Calibration-object identification method and apparatus, and electronic device and storage medium

Abstract

Provided in the embodiments of the present application are a calibration-object identification method and apparatus, and an electronic device and a storage medium. The method comprises: acquiring a captured image of a plurality of calibration balls that is captured in a direction to be determined; on the basis of three-dimensional coordinates of the calibration balls, projecting the plurality of calibration balls onto a plane corresponding to said direction, and determining two-dimensional coordinates, on the plane, of spherical areas corresponding to the plurality of calibration balls; on the basis of the two-dimensional coordinates, determining circle-center coordinates of each spherical area on the plane; on the basis of circle-center coordinates corresponding to three spherical areas in the captured image which are sequentially adjacent to each other, determining first included-angle data corresponding to the captured image, and acquiring second included-angle data corresponding to target template data in each direction; and on the basis of the first included-angle data and the second included-angle data, determining a target direction, so as to determine, on the basis of the target direction, the serial number of each calibration ball. Therefore, two-dimensional coordinates and serial numbers of calibration balls can be more accurately determined.

Description

Calibration object identification method, device, electronic device and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on February 28, 2024, with application number 202410217707.1 and invention name “Calibration object identification method, device, electronic device and storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application belongs to the technical field of vehicle four-wheel alignment systems, and in particular relates to a calibration object recognition method, device, electronic device and storage medium. Background Art

[0003] The non-contact vehicle four-wheel alignment system is mainly used to detect the alignment parameters of vehicle wheels, such as the relative position and angle between the wheels, and compare them with the original design parameters to determine the wheel alignment parameters, and then guide maintenance personnel to adjust the vehicle wheel alignment parameters to meet the vehicle design requirements, achieve the smoothness and safety of vehicle driving, and reduce vehicle fuel consumption and tire wear. When performing wheel alignment, it is necessary to uniformly construct the coordinate system of the wheel four-wheel alignment system. Establishing the coordinate system of the four-wheel alignment system requires determining the two-dimensional coordinates and serial number of the calibration ball (3D ball) of the marking unit in the non-contact vehicle four-wheel alignment system. The two-dimensional coordinates and serial numbers determined in the existing technology have the problem of low accuracy, which affects the positioning effect of the non-contact vehicle four-wheel alignment system. Technical issues

[0004] In response to the above problems, embodiments of the present application provide a calibration object recognition method, device, electronic device, and storage medium, which can more accurately determine the two-dimensional coordinates and serial number of the calibration sphere. Technical Solutions

[0005] The present invention provides a method for identifying a calibration object, the method comprising:

[0006] Acquire images of a plurality of calibration spheres taken in the direction to be determined;

[0007] Projecting the plurality of calibration spheres onto a plane corresponding to the direction to be determined based on the three-dimensional coordinates of the calibration spheres, and determining the two-dimensional coordinates of spherical regions corresponding to the plurality of calibration spheres on the plane;

[0008] Determine the coordinates of the center of each spherical area on the plane based on the two-dimensional coordinates;

[0009] Determining first angle data corresponding to the captured image based on the center coordinates of three spherical areas sequentially adjacent to each other in the captured image, and obtaining second angle data corresponding to target template data in various directions;

[0010] A target direction is determined based on the first angle data and the second angle data, so as to determine the serial numbers of the calibration spheres based on the target direction.

[0011] In some embodiments, the first angle data includes: an angle value and an angle direction, and the three sequentially adjacent spherical regions include: a first spherical region, a second spherical region, and a third spherical region. Determining the first angle data corresponding to the captured image based on the center coordinates corresponding to the three sequentially adjacent spherical regions in the captured image includes:

[0012] Connecting the coordinates of the center of the first spherical region and the coordinates of the center of the second spherical region to obtain a first straight line segment;

[0013] Connecting the coordinates of the center of the second spherical region with the coordinates of the center of the third spherical region to obtain a second straight line segment;

[0014] Determine the angle between the first straight line segment and the second straight line segment to obtain angle values ​​corresponding to three consecutively adjacent spherical regions;

[0015] Extending the first straight line segment toward the third spherical region to obtain a third straight line segment;

[0016] determining a vertical relationship between the third straight line segment and the second straight line segment;

[0017] The angle directions corresponding to the three consecutively adjacent spherical regions are determined based on the upper and lower relationships.

[0018] In some embodiments, determining the angle directions corresponding to three sequentially adjacent spherical regions based on the upper and lower relationship includes:

[0019] In a case where the upper-lower relationship is that the third straight line segment is above the second straight line segment, determining the angle direction corresponding to three consecutively adjacent spherical regions as a first direction;

[0020] In the case where the upper and lower relationship is that the third straight line segment is below the second straight line segment, the angle direction corresponding to three consecutively adjacent spherical areas is determined to be the second direction.

[0021] In some embodiments, determining the target direction based on the first angle data and the second angle data includes:

[0022] Comparing each of the angle directions with the corresponding angle directions in the target template data in each direction in sequence;

[0023] When the current angle direction is the same as the corresponding angle direction in the target template data for each direction, add a first preset score to the current score for each direction to obtain a first score value, determine an angle difference between the current angle value and the corresponding angle value in the target template data for each direction, and change the first score value based on a score corresponding to a range of the angle difference to obtain a total score corresponding to each direction;

[0024] When the current angle direction is different from the corresponding angle direction in the target template data of each direction, the current score of each direction is subtracted from the first preset score to obtain a second score value to obtain the total score corresponding to each direction;

[0025] The target direction is determined based on the total scores corresponding to each direction.

[0026] In some embodiments, obtaining the second angle data corresponding to the target template data in each direction includes:

[0027] sorting the spherical regions based on the coordinates of the circle center to obtain sorted spherical regions;

[0028] Determine the distance between two adjacent spherical areas based on the center coordinates of the circle;

[0029] determining whether there is a missing calibration sphere based on the number corresponding to the distance;

[0030] If it is determined that the calibration sphere is missing, determining the number of missing calibration spheres based on the number corresponding to the distance, and determining the missing calibration sphere based on the missing number and the distance;

[0031] Modify the spherical area in the initial template data corresponding to each direction based on the missing calibration sphere to obtain the target template data;

[0032] The second angle data corresponding to the target template data is determined based on the center coordinates of each spherical area in the target template data.

[0033] In some embodiments, determining the missing calibration sphere based on the missing quantity and the distance includes:

[0034] If there is at least one missing sphere and the difference between the target distance corresponding to the missing sphere and the distance other than the target distance is greater than a preset threshold and less than 2 times of the distance, it is determined that there is a missing calibration sphere at the position corresponding to the target distance;

[0035] If there is at least one missing sphere and the difference between the target distance corresponding to the missing sphere and the distance other than the target distance is greater than 2 times the distance, it is determined that at least two calibration spheres are missing at the position corresponding to the target distance;

[0036] The modifying of the spherical regions in the initial template data corresponding to each direction based on the missing calibration sphere includes: deleting the spherical regions at positions corresponding to the target distances in the initial template data.

[0037] In some embodiments, determining the missing calibration sphere based on the missing quantity and the distance includes:

[0038] If the number of missing spheres is at least two and the difference between the target distance and a distance other than the target distance is greater than a preset threshold and less than 2 times the distance, it is determined that a calibration sphere is missing at the position corresponding to the target distance, and it is determined that a calibration sphere is missing at at least one of the two ends of the sorting;

[0039] If the number of missing calibration spheres is at least two and the difference between the target distance and the distance other than the first target distance is greater than twice the distance, determine that at least two calibration spheres are missing at the position corresponding to the second target distance, determine whether the number of missing calibration spheres at the position corresponding to the target distance reaches the missing number, and if it does not reach the missing number, determine that at least one of the two ends of the sorting has a missing calibration sphere;

[0040] The modifying of the spherical areas in the template data corresponding to each direction based on the missing calibration sphere includes: deleting the spherical areas at the positions corresponding to the target distance in the initial template data, and deleting the spherical areas at both ends of the initial template data.

[0041] In some embodiments, determining the missing calibration sphere based on the missing quantity and the distance includes:

[0042] When the number of missing points is at least one and the difference between the non-target distance and the distance other than the target distance is greater than a preset threshold, determining that the calibration sphere is missing at least one of the two ends of the sorting;

[0043] The modifying of the spherical regions in the template data corresponding to each direction based on the missing calibration sphere includes: deleting the spherical regions at both ends of the template data.

[0044] In some embodiments, the first angle data includes: a first angle value, the second angle data includes: a second angle value, and determining the target direction based on the first angle data and the second angle data includes:

[0045] Calculating the Euclidean distance between the first angle value and the second angle value to obtain a calculated value;

[0046] The direction corresponding to the target template data corresponding to the minimum calculated value is determined as the target direction.

[0047] The present invention provides a device for identifying a calibration object, including:

[0048] A first acquisition module is used to acquire images of a plurality of calibration spheres taken in a direction to be determined;

[0049] a first determining module, configured to project the plurality of calibration spheres onto a plane corresponding to the direction to be determined based on the three-dimensional coordinates of the calibration spheres, and determine the two-dimensional coordinates of spherical regions corresponding to the plurality of calibration spheres on the plane;

[0050] a second determining module, configured to determine the coordinates of the center of each spherical area on the plane based on the two-dimensional coordinates;

[0051] a third determining module, configured to determine first angle data corresponding to the captured image based on the center coordinates of three spherical regions sequentially adjacent to each other in the captured image, and obtain second angle data corresponding to the target template data in each direction;

[0052] The fourth determination module is configured to determine a target direction based on the first angle data and the second angle data, so as to determine a sequence number of each calibration sphere based on the target direction.

[0053] An embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned calibration object identification methods when executing the computer program.

[0054] An embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any of the above-mentioned calibration object recognition methods is implemented.

[0055] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the electronic device executes any one of the above methods.

[0056] The embodiments of the present application provide a calibration object recognition method, device, electronic device and storage medium, which obtain captured images of multiple calibration spheres captured from a direction to be determined; project the multiple calibration spheres onto a plane corresponding to the direction to be determined based on the three-dimensional coordinates of the calibration spheres, and determine the two-dimensional coordinates of the spherical areas corresponding to the multiple calibration spheres on the plane; determine the center coordinates of each spherical area on the plane based on the two-dimensional coordinates; determine first angle data corresponding to the captured image based on the center coordinates corresponding to three adjacent spherical areas in the captured image, and obtain second angle data corresponding to target template data in each direction; determine the target direction based on the first angle data and the second angle data, and determine the serial number of each calibration sphere based on the target direction, so as to more accurately determine the two-dimensional coordinates and serial number of the calibration sphere. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Hereinafter, the present application will be described in more detail based on embodiments with reference to the accompanying drawings.

[0058] FIG1 is a schematic diagram of a non-contact vehicle four-wheel alignment system provided in an embodiment of the present application;

[0059] FIG2 is a schematic diagram of a calibration sphere in a calibration unit provided in an embodiment of the present application;

[0060] FIG3 is a schematic diagram of an implementation flow of a calibration object recognition method provided by the present application;

[0061] FIG4 is a schematic diagram of first angle data determined according to an embodiment of the present application;

[0062] FIG5 is a schematic diagram of a distance of a spherical area provided in an embodiment of the present application;

[0063] FIG6 is a schematic diagram of a missing calibration sphere provided in an embodiment of the present application;

[0064] FIG7 is a schematic diagram of a sorting process provided by an embodiment of the present application in which a calibration ball is missing in the middle and a calibration ball is missing at the left end;

[0065] FIG8 is a schematic diagram of a method according to an embodiment of the present application in which at least one of the two ends has a missing calibration ball;

[0066] FIG9 is a schematic diagram of a method of sorting provided in an embodiment of the present application in which a calibration sphere is missing at at least one end;

[0067] FIG10 is a schematic structural diagram of a calibration object recognition device provided in an embodiment of the present application;

[0068] FIG11 is a schematic diagram of the composition structure of an electronic device provided in an embodiment of the present application.

[0069] In the drawings, like components are given like reference numerals, and the drawings are not drawn to scale. Modes for Carrying Out the Invention

[0070] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0071] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0072] If similar descriptions of "first\second\third" appear in the application documents, the following explanation will be added. In the following description, the terms "first\second\third" are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0073] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0074] Based on the problems existing in the related art, the embodiments of the present application provide a calibration object recognition method that can be applied to electronic devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). The embodiments of the present application do not impose any restrictions on the specific types of electronic devices. The calibration object can be a calibration object in a calibration unit in a non-contact vehicle four-wheel alignment system. The calibration object in the calibration unit in the non-contact vehicle four-wheel alignment system is a 3D ball. The non-contact vehicle four-wheel alignment system includes: 4 measurement units and 6 calibration units. FIG1 is a schematic diagram of a non-contact vehicle four-wheel alignment system provided in an embodiment of the present application. As shown in FIG1 , 1, 3, 6, and 8 are measurement units, 2, 4, 5, 7, 9, and 10 are calibration units. 1 and 2 share a computing platform, 3 and 4 share a computing platform, 5 and 6 share a computing platform, and 7 and 8 share a computing platform. Calibration units 9 and 10 include calibration balls, the coordinates of which are known, and the positional relationship between the corresponding calibration balls and the corresponding cameras is known. The measurement unit can be a camera. Calibration unit 1 can be considered to be on the left side of calibration ball 9, and calibration unit 6 is on the right side of calibration unit 9. FIG2 is a schematic diagram of a calibration ball in a calibration unit provided in an embodiment of the present application. As shown in FIG2 , 9 calibration balls are usually included in the calibration unit. The photographed image of the calibration sphere may be acquired by the measuring unit, so that the two-dimensional coordinates and serial number of the calibration sphere may be determined through the image.

[0075] The functions implemented by the calibration object identification method provided in the embodiment of the present application can be implemented by calling program codes by a processor of an electronic device, wherein the program codes can be stored in a computer storage medium.

[0076] The present application provides a calibration object recognition method. FIG3 is a schematic diagram of an implementation flow of a calibration object recognition method provided by the present application. As shown in FIG3 , the method includes:

[0077] Step S101: Acquire an image of the calibration sphere taken in a direction to be determined.

[0078] In an embodiment of the present application, the direction to be determined can be one or more of the forward direction, left side, and right side of the calibration unit. Taking the three directions as an example, taking the calibration unit 9 as an example, the measuring unit 1 can collect the captured image of the calibration sphere of the calibration unit 9, or the measuring unit in the direction of the calibration unit 10 can collect the captured image of the calibration sphere of the calibration unit 9, and the measuring unit No. 6 can be used to collect the captured image of the calibration sphere of the calibration unit 9.

[0079] In an embodiment of the present application, the electronic device can be connected to the measuring unit for communication and obtain a captured image of the calibration sphere from the measuring unit.

[0080] Step S102 : projecting the calibration sphere onto a plane corresponding to the direction to be determined based on the three-dimensional coordinates of the calibration sphere, and determining the two-dimensional coordinates of the spherical area corresponding to the calibration sphere on the plane.

[0081] In an embodiment of the present application, the calibration sphere can be projected onto the plane corresponding to the direction to be determined by means of a projection transformation. The projection transformation can be implemented through linear algebra and geometry. For example, a projection matrix can be used to convert three-dimensional coordinates into two-dimensional coordinates, and the three-dimensional coordinates can be multiplied by an appropriate matrix to obtain the two-dimensional coordinates.

[0082] In the embodiment of the present application, after the calibration sphere is projected, the corresponding projection is a spherical area.

[0083] For example, taking the direction to be determined as the forward direction, left side, and right side of the calibration unit as an example, the two-dimensional coordinates corresponding to the three planes can be obtained.

[0084] Step S103: determining the center coordinates of each spherical area on the plane based on the two-dimensional coordinates.

[0085] In the embodiment of the present application, a sphere can be obtained by fitting the two-dimensional coordinates of part of the spherical region, thereby obtaining a spherical region, and then the center point of the sphere is determined, so that the center point is the center coordinate of each spherical region in the plane.

[0086] In the embodiment of the present application, the spherical area is obtained by fitting, so that the coordinates of the center of the circle can be determined even if part of the spherical area is not identified.

[0087] Step S104 : determining first angle data corresponding to the captured image based on the center coordinates of three adjacent spherical regions in the captured image, and obtaining second angle data corresponding to the target template data in each direction.

[0088] In the embodiment of the present application, the first angle data may include: an angle value and / or an angle direction.

[0089] In an embodiment of the present application, three spherical areas adjacent in sequence may include: a first spherical area, a second spherical area, and a third spherical area. A first straight line segment can be obtained by connecting the center coordinates of the first spherical area with the center coordinates of the second spherical area; a second straight line segment can be obtained by connecting the center coordinates of the second spherical area with the center coordinates of the third spherical area; and the angle between the first straight line segment and the second straight line segment can be determined to obtain the angle values ​​corresponding to the three spherical areas adjacent in sequence. In this way, the corresponding first angle data in the captured image can be obtained. Figure 4 is a schematic diagram of a determined first angle data provided by an embodiment of the present application. As shown in Figure 4, 7 angle values ​​can be obtained for 9 spherical areas. In Figure 4, the solid line is a line connecting the centers of 2 spherical areas. The two adjacent connecting straight lines form an angle, thereby obtaining the angle value of the angle.

[0090] In an embodiment of the present application, the first straight line segment can be extended toward the third spherical area to obtain a third straight line segment; the up-down relationship between the third straight line segment and the second straight line segment is determined; and based on the up-down relationship, the angle directions corresponding to the three adjacent spherical areas are determined.

[0091] Continuing to refer to FIG4 , the third straight line segment is represented by a dotted line, and the angle direction can be determined by determining the upper and lower parts of the straight line segment corresponding to the dotted line.

[0092] In an embodiment of the present application, when the upper and lower relationship is that the third straight line segment is above the second straight line segment, the angle direction corresponding to the three adjacent spherical areas is determined to be the first direction; when the upper and lower relationship is that the third straight line segment is below the second straight line segment, the angle direction corresponding to the three adjacent spherical areas is determined to be the second direction.

[0093] In the embodiment of the present application, the first direction and the second direction can be represented by numerical values. For example, the first direction can be represented by 1 and the second direction can be represented by 0.

[0094] Following the example in FIG4 , the angle direction corresponding to the captured image can be expressed as: 0100100.

[0095] In an embodiment of the present application, the same method can be used to obtain the second angle data corresponding to the target template data in each direction. The target template data can be obtained by modifying the initial template data, which includes images of the spherical areas of all spheres. In an embodiment of the present application, different directions correspond to different viewing angles and different images of their spherical areas. When modifying, the initial template data can be modified based on whether the calibration sphere is missing, thereby obtaining the target template data. For example, if it is determined that a calibration sphere is missing, the spherical area corresponding to the calibration sphere in the initial template data is deleted, thereby obtaining the target template data.

[0096] In the embodiment of the present application, the initial template data can consist of three groups, corresponding to the template data corresponding to the forward direction, the left side, and the right side respectively.

[0097] Step S105: determining a target direction based on the first angle data and the second angle data, so as to determine a sequence number of each calibration sphere based on the target direction.

[0098] In an embodiment of the present application, the first angle data may be matched with the second angle data, and the direction corresponding to the matched second angle data may be determined as the target direction.

[0099] Exemplarily, if the first angle data matches the target template data corresponding to the forward direction, the forward direction may be determined as the target direction.

[0100] In the embodiment of the present application, after the target direction is determined, the serial numbers of the calibration balls can be determined, for example, the serial numbers of the calibration balls can be determined in order from left to right.

[0101] An embodiment of the present application provides a calibration object recognition method, which obtains a captured image of the calibration sphere captured from a direction to be determined; projects the calibration sphere onto a plane corresponding to the direction to be determined based on the three-dimensional coordinates of the calibration sphere, and determines the two-dimensional coordinates of the spherical area corresponding to the calibration sphere in the plane; determines the center coordinates of each spherical area in the plane based on the two-dimensional coordinates; determines first angle data corresponding to the captured image based on the center coordinates corresponding to three adjacent spherical areas in the captured image, and obtains second angle data corresponding to target template data in each direction; determines the target direction based on the first angle data and the second angle data, and determines the serial number of each calibration sphere based on the target direction, so as to more accurately determine the two-dimensional coordinates and serial number of the calibration sphere.

[0102] In some embodiments, step S105 may be implemented by the following steps:

[0103] Step S1051 , sequentially comparing each of the angle directions with the corresponding angle directions in the target template data of each direction.

[0104] In an embodiment of the present application, the angle direction and the corresponding angle direction in the target template data in each direction can be converted into a vector, and the comparison is performed by calculating the dot product and modulus of the vector.

[0105] Step S1052, when the current angle direction is the same as the corresponding angle direction in the target template data of each direction, add the current score of each direction to a first preset score to obtain a first score value, and determine the angle difference between the current angle value and the corresponding angle value in the target template data of each direction, and change the first score value based on the score corresponding to the range of the angle difference to obtain the total score corresponding to each direction.

[0106] In the embodiment of the present application, the current angle direction can be any angle direction being compared. The first preset score can be configured, and for example, can be configured to be 2 points.

[0107] The current score may be a score determined during the calculation process. If the current angle direction is the same as the corresponding angle direction in the target template data in each direction, the current score may be increased by 2 points to reach the first score value.

[0108] In an embodiment of the present application, if the directions are the same, it is necessary to determine the angle difference between the current angle value and the corresponding angle value in the target template data in each direction. Different angle differences can correspond to different scores. The angle difference can include: a first angle difference and a second angle difference. The first angle difference can correspond to adding a first score, and the second angle difference can correspond to adding a second score. The first angle difference can be smaller than the second angle difference, and the first score is greater than the second score.

[0109] Exemplarily, the first angle difference can be 0 to 10°, and the first score corresponds to plus 2 points. The second angle difference can correspond to 10 to 15°, and the second score can correspond to plus 1 point. In some embodiments, it can also include: the third angle difference corresponds to the third score. Exemplarily, the third angle difference is: 15 to 30°, and the corresponding third score is minus 1 point. In some embodiments, it can also include: the fourth angle difference corresponds to the fourth score. The fourth angle difference can be above 30°, and the fourth score is minus 2 points.

[0110] In the embodiment of the present application, the total score corresponding to the target template data in each direction, that is, the total score corresponding to each direction, can be obtained by sequential calculation.

[0111] Step S1053, when the current angle direction is different from the corresponding angle direction in the target template data of each direction, the current score of each direction is subtracted from the first preset score to obtain a second score value to obtain the total score corresponding to each direction.

[0112] Continuing with the above example, you can subtract 2 points from the current score to get the total score corresponding to each direction.

[0113] Step S1054: determining the target direction based on the total scores corresponding to the various directions.

[0114] In the embodiment of the present application, the direction corresponding to the largest total score may be determined as the target direction.

[0115] The method provided in the embodiment of the present application can accurately calculate the scores corresponding to each direction by adopting a voting mechanism, thereby accurately determining the direction.

[0116] In some embodiments, some of the marking balls may not be recognized. In this case, the marking balls may be considered missing.

[0117] In some embodiments, determining the second angle data corresponding to the target template data in each direction may be achieved by the following steps:

[0118] Step S1041 : sorting the spherical regions based on the circle center coordinates to obtain sorted spherical regions.

[0119] In the embodiment of the present application, the spherical regions may be sorted from left to right based on the coordinates of the circle center, thereby obtaining sorted spherical regions.

[0120] Step S1042: determining the distance between two adjacent spherical areas based on the circle center coordinates.

[0121] In an embodiment of the present application, the distance between two adjacent spherical areas can be determined based on the center coordinates of the two adjacent spherical areas. Figure 5 is a schematic diagram of the distance between spherical areas provided in an embodiment of the present application. As shown in Figure 5, if there are 9 balls, there are 8 corresponding distances.

[0122] Step S1043: Determine whether any calibration sphere is missing based on the number corresponding to the distance.

[0123] In the embodiment of the present application, the number of distances can be counted to obtain the corresponding quantity.

[0124] In the embodiment of the present application, whether the calibration sphere is missing can be determined by comparing the preset number and the number corresponding to the distance.

[0125] The preset number can be the number of distances between the corresponding spherical areas when the calibration ball is not missing. The preset number and the number corresponding to the distance can be compared to determine whether the calibration ball is missing.

[0126] Step S1044: When it is determined that the calibration sphere is missing, the number of missing calibration spheres is determined based on the number corresponding to the distance, and the missing calibration sphere is determined based on the missing number and the distance.

[0127] Step S1045 : modifying the spherical regions in the initial template data corresponding to each direction based on the missing calibration sphere to obtain target template data.

[0128] In the embodiment of the present application, a common modification may be deletion.

[0129] Step S1046: determining the second angle data corresponding to the target template data based on the center coordinates of each spherical area in the target template data.

[0130] In the embodiment of the present application, the second angle data may include: an angle value and / or an angle direction. The method for determining the second angle data may refer to the method for determining the first angle data.

[0131] In some embodiments, step S1044, determining the missing calibration spheres based on the missing quantity and the distance may be implemented in the following manner:

[0132] When there is at least one missing number and the difference between the target distance corresponding to the missing number and the distance other than the target distance is greater than a preset threshold and less than 2 times of the distance, it is determined that there is a calibration sphere missing at the position corresponding to the target distance.

[0133] In an embodiment of the present application, at least one can be one. When the number of missing items is at least one and the difference between the target distance corresponding to the number of missing items and the distance other than the target distance is greater than a preset threshold and less than 2 times of the distance, it can be considered that a calibration sphere is missing in the middle segment of the sorting. Figure 6 is a schematic diagram of a missing calibration sphere provided in an embodiment of the present application, as shown in Figure 6.

[0134] When there is at least one missing number and the difference between the target distance corresponding to the missing number and the distance other than the target distance is greater than 2 times the distance, it is determined that at least 2 calibration spheres are missing at the position corresponding to the target distance.

[0135] In the embodiment of the present application, it can be considered that there are at least two calibration balls missing in the middle position of the sorting.

[0136] At this time, step S1045, the modification of the spherical area in the initial template data corresponding to each direction based on the missing calibration sphere can be achieved in the following manner:

[0137] The spherical area at the position corresponding to the target distance in the initial template data is deleted.

[0138] In some embodiments, step S1044, determining the missing calibration spheres based on the missing quantity and the distance, can be implemented by the following steps:

[0139] When the number of missing points is at least two and the difference between the target distance and the distance other than the target distance is greater than a preset threshold and less than 2 times of the distance, it is determined that a calibration sphere is missing at the position corresponding to the target distance, and it is determined that a calibration sphere is missing at at least one of the two ends of the sorting.

[0140] FIG7 is a schematic diagram of a sorting method provided by an embodiment of the present application in which a calibration ball is missing in the middle and a calibration ball is missing at the left end, as shown in FIG7 .

[0141] When the number of missing balls is at least two and the difference between the target distance and the distance other than the target distance is greater than 2 times of the distance, determine that at least two calibration balls are missing at the position corresponding to the target distance, and determine whether the number of missing calibration balls at the position corresponding to the target distance reaches the missing number. If the missing number is not reached, determine that a calibration ball is missing at at least one of the two ends of the sorting.

[0142] FIG8 is a schematic diagram of an embodiment of the present application in which two calibration balls are missing in the middle of an arrangement and a calibration ball is missing at at least one of the two ends. As shown in FIG8 , one calibration ball is missing at the left end.

[0143] At this time, step S1045, the spherical area in the template data corresponding to each direction is modified based on the missing calibration sphere, including: deleting the spherical area at the position corresponding to the target distance in the initial template data, and deleting the spherical areas at both ends of the initial template data.

[0144] In some embodiments, step S1044, determining the missing calibration spheres based on the missing quantity and the distance, may include:

[0145] When the number of missing spheres is at least one and the difference between the target-absent distance and the distance other than the target distance is greater than a preset threshold, it is determined that the calibration sphere is missing at least at one of the two ends of the sorting.

[0146] FIG9 is a schematic diagram of a method of sorting provided in an embodiment of the present application in which a calibration sphere is missing at at least one end, as shown in FIG9 .

[0147] At this time, step S1045 of modifying the spherical regions in the template data corresponding to each direction based on the missing calibration sphere includes: deleting the spherical regions at both ends of the template data.

[0148] The method provided in the embodiment of the present application determines the position of the missing calibration sphere and then modifies the initial template data, thereby being able to identify the serial number of the calibration sphere even when the calibration sphere is missing.

[0149] In some embodiments, the first angle data includes: a first angle value, the second angle data includes: a second angle value, and determining the target direction based on the first angle data and the second angle data includes: calculating the Euclidean distance between the first angle value and the second angle value to obtain a calculated value; and determining the direction corresponding to the target template data corresponding to the minimum calculated value as the target direction.

[0150] In the embodiment of the present application, the first angle value and the second angle value are represented as vectors. The Euclidean distance between the two vectors is calculated to obtain a calculated value. The direction corresponding to the target template data corresponding to the minimum calculated value is found and determined as the target direction.

[0151] Based on the foregoing embodiments, an embodiment of the present application provides a calibration object identification device, wherein the modules included in the device and the units included in each module can be implemented by a processor in a computer device; of course, they can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0152] The present application provides a calibration object recognition device. FIG10 is a schematic diagram of the structure of a calibration object recognition device provided in the present application. As shown in FIG10 , the calibration object recognition device 1000 includes:

[0153] A first acquisition module 1001 is configured to acquire images of a plurality of calibration spheres taken in a direction to be determined;

[0154] A first determining module 1002 is configured to project the plurality of calibration spheres onto a plane corresponding to the direction to be determined based on the three-dimensional coordinates of the calibration spheres, and determine the two-dimensional coordinates of spherical regions corresponding to the plurality of calibration spheres on the plane;

[0155] A second determining module 1003 is configured to determine the coordinates of the center of each spherical area on the plane based on the two-dimensional coordinates;

[0156] A third determining module 1004 is configured to determine first angle data corresponding to the captured image based on the center coordinates of three adjacent spherical regions in the captured image, and obtain second angle data corresponding to the target template data in each direction;

[0157] The fourth determining module 1005 is configured to determine a target direction based on the first angle data and the second angle data, so as to determine a sequence number of each calibration sphere based on the target direction.

[0158] In some embodiments, the first angle data includes: an angle value and an angle direction; the three adjacent spherical areas include: a first spherical area, a second spherical area, and a third spherical area; and the third determination module includes:

[0159] a first connecting unit, configured to connect the coordinates of the center of the first spherical region with the coordinates of the center of the second spherical region to obtain a first straight line segment;

[0160] a second connecting unit, configured to connect the center coordinates of the second spherical region with the center coordinates of the third spherical region to obtain a second straight line segment;

[0161] a first determining unit, configured to determine an angle between the first straight line segment and the second straight line segment to obtain angle values ​​corresponding to three consecutively adjacent spherical regions;

[0162] a first extending unit, configured to extend the first straight line segment toward the third spherical region to obtain a third straight line segment;

[0163] a second determining unit, configured to determine a vertical relationship between the third straight line segment and the second straight line segment;

[0164] The third determining unit is configured to determine the angle directions corresponding to three sequentially adjacent spherical regions based on the upper and lower relationship.

[0165] In some embodiments, the third determining unit includes:

[0166] a first determining subunit, configured to determine, when the upper-lower relationship is that the third straight line segment is above the second straight line segment, that the included angle direction corresponding to three consecutively adjacent spherical regions is a first direction;

[0167] The second determining subunit is configured to determine, when the upper and lower relationship is that the third straight line segment is below the second straight line segment, that the included angle direction corresponding to three consecutively adjacent spherical regions is the second direction.

[0168] In some embodiments, the fourth determining module includes:

[0169] a comparing unit, configured to sequentially compare each of the angle directions with the corresponding angle directions in the target template data of each direction;

[0170] a first scoring unit, configured to, when a current angle direction is the same as a corresponding angle direction in the target template data for each direction, add a first preset score to a current score for each direction to obtain a first score value, determine an angle difference between the current angle value and the corresponding angle value in the target template data for each direction, and change the first score value based on a score corresponding to a range of the angle difference to obtain a total score corresponding to each direction;

[0171] A second obtaining unit is configured to, when the current angle direction is different from the corresponding angle direction in the target template data of each direction, subtract the first preset score from the current score of each direction to obtain a second score value, so as to obtain a total score corresponding to each direction;

[0172] The fourth determining unit is configured to determine the target direction based on the total scores corresponding to the directions.

[0173] In some embodiments, the third determining module further includes:

[0174] a sorting unit, configured to sort the spherical regions based on the coordinates of the circle center to obtain sorted spherical regions;

[0175] a fifth determining unit, configured to determine a distance between two adjacent spherical areas based on the circle center coordinates;

[0176] a sixth determining unit, configured to determine whether a calibration sphere is missing based on the number corresponding to the distance;

[0177] a seventh determining unit, configured to, if it is determined that the calibration sphere is missing, determine the number of missing calibration spheres based on the number corresponding to the distance, and determine the missing calibration sphere based on the missing number and the distance;

[0178] The modification unit is used to modify the spherical area in the initial template data corresponding to each direction based on the missing calibration sphere to obtain the target template data.

[0179] An eighth determining unit is configured to determine second angle data corresponding to the target template data based on the center coordinates of each spherical area in the target template data.

[0180] In some embodiments, the seventh determining unit includes:

[0181] a first determining subunit, configured to determine that a calibration sphere is missing at a position corresponding to the target distance when the number of missing spheres is at least one and the difference between the target distances corresponding to the number of missing spheres and the distances other than the target distances is greater than a preset threshold and less than 2 times the distance;

[0182] a second determining subunit, configured to determine that at least two calibration spheres are missing at a position corresponding to the target distance when the number of missing spheres is at least one and the difference between the target distances corresponding to the number of missing spheres and the distances other than the target distances is greater than twice the distance;

[0183] The modifying unit includes: a first modifying subunit, configured to delete the spherical area at a position corresponding to the target distance in the initial template data.

[0184] In some embodiments, the seventh determining unit includes:

[0185] a third determining subunit, configured to determine that a calibration sphere is missing at a position corresponding to the target distance if the number of missing spheres is at least two and the difference between the target distance and a distance other than the target distance is greater than a preset threshold and less than twice the distance, and to determine that a calibration sphere is missing at at least one of the two ends of the sorting;

[0186] a fourth determining subunit, configured to, if the number of missing calibration spheres is at least two and the difference between the target distance and a distance other than the target distance is greater than twice the distance, determine that at least two calibration spheres are missing from the position corresponding to the target distance, determine whether the number of missing calibration spheres from the position corresponding to the target distance reaches the missing number, and if the number of missing calibration spheres has not reached the missing number, determine that at least one of the two ends of the sorting is missing;

[0187] The modifying unit includes: a second modifying subunit, configured to delete the spherical area at the position corresponding to the target distance in the initial template data, and delete the spherical areas at both ends of the initial template data.

[0188] In some embodiments, the seventh determining unit includes:

[0189] a fifth determining subunit, configured to determine that a calibration sphere is missing from at least one of the two ends of the sorting when the number of missing spheres is at least one and when a difference between the non-target distance and the distance other than the target distance is greater than a preset threshold;

[0190] The modifying unit includes: a third modifying subunit, configured to delete the spherical areas at both ends of the template data.

[0191] In some embodiments, the first angle data includes: a first angle value, the second angle data includes: a second angle value, and the fourth determination module includes:

[0192] a calculating unit, configured to calculate a Euclidean distance between the first angle value and the second angle value to obtain a calculated value;

[0193] The ninth determining unit is configured to determine the direction corresponding to the target template data corresponding to the minimum calculated value as the target direction.

[0194] An embodiment of the present application provides an electronic device. FIG11 is a schematic diagram of the composition structure of the electronic device provided in the embodiment of the present application. As shown in FIG11 , the electronic device 500 includes: a processor 501, at least one communication bus 502, a user interface 503, at least one external communication interface 504, and a memory 505. The communication bus 502 is configured to implement connection and communication between these components. The user interface 503 may include a display screen, and the external communication interface 504 may include a standard wired interface and a wireless interface. The processor 501 is configured to execute the program of the calibration object recognition method stored in the memory to implement the steps in the calibration object recognition method provided in the above embodiment.

[0195] In the embodiments of the present application, if the above-mentioned calibration object identification method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0196] Accordingly, an embodiment of the present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the calibration object identification method provided in the above embodiment are implemented.

[0197] An embodiment of the present application further provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes any one of the calibration object recognition methods described above.

[0198] The description of the above electronic device and storage medium embodiments is similar to the description of the above method embodiments and has similar beneficial effects as the method embodiments. For technical details not disclosed in the computer device and storage medium embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0199] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0200] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0201] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0202] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0203] In addition, all functional units in the embodiments of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the above-mentioned integrated units can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0204] Those skilled in the art will understand that all or part of the steps of the above-mentioned method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROMs), magnetic disks, optical disks, and other media that can store program codes.

[0205] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a controller to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks or optical disks.

[0206] The above is merely an embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A calibration object recognition method, characterized in that: The method comprises: Acquire images of a plurality of calibration spheres taken in the direction to be determined; Projecting the plurality of calibration spheres onto a plane corresponding to the direction to be determined based on the three-dimensional coordinates of the calibration spheres, and determining the two-dimensional coordinates of spherical regions corresponding to the plurality of calibration spheres on the plane; Determine the coordinates of the center of each spherical area on the plane based on the two-dimensional coordinates; Determining first angle data corresponding to the captured image based on the center coordinates of three spherical areas sequentially adjacent to each other in the captured image, and obtaining second angle data corresponding to target template data in various directions; A target direction is determined based on the first angle data and the second angle data, so as to determine the serial numbers of the calibration spheres based on the target direction.

2. The method according to claim 1, characterized in that The first angle data includes: an angle value and an angle direction, and the three sequentially adjacent spherical areas include: a first spherical area, a second spherical area, and a third spherical area. Determining the first angle data corresponding to the captured image based on the center coordinates corresponding to the three sequentially adjacent spherical areas in the captured image includes: Connecting the coordinates of the center of the first spherical region and the coordinates of the center of the second spherical region to obtain a first straight line segment; Connecting the coordinates of the center of the second spherical region with the coordinates of the center of the third spherical region to obtain a second straight line segment; Determine the angle between the first straight line segment and the second straight line segment to obtain angle values ​​corresponding to three consecutively adjacent spherical regions; Extending the first straight line segment toward the third spherical region to obtain a third straight line segment; determining a vertical relationship between the third straight line segment and the second straight line segment; The angle directions corresponding to the three consecutively adjacent spherical regions are determined based on the upper and lower relationships.

3. The method according to claim 2, characterized in that The determining of the angle directions corresponding to the three sequentially adjacent spherical regions based on the upper and lower relationship includes: In a case where the upper-lower relationship is that the third straight line segment is above the second straight line segment, determining the angle direction corresponding to three consecutively adjacent spherical regions as a first direction; In the case where the upper and lower relationship is that the third straight line segment is below the second straight line segment, the angle direction corresponding to three consecutively adjacent spherical areas is determined to be the second direction.

4. The method according to claim 3, characterized in that The determining the target direction based on the first angle data and the second angle data includes: Comparing each of the angle directions with the corresponding angle directions in the target template data in each direction in sequence; When the current angle direction is the same as the corresponding angle direction in the target template data for each direction, add a first preset score to the current score for each direction to obtain a first score value, determine an angle difference between the current angle value and the corresponding angle value in the target template data for each direction, and change the first score value based on a score corresponding to a range of the angle difference to obtain a total score corresponding to each direction; When the current angle direction is different from the corresponding angle direction in the target template data of each direction, the current score of each direction is subtracted from the first preset score to obtain a second score value to obtain the total score corresponding to each direction; The target direction is determined based on the total scores corresponding to each direction.

5. The method according to claim 1, wherein The obtaining of the second angle data corresponding to the target template data in each direction includes: sorting the spherical regions based on the coordinates of the circle center to obtain sorted spherical regions; Determine the distance between two adjacent spherical areas based on the circle center coordinates; determining whether there is a missing calibration sphere based on the number corresponding to the distance; If it is determined that the calibration sphere is missing, determining the number of missing calibration spheres based on the number corresponding to the distance, and determining the missing calibration sphere based on the missing number and the distance; Modify the spherical area in the initial template data corresponding to each direction based on the missing calibration sphere to obtain the target template data; The second angle data corresponding to the target template data is determined based on the center coordinates of each spherical area in the target template data.

6. The method according to claim 5, characterized in that The determining of the missing calibration sphere based on the missing quantity and the distance includes: If there is at least one missing sphere and the difference between the target distance corresponding to the missing sphere and the distance other than the target distance is greater than a preset threshold and less than 2 times of the distance, it is determined that there is a missing calibration sphere at the position corresponding to the target distance; If there is at least one missing sphere and the difference between the target distance corresponding to the missing sphere and the distance other than the target distance is greater than 2 times the distance, it is determined that at least two calibration spheres are missing at the position corresponding to the target distance; The modifying of the spherical regions in the initial template data corresponding to each direction based on the missing calibration sphere includes: deleting the spherical regions at positions corresponding to the target distances in the initial template data.

7. The method according to claim 5, characterized in that The determining of the missing calibration sphere based on the missing quantity and the distance includes: If the number of missing spheres is at least two and the difference between the target distance and a distance other than the target distance is greater than a preset threshold and less than 2 times the distance, it is determined that a calibration sphere is missing at the position corresponding to the target distance, and it is determined that a calibration sphere is missing at at least one of the two ends of the sorting; If the number of missing calibration spheres is at least two and the difference between the target distance and the distance other than the target distance is greater than 2 times the distance, determine that at least two calibration spheres are missing at the position corresponding to the target distance, determine whether the number of missing calibration spheres at the position corresponding to the target distance reaches the missing number, and if it does not reach the missing number, determine that at least one of the two ends of the sorting has a missing calibration sphere; The modifying of the spherical areas in the template data corresponding to each direction based on the missing calibration sphere includes: deleting the spherical areas at the positions corresponding to the target distance in the initial template data, and deleting the spherical areas at both ends of the initial template data.

8. The method according to claim 5, characterized in that The determining of the missing calibration sphere based on the missing quantity and the distance includes: When the number of missing points is at least one and the difference between the non-target distance and the distance other than the target distance is greater than a preset threshold, determining that the calibration sphere is missing at least one of the two ends of the sorting; The modifying of the spherical regions in the template data corresponding to each direction based on the missing calibration sphere includes: deleting the spherical regions at both ends of the template data.

9. The method according to any one of claims 6 to 8, characterized in that The first angle data includes: a first angle value, the second angle data includes: a second angle value, and determining the target direction based on the first angle data and the second angle data includes: Calculating the Euclidean distance between the first angle value and the second angle value to obtain a calculated value; The direction corresponding to the target template data corresponding to the minimum calculated value is determined as the target direction.

10. A calibration object recognition device, characterized in that: include: A first acquisition module is used to acquire images of a plurality of calibration spheres taken in a direction to be determined; a first determining module, configured to project the plurality of calibration spheres onto a plane corresponding to the direction to be determined based on the three-dimensional coordinates of the calibration spheres, and determine the two-dimensional coordinates of spherical regions corresponding to the plurality of calibration spheres on the plane; a second determining module, configured to determine the coordinates of the center of each spherical area on the plane based on the two-dimensional coordinates; a third determining module, configured to determine first angle data corresponding to the captured image based on the center coordinates of three spherical regions sequentially adjacent to each other in the captured image, and obtain second angle data corresponding to the target template data in each direction; The fourth determination module is configured to determine a target direction based on the first angle data and the second angle data, so as to determine a sequence number of each calibration sphere based on the target direction.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images