Camera parameter calibration method and device, equipment, medium and product

By obtaining the motion trajectory information of the equipment and cameras and establishing the overall target conversion function, the problem of strict environment and poor flexibility of the external parameter calibration method of vehicle-mounted cameras in the prior art is solved, and the calibration accuracy and flexibility are improved.

CN118941643APending Publication Date: 2024-11-12XUANCHENG LUXSHARE PRECISION IND CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410941311.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing vehicle-mounted camera external parameter calibration method has strict environmental requirements, poor flexibility, and affects the algorithm accuracy when lane lines are damaged.

Method used

By obtaining the movement status data of the device to which the camera to be calibrated and the keyframe image set, determining the motion trajectory information of the device and the camera, establishing the overall target conversion function between the device and the camera, and then calculating the final external parameters.

Benefits of technology

Reduces the requirements for calibration environment and improves calibration flexibility and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941643A_ABST
    Figure CN118941643A_ABST
Patent Text Reader

Abstract

The invention discloses a camera parameter calibration method and device, equipment, a medium and a product. The method comprises the following steps: acquiring moving state data and a key frame image set of equipment to which a to-be-calibrated camera belongs; determining motion track information under an equipment coordinate system according to the moving state data; determining camera track information in a camera coordinate system according to the key frame image set; determining a total target transfer function between the equipment coordinate system and the camera coordinate system according to the motion track information, the camera track information and preset weight information; and determining final external parameters of the to-be-calibrated camera according to the current external parameters of the to-be-calibrated camera and the total target transfer function. And establishing a total target transfer function between the two coordinate systems through the motion track information and the camera track information, and determining final external parameters through the total target function. The requirement for the calibration environment is lowered, the flexibility of the calibration mode is improved, and then the calibration precision is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of camera calibration technology, and in particular to a camera parameter calibration method, device, equipment, medium and product. Background Art

[0002] In vehicle autonomous driving and intelligent assisted driving systems, vehicle cameras play an important role in perceiving and understanding the surrounding environment. In order to ensure that the camera accurately obtains scene information, it is necessary to accurately calibrate the camera's external parameters, that is, the position and posture of the camera relative to the vehicle coordinate system.

[0003] At present, most of the external parameter calibration solutions for vehicle-mounted cameras are factory calibration, which uses known calibration plates or feature points to calibrate the external parameters of the camera. This method requires the acquisition of images containing calibration plates or feature points, and the use of image processing algorithms (such as OpenCV) to extract feature points or corner points. Then, the external parameters of the camera are calculated by the calibration algorithm. There is also a multi-view calibration method, which uses multiple cameras or images from multiple perspectives of the camera to calibrate the external parameters. This method requires matching and aligning multiple cameras or images from multiple perspectives, and then calculating the external parameters of the camera through three-dimensional reconstruction or stereo vision algorithms. Existing online calibration solutions generally use lane lines or arrange specific calibration plates on the driving section to assist in calibration.

[0004] However, the above methods have strict requirements on the calibration environment, and have accuracy requirements on the layout of the calibration plate and the distance between corner points. In addition, the calibration method is not flexible enough and can only be calibrated in a specific venue. Finally, the calibration stability of the method is poor. When the lane line is damaged, it will affect the accuracy of the subsequent algorithm. Summary of the invention

[0005] The present invention provides a camera parameter calibration method, device, equipment, medium and product to improve the flexibility and accuracy of camera parameter calibration.

[0006] According to a first aspect of the present invention, a method for calibrating camera parameters is provided, comprising:

[0007] Obtain the movement status data and key frame image set of the device to which the camera to be calibrated belongs;

[0008] Determine the motion trajectory information in the device coordinate system according to the movement state data;

[0009] Determining camera trajectory information in a camera coordinate system according to the key frame image set;

[0010] Determine a total target conversion function between the device coordinate system and the camera coordinate system according to the motion trajectory information, the camera trajectory information and preset weight information;

[0011] The final external parameters of the camera to be calibrated are determined according to the current external parameters of the camera to be calibrated and the overall target conversion function.

[0012] According to a second aspect of the present invention, there is provided a camera parameter calibration device, comprising:

[0013] An information acquisition module is used to obtain the movement status data and key frame image set of the device to which the camera to be calibrated belongs;

[0014] A first determination module, used to determine the motion trajectory information in the device coordinate system according to the movement state data;

[0015] A second determination module, used to determine camera trajectory information in a camera coordinate system according to the key frame image set;

[0016] A third determination module, configured to determine a total target conversion function between the device coordinate system and the camera coordinate system according to the motion trajectory information, the camera trajectory information and preset weight information;

[0017] The fourth determination module is used to determine the final external parameters of the camera to be calibrated according to the current external parameters of the camera to be calibrated and the overall target conversion function.

[0018] According to a third aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the camera parameter calibration method described in any embodiment of the present invention.

[0022] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the camera parameter calibration method described in any embodiment of the present invention when executed.

[0023] According to a fifth aspect of the present invention, an embodiment of the present invention further provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the camera parameter calibration method of any embodiment of the present invention is implemented.

[0024] The technical solution of the embodiment of the present invention is to obtain the mobile state data and key frame image set of the device to which the camera to be calibrated belongs; determine the motion trajectory information in the device coordinate system according to the mobile state data; determine the camera trajectory information in the camera coordinate system according to the key frame image set; determine the total target conversion function between the device coordinate system and the camera coordinate system according to the motion trajectory information, the camera trajectory information and the preset weight information; determine the final external parameters of the camera to be calibrated according to the current external parameters of the camera to be calibrated and the total target conversion function. By combining the motion trajectory information and the camera trajectory information, the total target conversion function between the two coordinate systems is established, and the final external parameters are determined by the total target function. The requirements for the calibration environment are reduced, the flexibility of the calibration method is improved, and the accuracy of the calibration is thereby improved.

[0025] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a flow chart of a camera parameter calibration method provided according to Embodiment 1 of the present invention;

[0028] Figure 2 is a flow chart of a camera parameter calibration method provided according to Embodiment 2 of the present invention;

[0029] Figure 3 is a structural schematic diagram of a camera parameter calibration device provided according to Embodiment 3 of the present invention;

[0030] Figure 4 It is a schematic diagram of the structure of an electronic device implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1

[0034] Figure 1 A flow chart of a camera parameter calibration method is provided for the first embodiment of the present invention. This embodiment is applicable to the calibration of camera external parameters. The method can be executed by a camera parameter calibration device. The camera parameter calibration device can be implemented in the form of hardware and / or software. The camera parameter calibration device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0035] S110, obtaining the movement state data and key frame image set of the device to which the camera to be calibrated belongs.

[0036] In this embodiment, the camera to be calibrated can be understood as a camera that needs to be calibrated for external parameters, such as a vehicle-mounted camera. The device can be understood as the device on which the camera to be calibrated is installed, such as the device corresponding to the vehicle-mounted camera is a vehicle. The mobile state data can be understood as the driving information corresponding to the movement of the device, such as speed and turning angle. The key frame image set can be understood as a set of multiple frame images of key frames collected by the camera to be calibrated.

[0037] Specifically, a relatively flat road surface (such as a city road, etc.) can be selected in advance, and the device to which the camera to be calibrated belongs can be controlled to go straight and turn several times. The mobile state signal is received in real time by the controller and other devices in the device, and the mobile state data is processed and sent to the processor. The processor can obtain the mobile state data of the device and record it in the memory. A time interval ΔT can be set, and a frame of image data can be collected and recorded every ΔT as a key frame image, and the original image collected by the camera to be calibrated can be obtained as a key frame image set. Ensure that the posture of the device and the camera to be calibrated changes greatly during the data collection process to obtain more accurate calibration results.

[0038] Exemplarily, if the camera to be calibrated is a vehicle-mounted camera, the device corresponds to a vehicle. A flat road surface (such as a city road) can be selected in advance, the vehicle can be started, and the calibration device can be powered on through the vehicle. At this time, the MCU controller and the SOC controller of the vehicle start working. The MCU controller receives and processes the wheel pulse signal and the steering wheel angle signal data in real time to obtain the speed and front wheel angle of the vehicle. By integrating the speed and front wheel angle of the vehicle, the real-time position and yaw angle of the vehicle are obtained, and the obtained data are transmitted to the processor as mobile state data and saved and recorded in the memory. The SOC controller in the vehicle can receive the original image data collected by the camera to be calibrated in real time, and record the original image data as a key frame image set in the memory. The specific control method can be to control the vehicle to go straight for 5-15 meters, then turn left (steering wheel angle 360° to the left) and drive 5-10 meters, and then turn right (steering wheel angle 360° to the right) and drive 5-10 meters. The actual driving distance and steering wheel angle can be adjusted appropriately according to the road conditions. Try to ensure smoothness when the steering wheel changes to achieve the purpose of smooth steering.

[0039] For example, the rear axle center (RAC) position at the time of vehicle startup is used as the origin of the world coordinate system (Cartesian coordinate system), the vehicle forward direction is the positive direction of the X axis, the left direction of the vehicle is the positive direction of the Y axis, and the vehicle motion model uses the Ackerman geometric motion model, which is described as follows:

[0040] X=v*cos(ψ)

[0041] Y=v*sin(ψ)

[0042] ψ=v*tan(δ) / L

[0043] Among them, X is the x-axis coordinate value of RAC, unit is m, Y is the y-axis coordinate value of RAC, unit is m, ψ is the yaw angle (also called heading angle) of the vehicle, unit is rad, v is the vehicle speed, unit is m / s, L is the wheelbase, unit is m, and δ is the front wheel steering angle, unit is rad.

[0044] According to the motion model, the state of the vehicle is described by (X, Y, ψ), and the vehicle state (0, 0, 0) is recorded when the vehicle starts. During the driving process of the vehicle, the MCU controller records the wheel pulses in real time and calculates the vehicle's speed v and front wheel angle δ. Given the vehicle state at the current time k (X(k), Y(k), ψ(k)), the speed v and front wheel angle δ are substituted into the motion model, and the vehicle state at time k+1 (X(k+1), Y(k+1), ψ(k+1)) can be calculated. According to the initial state of the vehicle (0, 0, 0), the speed v and front wheel angle δ at each moment are substituted into the model, and the vehicle state (X(N), Y(N), ψ(N)) is obtained at all times of the vehicle's driving by iterative calculation. The MCU controller transmits the vehicle state obtained each time to the SOC controller for storage, thereby obtaining the complete motion trajectory of the vehicle, and the vehicle posture change at any time interval, that is, the vehicle state change, can also be obtained.

[0045] S120: Determine the motion trajectory information in the device coordinate system according to the movement state data.

[0046] In this embodiment, the device coordinate system can be understood as a coordinate system established with the device as the center, for example, the direction of the device moving forward is the positive direction of the X axis, and the left direction is the positive direction of the Y axis. The motion trajectory information can be understood as the complete motion trajectory of the device and the collection of motion states at each moment.

[0047] Specifically, the processor can take the device startup moment as the initial moment, that is, the starting point of the motion trajectory, and input the movement state data into a preset device motion model, such as the Ackerman set motion model, to determine the device state in the device coordinate system at each moment, and then determine the motion trajectory information in the device coordinate system.

[0048] S130. Determine camera trajectory information in a camera coordinate system according to the key frame image set.

[0049] In this embodiment, the camera coordinate system can be understood as a coordinate system established with the camera to be calibrated as the center, for example, it can be a Cartesian coordinate system. The camera coordinate system can use a right-hand system, the horizontal right direction is the positive direction of the x-axis, the optical axis direction is the positive direction of the y-axis, and the vertical upward direction is the positive direction of the z-axis. The camera trajectory information can be understood as the trajectory of the movement of the camera to be calibrated and the collection of the state of the camera to be calibrated at each moment.

[0050] Specifically, the processor can extract feature points from the key frame image, take the posture of the camera to be calibrated in the first key frame image as the initial posture, determine the camera state in each frame image in the camera coordinate system through the change relationship between the same feature points in adjacent frames, and then determine the camera trajectory information.

[0051] S140: Determine a total target conversion function between the device coordinate system and the camera coordinate system according to the motion trajectory information, the camera trajectory information and the preset weight information.

[0052] In this embodiment, the preset weight information can be understood as a set of weights of the conversion relationship between the device coordinate system and the camera coordinate system. The total target conversion function can be understood as the sum of different conversion relationships between the device coordinate system and the camera coordinate system.

[0053] Specifically, the processor can perform data fusion processing based on the motion trajectory information and the camera trajectory information, divide the fused trajectory into segments, and determine the mutual conversion relationship between the two coordinate systems of each segment of the trajectory, and determine the transformation function of each segment of the trajectory by multiplying the preset weight information with the mutual conversion relationship, and add the transformation functions of each segment of the trajectory to obtain the total target transformation function.

[0054] S150 : Determine final external parameters of the camera to be calibrated according to the current external parameters of the camera to be calibrated and the overall target conversion function.

[0055] In this embodiment, the current external parameters can be understood as the external parameters of the currently used camera, and the final external parameters can be understood as the calibrated external parameters.

[0056] Specifically, the processor can perform nonlinear optimization on the total target conversion function according to the current external parameters of the camera to be calibrated, calculate the gradient change value of the current external parameters, and then update the current external parameters until the gradient change value of the parameters is very small. When the convergence condition is met, the optimization ends and the final external parameters of the camera to be calibrated are obtained.

[0057] The technical solution of the embodiment of the present invention is to obtain the mobile state data and key frame image set of the device to which the camera to be calibrated belongs; determine the motion trajectory information in the device coordinate system according to the mobile state data; determine the camera trajectory information in the camera coordinate system according to the key frame image set; determine the total target conversion function between the device coordinate system and the camera coordinate system according to the motion trajectory information, the camera trajectory information and the preset weight information; determine the final external parameters of the camera to be calibrated according to the current external parameters of the camera to be calibrated and the total target conversion function. By combining the motion trajectory information and the camera trajectory information, the total target conversion function between the two coordinate systems is established, and the final external parameters are determined by the total target function. The requirements for the calibration environment are reduced, the flexibility of the calibration method is improved, and the accuracy of the calibration is thereby improved.

[0058] Embodiment 2

[0059] Figure 2This is a flow chart of a camera parameter calibration method provided in the second embodiment of the present invention. This embodiment is a further refinement of the above embodiment. Figure 2 As shown, the method includes:

[0060] S201, obtaining the movement state data and key frame image set of the device to which the camera to be calibrated belongs.

[0061] S202: Determine the motion trajectory information in the device coordinate system according to the movement state data.

[0062] S203 , preprocessing each key image frame included in the key frame image set to obtain a feature image set including feature points.

[0063] In this embodiment, the feature image set can be understood as a set of images divided into feature points.

[0064] Specifically, the region of interest ROI (Region of Interest) of the image can be set in advance, and the processor can perform region of interest filtering on each key image included in the key frame image set to filter out areas without feature points such as the ground and the sky, such as extracting ORB (Oriented FAST and Rotated BRIEF) feature points in the image ROI to obtain a feature image including the feature points, thereby forming a feature image set.

[0065] S204 , performing feature point matching on two feature images of adjacent frames in the feature image set to obtain a feature point matching relationship.

[0066] In this embodiment, the feature point matching relationship can be understood as the matching relationship of feature points between two adjacent frame images, that is, indicating which points in the previous and next frames are corresponding.

[0067] Specifically, the processor may perform feature point matching on two feature images of adjacent frames in the feature image set, such as using a Brute Force (BF) algorithm to perform feature point matching, to obtain a feature point matching relationship between the feature points.

[0068] S205 , for a feature image combination in adjacent frames in the feature image set, determine a reprojection error of feature points in the feature image combination according to preset optimization parameters and a feature point matching relationship.

[0069] In this embodiment, the feature image combination can be understood as a combination of two feature images in adjacent frames. The preset optimization parameter can be understood as a parameter used to represent the transformation relationship between the two frames of images, and a 6-dimensional vector defined by the Lie algebra se(3) can be used as the preset optimization parameter. The reprojection error can be understood as representing the movement distance of two feature points in different frame images.

[0070] Specifically, for the feature image combination in adjacent frames in the feature image set, the processor can determine the same feature points in the feature image combination according to the preset optimization parameters and the feature point matching relationship, project the feature points of the subsequent frame image to the previous frame image according to the preset optimization parameters, and determine the distance between the two feature points in the previous frame image to obtain the reprojection error of each feature point after the transformation.

[0071] For example, take a feature point matching relationship as an example. Assume that p1 is a point on the T-th frame image, p2 is a point on the T+1-th image, and the preset optimization parameter ξ describes the transformation relationship between the two frames of images. The optimization parameter ξ is used to map the p2 point on the T+1-th image to the T-th frame image, which is recorded as p3. Then the reprojection error is ||p1-p3||, which is the distance between the p1 point and the p3 point.

[0072] S206: Determine the camera pose of each key frame image in the camera coordinate system according to each reprojection error and the initial pose.

[0073] In this embodiment, the initial position can be understood as the initial state of the camera in the first frame image (initial moment), which can be represented by a 6-dimensional vector, that is, (0,0,0,0,0,0). The camera posture can be understood as the position of the camera to be calibrated in each frame image in the camera coordinate system.

[0074] It can be known that the motion relationship between images is equivalent to the relationship between the camera coordinate systems at two moments, including three rotations and three translations, which are described by Lie algebra se(3). The definition of Lie algebra se(3) is as follows:

[0075]

[0076] In the formula, ρ is a 3D vector used to describe the three translations, Φ is a 3D vector used to describe the three rotations, and its value satisfies the definition of Lie algebra so(3). The definition of Lie algebra so(3) is as follows:

[0077]

[0078] Specifically, the processor can add the reprojection error of the second frame image relative to the first frame image to the initial posture, determine the position of the camera to be calibrated in the second frame image in the camera coordinate system, that is, the camera posture, and so on, determine the camera posture of adjacent frame images through the reprojection error, and then obtain the camera posture of each key frame image in the camera coordinate system.

[0079] S207: Determine camera trajectory information according to the posture of each camera.

[0080] Specifically, the processor can connect through the postures of each camera to obtain camera trajectory information.

[0081] S208 , fusing the motion trajectory information and the camera trajectory information to obtain fused trajectory information.

[0082] In this embodiment, the fused trajectory information may be understood as the result of alignment and fusion of the motion trajectory information and the camera trajectory information at each moment.

[0083] Specifically, the processor can first use a filter (such as a low-pass filter, etc.) to filter the motion trajectory information and the camera trajectory information, remove the data with large errors, and reduce the error of the data with large errors on the subsequent determination of parameters. Secondly, the two trajectory information after filtering are time-stamp aligned. When the clock sources of the two data are inconsistent, the clock sources need to be unified. The processor can match the timestamp of each key frame with the timestamp of the motion trajectory information to obtain the fused trajectory information.

[0084] S209 , segmenting the fused trajectory information to obtain segmented trajectory information.

[0085] In this embodiment, the segmented trajectory information may be understood as all trajectory information after being divided into small distances.

[0086] Specifically, the processor may segment the fused trajectory information, for example, segment it according to equal time or equal distance, to obtain segmented trajectory information.

[0087] S210 . For each sub-segmented trajectory in the segmented trajectory information, determine a sub-target conversion function set between the device coordinate system and the camera trajectory information under the sub-segmented trajectory according to preset weight information and the sub-segmented trajectory information.

[0088] In this embodiment, the sub-segment trajectory can be understood as the segmented trajectory. The sub-segment trajectory information can be understood as the motion trajectory and camera trajectory at each moment in the sub-segment trajectory. The sub-target conversion function set can be understood as the set of all sub-target conversion functions included in the sub-segment trajectory.

[0089] Specifically, for each sub-segmented trajectory in the segmented trajectory information, a sub-target conversion function between the device coordinate system and the camera trajectory information at each time point under the sub-segmented trajectory is determined according to the preset weight information and the sub-segmented trajectory information to form a sub-target conversion function set.

[0090] Further, based on the above embodiment, the step of determining the sub-target conversion function set between the device coordinate system and the camera trajectory information under the sub-segment trajectory according to the preset weight information and the sub-segment trajectory information can be optimized as follows:

[0091] Determine the initial moment in the sub-segment trajectory information, set the first camera state and the first device state corresponding to the initial moment to zero, and obtain the initial camera state and the initial device state; update the sub-segment trajectory information according to the initial camera state and the initial device state to obtain the target sub-segment trajectory information; determine the rotation matrix relationship and the coordinate transformation relationship between the device coordinate system and the camera trajectory information according to the target sub-segment trajectory information; determine the sub-target transformation function set of all moments in the target sub-segment trajectory information according to the rotation matrix relationship, the coordinate transformation relationship and the preset weight information.

[0092] In this embodiment, the initial moment can be understood as the first moment in the sub-segment trajectory information. The first camera state can be understood as the camera state corresponding to the initial moment. The first device state can be understood as the device state corresponding to the initial moment. The initial camera state can be understood as the camera state after being reset to zero at the initial moment. The initial device state can be understood as the device state after being reset to zero at the initial moment. The target sub-segment trajectory information can be understood as the updated trajectory information starting from the initial camera state and the initial device state. The rotation matrix relationship can be understood as the rotation relationship between the camera coordinate system and the device coordinate system. The coordinate transformation relationship can be understood as the translation relationship between the camera coordinate system and the device coordinate system.

[0093] Specifically, the processor can use the first moment in the sub-segment trajectory information as the initial moment, set the first camera state and the first device state corresponding to the initial moment to zero, and obtain the initial camera state and the initial device state. According to the initial camera state and the initial device state, the camera state and the device state at the subsequent moments of the initial moment in the sub-segment trajectory information are updated to obtain the target sub-segment trajectory information. The processor can determine the rotation matrix relationship and the coordinate transformation relationship between the device coordinate system and the camera trajectory information based on the camera state and the device state at any two moments in the target sub-segment trajectory information. The processor can determine the sub-target transformation function set for all moments in the target sub-segment trajectory information based on the rotation matrix relationship, the coordinate transformation relationship and the preset weight information.

[0094] Exemplarily, at any two moments in the i-th target sub-segment trajectory (such as the camera coordinate system is from moment C1 to moment C2, based on the same timestamp, the device coordinate system corresponds to moment W1 to moment W2), the transformation relationship between the camera coordinate system at these two moments calculated by the updated camera state is R1 and t1, where R1 represents the rotation vector in the camera coordinate system, and t1 represents the translation vector in the camera coordinate system. The transformation relationship between the device coordinate system at these two moments calculated by the updated device state is R2 and t2, where R2 represents the rotation vector in the device coordinate system, and t2 represents the translation vector in the device coordinate system. There is a rotation matrix relationship from coordinate system C2 to coordinate system W1: R1R=RR2, which is equivalent to another form The rotation vector Φ∈so(3) is a 3D vector that describes the rotation relationship between the camera coordinate system and the vehicle body coordinate system on the actual device. Each rotation vector has a corresponding rotation matrix R, and the calculation relationship between the two is given by the formula R=exp(Φ^). The translation vector t∈R 3 , is a 3D vector that describes the rotation relationship between the camera coordinate system and the device coordinate system on the actual device. The k scale factors s, denoted as s[k], are k-dimensional vectors. There is also a coordinate transformation relationship: R1t+t1=Rt2+t, which is equivalent to another form (1-R1)t+s k Rt2-t1=0. The sub-goal conversion function can be expressed as cost:

[0095]

[0096] Among them, d1 is the rotation constraint weight in the preset weight information, and d2 is the translation constraint weight in the preset weight information.

[0097] Among them, the steps of updating the sub-segment trajectory information according to the initial camera state and the initial device state to obtain the target sub-segment trajectory information can be refined as follows:

[0098] According to the first camera state at other moments in the sub-segment trajectory information, determine the first relative state change of the first camera state relative to the camera state at the initial moment; according to the initial camera state and each first relative state change, determine the updated second camera state at each moment; according to the first device state at other moments in the sub-segment trajectory information, determine the second relative state change of the first device state relative to the device state at the initial moment; according to the initial device state and each second relative state change, determine the updated second device state at each moment; according to each second camera state and each second device state, obtain the target sub-segment trajectory information.

[0099] In this embodiment, the first camera state can be understood as the unupdated camera state at adjacent moments in the sub-segment trajectory information. Other moments can be understood as all moments in the sub-segment trajectory information except the initial moment. The camera state at the initial moment can be understood as the camera state at the initial moment when it is not reset to zero. The first relative state change can be understood as indicating the change in the camera state between the previous and next moments. The second camera state can be understood as the updated camera state. The first device state can be understood as the unupdated device state at other moments in the sub-segment trajectory information. The second relative state change can be understood as indicating the change in the device state between the previous and next moments. The second device state can be understood as the updated device state.

[0100] Specifically, the processor can determine the first relative state change of the first camera state relative to the camera state at the initial moment based on the first camera state at other moments in the sub-segment trajectory information, and the processor can determine the state of each camera at the corresponding moment based on the initial camera state and each first relative state change, that is, obtain the updated second camera state. The processor can determine the second relative state change of the first device state relative to the device state at the initial moment based on the first device state at other moments in the sub-segment trajectory information, and determine the device state at the corresponding moment based on the initial device state and each second relative state change, that is, obtain the updated second device state. The processor can correspond each second camera state to each second device state to obtain the target sub-segment trajectory information.

[0101] Exemplarily, taking the camera trajectory in the sub-segment trajectory information as an example, assuming that the state of the starting point a of the i-th small segment of the camera trajectory is a_ξ (this state is the state when it is not reset to zero), and there is a position b on the small segment of the trajectory whose state is b_ξ, then the first relative state change of b relative to a is inv(exp(a_ξ^))^exp(b_ξ^), where exp(ξ^) is the exponential mapping of ξ, and the transformation matrix is ​​obtained. Inv is the matrix inversion operation. By adding the initial camera state after setting to zero to the first relative state change, the second camera state after the position of b is updated can be obtained.

[0102] S211. Determine the total goal conversion function based on the sum of each sub-goal conversion function set.

[0103] Specifically, the processor may sum up all sub-goal transfer functions in a sub-goal transfer function set corresponding to all sub-segment trajectory information, that is, the sum of the sub-goal transfer functions at all times on the entire trajectory, to obtain a total goal transfer function.

[0104] Exemplarily, the overall target conversion function J can be determined by the following formula:

[0105]

[0106] S212, determining the parameter to be optimized when the total objective conversion function reaches a minimum value, and using the parameter to be optimized as the next external parameter.

[0107] In this embodiment, the parameter to be optimized can be understood as an unknown parameter in the calculated total target conversion function. The next external parameter can be understood as an updated external parameter.

[0108] Specifically, the processor can determine the unknown function when the total target conversion function reaches a minimum value, that is, R, t and s in the formula i , since R is the exponential mapping of the rotation vector Φ, the rotation vector Φ can be calculated through R, that is, the parameters to be optimized are the rotation vector Φ and the translation vector t, and the parameters to be optimized are used as the next external parameters.

[0109] Exemplarily, a nonlinear optimization algorithm may be used to determine the parameters to be optimized when the total objective conversion function is at a minimum. The general form of nonlinear optimization is as follows:

[0110] m27n277mi2ef(x)

[0111] subjecttog(x)i≤0i=1,...,

[0112] h(x)j=0j=1,...,k

[0113] x∈R”

[0114] There exists a set of solutions x* in n-dimensional real space, which makes the nonlinear objective function f(x) take the minimum value under the condition that the inequality constraint g(x*)≤0 and the equality constraint h(x*)=0 are satisfied. Wherein, f(x) is the overall objective conversion function in the present invention, g(x) is the inequality constraint, and h(x) is the equality constraint.

[0115] S213. Calculate the gradient change value of the parameter according to the current external parameter and the next external parameter.

[0116] In this embodiment, the gradient change value can be understood as a value used to reflect the change of the external parameter.

[0117] Specifically, the processor may subtract the current external parameter from the next external parameter to obtain a gradient change value of the parameter.

[0118] S214: If the gradient change value satisfies the convergence condition, the next external parameter is used as the final external parameter of the camera to be calibrated.

[0119] In this embodiment, the convergence condition can be understood as a set minimum value.

[0120] Specifically, the processor may compare the gradient change value with the minimum value set by the convergence condition, and when the convergence condition is met, use the next external parameter as the final external parameter of the camera to be calibrated.

[0121] S215. Otherwise, replace the current external parameter with the next external parameter, and continue with the step of determining the next external parameter.

[0122] Specifically, when the convergence condition is not met, the next external parameter replaces the current external parameter, and the step of determining the next external parameter is continued.

[0123] The technical solution of the embodiment of the present invention obtains the mobile state data and key frame image set of the device to which the camera to be calibrated belongs, and determines the motion trajectory information in the device coordinate system according to the mobile state data. The key frame image set is preprocessed to obtain a feature image set including feature points, and feature point matching is performed on it to determine the feature point matching relationship. Based on the 6-dimensional vector that satisfies the definition of Lie algebra as a preset optimization parameter, the reprojection error of the feature points in the feature image combination is determined based on the feature point matching relationship and the preset optimization parameter. The camera trajectory information in the camera coordinate system is determined by the reprojection error. According to the motion trajectory information and the camera trajectory information, the trajectory information is determined and fused, and then the fused trajectory information is segmented. Based on the segmented trajectory information, the rotation matrix relationship and coordinate matrix relationship of the mutual conversion between the device coordinate system and the camera coordinate system in the segmented trajectory information are determined. Through the rotation matrix relationship, the coordinate matrix relationship and the preset weight information, the sub-target conversion function set is determined to obtain the target conversion function at a finer scale, which provides a data basis for the subsequent determination of external parameters. The total target conversion function is determined by the sub-target conversion function set, the next external parameter in the total target conversion function is determined based on the nonlinear optimization method, the current external parameter is optimized based on the next external parameter, and the final external parameter of the camera to be calibrated is determined. The requirements for the calibration environment are reduced, the flexibility of the calibration method is improved, and the accuracy of the calibration is improved.

[0124] Embodiment 3

[0125] Figure 3 This is a schematic diagram of the structure of a camera parameter calibration device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0126] An information acquisition module 31 is used to acquire the movement state data and key frame image set of the device to which the camera to be calibrated belongs;

[0127] A first determination module 32, configured to determine motion track information in a device coordinate system according to the movement state data;

[0128] A second determination module 33, configured to determine camera trajectory information in a camera coordinate system according to the key frame image set;

[0129] A third determination module 34 is used to determine a total target conversion function between the device coordinate system and the camera coordinate system according to the motion trajectory information, the camera trajectory information and preset weight information;

[0130] The fourth determination module 35 is used to determine the final external parameters of the camera to be calibrated according to the current external parameters of the camera to be calibrated and the overall target conversion function.

[0131] The technical solution of the embodiment of the present invention is to obtain the mobile state data and key frame image set of the device to which the camera to be calibrated belongs; determine the motion trajectory information in the device coordinate system according to the mobile state data; determine the camera trajectory information in the camera coordinate system according to the key frame image set; determine the total target conversion function between the device coordinate system and the camera coordinate system according to the motion trajectory information, the camera trajectory information and the preset weight information; determine the final external parameters of the camera to be calibrated according to the current external parameters of the camera to be calibrated and the total target conversion function. By combining the motion trajectory information and the camera trajectory information, the total target conversion function between the two coordinate systems is established, and the final external parameters are determined by the total target function. The requirements for the calibration environment are reduced, the flexibility of the calibration method is improved, and the accuracy of the calibration is thereby improved.

[0132] Further, the second determining module 33 is specifically configured to:

[0133] Preprocessing each key image frame included in the key frame image set to obtain a feature image set including feature points;

[0134] Performing feature point matching on two feature images of adjacent frames in the feature image set to obtain a feature point matching relationship;

[0135] For a feature image combination under adjacent frames in the feature image set, determining a reprojection error of a feature point in the feature image combination according to preset optimization parameters and the feature point matching relationship;

[0136] Determining the camera pose of each of the key frame images in the camera coordinate system according to the reprojection errors and the initial pose;

[0137] The camera trajectory information is determined according to each of the camera postures.

[0138] Further, the third determination module 34 includes:

[0139] An information fusion unit, used for fusing the motion trajectory information and the camera trajectory information to obtain fused trajectory information;

[0140] A first determining unit, configured to perform segmentation according to the fused trajectory information to obtain segmented trajectory information;

[0141] A second determining unit is used to determine, for each sub-segmented trajectory in the segmented trajectory information, a sub-target conversion function set between the device coordinate system and the camera trajectory information under the sub-segmented trajectory according to the preset weight information and the sub-segmented trajectory information;

[0142] The third determination unit is used to determine the total target conversion function according to the sum of each of the sub-target conversion function sets.

[0143] Wherein, the second determining unit includes:

[0144] A first determining subunit is used to determine an initial moment in the sub-segment trajectory information, reset a first camera state and a first device state corresponding to the initial moment to zero, and obtain an initial camera state and an initial device state;

[0145] A second determining subunit is used to update the sub-segment trajectory information according to the initial camera state and the initial device state to obtain target sub-segment trajectory information;

[0146] A third determination subunit is used to determine a rotation matrix relationship and a coordinate conversion relationship between the device coordinate system and the camera trajectory information according to the target sub-segment trajectory information;

[0147] The fourth determination subunit is used to determine the sub-target conversion function set at all moments in the target sub-segment trajectory information according to the rotation matrix relationship, the coordinate transformation relationship and the preset weight information.

[0148] Wherein, the second determining subunit is specifically used for:

[0149] Determine, according to the first camera state at other moments in the sub-segment trajectory information, a first relative state change amount of the first camera state relative to the camera state at the initial moment;

[0150] Determining an updated second camera state at each moment according to the initial camera state and each of the first relative state changes;

[0151] Determine, according to the first device state at other times in the sub-segment trajectory information, a second relative state change amount of the first device state relative to the device state at the initial time;

[0152] Determine the updated second device state at each time according to the initial device state and each second relative state change amount;

[0153] According to each second camera status and each second device status, target sub-segment trajectory information is obtained.

[0154] Furthermore, the fourth determining module 35 is specifically configured to:

[0155] Determine the parameter to be optimized when the total objective conversion function reaches a minimum value, and use the parameter to be optimized as the next external parameter;

[0156] Calculating a gradient change value of a parameter according to the current external parameter and the next external parameter;

[0157] If the gradient change value satisfies the convergence condition, the next external parameter is used as the final external parameter of the camera to be calibrated;

[0158] Otherwise, the current external parameter is replaced by the next external parameter, and the step of determining the next external parameter is continued.

[0159] The camera parameter calibration device provided in the embodiment of the present invention can execute the camera parameter calibration method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0160] Embodiment 4

[0161] Figure 4 A schematic diagram of the structure of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0162] like Figure 4As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0163] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0164] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as a calibration method for camera parameters.

[0165] In some embodiments, the calibration method of the camera parameters may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the calibration method of the camera parameters described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the calibration method of the camera parameters in any other appropriate manner (e.g., by means of firmware).

[0166] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0167] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0168] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0169] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0170] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0171] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0172] In one embodiment, the embodiment of the present invention further includes a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, the calibration method of the X camera parameters of any embodiment of the present invention is implemented.

[0173] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0174] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0175] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A camera parameter calibration method, characterized in that: include: Obtain the movement status data and key frame image set of the device to which the camera to be calibrated belongs; Determine the motion trajectory information in the device coordinate system according to the movement state data; Determining camera trajectory information in a camera coordinate system according to the key frame image set; Determine a total target conversion function between the device coordinate system and the camera coordinate system according to the motion trajectory information, the camera trajectory information and preset weight information; The final external parameters of the camera to be calibrated are determined according to the current external parameters of the camera to be calibrated and the overall target conversion function.

2. The method according to claim 1, characterized in that The step of determining the camera trajectory information in the camera coordinate system according to the key frame image set includes: Preprocessing each key image frame included in the key frame image set to obtain a feature image set including feature points; Performing feature point matching on two feature images of adjacent frames in the feature image set to obtain a feature point matching relationship; For a feature image combination under adjacent frames in the feature image set, determining a reprojection error of a feature point in the feature image combination according to preset optimization parameters and the feature point matching relationship; Determining the camera pose of each of the key frame images in the camera coordinate system according to the reprojection errors and the initial pose; The camera trajectory information is determined according to each of the camera postures.

3. The method according to claim 1, characterized in that The determining, according to the motion trajectory information, the camera trajectory information and the preset weight information, a total target conversion function between the device coordinate system and the camera coordinate system comprises: Fusing the motion trajectory information and the camera trajectory information to obtain fused trajectory information; Segmenting according to the fused trajectory information to obtain segmented trajectory information; For each sub-segmented trajectory in the segmented trajectory information, according to the preset weight information and the sub-segmented trajectory information, determine a sub-target conversion function set between the device coordinate system and the camera trajectory information under the sub-segmented trajectory; The total objective conversion function is determined according to the sum of each of the sub-objective conversion function sets.

4. The method according to claim 3, characterized in that The determining, according to the preset weight information and the sub-segment trajectory information, a sub-target conversion function set between the device coordinate system and the camera trajectory information under the sub-segment trajectory includes: Determine an initial moment in the sub-segment trajectory information, reset a first camera state and a first device state corresponding to the initial moment to zero, and obtain an initial camera state and an initial device state; The sub-segment trajectory information is updated according to the initial camera state and the initial device state to obtain the target sub-segment trajectory information; Determine a rotation matrix relationship and a coordinate conversion relationship between the device coordinate system and the camera trajectory information according to the target sub-segment trajectory information; According to the rotation matrix relationship, the coordinate transformation relationship and the preset weight information, a sub-target transformation function set at all moments in the target sub-segment trajectory information is determined.

5. The method according to claim 4, characterized in that The updating of the sub-segment trajectory information according to the initial camera state and the initial device state to obtain the target sub-segment trajectory information includes: Determine, according to the first camera state at other moments in the sub-segment trajectory information, a first relative state change amount of the first camera state relative to the camera state at the initial moment; Determining an updated second camera state at each moment according to the initial camera state and each of the first relative state changes; Determine, according to the first device state at other times in the sub-segment trajectory information, a second relative state change amount of the first device state relative to the device state at the initial time; Determine the updated second device state at each time according to the initial device state and each second relative state change amount; According to each second camera status and each second device status, target sub-segment trajectory information is obtained.

6. The method according to claim 1, characterized in that The step of determining final external parameters of the camera to be calibrated according to the current external parameters of the camera to be calibrated and the overall target conversion function includes: Determine the parameter to be optimized when the total objective conversion function reaches a minimum value, and use the parameter to be optimized as the next external parameter; Calculating a gradient change value of a parameter according to the current external parameter and the next external parameter; If the gradient change value satisfies the convergence condition, the next external parameter is used as the final external parameter of the camera to be calibrated; Otherwise, the current external parameter is replaced by the next external parameter, and the step of determining the next external parameter is continued.

7. A camera parameter calibration device, characterized in that: include: An information acquisition module is used to obtain the movement status data and key frame image set of the device to which the camera to be calibrated belongs; A first determination module, used to determine the motion trajectory information in the device coordinate system according to the movement state data; A second determination module, configured to determine camera trajectory information in a camera coordinate system according to the key frame image set; A third determination module, configured to determine a total target conversion function between the device coordinate system and the camera coordinate system according to the motion trajectory information, the camera trajectory information and preset weight information; The fourth determination module is used to determine the final external parameters of the camera to be calibrated according to the current external parameters of the camera to be calibrated and the overall target conversion function.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the camera parameter calibration method described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the camera parameter calibration method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the camera parameter calibration method according to any one of claims 1 to 6.

Citation Information

Cited By

  • Accident restoration method and device, electronic equipment and storage medium

    CN119990320A