Product measurement methods, devices, equipment and media

Abstract

This invention discloses a product measurement method, apparatus, device, and medium, relating to the fields of machine vision and industrial automation inspection. The method includes: determining the current image coordinates from a current image acquired by an image acquisition device; determining first physical coordinates based on the correlation between the image coordinates of pre-calibrated calibration points and the physical coordinates of each calibration point; determining auxiliary points and auxiliary physical coordinates based on the correlation between the current point position, pre-calibrated candidate points, and candidate physical coordinates of the center of the field of view in the image acquisition device; and linearly moving the auxiliary points and auxiliary physical coordinates, a reference point, and the reference physical coordinates of the center of the field of view at the reference point, along with the first physical coordinates, to obtain the second physical coordinates of the target position. This technical solution solves the error caused by image distortion from a large-field-of-view lens, enabling accurate measurement of the dimensions of large-size automotive glass.

Description

Technical Field

[0001] This invention relates to the field of machine vision and industrial automation inspection, specifically to a product measurement method, apparatus, equipment, and medium. Background Technology

[0002] Currently, a new round of technological revolution and industrial transformation is flourishing globally. The automotive industry is rapidly integrating with technologies in energy, transportation, and information and communication, with electrification, connectivity, and intelligence becoming the development trend of the automotive industry. In the process of transforming new energy vehicles into intelligent terminals, the front display panel, as the primary gateway for human interaction, is becoming increasingly larger and more diverse in shape, with some reaching 1.5 meters in length and exhibiting various irregular forms.

[0003] During product manufacturing, full-process dimensional management is required. Traditional 3D measuring machines have low measurement efficiency and high requirements for the measurement environment, making them unsuitable for the mass production requirements of automotive glass and limiting them to sampling and measurement equipment. Summary of the Invention

[0004] This invention provides a product measurement method, apparatus, equipment, and medium. By correcting distortion in wide-field-of-view lens images and resolving installation and motion errors of the motion mechanism through motion calibration, the measurement accuracy of large-size automotive glass is ensured.

[0005] In a first aspect, embodiments of the present invention provide a product measurement method, comprising:

[0006] When the motion mechanism is in its current position, acquire the current image of the target product captured by the image acquisition device on the motion mechanism, and determine the current image coordinates of the target position in the target product based on the current image;

[0007] Based on the current image coordinates and the pre-calibrated motion mechanism in the reference position state, the first physical coordinates of the target position in the reference position state are determined.

[0008] Based on the current position and the correlation between the candidate positions of the pre-calibrated motion mechanism and the candidate physical coordinates of the center of the field of view in the image acquisition device, determine each auxiliary position in the current position interval to which the current position belongs and each auxiliary physical coordinate of the center of the field of view in each auxiliary position state;

[0009] Based on each auxiliary point and each auxiliary physical coordinate of the center of the field of view in each auxiliary point state, the reference point and the reference physical coordinate of the center of the field of view in the reference point state, and the first physical coordinate of the target position in the reference point state, the second physical coordinate of the target position in the current point state is obtained by linearly moving the reference point and the reference physical coordinate of the target position in the current point state.

[0010] Secondly, embodiments of the present invention also provide a product measuring device, comprising:

[0011] The current image coordinate determination module is used to acquire the current image of the target product captured by the image acquisition device on the motion mechanism when the motion mechanism is in the current position state, and determine the current image coordinates of the target position in the target product based on the current image;

[0012] The first physical coordinate determination module is used to determine the first physical coordinates of the target position in the reference position state based on the current image coordinates and the correlation between the image coordinates and physical coordinates of each calibration point on the calibration board when the motion mechanism is in the reference position state.

[0013] The auxiliary physical coordinate determination module is used to determine each auxiliary point in the current point interval to which the current point belongs and each auxiliary physical coordinate of the center of the field of view in each auxiliary point state, based on the current point position and the correlation between each candidate point of the pre-calibrated motion mechanism and the candidate physical coordinate of the center of the field of view in the image acquisition device.

[0014] The second physical coordinate determination module is used to linearly move based on each auxiliary point and each auxiliary physical coordinate of the center of the field of view in each auxiliary point state, the reference point and the reference physical coordinate of the center of the field of view in the reference point state, and the first physical coordinate of the target position in the reference point state, to obtain the second physical coordinate of the target position in the current point state.

[0015] Thirdly, embodiments of the present invention also provide an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the product measurement method as described in any of the embodiments of the present invention.

[0016] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the product measurement method as described in any of the embodiments of the present invention.

[0017] This invention ensures the measurement accuracy of large-size automotive glass by correcting distortion in wide-field-of-view lens images and addressing installation and motion errors of the motion mechanism through motion calibration. Attached Figure Description

[0018] Figure 1 This is a flowchart of a product measurement method provided according to an embodiment of the present invention;

[0019] Figure 2This is a design diagram of the vehicle-mounted glass lighting path used in the embodiments of the present invention;

[0020] Figure 3 This is a design drawing of the calibration board used in the embodiments of the present invention;

[0021] Figure 4 This is a flowchart of a product measurement method provided according to an embodiment of the present invention;

[0022] Figure 5 This is a structural block diagram of a product measuring device according to an embodiment of the present invention;

[0023] Figure 6 This is a structural block diagram of an electronic device provided according to an embodiment of the present invention. Detailed Implementation

[0024] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0025] Furthermore, it should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of data and other data involved in the technical solution of this invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0026] Figure 1 This is a flowchart of a product measurement method according to an embodiment of the present invention. This method is applicable to situations involving product dimensional measurement, particularly for measuring the dimensions of large-size automotive glass. The method of this embodiment can meet the requirements for dimensional measurement of automotive glass and improve the accuracy of measuring large-size automotive glass. This method can be executed by the product measurement device provided in this embodiment, which can be implemented using software and / or hardware. The device can be an electronic device with computing capabilities. The method specifically includes the following steps:

[0027] S110. When the motion mechanism is in its current position, acquire the current image of the target product captured by the image acquisition device on the motion mechanism, and determine the current image coordinates of the target position in the target product based on the current image.

[0028] Among them, the motion mechanism is a high-precision XY motion mechanism; the current point is the position coordinate of the motion mechanism; the image acquisition device is a camera that captures the target product, preferably a wide-field-of-view lens camera; the target product is the vehicle glass to be measured; the current image is the image acquired by the wide-field-of-view lens camera taking a picture of the vehicle glass to be measured; the target position is any position information in the acquired image.

[0029] Specifically, after the vehicle glass to be measured is placed on the platform, the system controls the platform to move to the set initial measurement position. At the current initial measurement position, the large-field-of-view camera takes pictures of the vehicle glass to be measured to obtain the corresponding image information, and determines the image coordinates of a target position based on the image information.

[0030] Preferably, to better complete product measurement, the target position in this embodiment of the invention can be a right-angled glass edge, such as PL. i (x k y k (i = 1, 2; k = 0, 1); and further obtain the current motion mechanism point coordinates Pt. cur (x ptd y ptd ).

[0031] Understandably, a high-precision XY motion mechanism is used to ensure accurate product positioning; a high-precision camera is used to measure product features to ensure accurate dimensional measurement; a wide-field-of-view camera is used to reduce measurement time and improve efficiency; and the dimensional measurement of automotive glass can be completed in a single photograph.

[0032] Optionally, before determining the current image coordinates of the target location within the target product, the process may include illuminating the vehicle's glass. For example... Figure 2 As shown, in this embodiment of the invention, before measuring the size of a large-size automotive glass, a highly uniform linear side surface light is used as the light source to illuminate the large-size automotive glass. Specifically:

[0033] Using highly uniform linear side surface light as the light source, the light source is reflected through a silver-plated reflective module. The vehicle glass to be measured is placed on a platform constructed of highly transparent optical glass, and the light is turned on to illuminate the vehicle glass.

[0034] Understandably, by using highly uniform linear side surface light as the light source, light from different directions is eliminated, preventing uneven brightness and excessive edge transition pixels in different areas caused by lighting, which would seriously affect the measurement and recognition accuracy under a large field of view lens, and effectively avoiding measurement errors caused by lighting on large-size automotive glass.

[0035] S120. Based on the current image coordinates and the pre-calibrated motion mechanism in the reference position state, determine the first physical coordinates of the target position in the reference position state.

[0036] Among them, the reference point state is the initial point state; the relationship between the image coordinates and the physical coordinates of each calibration point on the calibration board is the relationship between the image coordinates and the physical coordinates on the calibration board, which can be converted by the corresponding transformation matrix; the first physical coordinate is the physical coordinate on the calibration board corresponding to the current image coordinate in the reference point state.

[0037] Specifically, by establishing the correlation between the image coordinates and physical coordinates of each calibration point on the calibration plate, based on the pre-calibrated motion mechanism being in a reference position state, the image coordinates are converted into physical coordinates corresponding to the reference position state. Preferably, the acquired current image coordinates PL i (x k y k ), converted to the first physical coordinate QTmp on the calibration plate coordinate system. i (x tk y tk ).

[0038] Optionally, determining the first physical coordinates of the target position in the reference point state based on the current image coordinates and the pre-calibrated relationship between the image coordinates and physical coordinates of each calibration point on the calibration plate when the motion mechanism is in the reference point state includes:

[0039] S121. Based on the current image coordinates and the image coordinates of each calibration point on the calibration board when the pre-calibrated motion mechanism is in the reference position state, determine the image coordinates of the four calibration points closest to the current image coordinates, and obtain the physical coordinates of the four calibration points.

[0040] In this system, the pre-calibrated motion mechanism is in a reference position state, and the image coordinates of each calibration point on the calibration plate are the pre-constructed image coordinates of the circular feature points corresponding to the circular feature points in the calibration plate.

[0041] Specifically, since the pre-calibrated motion mechanism is in the reference position state, the image coordinates of each calibration point on the calibration plate are all located at the center of the circular feature point of the calibration plate. However, the current image coordinates may not be located at the center point coordinates of the graphic feature point. Therefore, the image coordinates of the four calibration points closest to the current image coordinates are obtained, and the physical coordinates on the corresponding calibration plate are further obtained.

[0042] Optionally, the image coordinates of each calibration point on the calibration board and the corresponding physical coordinates on the calibration board can be obtained in the following way:

[0043] The preferred calibration plate is a circular calibration plate with a QR code checkerboard pattern, such as... Figure 3 As shown, it is placed on a platform, ensuring that the calibration board is positioned under a wide-view lens camera, so that the coordinate systems of both are aligned, and that the features of the calibration board are clearly visible and cover the effective ROIs in the field of view.

[0044] Specifically, when the motion mechanism moves to the reference point, the center coordinates of all circular feature points identified within the effective ROI are calculated; the circular feature points are sorted from left to right and top to bottom according to the camera coordinate system, and then the physical coordinates of the calibration board's physical center point corresponding to the QR code information in the circle are identified in the sorted order; the image coordinates P of the center point of the circular feature points are then calculated. c (x, y) and the corresponding coordinates of the center Q of the circular feature point on the calibration plate m (x, y) correspond one-to-one, and the image coordinates P of the center point of the circular feature points are arranged row by row. c (x, y) are stored in a two-dimensional array P of the image of the center point of the circular feature points. cn [Y][X] represents the physical coordinates of the center point Q of the calibration board. m (x, y) are stored in the physical two-dimensional array Q, which represents the center point of the circular feature point on the calibration board. mn [Y][X] in.

[0045] For example, the center point image two-dimensional array P is obtained by looking up a table. cn Retrieve the row and column indices of the four points closest to the current image coordinates from [Y][X]; for example, write the row indices into the array Y in ascending order of distance. c [j] and column index array X c [j], using array Y c [j] and X c [j] Search for the value P in the center point image two-dimensional array and the center point physical two-dimensional array respectively. c (x, y) and Q m (x, y), arrange P in order c Write the x, y, and 1 of (x, y) into matrices TP[j][0], TP[j][1], and TP[j][2] respectively, and then write Q... m The x and y values ​​of (x, y) are written into matrices TQ[j][0] and TQ[j][1], respectively.

[0046] S122. Based on the image coordinates and physical coordinates of the four calibration points, determine the transformation matrix of the target position under the reference point state.

[0047] The transformation matrix of the target position under the reference point state can be obtained based on the image coordinates and physical coordinates corresponding to the four calibration points.

[0048] For example, based on the TP and TQ obtained above, the transformation matrix T between the image coordinate system and the calibration plate coordinate system is calculated using the following formula:

[0049]

[0050] S123. The transformation matrix is ​​used to transform the current image coordinates to obtain the first physical coordinates of the target position under the reference point state.

[0051] Then, by combining the transformation matrix T obtained above, matrix transformation can be performed on the current image coordinates to calculate the first physical coordinates of the current image coordinates in the calibration plate coordinate system.

[0052] Understandably, wide-field-of-view (ROI) cameras exhibit greater distortion compared to narrow-field-of-view images due to mounting and lens inherent limitations. Measurement errors caused by this distortion must be considered when performing dimensional measurements. However, in sufficiently small areas, image distortion is negligible. Therefore, dividing the effective region of interest (ROI) into several small regions using a checkerboard calibration board and performing a coordinate system transformation between the image coordinates and the calibration board coordinates can effectively resolve the measurement error problem caused by image distortion from wide-field-of-view camera cameras.

[0053] S130. Based on the current position and the correlation between the candidate positions of the pre-calibrated motion mechanism and the candidate physical coordinates of the center of vision in the image acquisition device, determine each auxiliary position in the current position interval to which the current position belongs and each auxiliary physical coordinate of the center of vision in each auxiliary position state.

[0054] Among them, the relationship between the candidate points of the pre-calibrated motion mechanism and the candidate physical coordinates of the field of view center in the image acquisition device is the relationship between the candidate points of the motion mechanism and the candidate physical coordinates of the field of view center of the large field of view lens camera; the current point interval is the motion interval in which the current motion mechanism is located at the current point; the auxiliary point is the coordinate point of the motion mechanism within the motion interval in which the current motion mechanism is located; and each auxiliary physical coordinate is the physical coordinate of the field of view center corresponding to the coordinate point of the current motion mechanism.

[0055] By determining the current position of the motion mechanism, its motion range in the X and Y directions is found in the two-dimensional array of the motion mechanism. Based on the motion range, the corresponding auxiliary position is found. Furthermore, the auxiliary physical coordinates of the center of the field of view under the current auxiliary position state are determined by the correlation between the candidate positions of the motion mechanism and the candidate physical coordinates of the center of the field of view in the image acquisition device.

[0056] For example, based on the current position Pt of the motion mechanism cur (x ptd y ptd ), from the two-dimensional array PT of the motion mechanism Axis [N+1][M+1] Determine the corresponding motion interval number in the X and Y directions, and then extract the auxiliary points PT of the motion mechanism within the corresponding interval. Axis [Y][X], and obtain the corresponding auxiliary physical coordinates PT of the field of view center from the correlation between each candidate point of the pre-calibrated motion mechanism and the candidate physical coordinates of the field of view center in the image acquisition device. center [Y][X].

[0057] Understandably, given the possible logical errors, values ​​are taken from smallest to largest within the motion range, the maximum value is removed, and the minimum value is retained to complete the auxiliary physical coordinate calculation of the center of the field of view, thereby reducing the amount of computation while ensuring accuracy.

[0058] S140. Based on each auxiliary point and each auxiliary physical coordinate of the center of the field of view in each auxiliary point state, the reference point and the reference physical coordinate of the center of the field of view in the reference point state, and the first physical coordinate of the target position in the reference point state, perform linear movement to obtain the second physical coordinate of the target position in the current point state.

[0059] The second physical coordinate is the actual position of the target location on the calibration plate coordinate system under the reference position state of the motion mechanism.

[0060] Based on each auxiliary point and the auxiliary physical coordinates of the center of the field of view in each auxiliary point state, obtain the verticality error caused by the installation of the motion mechanism; based on the reference point and the reference physical coordinates of the center of the field of view in the reference point state, and the first physical coordinate, perform linear movement to obtain the actual position of the target position in the reference point state of the motion mechanism.

[0061] Optionally, after determining the second physical coordinates of the target position under the current location status, a product reference coordinate system is further constructed so that the dimensions of the vehicle glass to be measured can be measured through the product reference coordinate system.

[0062] Three second physical coordinates are obtained to determine the right-angled glass edge segments L1 and L2 corresponding to the calibration plate coordinate system. Based on the point-line calculation formula, the intersection point LX(x, y) of the two line segments is obtained. Simultaneously, with L1 as the direction and the intersection point LX(x, y) as the origin, the product reference coordinate system XY0 is constructed. It should be noted that the specific construction calculation formula can use existing coordinate system construction methods, and this invention does not impose specific limitations on it.

[0063] Furthermore, the required measurement points of the vehicle glass to be measured are transformed to their positions on the product's reference coordinate system XY0 for measurement; it should be noted that this includes, but is not limited to, the image coordinates P corresponding to line segments, convex points, concave points, circles, and contour points. m (x m y m ), using the obtained P m (x m y m The transformation matrix of the vicinity is used to calculate the corresponding physical coordinates Q. m (x m y m (m represents the sequence number of the measured feature, m = 0, 1, 2, 3...).

[0064] Finally, calculations are performed on the items that need to be measured. It should be noted that this embodiment of the invention primarily uses point-to-line distances or point-to-point distances to measure and calculate each item.

[0065] The formula for calculating the distance from a point to a line is as follows:

[0066] Let P be the image coordinates obtained by the point motion mechanism that needs to be calculated. p (p x p y The coordinates of the first and last ends of the fitted line segment are L1 and L2 respectively. p1 (L x1 L y1 ), L p2 (L x2 L y2 ). Then calculate the term M1 i (i represents the sequence number of the item measured for this product, i = 1, 2, 3...).

[0067]

[0068] The formula for calculating the distance between points is as follows:

[0069] Let point 1 be P1(x1,y1) and point 2 be P2(x2,y2). Then the calculated term M2 i (i represents the sequence number of the item measured for this product, i = 1, 2, 3...).

[0070]

[0071] Optionally, after measuring the dimensions of the vehicle glass to be measured, the measurement results can be judged based on the set control requirements.

[0072] Specifically: the standard value of the control requirement is set as Si (i represents the serial number of the item measured for this product, i = 1, 2, 3…), the positive tolerance of the control requirement is set as Ui (i represents the serial number of the item measured for this product, i = 1, 2, 3…), and the negative tolerance of the control requirement is set as Di (i represents the serial number of the item measured for this product, i = 1, 2, 3…). Let M1 be the standard value of the control requirement. i and M2 i The collection is M i The product size is considered standard if the following conditions are met; otherwise, the product size is considered non-standard. The conditions are expressed by the following formula:

[0073]

[0074] Understandably, after calibrating and correcting the wide-view camera and motion mechanism, the back cover glass is placed on the loading platform for a photo measurement and identification calculation. Finally, according to the control requirements, it is determined whether the product meets the requirements and defective products are picked out, thereby improving the measurement efficiency of large-size automotive glass and further testing the dimensional standards of large-size automotive glass.

[0075] The technical solution of this invention involves, when the motion mechanism is in its current position state, acquiring the current image of the target product captured by the image acquisition device on the motion mechanism, and determining the current image coordinates of the target position in the target product based on the current image; determining the first physical coordinates of the target position in the reference position state based on the current image coordinates and the pre-calibrated correlation between the image coordinates and physical coordinates of each calibration point on the calibration plate when the motion mechanism is in a reference position state; and determining the auxiliary points in the current position interval to which the current position belongs and the candidate physical coordinates of the candidate points of the pre-calibrated motion mechanism and the center of the field of view in the image acquisition device based on the current position. The system uses auxiliary physical coordinates of the center of the field of view at auxiliary points. Based on these auxiliary points and their corresponding physical coordinates, the system uses reference points and their corresponding physical coordinates of the center of the field of view at reference points, as well as the first physical coordinates of the target position at the reference points, to perform a linear movement and obtain the second physical coordinates of the target position at the current point. This system solves the technical problem of inaccurate measurement of automotive glass dimensions due to errors in the camera and motion mechanism. By setting a calibration plate, it eliminates image distortion and measurement errors caused by the installation movement of the motion mechanism, further resolving the large field-of-view distortion problem. Furthermore, product measurement can be completed with a single photograph, reducing measurement time and improving measurement efficiency.

[0076] Optionally, the association between candidate points and candidate physical coordinates includes:

[0077] S131. Control the motion mechanism to move from the reference point with a step size of unit motion amount to obtain the candidate point.

[0078] Wherein, the unit motion amount is M and N parts of the effective motion range of the motion mechanism along the X and Y axes; the candidate point is the coordinate point of the motion mechanism corresponding to a motion point of the reference point along the X or Y axis with a unit motion amount.

[0079] Specifically, the position of the calibration plate on the platform is kept constant, and the effective motion range of the XY axis of the motion mechanism is [X a0 X an ] and [Y a0 Y an Divide the motion into M and N equal parts respectively, then the unit motion d in the X and Y axes is... x d y for:

[0080]

[0081] Control the motion mechanism from the reference point (X) a0 Y a0 First, move along the X-axis M times, with a unit motion amount of d. x Then move along the Y-axis once more, with a unit motion amount d y At the same time, the X-axis position is moved back to the initial X-axis position. a0 The position is determined, and the movement is repeated N times. At each movement point, the above operation is repeated to obtain a two-dimensional array P of the circular feature center points at each point. cnMN [Y][X] and the two-dimensional array Q of the physical coordinates of the calibration plate cnMN [Y][X] in.

[0082] S132. When the motion mechanism is in the state of the candidate point, obtain the candidate image coordinates of the center of the field of view in the image acquisition device on the motion mechanism.

[0083] Among them, the image coordinates of the field of view center point are the coordinates of the field of view center point of the wide field of view camera, which is a fixed coordinate point.

[0084] When the motion mechanism is at any point, the coordinates of the candidate image corresponding to the center point of the field of view of the wide-view camera are further obtained. Preferably, the current candidate point of the motion mechanism is set to PT. Axis (x pta y pta The candidate image coordinates PT are obtained as the center of the field of view in the wide-field-of-view image. center (x, y).

[0085] S133 determines the candidate physical coordinates of the center of the field of view based on the candidate image coordinates of the center of the field of view and the correlation between the image coordinates and physical coordinates of each calibration point on the calibration board when the motion mechanism is in the candidate position state, and obtains the correlation between the candidate position coordinates and the candidate physical coordinates.

[0086] Based on the pre-calibrated motion mechanism in the candidate position state, the candidate image coordinates of the center of the field of view are determined by the correlation between the image coordinates and physical coordinates of each calibration point on the calibration board. This process establishes the mapping relationship between the motion mechanism coordinate system and the calibration board coordinate system.

[0087] For example, the obtained candidate image coordinates PT of the field of view center are... center (x, y), using the pre-defined transformation relationship between image coordinates and calibration board, calculate the physical coordinates PT corresponding to the center of the field of view in the current candidate point state. center (x ptc y ptc ), sequentially assign PT points of each motion mechanism within the effective range of motion. Axis (x pta y pta Stored in a two-dimensional array PT of the motion mechanism Axis [N+1][M+1], corresponding to the auxiliary physical coordinates PT of the center of the field of view. center (x ptc y ptc Stored in the calibration board's two-dimensional array PT center [N+1][M+1].

[0088] It is understandable that by converting the coordinates of the motion mechanism into the physical coordinates corresponding to the center of the field of view, and then into the physical coordinates corresponding to the calibration plate, errors caused by the irregular movement of the motion mechanism are avoided. Based on the physical coordinates of the center of the field of view and the image coordinates, the physical coordinates corresponding to the motion mechanism and the physical coordinates corresponding to the calibration plate are correlated, avoiding installation errors caused by assembly during the motion of the motion mechanism, further reducing the amount of calculation, improving the calibration efficiency of the motion mechanism, and ensuring the accurate measurement of the vehicle glass in the future.

[0089] Figure 4 This is a flowchart of product measurement according to an embodiment of the present invention. Based on the above embodiments, this embodiment supplements the specific method for determining the second physical coordinates. It should be noted that for parts not detailed in this embodiment, please refer to the relevant descriptions in other embodiments. For example... Figure 4 As shown, the method includes:

[0090] S210. When the motion mechanism is in its current position, acquire the current image of the target product captured by the image acquisition device on the motion mechanism, and determine the current image coordinates of the target position in the target product based on the current image.

[0091] First, obtain the current image coordinates of the target location, denoted as PL. i (x k y k And further obtain the current position coordinates Pt of the motion mechanism. cur (x ptd y ptd ).

[0092] S220. Based on the current image coordinates and the pre-calibrated motion mechanism in the reference position state, the first physical coordinates of the target position are determined.

[0093] Based on the aforementioned pre-calibrated motion mechanism in the reference position state, the transformation matrix corresponding to the correlation between the image coordinates and physical coordinates of each calibration point on the calibration plate is used to calculate the image coordinates PL. i (x k y k The first physical coordinate QTmp of the calibration plate at the reference point is... i (x tk y tk ).

[0094] S230. Based on the current position and the correlation between the candidate positions of the pre-calibrated motion mechanism and the candidate physical coordinates of the center of vision in the image acquisition device, determine each auxiliary position in the current position interval to which the current position belongs and each auxiliary physical coordinate of the center of vision in each auxiliary position state.

[0095] Based on the pre-acquired and pre-calibrated correlation between each candidate point of the motion mechanism and the candidate physical coordinates of the field of view center in the image acquisition device, and based on the current point coordinates Pt of the motion mechanism... cur (x ptd y ptd From the two-dimensional array PT of the kinematic mechanism Axis Obtain the interval index x in the X and Y directions from [N+1][M+1]. t0 x t1 y t0 y t1 From the two-dimensional array PT of the motion mechanism Axis Extract the corresponding auxiliary points PT from [N+1][M+1]Axis [y t0 ][x t0 ](x a00 y a00 ), PT Axis [y t0 ][x t1 ](x a01 y a01 ) and PT Axis [y t1 ][x t0 ](x a10 y a10 From the calibration board's two-dimensional array PT center Extract the auxiliary physical coordinates PT of the center of vision under the state of each auxiliary point in [N+1][M+1]. center [y t0 ][x t0 ](x c00 y c00 ), PT center [y t0 ][x t1 ](x c01 y c01 ) and PT center [y t1 ][x t0 ](x c10 y c10 ).

[0096] S240. Based on the auxiliary physical coordinates of the center of vision at each auxiliary point, determine the distance between each auxiliary physical coordinate and the auxiliary point in the X and Y directions.

[0097] The distance between auxiliary points is PT of each auxiliary physical coordinate. center The distance length corresponding to the interval index in the X and Y directions. The specific calculation formula is as follows:

[0098]

[0099] S250. Based on each auxiliary physical coordinate and the distance between the auxiliary points, determine the projection of the components of the motion mechanism installation error in the X and Y directions.

[0100] Calculate the perpendicularity error caused by the installation of the motion mechanism, and obtain the projections XR1, XR2 and YR1, YR2 of the current auxiliary point coordinates in the XY direction. The specific calculation formula is as follows:

[0101]

[0102] Understandably, by calculating the auxiliary physical coordinates of the visual center corresponding to the point interval, the angular relationship can be further calculated to avoid verticality errors caused by the installation of the motion mechanism.

[0103] S260. Based on the current point position, the auxiliary point positions, and the distance between the auxiliary points in the X and Y directions, determine the distance components in the X and Y directions.

[0104] Based on the current location Pt of the sports institution cur (x ptd y ptd ), each auxiliary point PT Axis The components CX and CY of the current position of the motion mechanism relative to the image in the X and Y directions are calculated using [Y][X] and the distances D1 and D2 from auxiliary points. The specific calculation formula is as follows:

[0105]

[0106] S270. Based on the first physical coordinates of the target position, the distance components in the X and Y directions, the projection of the motion mechanism installation error components in the X and Y directions, and the reference physical coordinates of the center of the field of view in the reference position state, determine the second physical coordinates of the target position in the current position state.

[0107] The reference physical coordinates PT of the center of the field of view under the condition of finding the reference point position. center [0][0](x c0 y c0 ), set the first physical coordinates of the target location QTmp i (x tk y tk From the point range PT Axis [y t0 ][x t0 The physical coordinates of the center of the field of view corresponding to the reference point are linearly offset from the distance components of the first physical coordinates in the X and Y directions and the projection of the installation error of the motion mechanism in the X and Y directions, and the second physical coordinates of the target position are calculated.

[0108] Optionally, based on the first physical coordinates of the target position, the distance components in the X and Y directions, the projection of the motion mechanism installation error components in the X and Y directions, and the reference physical coordinates of the center of the field of view in the reference position state, the second physical coordinates of the target position in the current position state are determined, including:

[0109]

[0110] Among them, (x qk y qk (x) is the second physical coordinate;tk y tk ) represents the first physical coordinate; CX and CY represent the distance components of the motion mechanism in the X and Y directions; XR1, XR2, YR1, and YR2 represent the projections of the installation error of the motion mechanism in the X and Y directions; 9x c00 y c00 (x) represents the physical coordinates of the current point of the motion mechanism under the center of the field of view; c0 y c0 () represents the reference physical coordinates of the reference point below the center of the field of view.

[0111] The technical solution of this invention uses the two-dimensional array of the one-to-one correspondence between the large-view lens camera and the calibration plate obtained above, and further corrects the coordinate system of the motion mechanism to determine the association between the coordinate system of the motion mechanism and the coordinate system of the calibration plate, so as to improve the accuracy of dimensional measurement of large-size automotive glass by taking a picture, measuring, identifying and calculating at one time.

[0112] Figure 5 This is a structural block diagram of a product measuring device according to an embodiment of the present invention. The present invention is applicable to situations involving the measurement of product dimensions, particularly large-size automotive glass. It can meet the needs of measuring the dimensions of automotive glass and improve the accuracy of measuring large-size automotive glass through the method of the embodiments of the present invention. This device can be implemented using software and / or hardware, and can be implemented using electronic devices with computing capabilities. Figure 5 As shown, the product measuring device 300 includes a current image coordinate determination module 310, a first physical coordinate determination module 320, an auxiliary physical coordinate determination module 330, and a second physical coordinate determination module 340.

[0113] For example, the current image coordinate determination module 310 is used to acquire the current image of the target product captured by the image acquisition device on the motion mechanism when the motion mechanism is in the current position state, and determine the current image coordinates of the target position in the target product based on the current image;

[0114] The first physical coordinate determination module 320 is used to determine the first physical coordinates of the target position in the reference point state based on the current image coordinates and the correlation between the image coordinates and physical coordinates of each calibration point on the calibration board when the pre-calibrated motion mechanism is in the reference point state.

[0115] The auxiliary physical coordinate determination module 330 is used to determine each auxiliary point in the current point interval to which the current point belongs and each auxiliary physical coordinate of the center of the field of view in each auxiliary point state, based on the current point position and the correlation between each candidate point of the pre-calibrated motion mechanism and the candidate physical coordinate of the center of the field of view in the image acquisition device.

[0116] The second physical coordinate determination module 340 is used to linearly move based on each auxiliary point and each auxiliary physical coordinate of the center of the field of view in each auxiliary point state, the reference point and the reference physical coordinate of the center of the field of view in the reference point state, and the first physical coordinate of the target position in the reference point state, to obtain the second physical coordinate of the target position in the current point state.

[0117] The technical solution of this invention involves, when the motion mechanism is in its current position state, acquiring the current image of the target product captured by the image acquisition device on the motion mechanism, and determining the current image coordinates of the target position in the target product based on the current image; determining the first physical coordinates of the target position in the reference position state based on the current image coordinates and the pre-calibrated correlation between the image coordinates and physical coordinates of each calibration point on the calibration plate when the motion mechanism is in a reference position state; and determining the auxiliary points in the current position interval to which the current position belongs and the candidate physical coordinates of the candidate points of the pre-calibrated motion mechanism and the center of the field of view in the image acquisition device based on the current position. The system uses auxiliary physical coordinates of the center of the field of view at auxiliary points. Based on these auxiliary points and their corresponding physical coordinates, the system uses reference points and their corresponding physical coordinates of the center of the field of view at reference points, as well as the first physical coordinates of the target position at the reference points, to perform a linear movement and obtain the second physical coordinates of the target position at the current point. This system solves the technical problem of inaccurate measurement of automotive glass dimensions due to errors in the camera and motion mechanism. By setting a calibration plate, it eliminates image distortion and measurement errors caused by the installation movement of the motion mechanism, further resolving the large field-of-view distortion problem. Furthermore, product measurement can be completed with a single photograph, reducing measurement time and improving measurement efficiency.

[0118] Based on the above technical solutions, the device further includes an association generation module;

[0119] The association generation module is used to control the motion mechanism to move from a reference point with a step size of unit motion to obtain candidate points; when the motion mechanism is in the candidate point state, it obtains the candidate image coordinates of the center of the field of view in the image acquisition device on the motion mechanism; based on the candidate image coordinates of the center of the field of view, and the pre-calibrated association relationship between the image coordinates and physical coordinates of each calibration point on the calibration board when the motion mechanism is in the candidate point state, it determines the candidate physical coordinates of the center of the field of view in the candidate point state, and obtains the association relationship between the candidate point and the candidate physical coordinates.

[0120] Optionally, the first physical coordinate determination module 320 includes a physical coordinate determination unit, a transformation matrix determination unit, and a first physical coordinate determination unit:

[0121] The physical coordinate determination unit is used to determine the image coordinates of the four calibration points closest to the current image coordinates based on the current image coordinates and the image coordinates of each calibration point on the calibration board when the pre-calibrated motion mechanism is in the reference position state, and to obtain the physical coordinates of the four calibration points.

[0122] The transformation matrix determination unit is used to determine the transformation matrix of the target position under the reference point position state based on the image coordinates of the four calibration points and the physical coordinates of the four calibration points.

[0123] The first physical coordinate determination unit is used to transform the current image coordinates using the transformation matrix to obtain the first physical coordinates of the target position under the reference point state.

[0124] Optionally, the second physical coordinate determination module 340 includes a distance determination unit, a projection determination unit, a distance component determination unit, and a second physical coordinate determination unit:

[0125] The distance determination unit is used to determine the distance between each auxiliary physical coordinate in the X and Y directions based on each auxiliary physical coordinate of the center of the field of view in each auxiliary point position state.

[0126] The projection determination unit is used to determine the projection of the components of the motion mechanism installation error in the X and Y directions based on each auxiliary physical coordinate and the distance between the auxiliary points;

[0127] The distance component determination unit is used to determine the distance components in the X and Y directions based on the current point position, the distances between each auxiliary point position and each auxiliary physical coordinate in the X and Y directions.

[0128] The second physical coordinate determination unit is used to determine the second physical coordinates of the target position in the current position state based on the first physical coordinates of the target position, the distance components in the X and Y directions, the projection of the motion mechanism installation error components in the X and Y directions, and the reference physical coordinates of the center of the field of view in the reference position state.

[0129] Optionally, the second physical coordinate determination unit is specifically used for:

[0130]

[0131] Among them, (x qk y qk (x) is the second physical coordinate; tk y tk (x) represents the first physical coordinate; CX and CY represent the distance components of the motion mechanism in the X and Y directions; XR1, XR2, YR1, and YR2 represent the projections of the installation error of the motion mechanism onto the components in the X and Y directions; (x) c00 y c00 (x) represents the physical coordinates of the current point of the motion mechanism under the center of the field of view; c0 y c0 () represents the reference physical coordinates of the reference point below the center of the field of view.

[0132] The product measuring device provided in the embodiments of the present invention can execute the product measuring method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0133] According to embodiments of the present invention, the present invention also provides an electronic device and a readable storage medium.

[0134] Figure 6 This is a structural block diagram of an electronic device provided according to an embodiment of the present invention. Figure 6 A block diagram of an exemplary electronic device 12 suitable for implementing embodiments of the present invention is shown. Figure 6 The electronic device 12 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0135] like Figure 6 As shown, the electronic device 12 is represented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0136] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0137] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0138] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 6 Not shown; usually referred to as a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0139] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some set of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0140] Electronic device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the electronic device 12, and / or with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, electronic device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 6 As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18. It should be understood that, although... Figure 6 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0141] The processing unit 16 performs various functional applications and data processing by running at least one of the other programs among a plurality of programs stored in the system memory 28, such as implementing a product measurement method provided in an embodiment of the present invention.

[0142] This invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a product measurement method provided in any embodiment of this invention.

[0143] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A product measurement method, characterized in that, include: When the motion mechanism is in its current position, acquire the current image of the target product captured by the image acquisition device on the motion mechanism, and determine the current image coordinates of the target position in the target product based on the current image; Based on the current image coordinates and the pre-calibrated motion mechanism in the reference position state, the correlation between the image coordinates and physical coordinates of each calibration point on the calibration board is determined, and the first physical coordinates of the target position in the reference position state are determined; the reference position state is the initial position state; the first physical coordinates are the physical coordinates on the calibration board corresponding to the current image coordinates in the reference position state. Based on the current position and the correlation between the pre-calibrated candidate positions of the motion mechanism and the candidate physical coordinates of the field of view center in the image acquisition device, the auxiliary positions in the current position interval to which the current position belongs and the auxiliary physical coordinates of the field of view center in each auxiliary position state are determined; the candidate position is the coordinate point of the motion mechanism corresponding to a motion point of a unit motion along the X-axis or Y-axis of the reference position; the auxiliary position is found by searching the motion interval in the X and Y directions of the motion mechanism in the two-dimensional array of the motion mechanism based on the current position of the motion mechanism; Based on each auxiliary point and each auxiliary physical coordinate of the center of the field of view in each auxiliary point state, the reference point and the reference physical coordinate of the center of the field of view in the reference point state, and the first physical coordinate of the target position in the reference point state, a linear movement is performed to obtain the second physical coordinate of the target position in the current point state; the second physical coordinate is the actual position of the target position on the calibration plate coordinate system in the reference point state of the motion mechanism. This also includes: determining the candidate physical coordinates of the field of view center in the candidate point state based on the candidate image coordinates of the field of view center and the correlation between the image coordinates and physical coordinates of each calibration point on the calibration board when the motion mechanism is in the candidate point state, obtaining the candidate physical coordinates of each candidate point on the calibration board corresponding to each candidate point coordinate; and determining the correlation between the candidate point coordinates and the candidate physical coordinates.

2. The method according to claim 1, characterized in that, The step of determining the first physical coordinates of the target position in the reference position state based on the current image coordinates and the pre-calibrated relationship between the image coordinates and physical coordinates of each calibration point on the calibration board when the motion mechanism is in the reference position state includes: Based on the current image coordinates and the image coordinates of each calibration point on the calibration board when the pre-calibrated motion mechanism is in the reference position state, determine the image coordinates of the four calibration points closest to the current image coordinates, and obtain the physical coordinates of the four calibration points; Based on the image coordinates and physical coordinates of the four calibration points, determine the transformation matrix of the target position under the reference point position state; The transformation matrix is ​​used to transform the current image coordinates to obtain the first physical coordinates of the target position under the reference point state.

3. The method according to claim 1, characterized in that, The process of linearly moving the target position based on each auxiliary point and the auxiliary physical coordinates of the center of view in each auxiliary point state, the reference point and the reference physical coordinates of the center of view in the reference point state, and the first physical coordinates of the target position in the reference point state, to obtain the second physical coordinates of the target position in the current point state, includes: Based on the auxiliary physical coordinates of the center of vision at each auxiliary point, determine the distance between each auxiliary physical coordinate and the auxiliary point in the X and Y directions; Based on the auxiliary physical coordinates and the distances to the auxiliary points, determine the projections of the motion mechanism installation error components in the X and Y directions; Based on the current point, each of the auxiliary points, and the distances between the auxiliary points in the X and Y directions, determine the distance components in the X and Y directions; Based on the first physical coordinates of the target position, the distance components in the X and Y directions, the projection of the motion mechanism installation error components in the X and Y directions, and the reference physical coordinates of the center of the field of view in the reference position state, determine the second physical coordinates of the target position in the current position state.

4. The method according to claim 3, characterized in that, Based on the first physical coordinates of the target location, the distance components in the X and Y directions, the projections of the motion mechanism installation error components in the X and Y directions, and the reference physical coordinates of the center of the field of view in the reference point state, the second physical coordinates of the target location in the current point state are determined, including: ； in, The second physical coordinate; The first physical coordinate; and For the distance components of the motion mechanism in the X and Y directions; The projection of the components of the installation error of the motion mechanism in the X and Y directions; The physical coordinates of the current point of the motion mechanism under the center of the field of vision; The reference physical coordinates of the reference point are located at the center of the field of view.

5. A product measuring device, characterized in that, include: The current image coordinate determination module is used to acquire the current image of the target product captured by the image acquisition device on the motion mechanism when the motion mechanism is in the current position state, and determine the current image coordinates of the target position in the target product based on the current image; The first physical coordinate determination module is used to determine the first physical coordinate of the target position in the reference point state based on the current image coordinates and the pre-calibrated correlation between the image coordinates and physical coordinates of each calibration point on the calibration board when the motion mechanism is in the reference point state; the reference point state is the initial point state; the first physical coordinate is the physical coordinate on the calibration board corresponding to the current image coordinates in the reference point state. The auxiliary physical coordinate determination module is used to determine, based on the current point position and the correlation between the candidate points of the pre-calibrated motion mechanism and the candidate physical coordinates of the center of the field of view in the image acquisition device, each auxiliary point in the current point position interval to which the current point position belongs and each auxiliary physical coordinate of the center of the field of view in each auxiliary point position state; the candidate point position is the coordinate point of the motion mechanism corresponding to a motion point position that moves a unit amount of motion along the X-axis or Y-axis from the reference point position; the auxiliary point position is found by searching for the motion interval in the X and Y directions of the motion mechanism in the two-dimensional array of the motion mechanism based on the current point position of the motion mechanism. The second physical coordinate determination module is used to linearly move based on each auxiliary point and each auxiliary physical coordinate of the center of the field of view in each auxiliary point state, the reference point and the reference physical coordinate of the center of the field of view in the reference point state, and the first physical coordinate of the target position in the reference point state, to obtain the second physical coordinate of the target position in the current point state; the second physical coordinate is the actual position of the target position on the calibration plate coordinate system in the reference point state of the motion mechanism. This also includes: determining the candidate physical coordinates of the field of view center in the candidate point state based on the candidate image coordinates of the field of view center and the correlation between the image coordinates and physical coordinates of each calibration point on the calibration board when the motion mechanism is in the candidate point state, obtaining the candidate physical coordinates of each candidate point on the calibration board corresponding to each candidate point coordinate; and determining the correlation between the candidate point coordinates and the candidate physical coordinates.

6. The apparatus according to claim 5, wherein the first physical coordinate determination module comprises a physical coordinate determination unit, a transformation matrix determination unit, and a first physical coordinate determination unit: The physical coordinate determination unit is used to determine the image coordinates of the four calibration points closest to the current image coordinates based on the current image coordinates and the image coordinates of each calibration point on the calibration board when the pre-calibrated motion mechanism is in the reference position state, and to obtain the physical coordinates of the four calibration points. The transformation matrix determination unit is used to determine the transformation matrix of the target position under the reference point position state based on the image coordinates of the four calibration points and the physical coordinates of the four calibration points. The first physical coordinate determination unit is used to transform the current image coordinates using the transformation matrix to obtain the first physical coordinates of the target position under the reference point state.

7. The apparatus according to claim 5, wherein the second physical coordinate determination module comprises a distance determination unit, a projection determination unit, a distance component determination unit, and a second physical coordinate determination unit: The distance determination unit is used to determine the distance between each auxiliary physical coordinate in the X and Y directions based on the auxiliary physical coordinates of the center of the field of view in each auxiliary point position state. The projection determination unit is used to determine the projection of the components of the motion mechanism installation error in the X and Y directions based on each auxiliary physical coordinate and the distance between the auxiliary points; The distance component determination unit is used to determine the distance components in the X and Y directions based on the current point position, the distances between each auxiliary point position and each auxiliary physical coordinate in the X and Y directions. The second physical coordinate determination unit is used to determine the second physical coordinates of the target position in the current position state based on the first physical coordinates of the target position, the distance components in the X and Y directions, the projection of the motion mechanism installation error components in the X and Y directions, and the reference physical coordinates of the center of the field of view in the reference position state.

8. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the product measurement method as described in any one of claims 1-4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the product measurement method as described in any one of claims 1-4.

Images