection method of the present invention;

[0037] Figure 2 It is a schematic diagram of the vehicle wheelbase and track;

[0038] Figure 3 This is a schematic diagram of a Bluetooth positioning wheel;

[0039] Figure 4 It is a top-down view and angle decomposition diagram;

[0040] Figure 5 It is a schematic diagram of the roll angle and angle decomposition;

[0041] Figure 6 This is a diagram illustrating the toe angle;

[0042] Figure 7 It is a diagram illustrating the camber angle;

[0043] Figure 8 It is a diagram illustrating the kingpin inclination angle;

[0044] Fig. 9 This is a diagram illustrating the caster angle;

[0045] Fig.10 It is a spatial diagram of toe angle and camber angle;

[0046] Fig.11 It is a spatial diagram of the kingpin inclination angle and the kingpin caster angle;

[0047] Fig.12 It is the camera calibration flow chart;

[0048] Fig.13 It is a physical simulation diagram of the visual inspection part;

[0049] Fig.14 It is the flow chart of pose parameter calculation. DETAILED DESCRIPTION

[0050] Many modifications and changes made by those skilled in the art based on the principles of the present invention belong to the protection scope of the present invention.

[0051] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when an element or component is said to be "connected" to another element or component, it may be directly connected to the other element or component, or there may be an intermediate element or component. The term "and / or" used herein includes any unit and all combinations of one or more associated listed items.

[0052] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] like Figure 1 FIG. 1 is a flow chart of a vehicle chassis comprehensive detection method of the present invention. The embodiment of the present invention provides a vehicle chassis comprehensive detection method based on a visual detection method, comprising the following steps:

[0054] S1: A Bluetooth sensor supporting AoA broadcasting is installed at the center of each wheel, and two AoA-supported receivers are deployed at fixed positions around the vehicle; the PC is connected via Bluetooth; the PC sends wheel position positioning operation instructions to perform wheel position positioning.

[0055] Park the vehicle on a level surface, with the front of the vehicle facing the reference direction (such as a wall marking line), calibrate the vehicle axis using a laser level to ensure there is no deflection, and establish the vehicle coordinate system. Input parameters: Figure 2 The wheelbase is shown as W and L.

[0056] like Figure 3 Use non-metallic clamps (such as nylon wheel clamps) to fix four Bluetooth 5.1+sensors Nordic nRF5340 that support AoA broadcasting at the wheel axle center, and two receivers that support AoA (such as Nordic nRF52833 + antenna array) are deployed at fixed positions around the vehicle, 1 meter in front of the front of the vehicle, 0.5 meter in height, and 1 meter behind the rear of the vehicle, 0.5 meter in height. Configure Bluetooth and connect to Bluetooth on the PC.

[0057] A one-master-multiple-slave Bluetooth network configuration is adopted. The master device is a PC and a dual-mode Bluetooth module, which controls the slave device, receives AoA data, executes the MUSIC angle estimation algorithm, and calculates coordinates. The slave device is a wheel Bluetooth sensor, which broadcasts AoA signals and responds to SPP instructions. The Bluetooth module supports the SPP protocol and sets the baud rate to 0.92 M bps to match the data transmission requirements.

[0058] The following details the positioning method based on AoA:

[0059] Assuming the antenna array spacing is d and the signal wavelength is λ, the relationship between the phase difference Δϕ of the signals received by adjacent antennas and the arrival angle θ is:

[0060] ;

[0061] Using the MUSIC algorithm to estimate the arrival angle, first construct the received signal covariance matrix R:

[0062] ; Perform eigendecomposition on R to separate the signal subspace and the noise subspace; N is the number of signal acquisitions.

[0063] Search for the angle that maximizes :

[0064] ;

[0065] Coordinate calculation: If the coordinates of receiver 1 are (x1, y1), the angle of arrival can be measured ; The coordinates of receiver 2 are (x2, y2), and the angle of arrival is measured , then the target coordinates (x, y) satisfy:

[0066] ;

[0067] The solution is: ;

[0068] After calculating the coordinate values ​​of the four tires, the coordinate values ​​are matched within the set interval to determine the front and rear wheels, left and right wheels, and the data displayed on the PC will also be output according to the tire position.

[0069] S2: The PC sends a command to start the inclination sensor and level to measure the pitch angle and roll angle;

[0070] After the PC sends the detection command, the tilt sensor performs a top-down angle based on the coordinate system. Figure 4 and the roll angle as Figure 5 The top angle refers to the front and back tilt when rotating around the Y axis, and the roll angle refers to the left and right tilt when rotating around the X axis.

[0071] The specific measurement process is as follows: the vehicle is parked on the flip board and the body is straightened. The tilt sensor measures the top view and roll angle of each wheel in the vehicle coordinate system and records the , and verify that the level is consistent.

[0072] Since the angle is tilted due to the uneven ground, a rotation matrix is ​​required Make corrections, including ; then through The inverse transformation is compensated into the parameters of the wheel alignment.

[0073] S3: The PC sends a command to start the load cell to measure the load of each wheel, and compensates the wheel load according to the ground inclination to obtain the actual pressure. , calculate the center of gravity coordinates according to the moment balance; compensate the wheel alignment parameters according to the offset of the center of gravity coordinates;

[0074] Each flip board corresponds to a tire. There are four weighing instruments on a flip board, distributed at the four corners of the flip board. Due to the different inclinations of the ground, the following are used: Figure 4 and Figure 5 (Incline force decomposition diagram) Multi-point compensation of wheel load to obtain more accurate load-bearing capacity. The correction of single load cell data is as follows:

[0075] , i=(1, 2, 3, 4…4n, n is the number of wheels); use the force and moment balance equation to solve the center of gravity coordinates .

[0076] (m is the mass of the car, g is the acceleration due to gravity);

[0077] Construct the moment balance equation in the vehicle body coordinate system: Assume that the coordinates of the contact point of each k-th wheel in the global coordinate system are , the total vertical force is: ,but:

[0078] ;

[0079] After obtaining the center of gravity coordinates, the compensation angles of camber angle, toe angle, caster angle, and kingpin inclination angle can be calculated.

[0080] Camber center of gravity correction: ;in It is the difference in suspension compression caused by the center of gravity height, . is the initial camber angle, Is to use jack to raise the suspension This step will be used in step S4.

[0081] Correction of the center of gravity of the toe-in foot: ;in It is the difference in suspension compression caused by the center of gravity height, . is the initial camber angle, Is to use jack to raise the suspension This step will be used in step S4.

[0082] Caster angle center of gravity correction: ;in is the caster angle change rate, , It is the difference in the change of the kingpin caster angle.

[0083] Kingpin inclination angle center of gravity correction: ;in is the kingpin inclination angle sensitivity coefficient, . You can find it through the manual.

[0084] The above formula mentions are the pitch stiffness and roll stiffness;

[0085] ,in is the spring rate, r is the leverage ratio, W is the track width, and L is the wheelbase.

[0086] S4: PC starts industrial camera detection to visually detect the camber angle, toe angle, caster angle, and kingpin inclination angle of the wheel;

[0087] The present invention has a certain effect on the toe angle. Figure 6 , camber angle Figure 7 、Kingpin inclination angle Figure 8 、The caster angle is Fig. 9 A legend was provided.

[0088] like Fig.10 As shown, assume that planes xoz, xoy, yoz are the horizontal plane of the vehicle body, the transverse plane of the vehicle body, and the longitudinal plane of the vehicle body, respectively, plane ABCD is the wheel plane, and OG is the tire rotation axis vector perpendicular to ABCD. The wheel plane ABCD intersects with planes xoz and yoz at straight lines EF and MN, respectively, and the direction vector of OG is N=(n1, n2, n3).

[0089] According to the concept of toe angle, the angle between OF and Z axis is the toe angle. . Let the unit normal vector of face xoz be (0,1,0), so:

[0090] ;

[0091] Then the OF and z-axis direction vectors are (n3,0, n1) and (0,0,1) respectively. The angle between the two vectors in space is calculated by the formula:

[0092] ;

[0093] That is, the toe angle is:

[0094] ;

[0095] The angle between plane ABCD and xoz is the camber angle , let the normal vectors of plane ABCD and xoz be N=(n1, n2, n3) and (0,1,0) respectively, then we can get:

[0096] ;

[0097] That is, the camber angle is:

[0098] ;

[0099] like Fig.11 As shown in the figure, assume that OG' is the kingpin of the car, and its direction cosine is set to E=(e1, e2, e3). OE and OF are the projections of OG' on the transverse plane xoy and the longitudinal plane yoz of the car body respectively. It can be seen that YOE and YOF are the kingpin inclination angles respectively. and caster angle Assume the length of the kingpin axis is a, and the angles between OG' and the x, y, and z axes are . From this we can get:

[0100] ;

[0101] Thus we can get:

[0102] ;

[0103] After obtaining the operational relationship of these angles in visual space coordinates, the next step is to visually detect the wheel parameters. Fig.12 This is the camera calibration flow chart. Perform camera calibration. Fig.13It is a physical simulation diagram of the visual inspection part. The present invention adopts a plane calibration method to calibrate the reflective sheet on the wheel, and then performs image acquisition. The calibration plate image is acquired from multiple angles to reduce the error caused by randomness. First, four images are acquired from the front of the calibration plate, and then the calibration plate is deflected at a certain angle from the top, bottom, left and right, and five pictures are taken from each angle, and a total of 24 calibration images are acquired. Toe angle and camber angle experimental image acquisition: Utilize the self-locking effect of the car steering wheel locking rod, lock the steering wheel, turn the wheel, simulate the forward and backward movement of the car, and then use the camera to acquire the image of the target plate when the wheel rotates. Kingpin inclination angle and caster angle image acquisition: Fix the car brake pedal to prevent the wheel from rolling when turning, and then use the steering wheel to make the car turn to the left and right by a certain angle, and in this process, use the camera to acquire.

[0104] The 24 collected calibration images are made into an image list file lst.yaml in yaml format to facilitate OpenCV's batch reading of images. The yaml format is the standard format for OpenCV file reading.

[0105] Define related variables, initialize variables such as the number of images, calibration plate size (the number of feature points in each image), camera internal parameter matrix, stored image feature points, and allocate storage space.

[0106] Load the step lst file, read each image and binarize it. After the image is binarized, detect and extract the feature points in the image, compare the number of detected feature points with the number of feature points of each image in the initialization, if they are equal, save the extracted feature points, if the number is smaller than the preset value, do not save, then extract the next image, repeat this operation until all image feature points are extracted. After the feature points are successfully extracted, sort the feature points and draw them in order. In this experiment, the feature points are sorted from left to right and from top to bottom.

[0107] After obtaining the world coordinates and image coordinates of the center of the calibration plate, the internal parameters and distortion parameters are solved according to the camera calibration parameter solution formula, and the calibration reprojection error is calculated: after calling the calibrateCamera function to solve the internal parameters and distortion parameters, the projection coordinates of the world coordinates of the center of the circle on the image are calculated, and then the obtained coordinates are compared with the coordinates extracted by the findCirclesGrid function to calculate the mean square error value.

[0108] After completing the camera calibration, the original image is preprocessed. The specific operations are as follows:

[0109] First, we perform a binarization operation on the image. By setting an appropriate threshold, we compare the gray value of each pixel with the set threshold, so as to highlight the required part from the image. The binarization formula is:

[0110] ;

[0111] Where g(x, y) represents the gray value of each pixel after the thresholding operation. Pixels with gray values ​​less than the threshold T are considered as background, otherwise they are considered as foreground.

[0112] Then, Gaussian filtering is performed. The image collected by the present invention is less affected by salt and pepper noise, so the image is smoothed by Gaussian filtering. For the Gaussian filter, the weight corresponding to the pixel is proportional to the distance between the pixel and the center pixel. The formula of the one-dimensional Gaussian function is: ; The normalization coefficient A is to ensure that the sum of the weights is equal to 1. The value determines the width of the Gaussian function curve. The larger the value, the flatter the function curve. The Gaussian function is a symmetrical bell-shaped curve, which is very suitable for filtering. The farther away from the center point, the smaller the corresponding weight, so the transition between pixels will be smoother. Because the Gaussian filter can be split into two one-dimensional filters, fewer multiplication operations are performed after the split, which facilitates matrix operations on the image. Therefore, when applying a two-dimensional Gaussian filter to an image, first apply a one-dimensional Gaussian filter to the horizontal lines to filter out the high-frequency components in the horizontal direction, and then apply another one-dimensional Gaussian filter to the vertical lines to filter out the high-frequency components in the vertical direction.

[0113] Then, the image segmentation process is performed. The present invention adopts the GrabCutt algorithm to perform static image segmentation. The method steps are as follows: The GrabCut algorithm is an algorithm based on a mixed Gaussian model. The mixed Gaussian model is: ; in, refers to the weight of the i-th Gaussian distribution in the mixture model, The sum of is 1, that is , k is the number of Gaussian distributions in the Gaussian mixture model. It refers to the mean of the i-th Gaussian distribution and indicates the center position of the Gaussian distribution. It refers to the covariance matrix of the i-th Gaussian distribution. In the image, a mixed Gaussian model with k Gaussian components is used to model the background and foreground respectively, so each pixel in the image corresponds to a Gaussian component, and the energy model for the image is E=U+V, where U is the area term, which represents the negative logarithm of the probability that the pixel belongs to the background or foreground, and V is the boundary term, which represents the weight of a certain pixel belonging to the boundary.

[0114] ; in Represents the estimated category label of the nth pixel in the image. There are two categories here, foreground and background. Represents the index of the nth pixel, indicating the position of the pixel in the image. represents the true label of the nth pixel, indicating the actual category of the pixel.

[0115] In the Gaussian mixture model, , and They are used to describe the weight size, mean component and covariance matrix in each Gaussian component. These three variables together constitute the parameters of the Gaussian function. As long as the values ​​of these three variables are found, the corresponding region term U can be found, and then the probability of each pixel belonging to the foreground or background can be calculated. The next step is to determine the boundary weight V in the energy model.

[0116] ; Usually Euclidean distance Determine the similarity between pixels. The parameter b in the formula is the scaling factor. A lower image contrast will make the Euclidean distance between pixels m and n belonging to different target areas very small, and mistakenly judge that m and n belong to the same target area. A higher image contrast will make the Euclidean distance between pixels m and n with high similarity larger, and mistakenly judge that m and n belong to different target areas. The function of the parameter b is to adjust this misjudgment operation, that is, to increase the difference between pixels when the image contrast is low through a larger b value, and to reduce the difference between pixels when the image contrast is high through a smaller b value. In this way, whether in high-contrast areas or low-contrast areas, the V item can be guaranteed to work normally. The constant item g takes an empirical value of 50, and finally determines the boundary weight V. The specific steps are as follows: First, mark the area to be processed on the image. The pixels outside the marked area are background pixels, i.e., pixel labels. , all pixels in the marked area are initialized as possible foreground pixels, and the pixel label The labeled pixels are divided into k categories by the k-means algorithm, which is used to initialize k Gaussian components. For each pixel assigned to a Gaussian component, there is a corresponding Gaussian component Correspondingly, we have:

[0117] ;

[0118] For given image data, the GMM parameters are obtained. Its parameter mean and covariance can be estimated by the RGB values ​​of the marked pixel samples. The number of pixels corresponding to this Gaussian component is divided by the total number of pixels, and the weight corresponding to each Gaussian component is calculated using this value.

[0119] ;

[0120] According to the energy distribution formula E and the method described above, the corresponding regional weights and boundary weights are obtained to estimate the image segmentation; repeat the above operations, learn and optimize the GMM model parameters, obtain the final segmentation result, and smooth the segmented image.

[0121] Finally, the image features are extracted. The present invention uses Hough transform to extract features. The purpose of Hough transform is to find a mapping relationship from the image area to the parametric equation so that the specific curve in the image area can be described by the parametric equation. For the pixel area, we use x, y, r (x, y are the coordinates of the center of the circle, and r is the radius) as parameters to establish a parametric equation:

[0122] ;

[0123] We can regard the target image area as a set of multiple circular areas. Then, for each circular boundary, there is an equation with a specific radius corresponding to it in the parameter space. The Hough transform is to make each pixel in the target area correspond one-to-one in the parameter space. The boundary points of the circular area are composed of all pixels whose intensity values ​​in the image are not 0. If a certain pixel point (x, y) moves around the circular boundary determined by the characteristic parameters, then there must be multiple circular rings determined by different parameters intersecting at a point (a, b). (a, b) is the coordinate of the center of a certain circular area. At this time, the calculation of the center of the circle is transformed into the problem of seeking the intersection of circles with different parameters. It can be seen that its basic strategy is: to find the trajectory of a specific point in the parameter space through the pixel points that may be the boundary points, and to count the specific points found through the counter. If the value is larger than the preset value, the circle obtained at this time is a circle that meets the requirements. The steps to extract the coordinates of the center of the circle are as follows:

[0124] Determine the analytical expression set of the curve to be identified and establish the parametric equation;

[0125] Construct a counter N[a][b] for each parameter in the analytical expression set and initialize the value of the counter;

[0126] Traverse the valid pixels of the image and substitute the pixel coordinates in the image into the parametric equation. If it satisfies:

[0127] ; then the corresponding counter value is increased by 1; in the counter, find the parameter (a, b) corresponding to the maximum value, (a, b) is the coordinate of the center of the circle we want to obtain.

[0128] After the image is preprocessed, the image is combined with the obtained coordinates to solve the pose parameters. Fig.14 As shown, the wheel posture parameters are finally output.

[0129] Finally, the wheel alignment parameters are calculated, and the corresponding wheel alignment parameters are obtained according to the wheel alignment parameter calculation formula described earlier in this article.

[0130] Pseudo code for obtaining pose parameters:

[0131] Define variables to store 2D image coordinates A1, feature point camera coordinates A2, and world coordinates A3;

[0132] A1 and A2 are initialized to 0, and A3 is initialized according to the camera calibration method;

[0133] Extract 2D image coordinates;

[0134] Substitute the camera internal parameters to obtain the camera coordinates A2 of the two-dimensional image coordinates;

[0135] Using pose parameters as variables , combine A2 and A3 to establish the objective function:

[0136] ;

[0137] Before obtaining the extreme value of the objective equation, perform the following operations:

[0138] Least squares expansion of objective function;

[0139] Use SVD to calculate the corresponding location parameters ;

[0140] Pose parameters Substitute into the objective function.

[0141] There may be certain errors in the visual detection algorithm. The present invention adopts the weighting method to correct the angle and calculates the weight using the root mean square error. The specific process is as follows:

[0142] For each frame image, we have m feature points, and the reprojection error of each feature point can be written as:

[0143] ;

[0144] in is the actual observed position of the feature point in image coordinates, It is the theoretical position projected after posture calculation, and i represents the i-th wheel.

[0145] The formula for calculating the mean square error is as follows:

[0146] ;

[0147] Think of RMS as the standard deviation of the frame , the corresponding variance estimate is: ; m represents the number of feature points.

[0148] Therefore, the weight of each wheel in the jth frame is: ;

[0149] Finally, the weights are normalized, and the detected angles are weighted averaged to obtain the final detected angle value: ;

[0150] The weighted average method uses the inverse of the mean square error as the weight to solve problems such as image shooting angle, pixel blur in a certain frame, and light. It gives higher weights to images with good quality and lower weights to images with relatively weaker effects. After combining multiple frames of images for processing, errors in visual detection can be eliminated.

[0151] S5: According to the ground inclination angle and the center of gravity offset, the visually detected camber angle, toe angle, caster angle and kingpin inclination angle are corrected and compensated to obtain accurate wheel alignment parameters.

[0152] The inclination angle of the ground is detected by the inclination sensor; the weighing instrument cooperates with the inclination sensor to correct the center of gravity offset and deduce the center of gravity correction compensation angles of camber, toe, caster and kingpin inclination; the wheel posture parameters of camber, toe, caster and kingpin inclination in a static state are detected by vision; the precise wheel alignment parameters are obtained by combining the three.

[0153] Considering the inclination angle caused by uneven ground and the center of gravity shift, the camber angle detected by vision is , toe angle , caster angle , Kingpin inclination angle The ground tilt compensation and gravity center offset tilt correction are performed. The ground tilt compensation and gravity center offset tilt correction angles have been described above. The angle after camber compensation correction is , the angle after toe angle compensation correction is , the angle after the kingpin inclination angle compensation correction is , the angle after the caster compensation is Now let’s list the formulas for each angle:

[0154] Camber angle compensation corrected calculation formula:

[0155] ;

[0156] ;

[0157] The calculation formula of toe angle compensation after correction:

[0158] ;

[0159] Corrected calculation formula for kingpin inclination angle compensation:

[0160] ;

[0161] Corrected calculation formula for caster angle compensation:

[0162] .

[0163] Another embodiment of the present invention provides a vehicle chassis integrated detection system based on a visual detection method, the system comprising: a Bluetooth sensor module, wherein four Bluetooth sensors supporting AoA broadcasting are fixed at the axle center position of the wheel, and two receivers supporting AoA are deployed at fixed positions around the vehicle to obtain the coordinates of the wheel;

[0164] The tilt sensor detects the ground tilt angle. The tilt sensor measures the top view and roll angle of each wheel in the vehicle coordinate system and records ; The top view is the forward and backward tilt of the rotation around the Y axis The roll angle is the left-right tilt around the X axis. ; Use the rotation matrix to correct, , and then through Inverse transformation compensation to wheel alignment parameters;

[0165] The load cell detects the center of gravity deviation. There are four load cells in each flip board, evenly distributed in the four corners of the rectangular flip board. The wheel load is compensated according to the ground inclination to obtain the real pressure. , calculate the center of gravity coordinates according to the moment balance; compensate the wheel alignment parameters according to the offset of the center of gravity coordinates;

[0166] Visual inspection uses industrial cameras for camera calibration and PC for image preprocessing to obtain wheel posture parameters through visual inspection.

[0167] Wheel alignment parameter correction and compensation: angle correction and compensation are performed on the wheel posture parameters obtained by visual inspection according to the ground inclination angle and center of gravity offset to obtain accurate wheel alignment parameters.

[0168] Furthermore, the wheel load is compensated according to the ground inclination to obtain the real pressure Includes: Correction of each weighing instrument data:

[0169] , i=1, 2, 3, 4…4n, n is the number of wheels;

[0170] The compensation of wheel alignment parameters according to the offset of the center of gravity coordinates includes: calculating the center of gravity correction compensation angles of the camber angle, toe angle, caster angle and kingpin inclination angle according to the center of gravity coordinates.

[0171] Furthermore, the angle correction and compensation of the wheel posture parameters obtained by visual detection according to the ground inclination angle and the center of gravity offset includes: detecting the ground inclination angle according to the inclination sensor; correcting the center of gravity offset with a load cell in cooperation with the inclination sensor, and calculating the center of gravity correction compensation angles of the camber angle, toe angle, kingpin castor angle, and kingpin inclination angle; visually detecting the wheel posture parameters of the camber angle, toe angle, kingpin castor angle, and kingpin inclination angle in a stationary state; and combining the three to derive accurate wheel alignment parameters.

[0172] Furthermore, the ground inclination angle detected by the inclination sensor needs to be corrected using a rotation matrix, and the rotation matrix is:

[0173] ;

[0174] in are respectively the top angle and roll angle measured by the tilt sensor; The inverse transformation is compensated into the parameters of the wheel alignment.

[0175] Furthermore, the inclination sensor is installed at the center of the flip plate and is compared and verified using a level meter.

[0176] Furthermore, the Bluetooth sensor module adopts Bluetooth 5.1 communication protocol, supports SPP protocol, and has a baud rate of 0.92 M bps; adopts a one-master-multiple-slave Bluetooth network configuration, with the master device being a PC to control the slave device, receive AoA data, execute the MUSIC angle estimation algorithm, and calculate coordinates; the slave device is a wheel Bluetooth sensor to broadcast AoA signals and respond to SPP instructions.

[0177] The applicant of the present invention has made a detailed explanation and description of the implementation examples of the present invention in conjunction with the drawings in the specification. However, those skilled in the art should understand that the above implementation examples are only preferred implementation schemes of the present invention, and the detailed description is only to help readers better understand the spirit of the present invention, but not to limit the scope of protection of the present invention. On the contrary, any improvements or modifications based on the inventive spirit of the present invention should fall within the scope of protection of the present invention.

Claims

1. A vehicle chassis comprehensive detection system based on visual detection method, characterized in that: The system includes: a Bluetooth sensor module, wherein four Bluetooth sensors supporting AoA broadcasting are fixed at the axle center of the wheel, and two receivers supporting AoA are deployed at fixed positions around the vehicle to obtain the coordinates of the wheel; The tilt sensor detects the ground tilt angle. The tilt sensor measures the top view and roll angle of each wheel in the vehicle coordinate system and records ; The load cell detects the center of gravity deviation. There are four load cells in each flip board, evenly distributed in the four corners of the rectangular flip board. The wheel load is compensated according to the ground inclination to obtain the real pressure. , calculate the center of gravity coordinates according to the moment balance; compensate the wheel alignment parameters according to the offset of the center of gravity coordinates; Visual inspection uses industrial cameras for camera calibration and PC for image preprocessing to obtain wheel posture parameters through visual inspection. Wheel alignment parameter correction and compensation: angle correction and compensation are performed on the wheel posture parameters obtained by visual inspection according to the ground inclination angle and center of gravity offset to obtain accurate wheel alignment parameters.

2. A vehicle chassis comprehensive detection system based on a visual detection method according to claim 1, characterized in that: The wheel load is compensated according to the ground inclination to obtain the real pressure Including: correcting the data of each weighing instrument, , i=1, 2, 3, 4…4n, n is the number of wheels; The compensation of wheel alignment parameters according to the offset of the center of gravity coordinates includes: calculating the center of gravity correction compensation angles of the camber angle, toe angle, caster angle and kingpin inclination angle according to the center of gravity coordinates.

3. A vehicle chassis comprehensive detection system based on a visual detection method according to claim 2, characterized in that: The method of performing angle correction and compensation on wheel posture parameters obtained by visual detection according to the ground inclination angle and the center of gravity offset comprises: detecting the ground inclination angle according to the inclination sensor; performing center of gravity offset correction on the load cell in cooperation with the inclination sensor to deduce the center of gravity correction compensation angle of the camber angle, the toe angle, the kingpin castor angle and the kingpin inclination angle; performing angle correction and compensation on the wheel posture parameters in a static state according to visual detection of the camber angle, the toe angle, the kingpin castor angle and the kingpin inclination angle; and performing angle correction and compensation on the wheel posture parameters in a static state according to the ground inclination angle and the center of gravity correction compensation angle to obtain accurate wheel alignment parameters.

4. A vehicle chassis comprehensive detection system based on a visual detection method according to claim 3, characterized in that: The ground inclination angle detected by the inclination sensor needs to be corrected using a rotation matrix, which is: ， ； in and are respectively the top angle and roll angle measured by the tilt sensor; The inverse transformation is compensated into the parameters of the wheel alignment.

5. The vehicle chassis comprehensive detection system based on the visual detection method according to claim 4 is characterized in that: The inclination sensor is installed at the center of the flip plate and is compared and verified using a level meter.

6. A vehicle chassis comprehensive detection system based on a visual detection method according to claim 5, characterized in that: The Bluetooth sensor module adopts Bluetooth 5.1 communication protocol, supports SPP protocol, and has a baud rate of 0.92 M bps. It adopts a one-master-multiple-slave Bluetooth network configuration, with the master device being the PC end, which controls the slave device, receives AoA data, executes the MUSIC angle estimation algorithm, and calculates coordinates. The slave device is the wheel Bluetooth sensor, which broadcasts AoA signals and responds to SPP instructions.

7. A vehicle chassis comprehensive detection method based on a visual detection method, using a vehicle chassis comprehensive detection system based on a visual detection method according to any one of claims 1 to 6, characterized in that: The steps include: S1: A Bluetooth sensor supporting AoA broadcast is installed at the center of each wheel, and two AoA-supported receivers are deployed at fixed positions around the vehicle; the PC is connected via Bluetooth; the PC sends a wheel position positioning operation instruction to perform wheel position positioning; S2: The PC sends a command to start the inclination sensor and level to measure the pitch angle and roll angle. The pitch angle is the forward and backward tilt around the Y axis. The roll angle is the left-right tilt around the X axis. ; S3: The PC sends a command to start the load cell to measure the load of each wheel, and compensates the wheel load according to the ground inclination to obtain the actual pressure. , calculate the center of gravity coordinates according to the moment balance; compensate the wheel alignment parameters according to the offset of the center of gravity coordinates; S4: PC starts industrial camera detection to visually detect the camber angle, toe angle, caster angle, and kingpin inclination angle of the wheel; S5: According to the ground inclination angle and the center of gravity offset, the visually detected camber angle, toe angle, caster angle and kingpin inclination angle are corrected and compensated to obtain accurate wheel alignment parameters.

8. The vehicle chassis comprehensive detection method based on visual detection method according to claim 7 is characterized in that: The specific method of step S1 is as follows: S1.1 puts the car body in a straight position and then installs a Bluetooth sensor with AoA broadcast support on each wheel; S1.2 adopts the "one master and multiple slaves" Bluetooth network architecture: the PC is the master device and multiple Bluetooth sensors are slave devices; the Bluetooth module supports the SPP protocol and sets the baud rate to 0.92 Mbps to match the data transmission requirements; S1.3 builds the vehicle body coordinate system and sets a wheel slave range. The PC sends a signal through the communication channel. After receiving the command, the Bluetooth sensor determines the center position of the tire, stores and accesses its coordinate value, and returns it to the main device PC for range matching to determine the position of the tire.

9. The vehicle chassis comprehensive detection method based on visual detection method according to claim 8, characterized in that: The specific method of step S3 includes: S3.1 The PC sends a start command to the weighing instrument. Each flip board has four weighing instruments, which are distributed at the four corners of the flip board. The weighing instruments measure the weight of each tire at the four corners. , where i=1, 2, 3…16; S3.2 For each Perform tilt compensation and obtain ; S3.3 The center of gravity solution equation is established based on the moment balance to deduce the center of gravity coordinates; the wheel alignment parameters are compensated based on the offset of the center of gravity coordinates to deduce the center of gravity correction compensation angles of the camber angle, toe angle, caster angle, and kingpin inclination angle.

10. A vehicle chassis comprehensive detection method based on a visual detection method according to claim 9, characterized in that: The specific method of step S5 is: detecting the ground inclination angle according to the inclination sensor; performing gravity center offset correction with the load cell in cooperation with the inclination sensor, and calculating the gravity center correction compensation angle of the camber angle, toe angle, kingpin castor angle, and kingpin inclination angle; detecting the wheel posture parameters of the camber angle, toe angle, kingpin castor angle, and kingpin inclination angle in a static state according to visual detection; performing angle correction compensation on the wheel posture parameters in a static state according to the ground inclination angle and the gravity center correction compensation angle, and obtaining accurate wheel alignment parameters.

Images