A method and device for evaluating vehicle camera parameter calibration results
By setting up a projection device and a multi-camera system on the vehicle, the evaluation of camera parameter calibration results is automatically completed, and the limitations of relying on calibration plates and labor in the prior art are solved, the evaluation efficiency and accuracy are improved, and the efficiency without manual participation is achieved Evaluation of camera parameter calibration results.
Patent Information
- Application Number
- CN202010846468.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-08-20
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2040-08-20
AI Technical Summary
The existing evaluation methods for vehicle camera parameter calibration results require calibration plates and manual participation, which are highly restrictive, poorly applicable, and low evaluation efficiency.
By controlling the vehicle to be evaluated to move to the preset target position, the calibration evaluation image is output using the projection device, and automatic evaluation of the camera parameter calibration results is performed based on the image, including detecting the target projection position information, adjusting the vehicle body orientation, outputting the position adjustment reference image, and judging Clarity is obtained and the homogeneous coordinates of the target point are obtained by multiple camera devices for Euclidean distance calculation to evaluate the calibration results.
No calibration board and manual participation are required, which improves the evaluation efficiency and accuracy of camera parameter calibration results, is highly applicable, and can automatically complete the evaluation of camera parameter calibration results.
Smart Images

Figure CN111915606B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of machine vision detection, and more specifically, to a method and device for evaluating vehicle camera parameter calibration results. Background Art
[0002] At present, the camera device is the most important and commonly used device among the sensors used in autonomous vehicles. In actual use, the camera device needs to be calibrated in order to obtain accurate camera parameters, so that multiple camera devices can work together. After the camera parameters are calibrated, the calibration results of the camera parameters need to be evaluated to ensure the reliability of the data provided by the camera device. The existing evaluation method of the camera parameter calibration results usually places the vehicle to be evaluated in a specific calibration evaluation site and evaluates the calibration results through a calibration plate. At the same time, during the evaluation process, it is necessary to manually adjust the angle of the calibration plate multiple times to complete the evaluation of the camera parameter calibration results. It can be seen that the existing evaluation method of the camera parameter calibration results requires a calibration plate to complete the evaluation, the evaluation conditions are highly restrictive, the applicability is poor, and the evaluation efficiency is poor. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide a method and device for evaluating vehicle camera parameter calibration results, which can evaluate the camera parameter calibration results without a calibration board, has strong applicability, does not require manual participation, and is conducive to improving evaluation efficiency.
[0004] A first aspect of an embodiment of the present application provides a method for evaluating a vehicle camera parameter calibration result, comprising:
[0005] Controlling the vehicle to be evaluated to move to a preset target position, where there is a target projection position in front of the preset target position;
[0006] Outputting a calibration evaluation image at the target projection position by a projection device provided on the vehicle to be evaluated;
[0007] The camera parameter calibration result of the vehicle to be evaluated is evaluated according to the calibration evaluation image to obtain an evaluation result.
[0008] In the above implementation process, when evaluating the camera parameter calibration results, the vehicle to be evaluated is first controlled to move to a preset target position, in front of which there is a target projection position; then a calibration evaluation image is output at the target projection position through a projection device set on the vehicle to be evaluated; finally, the camera parameter calibration results of the vehicle to be evaluated are evaluated according to the calibration evaluation image to obtain an evaluation result. It can be seen that this method can evaluate the camera parameter calibration results without the need for a calibration plate, has strong applicability, does not require manual participation, and is conducive to improving evaluation efficiency.
[0009] Furthermore, after controlling the vehicle to be evaluated to move to a preset target position, the method further includes:
[0010] Detecting the position information of the target projection position;
[0011] The body orientation of the vehicle to be evaluated is adjusted according to the position information so that the body of the vehicle to be evaluated faces the target projection position.
[0012] In the above implementation process, after the vehicle reaches the preset target position, it is also necessary to adjust the body orientation of the vehicle to be evaluated so that it faces the target projection position, so that the calibrated evaluation image can be accurately projected at the target projection position, which is conducive to improving the accuracy of the evaluation.
[0013] Further, after adjusting the body orientation of the vehicle to be evaluated according to the position information, the method further includes:
[0014] Controlling a projection device provided on the vehicle to be evaluated to output a position adjustment reference image at the target projection position;
[0015] Acquire the target projection clarity of the position adjustment reference image at the target projection position;
[0016] Determining whether the target projection clarity is greater than a preset clarity threshold;
[0017] If not, the position of the vehicle to be evaluated is controlled to be adjusted according to the target projection clarity until the projection clarity corresponding to the adjusted position is greater than the preset clarity threshold.
[0018] In the above implementation process, before projecting the calibration evaluation image, it is also necessary to fine-tune the position of the vehicle to be evaluated so that the projected image is clearly visible, which is conducive to improving the accuracy of the evaluation.
[0019] Further, the step of evaluating the camera parameter calibration result of the vehicle to be evaluated according to the calibration evaluation image to obtain the evaluation result includes:
[0020] Acquiring first homogeneous coordinates of a plurality of target points in the calibration evaluation image through a first camera device disposed on the vehicle to be evaluated, and acquiring second homogeneous coordinates of the plurality of target points through a second camera device disposed on the vehicle to be evaluated;
[0021] Calculate the third homogeneous coordinates according to the pre-calculated coordinate transformation relationship and the first homogeneous coordinates;
[0022] Calculating the Euclidean distance between the third homogeneous coordinate and the second homogeneous coordinate;
[0023] The camera parameter calibration result of the vehicle to be evaluated is evaluated according to the Euclidean distance to obtain an evaluation result.
[0024] In the above implementation process, a first camera device and a second camera device are provided on the vehicle to be evaluated, and the projected calibration evaluation image includes multiple target points. When evaluating the camera parameter calibration result, the first homogeneous coordinates of each target point are first obtained by the first camera device, and the second homogeneous coordinates of each target point are obtained by the second camera device. Then, the first homogeneous coordinates are converted into third homogeneous coordinates according to a pre-calculated coordinate conversion relationship. Furthermore, the Euclidean distance between the third homogeneous coordinates and the second homogeneous coordinates is calculated. Finally, the camera parameter calibration result of the vehicle to be evaluated is evaluated according to the Euclidean distance to obtain an evaluation result.
[0025] Furthermore, the camera parameter calibration result of the vehicle to be evaluated is evaluated according to the Euclidean distance to obtain an evaluation result, including:
[0026] Calculate the distance average according to the Euclidean distance;
[0027] Determine whether the distance average is less than a preset threshold;
[0028] If yes, outputting an evaluation result indicating that the camera parameter calibration result is qualified;
[0029] If not, an evaluation result indicating that the camera parameter calibration result is unqualified is output, and the vehicle to be evaluated is controlled to re-execute the calibration operation for the first camera device and the second camera device.
[0030] In the above implementation process, when evaluating the camera parameter calibration result of the vehicle to be evaluated according to the Euclidean distance, first calculate the distance average of all Euclidean distances, and then determine whether the distance average is less than a preset threshold. If it is less than, it means that the camera parameter calibration result is qualified. If it is not less than, it means that the camera parameter calibration result is unqualified, and then obtain the corresponding evaluation result. When the camera parameter calibration result is unqualified, the vehicle to be evaluated can also be controlled to recalibrate the camera parameters of the first camera device and the second camera device.
[0031] A second aspect of an embodiment of the present application provides a device for evaluating a vehicle camera parameter calibration result, the device comprising:
[0032] A control module, used for controlling the vehicle to be evaluated to move to a preset target position, where there is a target projection position in front of the preset target position;
[0033] A projection output module, used for outputting a calibration evaluation image at the target projection position through a projection device provided on the vehicle to be evaluated;
[0034] The evaluation module is used to evaluate the camera parameter calibration result of the vehicle to be evaluated according to the calibration evaluation image to obtain an evaluation result.
[0035] In the above implementation process, when evaluating the camera parameter calibration results, the control module first controls the vehicle to be evaluated to move to the preset target position, and there is a target projection position in front of the preset target position; then the projection output module outputs the calibration evaluation image at the target projection position through the projection device set on the vehicle to be evaluated; finally, the evaluation module evaluates the camera parameter calibration results of the vehicle to be evaluated according to the calibration evaluation image to obtain the evaluation results. It can be seen that this method can evaluate the camera parameter calibration results without the need for a calibration plate, has strong applicability, does not require manual participation, and is conducive to improving evaluation efficiency.
[0036] Furthermore, the evaluation device further comprises:
[0037] A detection module, used for detecting the position information of the target projection position after the vehicle to be evaluated is controlled to move to a preset target position;
[0038] The adjustment module is used to adjust the body orientation of the vehicle to be evaluated according to the position information so that the body of the vehicle to be evaluated faces the target projection position.
[0039] In the above implementation process, after the vehicle reaches the preset target position, it is also necessary to adjust the body orientation of the vehicle to be evaluated so that it faces the target projection position, so that the calibrated evaluation image can be accurately projected at the target projection position, which is conducive to improving the accuracy of the evaluation.
[0040] Furthermore, the projection output module is further configured to control a projection device provided on the vehicle to be evaluated to output a position adjustment reference image at the target projection position after the vehicle body orientation of the vehicle to be evaluated is adjusted according to the position information;
[0041] The evaluation device also includes:
[0042] An acquisition module, used for acquiring a target projection clarity of the position adjustment reference image at the target projection position;
[0043] A judging module, used to judge whether the definition of the target projection is greater than a preset definition threshold;
[0044] The adjustment module is further configured to control the position of the vehicle to be evaluated to be adjusted according to the target projection clarity when it is determined that the clarity is not greater than the preset clarity threshold, until the projection clarity corresponding to the adjusted position is greater than the preset clarity threshold.
[0045] In the above implementation process, before projecting the calibration evaluation image, it is also necessary to fine-tune the position of the vehicle to be evaluated through the adjustment module so that the projected image is clearly visible, which is conducive to improving the accuracy of the evaluation.
[0046] A third aspect of an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the evaluation method for vehicle camera parameter calibration results described in any one of the first aspect of the embodiments of the present application.
[0047] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the evaluation method for vehicle camera parameter calibration results described in any one of the first aspect of the embodiment of the present application is executed. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0049] Figure 1 A schematic diagram of a flow chart of a method for evaluating vehicle camera parameter calibration results provided in Example 1 of the present application;
[0050] Figure 2 A schematic diagram of a flow chart of a method for evaluating vehicle camera parameter calibration results provided in Embodiment 2 of the present application;
[0051] Figure 3 A schematic diagram of the structure of a device for evaluating vehicle camera parameter calibration results provided in Embodiment 3 of the present application;
[0052] Figure 4 A schematic diagram of the structure of a device for evaluating vehicle camera parameter calibration results provided in Embodiment 4 of the present application;
[0053] Figure 5 A schematic diagram of positional relationships for evaluating camera parameter calibration results provided in Example 1 of the present application.
[0054] Icons: A-vehicle to be evaluated, B-first camera device, C-second camera device, D-projection device, E-preset target position, F-target projection position, G-projection image. DETAILED DESCRIPTION
[0055] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0056] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0057] Example 1
[0058] Please see Figure 1 , Figure 1 A flow chart of a method for evaluating the calibration results of vehicle camera parameters is provided for an embodiment of the present application. The method for evaluating the calibration results of vehicle camera parameters includes:
[0059] S101, controlling the vehicle to be evaluated to move to a preset target position, where there is a target projection position in front of the preset target position.
[0060] In an embodiment of the present application, when controlling the vehicle to be evaluated to move to a preset target position, the positioning information of the preset target position can be set in advance, and the vehicle to be evaluated can be automatically controlled to move to the preset target position according to the positioning information; the vehicle to be evaluated can also be manually controlled to move to the preset target position through a controller; the vehicle to be evaluated can also be manually controlled to move to the preset target position through remote driving; the vehicle to be evaluated can also be controlled to move to the preset target position by manual driving, which is not limited to this embodiment of the present application.
[0061] In the embodiment of the present application, there is a target projection position in front of the preset target position. In actual use, the target projection position has the characteristics of being flat and non-reflective.
[0062] In the embodiment of the present application, in actual use, as long as there is a flat fixed object, such as a curtain, an upright wooden board, a metal plate, a wall, a projection board, or other object with flat, non-reflective features, it can be used as the target projection position, and any position in front of the target projection position can be determined as the preset target position.
[0063] In an embodiment of the present application, when the vehicle to be evaluated is controlled to move to a preset target position by manual driving, a target projection position is first determined, and then the vehicle to be evaluated is controlled to move to the target projection position by manual driving. At this time, the position of the vehicle to be evaluated is the preset target position.
[0064] S102: Outputting a calibration evaluation image at a target projection position through a projection device provided on the vehicle to be evaluated.
[0065] In an embodiment of the present application, after the vehicle to be evaluated is controlled to move to a preset target position by manual driving, the projection device provided on the vehicle to be evaluated can be turned on to output a target projection image at the target projection position, and then the position of the vehicle to be evaluated is fine-tuned through the target projection image so that the target projection image at the target projection position is clear and bright. Finally, a calibrated evaluation image is output at the target projection position through the projection device. At this time, the output calibrated evaluation image is also clear and bright, which is beneficial to improve the accuracy of subsequent evaluation of the camera parameter calibration results of the vehicle to be evaluated.
[0066] In the embodiment of the present application, the content of the calibrated evaluation image may include a unique identification code, a picture, text, multiple marking points, etc., which is not limited in the embodiment of the present application.
[0067] After step S103, the following steps are also included:
[0068] S103 . Evaluate the camera parameter calibration result of the vehicle to be evaluated according to the calibration evaluation image to obtain an evaluation result.
[0069] Please also read Figure 5 , Figure 5 Schematic diagram of positional relationship for evaluating camera parameter calibration results provided by an embodiment of the present application. Figure 5 As shown, the vehicle A to be evaluated is located at a preset target position E, and there is a target projection position F in front of the preset target position E. The vehicle A to be evaluated is provided with a first camera device B, a second camera device C and a projection device D. The vehicle A to be evaluated can output a projection image G at the target projection position F through the projection device D.
[0070] In the embodiment of the present application, the execution subject of the method can be a controller, a server, a computer, a smart phone, a tablet computer, a vehicle to be evaluated, and other devices, and no limitation is made in this embodiment.
[0071] It can be seen that implementation Figure 1 The described evaluation method for vehicle camera parameter calibration results can evaluate the camera parameter calibration results without the need for a calibration board, has strong applicability, does not require manual participation, and is conducive to improving evaluation efficiency.
[0072] Example 2
[0073] Please see Figure 2 , Figure 2 A schematic diagram of a flow chart of a method for evaluating a vehicle camera parameter calibration result provided in an embodiment of the present application. Figure 2 As shown, the evaluation method of the vehicle camera parameter calibration result includes:
[0074] S201, controlling the vehicle to be evaluated to move to a preset target position, where there is a target projection position in front of the preset target position.
[0075] S202: Detect the position information of the target projection position.
[0076] S203 . Adjust the body orientation of the vehicle to be evaluated according to the position information so that the body of the vehicle to be evaluated faces the target projection position.
[0077] In the embodiment of the present application, the position information of the target projection position is detected, and is used to detect the positional relationship between the target projection position and the preset target position, which is beneficial to adjust the body orientation of the vehicle to be evaluated so that the body of the vehicle to be evaluated is facing the target projection position, which is beneficial to accurately project the corresponding image at the target projection position, reducing the error caused by inaccurate projection image, and is beneficial to improving the evaluation accuracy.
[0078] S204: Control the projection device provided on the vehicle to be evaluated to output a position adjustment reference image at the target projection position.
[0079] In the embodiment of the present application, the position adjustment reference image can be a unique identification image, a picture image, a text image, an image including multiple marking points, etc., which is not limited in the embodiment of the present application. Specifically, the unique identification image can be a QR code image, a bar code image, etc., which is not limited in the embodiment of the present application.
[0080] S205 , obtaining the target projection clarity of the position adjustment reference image at the target projection position.
[0081] As an optional implementation, a camera device on the vehicle to be evaluated can be used to take a photo of the actual projection of the position-adjusted reference image at the target projection position, and then the projection image at the target projection position in the actual projection photo can be analyzed for clarity, thereby obtaining the target projection clarity of the position-adjusted reference image at the target projection position.
[0082] After step S205, the method further includes the following steps:
[0083] S206, determining whether the target projection clarity is greater than a preset clarity threshold, if yes, executing steps S208 to S212; if no, executing steps S207 to S212.
[0084] S207 . Control the position of the vehicle to be evaluated to adjust according to the target projection clarity, until the projection clarity corresponding to the adjusted position is greater than a preset clarity threshold.
[0085] S208 , outputting a calibration evaluation image at a target projection position through a projection device provided on the vehicle to be evaluated.
[0086] In an embodiment of the present application, the calibration evaluation image includes multiple target point images used for calibration evaluation. The content of the calibration evaluation image may include a unique identification code, a picture, text, multiple marking points, etc., which is not limited to this embodiment of the present application.
[0087] S209, obtaining first homogeneous coordinates of multiple target points in the calibration evaluation image through a first camera device set on the vehicle to be evaluated, and obtaining second homogeneous coordinates of multiple target points through a second camera device set on the vehicle to be evaluated.
[0088] In the embodiment of the present application, two camera devices are provided on the vehicle to be evaluated, namely a first camera device and a second camera device, and the calibration results of the vehicle camera parameters are evaluated, that is, the calibration internal and external parameters of the first camera device and the second camera device are evaluated.
[0089] In an embodiment of the present application, the calibrated internal and external parameters of the first camera device and the second camera device include the intrinsic parameter matrix A1 of the first camera device, the intrinsic parameter matrix A2 of the second camera device, the rotation and translation matrix Tc from the first camera device coordinate system to the second camera device coordinate system, the rotation and translation matrix T'c from the second camera device coordinate system to the first camera device coordinate system, and the transformation relationship [Rwi Twi] between the first camera device coordinate system or the second camera device coordinate system and the world coordinate system, where i = 1, 2, 3, ..., m, where m is the number of calibrated poses.
[0090] In the embodiment of the present application, Tc=[t1 t2 t3] T ; T'c = [t'1t'2t'3] T .
[0091] In the embodiment of the present application, when evaluating the calibration results of vehicle camera parameters, both the internal and external parameters of the calibration are known.
[0092] In the embodiment of the present application, when executing step S209, the first homogeneous coordinates of each target point are first obtained by the first camera device, and then the second homogeneous coordinates of each target point are obtained by the second camera device. In fact, for the same target point, there is a first homogeneous coordinate and a second homogeneous coordinate.
[0093] In the embodiment of the present application, homogeneous coordinates represent an originally n-dimensional vector using an n+1-dimensional vector, and refer to a coordinate system used in projective geometry.
[0094] In the embodiment of the present application, there are n target points. For one of the target points P j , let P j1 The first homogeneous coordinate obtained by the first camera device, P j2 is the second homogeneous coordinate obtained by the second camera device, where j=1, 2, 3, ..., n. Specifically, P j1 =[u pj1 v pj1 1] T , P j2 =[u pj2 v pj2 1] T .
[0095] In the embodiment of the present application, the initial coordinates of the target point obtained by the camera device are actually two-dimensional coordinates, which can be converted to obtain homogeneous coordinates. j , the two-dimensional coordinates obtained by the first camera device are W pj1 =[u pj1 v pj1 ] T , and then the two-dimensional coordinate is W pj1 Performing a three-dimensional homogeneous transformation, we can obtain the first homogeneous coordinate P of the target point P. j1 =[u pj1 v pj1 1] T .
[0096] After step S209, the following steps are also included:
[0097] S210: Calculate the third homogeneous coordinates according to the pre-calculated coordinate transformation relationship and the first homogeneous coordinates.
[0098] In the embodiment of the present application, the coordinate transformation relationship is:
[0099] P j1 ·A1·Tc·A2 T =P j2 ';
[0100] Where, Tc = [t1 t2 t3] T ;
[0101] Among them, j = 1, 2, 3, ..., n, n is the number of target points.
[0102] Among them, P j1 represents the first homogeneous coordinates acquired by the first camera device, P j2 ' represents the third homogeneous coordinate, A1 is the intrinsic parameter matrix of the first camera device, A2 is the intrinsic parameter matrix of the second camera device, and Tc is the rotation and translation matrix from the coordinate system of the first camera device to the coordinate system of the second camera device.
[0103] In the embodiment of the present application, for each target point, there is a first homogeneous coordinate and a second homogeneous coordinate, and the third homogeneous coordinate of each target point can be calculated through the coordinate conversion relationship. After executing step S210, each target point has a first homogeneous coordinate, a second homogeneous coordinate and a third homogeneous coordinate.
[0104] In the embodiment of the present application, a target point P is set j In theory, if the target point P is acquired by the first camera device j The first homogeneous coordinate of is P j1 '=[u pj1 'v pj1 '1] T , obtain the target point P through the second camera device j The second homogeneous coordinate of is P j2 '=[u pj2 'v pj2 '1] T For P j1 ' and P j2 ', for the same point P j , convert the first homogeneous coordinate into the three-dimensional coordinate of the first space, and convert the second homogeneous coordinate into the three-dimensional coordinate of the second space. The three-dimensional coordinate of the first space and the three-dimensional coordinate of the second space are both point P j The three-dimensional coordinates in the world coordinate system, so the first three-dimensional coordinates are the second three-dimensional coordinates, uniformly set to P j '=[x j y j z j ] T . Then the first homogeneous coordinate P j1 'Convert to the world coordinate system and get the first space three-dimensional coordinate P j The formula for ' is:
[0105] P j1 '·A1·[Rw1 Tw1]=P j '=[xj y j z j ] T ;
[0106] Convert the second homogeneous coordinates to the world coordinate system to obtain the second space three-dimensional coordinates P j The formula for ' is:
[0107] P j2 '·A2·[Rw2 Tw2]=P j '=[x j y j z j ] T ;
[0108] From the above two formulas we can get:
[0109] P j1 '·A1·[Rw1 Tw1]=P j '=[x j y j z j ] T =P j2 '·A2·[Rw2 Tw2];
[0110] Right now:
[0111] P j1 '·A1·[Rw1 Tw1]=P j2 '·A2·[Rw2 Tw2];
[0112] Simplified, we get:
[0113] P j1 '·A1·[Rw1 Tw1]·A2 T ·[Rw2 Tw2] T =P j2 ';
[0114] P j1 '·A1·[t1 t2 t3] T A2 T =P j2 ';
[0115] Where, [Rw1 Tw1] · [Rw2 Tw2] T =Tc=[t1 t2 t3] T ;
[0116] Among them, [Rw1 Tw1] is the conversion relationship between the first camera device coordinate system and the world coordinate system, and [Rw2 Tw2] is the conversion relationship between the second camera device coordinate system and the world coordinate system.
[0117] According to the above calculation process, the coordinate transformation relationship can be calculated:
[0118] P j1 ·A1·[t1 t2 t3] T A2 T =P j2 ';
[0119] And because Tc=[t1 t2 t3] T ;
[0120] It can also be written as:
[0121] P j1 ·A1·Tc·A2 T =P j2 ';
[0122] Through the coordinate conversion relationship, the first homogeneous coordinate P obtained by the first camera device can be converted into j1 Transformed into homogeneous coordinates P in the coordinate system of the second camera device j2 ', recorded as the third homogeneous coordinate.
[0123] After step S210, the following steps are also included:
[0124] S211. Calculate the Euclidean distance between the third homogeneous coordinate and the second homogeneous coordinate.
[0125] In the embodiment of the present application, the first homogeneous coordinate is substituted into the coordinate conversion relationship to obtain the third homogeneous coordinate, which is the measured value. In fact, the first homogeneous coordinate is the coordinate of point P obtained by the first camera device, which is the true value. Through the coordinate conversion relationship, the first homogeneous coordinate can be converted to the coordinate of point P under the second camera device, that is, the third homogeneous coordinate; on the other hand, the second homogeneous coordinate is the coordinate of point P obtained by the second camera device, which is the true value. By calculating the Euclidean distance between the third homogeneous coordinate and the second homogeneous coordinate, the deviation between the true value and the measured value in the coordinate system of the second camera device can be determined, and the vehicle camera parameter calibration result can be evaluated through this deviation.
[0126] In the embodiment of the present application, the formula for calculating the Euclidean distance between the third homogeneous coordinate and the second homogeneous coordinate is:
[0127]
[0128] Among them, ρ j is the Euclidean distance corresponding to the jth target point, and the third homogeneous coordinate is P j2 '=[u pj2 'v pj2 '1] T, the second homogeneous coordinate is P j2 =[u pj2 v pj2 1] T .
[0129] In the embodiment of the present application, for each target point, a Euclidean distance can be calculated according to its corresponding second homogeneous coordinate and third homogeneous coordinate.
[0130] After step S211, the following steps are also included:
[0131] S212 . Evaluate the camera parameter calibration result of the vehicle to be evaluated according to the Euclidean distance to obtain an evaluation result.
[0132] As an optional implementation, the camera parameter calibration result of the evaluated vehicle is evaluated according to the Euclidean distance to obtain an evaluation result, including:
[0133] Calculate the distance average based on Euclidean distance;
[0134] Determine whether the average distance is less than a preset threshold;
[0135] If yes, then output an evaluation result indicating that the camera parameter calibration result is qualified;
[0136] If not, an evaluation result indicating that the camera parameter calibration result is unqualified is output, and the vehicle to be evaluated is controlled to re-execute the calibration operation for the first camera device and the second camera device.
[0137] In the above embodiment, for the target point P 1 ,…,P j , P n , and its corresponding Euclidean distance is ρ 1 ,…,ρ j ,…,ρ n , then the formula for calculating the average distance ep is as follows:
[0138]
[0139] In the above embodiment, when it is determined that the distance average value is not less than the preset threshold, after outputting the evaluation result indicating that the camera parameter calibration result is unqualified, the camera parameter calibration program can be re-run at the original location to recalibrate the camera device on the vehicle to be evaluated.
[0140] In the embodiment of the present application, by implementing the above steps S209 to S212, the camera parameter calibration result of the evaluated vehicle can be evaluated according to the calibration evaluation image to obtain an evaluation result.
[0141] It can be seen that implementation Figure 2The described evaluation method for vehicle camera parameter calibration results can evaluate the camera parameter calibration results without the need for a calibration board, has strong applicability, does not require manual participation, and is conducive to improving evaluation efficiency.
[0142] Example 3
[0143] Please see Figure 3 , Figure 3 A schematic diagram of a vehicle camera parameter calibration result evaluation device provided in an embodiment of the present application. Figure 3 As shown, the evaluation device for the vehicle camera parameter calibration result includes:
[0144] The control module 310 is used to control the vehicle to be evaluated to move to a preset target position, and there is a target projection position in front of the preset target position.
[0145] The projection output module 320 is used to output a calibration evaluation image at a target projection position through a projection device provided on the vehicle to be evaluated.
[0146] The evaluation module 330 is used to evaluate the camera parameter calibration result of the evaluated vehicle according to the calibration evaluation image to obtain an evaluation result.
[0147] In the embodiments of the present application, the explanation of the evaluation device for the vehicle camera parameter calibration result can refer to the description in Embodiment 1 or Embodiment 2, which will not be further elaborated in this embodiment.
[0148] It can be seen that implementation Figure 3 The described evaluation device for vehicle camera parameter calibration results can evaluate the camera parameter calibration results without a calibration board, has strong applicability, does not require manual participation, and is conducive to improving evaluation efficiency.
[0149] Example 4
[0150] Please also read Figure 4 , Figure 4 : is a schematic diagram of another device for evaluating the calibration results of vehicle camera parameters provided in an embodiment of the present application. Figure 4 The evaluation device for the vehicle camera parameter calibration result shown is composed of Figure 3 The evaluation device for the vehicle camera parameter calibration result shown in FIG. Figure 4 As shown, the evaluation device also includes:
[0151] The detection module 340 is used to detect the position information of the target projection position after controlling the vehicle to be evaluated to move to the preset target position.
[0152] In the embodiment of the present application, after controlling the vehicle to be evaluated to move to a preset target position, the control module 310 may also trigger the detection module 340 to detect the position information of the target projection position.
[0153] The adjustment module 350 is used to adjust the body orientation of the vehicle to be evaluated according to the position information so that the body of the vehicle to be evaluated faces the target projection position.
[0154] In the embodiment of the present application, after the adjustment module 350 adjusts the body orientation of the vehicle to be evaluated, the projection output module 320 may be triggered to output a calibration evaluation image at a target projection position through a projection device provided on the vehicle to be evaluated.
[0155] As an optional implementation, the projection output module 320 is further used to control the projection device provided on the vehicle to be evaluated to output a position adjustment reference image at a target projection position after adjusting the body orientation of the vehicle to be evaluated according to the position information.
[0156] As an optional implementation, the evaluation device further includes:
[0157] The acquisition module 360 is used to acquire the target projection clarity of the position adjustment reference image at the target projection position.
[0158] The determination module 370 is used to determine whether the target projection clarity is greater than a preset clarity threshold.
[0159] The adjustment module 350 is further used to control the position of the evaluated vehicle to be adjusted according to the target projection clarity when it is determined that the clarity is not greater than the preset clarity threshold, until the projection clarity corresponding to the adjusted position is greater than the preset clarity threshold.
[0160] In the embodiment of the present application, the adjustment module 350 controls the position of the vehicle to be evaluated to adjust according to the target projection clarity until the projection clarity corresponding to the adjusted position is greater than the preset clarity threshold. The projection output module 320 can also be triggered to output a calibrated evaluation image at the target projection position through the projection device set on the vehicle to be evaluated.
[0161] As an optional implementation, the evaluation module 330 includes:
[0162] The acquisition submodule 331 is used to acquire first homogeneous coordinates of multiple target points in the calibration evaluation image through a first camera device set on the vehicle to be evaluated, and to acquire second homogeneous coordinates of multiple target points through a second camera device set on the vehicle to be evaluated.
[0163] The calculation submodule 332 is used to calculate the third homogeneous coordinate according to the pre-calculated coordinate conversion relationship and the first homogeneous coordinate; and calculate the Euclidean distance between the third homogeneous coordinate and the second homogeneous coordinate.
[0164] The evaluation submodule 333 is used to evaluate the camera parameter calibration result of the evaluated vehicle according to the Euclidean distance to obtain an evaluation result.
[0165] As an optional implementation, the evaluation submodule 333 includes:
[0166] A calculation unit, used to calculate the distance average based on the Euclidean distance.
[0167] The judging unit is used to judge whether the average value of the distance is less than a preset threshold.
[0168] The output unit is used to output an evaluation result indicating that the camera parameter calibration result is qualified when it is judged that the average distance value is less than a preset threshold value; and to output an evaluation result indicating that the camera parameter calibration result is unqualified when it is judged that the average distance value is not less than the preset threshold value, and control the vehicle to be evaluated to re-execute the calibration operation for the first camera device and the second camera device.
[0169] In the embodiments of the present application, the explanation of the evaluation device for the vehicle camera parameter calibration result can refer to the description in Embodiment 1 or Embodiment 2, which will not be further elaborated in this embodiment.
[0170] It can be seen that the evaluation device for the vehicle camera parameter calibration result described in this embodiment can evaluate the camera parameter calibration result without a calibration board, has strong applicability, does not require manual participation, and is conducive to improving evaluation efficiency.
[0171] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the evaluation method for vehicle camera parameter calibration results of any one of Embodiment 1 or Embodiment 2 of the present application.
[0172] An embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the evaluation method for vehicle camera parameter calibration results of any one of Embodiment 1 or Embodiment 2 of the present application is executed.
[0173] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0174] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0175] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps 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 random access memory (RAM), a magnetic disk or an optical disk.
[0176] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.
[0177] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0178] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
Claims
1. A method for evaluating vehicle camera parameter calibration results, characterized in that: include: Controlling the vehicle to be evaluated to move to a preset target position, where there is a target projection position in front of the preset target position, detecting position information of the target projection position, and adjusting the body orientation of the vehicle to be evaluated according to the position information so that the body of the vehicle to be evaluated faces the target projection position; Outputting a calibration evaluation image at the target projection position by a projection device provided on the vehicle to be evaluated; The camera parameter calibration result of the vehicle to be evaluated is evaluated according to the calibration evaluation image to obtain an evaluation result.
2. The evaluation method for vehicle camera parameter calibration results according to claim 1, characterized in that: After adjusting the body orientation of the vehicle to be evaluated according to the position information, the method further includes: Controlling a projection device provided on the vehicle to be evaluated to output a position adjustment reference image at the target projection position; Acquire the target projection clarity of the position adjustment reference image at the target projection position; Determining whether the target projection clarity is greater than a preset clarity threshold; If not, the position of the vehicle to be evaluated is controlled to be adjusted according to the target projection clarity until the projection clarity corresponding to the adjusted position is greater than the preset clarity threshold.
3. The method for evaluating the calibration results of vehicle camera parameters according to any one of claims 1 to 2, characterized in that: The step of evaluating the camera parameter calibration result of the vehicle to be evaluated according to the calibration evaluation image to obtain an evaluation result includes: Acquiring first homogeneous coordinates of a plurality of target points in the calibration evaluation image through a first camera device disposed on the vehicle to be evaluated, and acquiring second homogeneous coordinates of the plurality of target points through a second camera device disposed on the vehicle to be evaluated; Calculate the third homogeneous coordinate according to the pre-calculated coordinate transformation relationship and the first homogeneous coordinate; Calculating the Euclidean distance between the third homogeneous coordinate and the second homogeneous coordinate; The camera parameter calibration result of the vehicle to be evaluated is evaluated according to the Euclidean distance to obtain an evaluation result.
4. The evaluation method for vehicle camera parameter calibration results according to claim 3, characterized in that: The camera parameter calibration result of the vehicle to be evaluated is evaluated according to the Euclidean distance to obtain an evaluation result, including: Calculate the distance average according to the Euclidean distance; Determine whether the distance average is less than a preset threshold; If yes, outputting an evaluation result indicating that the camera parameter calibration result is qualified; If not, an evaluation result indicating that the camera parameter calibration result is unqualified is output, and the vehicle to be evaluated is controlled to re-execute the calibration operation for the first camera device and the second camera device.
5. A device for evaluating vehicle camera parameter calibration results, characterized in that: The evaluation device comprises: A control module, used for controlling the vehicle to be evaluated to move to a preset target position, where there is a target projection position in front of the preset target position; A detection module, used for detecting the position information of the target projection position after the vehicle to be evaluated is controlled to move to a preset target position; An adjustment module, used for adjusting the body orientation of the vehicle to be evaluated according to the position information, so that the body of the vehicle to be evaluated faces the target projection position; A projection output module, used for outputting a calibration evaluation image at the target projection position through a projection device provided on the vehicle to be evaluated; The evaluation module is used to evaluate the camera parameter calibration result of the vehicle to be evaluated according to the calibration evaluation image to obtain an evaluation result.
6. The evaluation device for vehicle camera parameter calibration results according to claim 5, characterized in that: The projection output module is further used to control a projection device provided on the vehicle to be evaluated to output a position adjustment reference image at the target projection position after adjusting the body orientation of the vehicle to be evaluated according to the position information; The evaluation device also includes: An acquisition module, used for acquiring a target projection clarity of the position adjustment reference image at the target projection position; A judging module, used to judge whether the definition of the target projection is greater than a preset definition threshold; The adjustment module is further configured to control the position of the vehicle to be evaluated to be adjusted according to the target projection clarity when it is determined that the clarity is not greater than the preset clarity threshold, until the projection clarity corresponding to the adjusted position is greater than the preset clarity threshold.
7. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the evaluation method for vehicle camera parameter calibration results according to any one of claims 1 to 4.
8. A readable storage medium, characterized in that: The readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the evaluation method for vehicle camera parameter calibration results according to any one of claims 1 to 4 is executed.
