Vehicle center line searching and calibrating method and device based on binocular camera

Abstract

The invention discloses a vehicle midline searching and calibrating method and device based on a binocular camera, and the method comprises the steps: controlling calibration equipment to execute first recognition on a moving target through a distance measurement instruction on the premise that the calibration equipment can normally execute calibration operation at present, and storing a corresponding first recognition result; and then the calibration equipment is controlled to execute second identification on the first target assembly and the second target assembly, so that construction of a plane where the to-be-calibrated vehicle is located and construction of a plane corresponding to the calibration equipment are achieved by combining the first identification result and the second identification result, and intelligent and accurate centering and calibration of the vehicle center line are achieved by conducting centering coincidence, calibration and correction on the two planes. The centering accuracy and efficiency and the calibration accuracy and efficiency of the center line of the vehicle are improved; distance measurement and identification are carried out through the binocular camera, compared with a traditional monocular vision or machine type measurement tool, space position information can be captured more accurately, and the accuracy of vehicle center line searching and calibration can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent equipment calibration, and in particular to a vehicle centerline finding and calibration method and device based on a binocular camera. Background Art

[0002] ADAS (Advanced Driver Assistance System) uses sensors installed on the vehicle (radar, cameras, etc.) to monitor the surrounding environment in real time while the car is driving, collect data, perform system calculations and analysis, and warn of possible dangers, allowing the driver to be aware of possible dangers and take measures, effectively increasing the safety of car driving. However, in the process of users using the vehicle, the vehicle will be repaired more or less based on various emergencies. Among them, if there are maintenance matters such as replacing the front windshield, repairing the suspension or changing the tire size, the presence of ADAS-related DTCs (fault codes), disassembly or replacement of ADAS sensors, the ADAS system needs to be recalibrated.

[0003] The conventional method of centering a vehicle through calibration equipment currently has the following drawbacks: 1. The traditional method of calibration through plumb bobs, tape measures, etc. is time-consuming and has low calibration accuracy; 2. The method of centering through lasers is affected by the specifications of the laser and has limitations in use. At the same time, some laser centering methods require the light beam to be reflected back through a reflector, resulting in a larger laser spot at a long distance, which reduces the centering accuracy of the calibration equipment. Subsequently, it is necessary to increase the number of centering times to improve the centering accuracy, which reduces the centering efficiency. It can be seen that it is particularly important to provide a corresponding solution to the technical problems of low calibration accuracy, low calibration efficiency, and low centering efficiency in the existing vehicle centering and calibration technology. Summary of the invention

[0004] The present invention provides a vehicle centerline finding and calibration method and device based on a binocular camera, which can be beneficial to improving the centering efficiency and centering accuracy of the vehicle as well as improving the calibration accuracy and calibration efficiency.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a vehicle centerline finding and calibration method based on a binocular camera, the method comprising:

[0006] Detecting whether the calibration device currently meets the operating conditions for performing the calibration operation on the vehicle to be calibrated, and when it is detected that the calibration device currently meets the operating conditions for performing the calibration operation, generating a distance measurement instruction for the calibration device, and controlling the calibration device to perform a first recognition operation on a set mobile target according to the distance measurement instruction, and storing a corresponding first recognition result, wherein the first recognition result at least includes a measured distance between the calibration device and the mobile target;

[0007] The mobile target is removed, and after determining that the first target component and the second target component are mounted at the set recording position, the calibration device is controlled to perform a second recognition operation on the first target component and the second target component to obtain a second recognition result for the first target component and the second target component, wherein the second recognition result includes first component recognition data corresponding to the first target component and second component recognition data corresponding to the second target component; the first target component and the second target component each include at least one binocular camera

[0008] According to the first recognition result and the second recognition result, performing parameter calibration on the calibration device to update the second recognition result, until after determining that the second recognition result meets a preset parameter calibration requirement, determining that the centering and calibration operation for the vehicle to be calibrated is completed;

[0009] The parameter calibration includes vehicle plane construction for the plane where the vehicle to be calibrated is located, device plane construction for the plane corresponding to the calibration device, and plane centering calibration.

[0010] As an optional implementation, in the first aspect of the present invention, when it is detected that the calibration device currently does not meet the operating conditions for performing the calibration operation, the method further includes:

[0011] Acquire target calibration parameters corresponding to the calibration device, where the target calibration parameters include current calibration parameters of the calibration device and reference calibration parameters corresponding to the current calibration parameters;

[0012] Comparing the current calibration parameter with the reference calibration parameter to obtain a difference parameter between the current calibration parameter and the reference calibration parameter;

[0013] Determining a parameter calibration item corresponding to the difference parameter, wherein the parameter calibration item at least includes a parameter calibration step;

[0014] According to the parameter calibration matters and in accordance with the parameter calibration steps, a device parameter calibration operation is performed on the calibration device to adjust the calibration device to an operating condition that satisfies the calibration operation.

[0015] As an optional implementation, in the first aspect of the present invention, the target calibration parameter includes at least one of height from the ground, device-vehicle offset distance, calibration position, and calibration status;

[0016] The height from the ground is used to indicate the relative distance between the height center of the beam on the calibration device and the ground;

[0017] The calibration device comprises a first laser emitting component, the first laser emitting component is used to emit an emission light parallel to the body of the vehicle to be calibrated, the direction of the emission light is the direction corresponding to the front and rear wheels on the same side of the vehicle to be calibrated; the device-vehicle offset distance is the distance between the emission light and the body center axis of the vehicle to be calibrated, and the axial direction corresponding to the body center axis is consistent with the direction of the emission light;

[0018] The calibration device further comprises at least two imaging components; the calibration position is used to indicate the component configuration positions of the two imaging components corresponding to the vehicle to be calibrated;

[0019] The calibration status is used to indicate the component status of the two imaging components. The calibration status includes a standby state or an operating state opposite to the standby state. The operating state is used to indicate that the two imaging components have completed component initialization operations.

[0020] As an optional implementation, in the first aspect of the present invention, controlling the calibration device to perform a first recognition operation on a set mobile target according to the ranging instruction includes:

[0021] After determining that the set moving target is at a preset distance measurement starting point and the second laser component on the moving target is switched to an on state, according to the distance measurement instruction, controlling any one of the two imaging components to perform target recognition on the moving target to obtain target recognition data for the moving target;

[0022] According to the target recognition data, in combination with the configuration position of any imaging component on the vehicle to be calibrated and the ranging starting point, the ranging distance between any imaging component and the ranging starting point is calculated;

[0023] Determine the configuration position, the ranging starting point, and the ranging distance corresponding to each imaging component as a first recognition result;

[0024] The straight-line distances between the two imaging components and the distance measurement starting point are the same, and the distance measurement starting point is set right in front of or right behind the vehicle to be calibrated.

[0025] As an optional embodiment, in the first aspect of the present invention, the two imaging components include a first imaging component and a second imaging component; the first imaging component and the first target component are arranged on the same side; the second imaging component and the second target component are arranged on the same side; the first target component includes a sub-target component; the second target component includes a third imaging component;

[0026] The controlling the calibration device to perform a second identification operation on the first target component and the second target component to obtain a second identification result for the first target component and the second target component includes:

[0027] Controlling the first imaging component to perform component recognition on the first target component, and obtaining first position data and first component distance corresponding to the first target component as first component recognition data;

[0028] Controlling the second imaging component to perform the component identification on the second target component, and obtaining second posture data and second component distance corresponding to the second target component as second component identification data;

[0029] Controlling the third imaging component to perform the component identification on the sub-target component, and obtaining third posture data and a third component distance corresponding to the sub-target component as third component identification data;

[0030] The first component identification data, the second component identification data, and the third component identification data are determined as a second identification result.

[0031] As an optional implementation manner, in the first aspect of the present invention, performing parameter calibration on the calibration device according to the first recognition result and the second recognition result includes:

[0032] Determining a reference vehicle plane corresponding to the vehicle to be calibrated according to the first recognition result;

[0033] determining a device calibration plane corresponding to the calibration device according to the second recognition result;

[0034] Taking the reference vehicle plane as a calibration target, and combining a plurality of set plane calibration factors, performing plane correction on the device calibration plane to obtain a plane correction result for the device calibration plane;

[0035] The multiple plane calibration factors include angle values ​​corresponding to multiple correction angles of a device beam on the calibration device relative to the vehicle to be calibrated, and the multiple correction angles include at least one of a yaw angle, a tilt angle, and a pitch angle.

[0036] As an optional implementation, in the first aspect of the present invention, taking the reference vehicle plane as a calibration target, combining the set multiple plane calibration factors, performing plane correction on the device calibration plane, and obtaining a plane correction result for the device calibration plane, includes:

[0037] Determine a first correction angle value corresponding to the reference vehicle plane and each correction angle, and obtain an error correction interval corresponding to each correction angle;

[0038] Determine a second correction angle value corresponding to the device calibration plane and each correction angle;

[0039] For each correction angle, based on the first correction angle value corresponding to the correction angle and the error correction interval, perform numerical correction on the second correction angle value corresponding to the correction angle to obtain a numerical correction result corresponding to the correction angle, wherein the numerical correction result corresponding to the correction angle includes a plurality of sub-correction angle values;

[0040] Determine the numerical correction result corresponding to each correction angle as a plane correction result for the device calibration plane;

[0041] And, the second recognition result meets the parameter calibration requirement including:

[0042] The numerical difference between the second correction value corresponding to each correction angle and the first correction value corresponding to the correction angle is within the error correction interval corresponding to the correction angle, and the reference vehicle plane and the equipment calibration plane are aligned and coincident; the alignment and coincidence of the reference vehicle plane and the equipment calibration plane at least includes the coincidence of the central axis of the reference vehicle plane and the central axis of the equipment calibration plane.

[0043] The second aspect of the present invention discloses a vehicle centerline finding and calibration device based on a binocular camera, the device comprising:

[0044] A detection module, used to detect whether the calibration device currently meets the operating conditions for performing a calibration operation on the vehicle to be calibrated;

[0045] an instruction generating module, configured to generate a distance measurement instruction for the calibration device when the detection module detects that the calibration device currently meets the operating conditions for performing the calibration operation;

[0046] A first recognition module, configured to control the calibration device to perform a first recognition operation on a set mobile target according to the distance measurement instruction, and store a corresponding first recognition result, wherein the first recognition result at least includes a measured distance between the calibration device and the mobile target;

[0047] a second identification module, for removing the mobile target, and after determining that the first target component and the second target component are mounted at the set recording position, controlling the calibration device to perform a second identification operation on the first target component and the second target component, and obtaining a second identification result for the first target component and the second target component, wherein the second identification result includes first component identification data corresponding to the first target component and second component identification data corresponding to the second target component; the first target component and the second target component each include at least one binocular camera

[0048] A calibration processing module is used to perform parameter calibration on the calibration device according to the first recognition result and the second recognition result to update the second recognition result, until it is determined that the second recognition result meets the preset parameter calibration requirements, and then determine that the centering and calibration operations for the vehicle to be calibrated are completed; wherein the parameter calibration includes vehicle plane construction for the plane where the vehicle to be calibrated is located, device plane construction for the plane corresponding to the calibration device, and plane centering calibration.

[0049] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0050] a parameter acquisition module, configured to acquire target calibration parameters corresponding to the calibration device when the detection module detects that the calibration device currently does not meet the operating conditions for performing the calibration operation, wherein the target calibration parameters include current calibration parameters of the calibration device and reference calibration parameters corresponding to the current calibration parameters;

[0051] A parameter comparison module, used for comparing the current calibration parameters with the reference calibration parameters to obtain a difference parameter between the current calibration parameters and the reference calibration parameters;

[0052] A determination module, used to determine a parameter calibration item corresponding to the difference parameter, wherein the parameter calibration item at least includes a parameter calibration step;

[0053] The calibration processing module is further used to perform a device parameter calibration operation on the calibration device according to the parameter calibration matters and the parameter calibration steps, so as to adjust the calibration device to meet the operating conditions for performing the calibration operation.

[0054] As an optional implementation, in the second aspect of the present invention, the target calibration parameter includes at least one of height from the ground, device-vehicle offset distance, calibration position, and calibration status;

[0055] The height from the ground is used to indicate the relative distance between the height center of the beam on the calibration device and the ground;

[0056] The calibration device comprises a first laser emitting component, the first laser emitting component is used to emit an emission light parallel to the body of the vehicle to be calibrated, the direction of the emission light is the direction corresponding to the front and rear wheels on the same side of the vehicle to be calibrated; the device-vehicle offset distance is the distance between the emission light and the body center axis of the vehicle to be calibrated, and the axial direction corresponding to the body center axis is consistent with the direction of the emission light;

[0057] The calibration device further comprises at least two imaging components; the calibration position is used to indicate the component configuration positions of the two imaging components corresponding to the vehicle to be calibrated;

[0058] The calibration status is used to indicate the component status of the two imaging components. The calibration status includes a standby state or an operating state opposite to the standby state. The operating state is used to indicate that the two imaging components have completed component initialization operations.

[0059] As an optional implementation, in the second aspect of the present invention, the first recognition module controls the calibration device to perform the first recognition operation on the set mobile target according to the ranging instruction, which specifically includes:

[0060] After determining that the set moving target is at a preset distance measurement starting point and the second laser component on the moving target is switched to an on state, according to the distance measurement instruction, controlling any one of the two imaging components to perform target recognition on the moving target to obtain target recognition data for the moving target;

[0061] According to the target recognition data, in combination with the configuration position of any imaging component on the vehicle to be calibrated and the ranging starting point, the ranging distance between any imaging component and the ranging starting point is calculated;

[0062] Determine the configuration position, the ranging starting point, and the ranging distance corresponding to each imaging component as a first recognition result;

[0063] The straight-line distances between the two imaging components and the distance measurement starting point are the same, and the distance measurement starting point is set right in front of or right behind the vehicle to be calibrated.

[0064] As an optional embodiment, in the second aspect of the present invention, the two imaging components include a first imaging component and a second imaging component; the first imaging component and the first target component are arranged on the same side; the second imaging component and the second target component are arranged on the same side; the first target component includes a sub-target component; the second target component includes a third imaging component;

[0065] The second recognition module controls the calibration device to perform a second recognition operation on the first target component and the second target component, and a method of obtaining a second recognition result for the first target component and the second target component specifically includes:

[0066] Controlling the first imaging component to perform component recognition on the first target component, and obtaining first position data and first component distance corresponding to the first target component as first component recognition data;

[0067] Controlling the second imaging component to perform the component identification on the second target component, and obtaining second posture data and second component distance corresponding to the second target component as second component identification data;

[0068] Controlling the third imaging component to perform the component identification on the sub-target component, and obtaining third posture data and a third component distance corresponding to the sub-target component as third component identification data;

[0069] The first component identification data, the second component identification data, and the third component identification data are determined as a second identification result.

[0070] As an optional implementation, in the second aspect of the present invention, the calibration processing module performs parameter calibration on the calibration device according to the first recognition result and the second recognition result, specifically including:

[0071] Determining a reference vehicle plane corresponding to the vehicle to be calibrated according to the first recognition result;

[0072] determining a device calibration plane corresponding to the calibration device according to the second recognition result;

[0073] Taking the reference vehicle plane as a calibration target, and combining a plurality of set plane calibration factors, performing plane correction on the device calibration plane to obtain a plane correction result for the device calibration plane;

[0074] The multiple plane calibration factors include angle values ​​corresponding to multiple correction angles of a device beam on the calibration device relative to the vehicle to be calibrated, and the multiple correction angles include at least one of a yaw angle, a tilt angle, and a pitch angle.

[0075] As an optional implementation, in the second aspect of the present invention, the calibration processing module uses the reference vehicle plane as a calibration target, combines multiple plane calibration factors, performs plane correction on the device calibration plane, and obtains the plane correction result for the device calibration plane in a manner that specifically includes:

[0076] Determine a first correction angle value corresponding to the reference vehicle plane and each correction angle, and obtain an error correction interval corresponding to each correction angle;

[0077] Determine a second correction angle value corresponding to the device calibration plane and each correction angle;

[0078] For each correction angle, based on the first correction angle value corresponding to the correction angle and the error correction interval, perform numerical correction on the second correction angle value corresponding to the correction angle to obtain a numerical correction result corresponding to the correction angle, wherein the numerical correction result corresponding to the correction angle includes a plurality of sub-correction angle values;

[0079] Determine the numerical correction result corresponding to each correction angle as a plane correction result for the device calibration plane;

[0080] And, the second recognition result meets the parameter calibration requirement including:

[0081] The numerical difference between the second correction value corresponding to each correction angle and the first correction value corresponding to the correction angle is within the error correction interval corresponding to the correction angle, and the reference vehicle plane and the equipment calibration plane are aligned and coincident; the alignment and coincidence of the reference vehicle plane and the equipment calibration plane at least includes the coincidence of the central axis of the reference vehicle plane and the central axis of the equipment calibration plane.

[0082] The third aspect of the present invention discloses another vehicle centerline finding and calibration device based on a binocular camera, the device comprising:

[0083] A memory storing executable program code;

[0084] a processor coupled to the memory;

[0085] The processor calls the executable program code stored in the memory to execute the vehicle centerline finding and calibration method based on a binocular camera disclosed in the first aspect of the present invention.

[0086] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the vehicle centerline search and calibration method based on binocular cameras disclosed in the first aspect of the present invention.

[0087] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0088] In an embodiment of the present invention, a vehicle centerline search and calibration method based on a binocular camera is provided, the method comprising: detecting whether a calibration device currently meets an operating condition for performing a calibration operation on a vehicle to be calibrated; when it is detected that the calibration device currently meets the operating condition for performing the calibration operation, generating a distance measurement instruction for the calibration device, and controlling the calibration device to perform a first recognition operation on a set moving target according to the distance measurement instruction, and storing a corresponding first recognition result, the first recognition result at least including a measured distance between the calibration device and the moving target; removing the moving target, and after determining that the first target component and the second target component are mounted at the set recording position, controlling the calibration device to perform a second recognition operation on the first target component and the second target component An identification operation is performed to obtain a second identification result for the first target component and the second target component, the second identification result including first component identification data corresponding to the first target component and second component identification data corresponding to the second target component; the first target component and the second target component each include at least one binocular camera; according to the first identification result and the second identification result, parameter calibration is performed on the calibration device to update the second identification result, until it is determined that the second identification result meets the preset parameter calibration requirements, and then it is determined that the centering and calibration operations for the vehicle to be calibrated are completed; wherein the parameter calibration includes vehicle plane construction for the plane where the vehicle to be calibrated is located, device plane construction for the plane corresponding to the calibration device, and plane centering calibration. It can be seen that in the implementation of the present invention, under the premise that the calibration device can currently perform the calibration operation normally, the calibration device is controlled by the ranging instruction to perform the first recognition of the mobile target and store the corresponding first recognition result; then the calibration device is controlled to perform the second recognition of the first and second target components, so that the plane where the vehicle to be calibrated is located and the plane corresponding to the calibration device are constructed through the first recognition result and the second recognition result, and the intelligent and precise centering and calibration of the vehicle centerline are realized by centering, aligning, calibrating and correcting the two planes, thereby improving the centering accuracy and efficiency of the vehicle centerline as well as the calibration accuracy and efficiency; wherein, by using the binocular camera for ranging and recognition, compared with the traditional monocular vision or machine-type measuring tools, the spatial position information can be captured more accurately, which is beneficial to improving the accuracy of vehicle centerline search and calibration. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] 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.

[0090] Figure 1 It is a flow chart of a vehicle centerline finding and calibration method based on a binocular camera disclosed in an embodiment of the present invention;

[0091] Figure 2 It is a flow chart of another vehicle centerline finding and calibration method based on a binocular camera disclosed in an embodiment of the present invention;

[0092] Figure 3 It is a structural schematic diagram of a vehicle centerline finding and calibration device based on a binocular camera disclosed in an embodiment of the present invention;

[0093] Figure 4 It is a structural schematic diagram of another vehicle centerline finding and calibration device based on a binocular camera disclosed in an embodiment of the present invention;

[0094] Figure 5 It is a structural schematic diagram of another vehicle centerline finding and calibration device based on a binocular camera disclosed in an embodiment of the present invention;

[0095] Figure 6 It is a structural schematic diagram of another vehicle centerline finding and calibration device based on a binocular camera disclosed in an embodiment of the present invention;

[0096] Figure 7 It is a structural schematic diagram of another vehicle centerline finding and calibration device based on a binocular camera disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0097] 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 are within the scope of protection of the present invention.

[0098] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0099] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0100] The present invention discloses a vehicle centerline search and calibration method and device based on a binocular camera. Under the premise that the calibration device can currently perform the calibration operation normally, the calibration device is controlled by a distance measurement instruction to perform a first recognition on a mobile target and store the corresponding first recognition result; the calibration device is then controlled to perform a second recognition on the first and second target components, so that the plane where the vehicle to be calibrated is located and the plane corresponding to the calibration device are constructed by the first recognition result and the second recognition result. By centering, aligning, calibrating and correcting the two planes, the intelligent and precise centering and calibration of the vehicle centerline are realized, and the centering accuracy and centering efficiency of the vehicle centerline are improved. The distance measurement and recognition by the binocular camera can capture the spatial position information more accurately than the traditional monocular vision or machine-type measuring tools, which is conducive to improving the accuracy of the vehicle centerline search and calibration. The following are detailed descriptions.

[0101] Embodiment 1

[0102] See also Figure 1 , Figure 1 : is a flow chart of a vehicle centerline search and calibration method based on a binocular camera disclosed in an embodiment of the present invention. Figure 1 The described vehicle centerline search and calibration method based on a binocular camera can be applied to a vehicle centerline search and calibration device based on a binocular camera, and the embodiments of the present invention are not limited thereto. Figure 1 As shown, the vehicle centerline finding and calibration method based on a binocular camera may include the following operations:

[0103] 101. Detect whether a calibration device currently meets an operating condition for executing a calibration operation on a vehicle to be calibrated, and generate a distance measurement instruction for the calibration device when it is detected that the calibration device currently meets the operating condition for executing the calibration operation.

[0104] In an embodiment of the present invention, by setting the operating condition, the operation of the equipment can be detected before the calibration equipment is actually started, so as to determine that the operating condition is met before starting the calibration equipment, thereby reducing the error caused by inaccurate equipment parameter settings of the calibration equipment to subsequent calibration operations.

[0105] 102. Control the calibration device to perform a first recognition operation on the set mobile target according to the distance measurement instruction, and store a corresponding first recognition result, where the first recognition result at least includes a measured distance between the calibration device and the mobile target.

[0106] 103. Remove the mobile target, and after determining that the first target assembly and the second target assembly are mounted at the set recording locations, control the calibration device to perform a second identification operation on the first target assembly and the second target assembly to obtain a second identification result for the first target assembly and the second target assembly.

[0107] In the embodiment of the present invention, the second recognition result includes first component recognition data corresponding to the first target component and second component recognition data corresponding to the second target component; the first target component and the second target component each include at least one binocular camera.

[0108] 104. Perform parameter calibration on the calibration device according to the first recognition result and the second recognition result to update the second recognition result, until it is determined that the second recognition result meets the preset parameter calibration requirement, and it is determined that the centering and calibration operation for the vehicle to be calibrated is completed.

[0109] In the embodiment of the present invention, the parameter calibration includes vehicle plane construction for the plane where the vehicle to be calibrated is located, device plane construction for the plane corresponding to the calibration device, and plane centering calibration.

[0110] It can be seen that the implementation Figure 1 The described vehicle centerline search and calibration method based on binocular camera, under the premise that the calibration device can currently perform the calibration operation normally, controls the calibration device through the ranging instruction to perform the first recognition of the mobile target and stores the corresponding first recognition result; then controls the calibration device to perform the second recognition of the first and second target components, so as to realize the construction of the plane where the vehicle to be calibrated is located and the construction of the corresponding plane of the calibration device through the first recognition result and the second recognition result, and realizes the intelligent and precise centering and calibration of the vehicle centerline by centering, aligning, calibrating and correcting the two planes, thereby improving the centering accuracy and efficiency of the vehicle centerline as well as the calibration accuracy and efficiency; wherein, by using the binocular camera for ranging and recognition, compared with the traditional monocular vision or machine-type measuring tools, it can capture the spatial position information more accurately, which is conducive to improving the accuracy of vehicle centerline search and calibration.

[0111] In an optional embodiment, when it is detected that the calibration device currently does not meet the operating conditions for performing the calibration operation, the method further includes:

[0112] Acquire target calibration parameters corresponding to the calibration device, where the target calibration parameters include current calibration parameters of the calibration device and reference calibration parameters corresponding to the current calibration parameters;

[0113] Compare the current calibration parameters with the reference calibration parameters to obtain the difference parameters of the current calibration parameters relative to the reference calibration parameters;

[0114] Determining a parameter calibration item corresponding to the difference parameter, the parameter calibration item at least comprising a parameter calibration step;

[0115] According to the parameter calibration matters and in accordance with the parameter calibration steps, a device parameter calibration operation is performed on the calibration device to adjust the calibration device to an operating condition that satisfies the calibration operation.

[0116] In this alternative embodiment, see Figure 6 , Figure 6 FIG. 1 is a schematic diagram of another vehicle centerline finding and calibration device based on a binocular camera disclosed in an embodiment of the present invention. Figure 6 As shown, the device includes a binocular camera assembly C1, a binocular camera assembly C2, a monocular camera assembly C3, a target T1, a target T2, a sub-target T3 (placed horizontally) and a moving target T4.

[0117] It should be noted that the target calibration parameter includes at least one of the height from the ground, the device-vehicle offset distance, the calibration position, and the calibration state;

[0118] The height from the ground is used to indicate the relative distance between the center of the beam height on the calibration equipment and the ground; correspondingly, the height from the ground is Figure 6 The relative distance between the center of the beam on which the target T1 and target T2 are installed and the ground;

[0119] The calibration device comprises a first laser emitting component, which is used to emit an emission light parallel to the body of the vehicle to be calibrated, and the direction of the emission light is the direction corresponding to the front and rear wheels on the same side of the vehicle to be calibrated; the device-vehicle offset distance is the distance between the emission light and the body center axis of the vehicle to be calibrated, and the axis direction corresponding to the body center axis is consistent with the direction of the emission light;

[0120] The calibration device also includes at least two imaging components; the calibration position is used to indicate the component configuration position of the two imaging components corresponding to the vehicle to be calibrated; wherein the two imaging components correspond to Figure 6 The binocular camera component C1 and the binocular camera component C2;

[0121] The calibration state is used to indicate the component states of the two imaging components. The calibration state includes a standby state or an operating state opposite to the standby state. The operating state is used to indicate that the two imaging components have completed component initialization operations.

[0122] In this optional embodiment, the above-mentioned method of performing the device parameter calibration operation on the calibration device according to the parameter calibration matters and the parameter calibration steps specifically includes:

[0123] When the parameter calibration item includes a first item corresponding to the height from the ground, the height center of the beam of the calibration device is adjusted according to a standard height from the ground that matches the default height from the ground, so that the height adjustment value from the ground is consistent with the standard height from the ground; specifically, the standard height from the ground is generally set to 300 mm;

[0124] When the parameter calibration item includes a second item corresponding to the device-vehicle offset distance, controlling the calibration device to perform a translation operation in a preset vertical direction until it is determined that the device-vehicle offset distance is lower than a preset offset error; the preset vertical direction is perpendicular to the body direction of the vehicle to be calibrated;

[0125] When the parameter calibration item includes a third item corresponding to the calibration position, a group of symmetrical installation sites corresponding to the vehicle to be calibrated is determined, and the two imaging components are respectively set at the group of symmetrical installation sites; each group of symmetrical installation sites includes two installation sites, and the two installation sites are set on both sides of the vehicle to be calibrated, and the distances corresponding to the two installation sites to the body center axis of the vehicle to be calibrated are consistent; specifically, a conventionally set group of symmetrical installation points can be the left rear wheel and the right rear wheel corresponding to the vehicle to be calibrated; further, a wheel hub clamp is installed at each installation point and is perpendicular to the ground; a binocular camera assembly C1 and C2 are respectively embedded in the left and right wheel hub clamps;

[0126] When the parameter calibration items include a fourth item corresponding to the calibration state, the component states corresponding to the two imaging components are switched to the operating state.

[0127] It can be seen that in this optional embodiment, an adjustment plan is set up for the calibration equipment that does not meet the requirements for performing the calibration operation: by comparing the current calibration parameters with the benchmark calibration parameters in real time, the parameter calibration matters are intelligently determined, and the deviation is quickly adjusted to ensure that the calibration equipment can continue to maintain the best working state. The equipment adjustment process setting before the operation of the calibration equipment improves the accuracy of the setting of the operating parameters of the calibration equipment, thereby reducing the impact of the equipment error of the calibration equipment, which is beneficial to improving the operational accuracy of the calibration equipment in performing subsequent operations to a certain extent.

[0128] Embodiment 2

[0129] See also Figure 2 , Figure 2 is a flow chart of another vehicle centerline finding and calibration method based on a binocular camera disclosed in an embodiment of the present invention. Figure 2 The described vehicle centerline search and calibration method based on a binocular camera can be applied to a vehicle centerline search and calibration device based on a binocular camera, and the embodiments of the present invention are not limited thereto. Figure 2As shown, the vehicle centerline finding and calibration method based on a binocular camera may include the following operations:

[0130] 201. Detect whether a calibration device currently meets an operating condition for executing a calibration operation on a vehicle to be calibrated, and generate a distance measurement instruction for the calibration device when it is detected that the calibration device currently meets the operating condition for executing the calibration operation.

[0131] 202. After determining that the set moving target is at a preset ranging starting point and the second laser component on the moving target is switched to an on state, according to the ranging instruction, control any one of the two imaging components to perform target recognition on the moving target to obtain target recognition data for the moving target.

[0132] In the embodiment of the present invention, the distance measurement starting point can be set at the center of the front wheel of the vehicle to be calibrated, or can be set at the center of the front bumper. The setting of the distance measurement starting point is adjusted according to different vehicle models, and the embodiment of the present invention does not limit this.

[0133] 203. Calculate the ranging distance between any imaging component and the ranging starting point according to the target recognition data and in combination with the configuration position of any imaging component on the vehicle to be calibrated and the ranging starting point.

[0134] 204. Determine the configuration position, ranging starting point, and ranging distance corresponding to each imaging component as a first recognition result.

[0135] In the embodiment of the present invention, the straight-line distances between the two imaging components and the distance measurement starting point are the same, and the distance measurement starting point is set right in front of or behind the vehicle to be calibrated.

[0136] 205. Store a corresponding first recognition result, where the first recognition result at least includes a measured distance between the calibration device and the mobile target.

[0137] 206. Remove the mobile target, and after determining that the first target assembly and the second target assembly are mounted at the set recording locations, control the calibration device to perform a second identification operation on the first target assembly and the second target assembly to obtain a second identification result for the first target assembly and the second target assembly.

[0138] 207. Perform parameter calibration on the calibration device according to the first recognition result and the second recognition result to update the second recognition result, until it is determined that the second recognition result meets the preset parameter calibration requirement, and it is determined that the centering and calibration operation for the vehicle to be calibrated is completed.

[0139] In the embodiment of the present invention, for other descriptions of step 201 and step 206-step 207, please refer to other specific descriptions of step 101 and step 103-step 104 in embodiment 1, and the embodiment of the present invention will not be repeated here.

[0140] It can be seen that the implementation Figure 2 The described vehicle centerline search and calibration method based on binocular camera controls any imaging component to perform recognition on a mobile target, and then combines the target recognition data, the ranging distance, and the corresponding configuration position of each imaging component to determine a first recognition result; the first recognition result is used to construct the plane where the vehicle to be calibrated is located, and data is prepared for the construction of the plane where the vehicle to be calibrated is located; at the same time, based on the intelligent recognition of the mobile target by the binocular camera, compared with traditional monocular vision or machine-type measurement tools, it can capture spatial position information more accurately, which is conducive to improving the determination accuracy of the ranging distance.

[0141] In an optional embodiment, the two imaging components include a first imaging component and a second imaging component; the first imaging component and the first target component are arranged on the same side; the second imaging component and the second target component are arranged on the same side; the first target component includes a sub-target component; the second target component includes a third imaging component;

[0142] In this optional embodiment, the corresponding relationship between the imaging component and the target component can also be that the first imaging component and the second target component are arranged on the same side; the second imaging component and the first target component are arranged on the same side, which is not limited in the embodiment of the present invention;

[0143] The above step 206 controls the calibration device to perform a second identification operation on the first target component and the second target component, and the method of obtaining the second identification result for the first target component and the second target component specifically includes:

[0144] Controlling the first imaging component to perform component recognition on the first target component, and obtaining first position data and first component distance corresponding to the first target component as first component recognition data;

[0145] Controlling the second imaging component to perform component recognition on the second target component, and obtaining second posture data and a second component distance corresponding to the second target component as second component recognition data;

[0146] Controlling the third imaging component to perform component recognition on the sub-target component, and obtaining third posture data and a third component distance corresponding to the sub-target component as third component recognition data;

[0147] The first component identification data, the second component identification data, and the third component identification data are determined as a second identification result.

[0148] It can be seen that in this optional embodiment, the first imaging component, the second imaging component and the third imaging component are used to perform intelligent and precise identification on the first and second target components and the sub-target components, respectively, so as to determine the second identification result. The second identification result is used to construct a device plane corresponding to the calibration device, thereby improving the identification and collection accuracy and reliability of the data required to construct the device plane.

[0149] In another optional embodiment, the above step 207 performs parameter calibration on the calibration device according to the first recognition result and the second recognition result, specifically including:

[0150] determining a reference vehicle plane corresponding to the vehicle to be calibrated according to the first recognition result;

[0151] determining a device calibration plane corresponding to the calibration device according to the second recognition result;

[0152] Taking the reference vehicle plane as the calibration target, and combining the set multiple plane calibration factors, plane correction is performed on the device calibration plane to obtain a plane correction result for the device calibration plane;

[0153] The multiple plane calibration factors include angle values ​​corresponding to multiple correction angles of a device beam on the calibration device relative to a vehicle to be calibrated, and the multiple correction angles include at least one of a yaw angle, a tilt angle, and a pitch angle.

[0154] In this optional embodiment, specifically, the reference vehicle plane corresponds to Figure 6 The plane formed by the height center of the beam of the middle calibration device, the first imaging component C1 and the second imaging component C2;

[0155] The calibration plane of the device corresponds to the plane surrounded by the first imaging component C1, the first target component T1, the second imaging component C2, the second target component T2, the third imaging component C3, and the sub-target component T3;

[0156] In this optional embodiment, further, the above-mentioned method of taking the reference vehicle plane as the calibration target, combining the set multiple plane calibration factors, performing plane correction on the device calibration plane, and obtaining the plane correction result for the device calibration plane specifically includes:

[0157] Determine a first correction angle value corresponding to each correction angle and obtain an error correction interval corresponding to each correction angle;

[0158] Determine a second correction angle value corresponding to the device calibration plane and each correction angle;

[0159] For each correction angle, based on the first correction angle value and the error correction interval corresponding to the correction angle, a second correction angle value corresponding to the correction angle is numerically corrected to obtain a numerical correction result corresponding to the correction angle, wherein the numerical correction result corresponding to the correction angle includes a plurality of sub-correction angle values;

[0160] Determine the numerical correction result corresponding to each correction angle as the plane correction result for the device calibration plane;

[0161] And, the second recognition result meets the parameter calibration requirement including:

[0162] The numerical difference between the second correction value corresponding to each correction angle and the first correction value corresponding to the correction angle is within the error correction interval corresponding to the correction angle, and the reference vehicle plane and the equipment calibration plane are aligned and coincident; the alignment and coincidence of the reference vehicle plane and the equipment calibration plane at least includes the coincidence of the central axis of the reference vehicle plane and the central axis of the equipment calibration plane.

[0163] In this alternative embodiment, see Figure 7 , Figure 7 is a structural schematic diagram of another vehicle centerline finding and calibration device based on a binocular camera disclosed in an embodiment of the present invention, such as Figure 7 As shown, by integrating and displaying the data collected by the first recognition result and the second recognition result on a dedicated display interface, and the display interface can issue corresponding control instructions, and adjust the calibration device based on the control instructions (actually, the crossbeam of the calibration device can be adjusted), thereby adjusting at least three parameter values ​​of the calibration device, and the three parameters include a target distance Distance, a target angle Angle (corresponding to the above-mentioned tilt angle) and a target offset Offset (corresponding to the above-mentioned yaw angle);

[0164] The target distance Distance is used to refer to the horizontal distance between the calibration device and the vehicle to be calibrated. Generally, the reference value of the target distance Distance is [-100mm, 100mm].

[0165] The target angle Angle is used to refer to the angle formed by the initial beam position of the calibration device and the beam position after real-time adjustment. Generally, the reference value of the target angle Angle is [-2°, 2°].

[0166] The target offset Offset is used to refer to the offset between the height center of the beam of the calibration equipment and the body axis center of the vehicle to be calibrated. Generally, the reference value of the target offset Offset is [-50mm, 50mm];

[0167] Among them, it should be noted that the initial position of the beam of the calibration device is taken as the zero point, and the beam of the calibration device includes a left wing, a center and a right wing; when the beam of the calibration device shifts to the left (it can be understood that the center position of the beam remains unchanged, and the center of gravity shifts to the left wing), the values ​​of the three parameters are negative numbers; when the beam of the calibration device shifts to the right (it can be understood that the center position of the beam remains unchanged, and the center of gravity shifts to the right wing), the values ​​of the three parameters are positive numbers; optionally, according to actual usage requirements, the positive and negative correspondence between the beam offset and the parameter value can also be reversed, which is not limited in this optional embodiment.

[0168] In this optional embodiment, further optionally, for the offset of the calibration device, in addition to being able to adjust the left and right wing offsets of the beam while controlling the beam center of the calibration device to remain unchanged as described above, the front and rear offsets of the beam center can also be adjusted, that is, the beam center is controlled to be close to the vehicle to be calibrated or away from the vehicle to be calibrated; optionally, the beam center can also be controlled to rotate in the vertical direction (corresponding to adjusting the above-mentioned pitch angle).

[0169] It can be seen that in this optional embodiment, by setting multiple correction angles, the calibration equipment can adapt to multi-dimensional calibration requirements, corresponding to the calibration requirements of yaw angle, tilt angle and pitch angle corresponding to front and back, left and right, up and down, thereby helping to improve the fineness and accuracy of centering and calibration operations.

[0170] Embodiment 3

[0171] See also Figure 3 , Figure 3 It is a structural diagram of a vehicle centerline finding and calibration device based on a binocular camera disclosed in an embodiment of the present invention. The vehicle centerline finding and calibration device based on a binocular camera can be a vehicle centerline finding and calibration terminal, device, system or server based on a binocular camera. The server can be a local server, a remote server, or a cloud server (also called a cloud server). When the server is a non-cloud server, the non-cloud server can communicate with the cloud server, which is not limited in the embodiment of the present invention. Figure 3 As shown, the vehicle centerline finding and calibration device based on a binocular camera may include a detection module 301, an instruction generation module 302, a first recognition module 303, a second recognition module 304 and a calibration processing module 305, wherein:

[0172] The detection module 301 is used to detect whether the calibration device currently meets the operating conditions for performing the calibration operation on the vehicle to be calibrated.

[0173] The instruction generation module 302 is used to generate a distance measurement instruction for the calibration device when the detection module 301 detects that the calibration device currently meets the operating conditions for performing the calibration operation.

[0174] The first recognition module 303 is used to control the calibration device to perform a first recognition operation on the set mobile target according to the distance measurement instruction, and store the corresponding first recognition result, which at least includes the measured distance between the calibration device and the mobile target.

[0175] The second identification module 304 is used to remove the mobile target and, after determining that the first target component and the second target component are mounted at the set recording position, control the calibration device to perform a second identification operation on the first target component and the second target component to obtain a second identification result for the first target component and the second target component, the second identification result including first component identification data corresponding to the first target component and second component identification data corresponding to the second target component; the first target component and the second target component each include at least one binocular camera.

[0176] The calibration processing module 305 is used to perform parameter calibration on the calibration device according to the first recognition result and the second recognition result to update the second recognition result, until it is determined that the second recognition result meets the preset parameter calibration requirements, and then the centering and calibration operations for the vehicle to be calibrated are completed; wherein the parameter calibration includes vehicle plane construction for the plane where the vehicle to be calibrated is located, device plane construction for the plane corresponding to the calibration device, and plane centering calibration.

[0177] It can be seen that the implementation Figure 3 The described vehicle centerline search and calibration device based on a binocular camera, under the premise that the calibration device can currently perform the calibration operation normally, controls the calibration device through a ranging instruction to perform a first recognition of a mobile target and stores the corresponding first recognition result; then controls the calibration device to perform a second recognition of the first and second target components, thereby realizing the construction of a plane where the vehicle to be calibrated is located and the construction of a corresponding plane of the calibration device through the first recognition result and the second recognition result, and realizing intelligent and precise centering and calibration of the vehicle centerline by centering, aligning, calibrating and correcting the two planes, thereby improving the centering accuracy and efficiency of the vehicle centerline as well as the calibration accuracy and efficiency; wherein, by using a binocular camera for ranging and recognition, compared with traditional monocular vision or machine-type measuring tools, it is possible to capture spatial position information more accurately, which is beneficial to improving the accuracy of vehicle centerline search and calibration.

[0178] In an alternative embodiment, see Figure 4 , Figure 4 FIG. 1 is a schematic diagram of another vehicle centerline finding and calibration device based on a binocular camera disclosed in an embodiment of the present invention. Figure 4 As shown, the device also includes a parameter acquisition module 306, a parameter comparison module 307 and a determination module 308, wherein:

[0179] The parameter acquisition module 306 is used to acquire the target calibration parameters corresponding to the calibration device when the detection module 301 detects that the calibration device currently does not meet the operating conditions for performing the calibration operation, where the target calibration parameters include the current calibration parameters of the calibration device and the reference calibration parameters corresponding to the current calibration parameters;

[0180] The parameter comparison module 307 is used to compare the current calibration parameters with the reference calibration parameters to obtain the difference parameters of the current calibration parameters relative to the reference calibration parameters;

[0181] A determination module 308, configured to determine a parameter calibration item corresponding to the difference parameter, wherein the parameter calibration item at least includes a parameter calibration step;

[0182] The calibration processing module 305 is further used to perform a device parameter calibration operation on the calibration device according to the parameter calibration items and the parameter calibration steps, so as to adjust the calibration device to an operating condition that satisfies the calibration operation.

[0183] In this optional embodiment, it should be noted that the target calibration parameter includes at least one of a height from the ground, a device-vehicle offset distance, a calibration position, and a calibration state;

[0184] The height from the ground is used to indicate the relative distance between the center of the beam height on the calibration equipment and the ground;

[0185] The calibration device includes a first laser emitting component, which is used to emit a light beam parallel to the body of the vehicle to be calibrated, and the direction of the emitted light beam is the direction corresponding to the front and rear wheels on the same side of the vehicle to be calibrated; the device-vehicle offset distance is the distance between the emitted light beam and the body center axis of the vehicle to be calibrated, and the axial direction corresponding to the body center axis is consistent with the direction of the emitted light beam;

[0186] The calibration device also includes at least two imaging components; the calibration position is used to indicate the component configuration positions of the two imaging components corresponding to the vehicle to be calibrated;

[0187] The calibration state is used to indicate the component states of the two imaging components. The calibration state includes a standby state or an operating state opposite to the standby state. The operating state is used to indicate that the two imaging components have completed the component initialization operation.

[0188] It can be seen that in this optional embodiment, an adjustment plan is set up for the calibration equipment that does not meet the requirements for performing the calibration operation: by comparing the current calibration parameters with the benchmark calibration parameters in real time, the parameter calibration matters are intelligently determined, and the deviation is quickly adjusted to ensure that the calibration equipment can continue to maintain the best working state. The equipment adjustment process setting before the operation of the calibration equipment improves the accuracy of the setting of the operating parameters of the calibration equipment, thereby reducing the impact of the equipment error of the calibration equipment, which is beneficial to improving the operational accuracy of the calibration equipment in performing subsequent operations to a certain extent.

[0189] In another optional embodiment, the first recognition module 303 controls the calibration device to perform the first recognition operation on the set moving target according to the ranging instruction, specifically including:

[0190] After determining that the set moving target is at the preset distance measurement starting point and the second laser component on the moving target is switched to the on state, according to the distance measurement instruction, controlling any one of the two imaging components to perform target recognition on the moving target to obtain target recognition data for the moving target;

[0191] According to the target recognition data, in combination with the configuration position of any imaging component on the vehicle to be calibrated and the ranging starting point, the ranging distance between any imaging component and the ranging starting point is calculated;

[0192] Determine the configuration position, ranging starting point, and ranging distance corresponding to each imaging component as a first recognition result;

[0193] The straight-line distances between the two imaging components and the distance measurement starting point are the same, and the distance measurement starting point is set right in front of or right behind the vehicle to be calibrated.

[0194] It can be seen that in this optional embodiment, by controlling any imaging component to perform recognition on the mobile target, and then combining the target recognition data, the ranging distance, and the corresponding configuration position of each imaging component, a first recognition result is determined; the first recognition result is used to construct the plane where the vehicle to be calibrated is located, and data is prepared for the construction of the plane where the vehicle to be calibrated is located; at the same time, based on the intelligent recognition of the mobile target by the binocular camera, compared with traditional monocular vision or machine-type measurement tools, it can more accurately capture spatial position information, which is beneficial to improve the determination accuracy of the ranging distance.

[0195] In another optional embodiment, the two imaging components include a first imaging component and a second imaging component; the first imaging component and the first target component are arranged on the same side; the second imaging component and the second target component are arranged on the same side; the first target component includes a sub-target component; the second target component includes a third imaging component;

[0196] The second identification module 304 controls the calibration device to perform a second identification operation on the first target component and the second target component, and obtains a second identification result for the first target component and the second target component in a manner that specifically includes:

[0197] Controlling the first imaging component to perform component recognition on the first target component, and obtaining first position data and first component distance corresponding to the first target component as first component recognition data;

[0198] Controlling the second imaging component to perform component recognition on the second target component, and obtaining second posture data and a second component distance corresponding to the second target component as second component recognition data;

[0199] Controlling the third imaging component to perform component recognition on the sub-target component, and obtaining third posture data and a third component distance corresponding to the sub-target component as third component recognition data;

[0200] The first component identification data, the second component identification data, and the third component identification data are determined as a second identification result.

[0201] It can be seen that in this optional embodiment, the first imaging component, the second imaging component and the third imaging component are used to perform intelligent and precise identification on the first and second target components and the sub-target components, respectively, so as to determine the second identification result. The second identification result is used to construct a device plane corresponding to the calibration device, thereby improving the identification and collection accuracy and reliability of the data required to construct the device plane.

[0202] In another optional embodiment, the calibration processing module 305 performs parameter calibration on the calibration device according to the first recognition result and the second recognition result, specifically including:

[0203] determining a reference vehicle plane corresponding to the vehicle to be calibrated according to the first recognition result;

[0204] determining a device calibration plane corresponding to the calibration device according to the second recognition result;

[0205] Taking the reference vehicle plane as the calibration target, and combining the set multiple plane calibration factors, plane correction is performed on the device calibration plane to obtain a plane correction result for the device calibration plane;

[0206] The multiple plane calibration factors include angle values ​​corresponding to multiple correction angles of a device beam on the calibration device relative to a vehicle to be calibrated, and the multiple correction angles include at least one of a yaw angle, a tilt angle, and a pitch angle.

[0207] In this optional embodiment, further, the calibration processing module 305 uses the reference vehicle plane as the calibration target, combines the set multiple plane calibration factors, performs plane correction on the device calibration plane, and obtains the plane correction result for the device calibration plane in a manner specifically including:

[0208] Determine a first correction angle value corresponding to each correction angle and obtain an error correction interval corresponding to each correction angle;

[0209] Determine a second correction angle value corresponding to the device calibration plane and each correction angle;

[0210] For each correction angle, based on the first correction angle value and the error correction interval corresponding to the correction angle, a second correction angle value corresponding to the correction angle is numerically corrected to obtain a numerical correction result corresponding to the correction angle, wherein the numerical correction result corresponding to the correction angle includes a plurality of sub-correction angle values;

[0211] Determine the numerical correction result corresponding to each correction angle as the plane correction result for the device calibration plane;

[0212] And, the second recognition result meets the parameter calibration requirement including:

[0213] The numerical difference between the second correction value corresponding to each correction angle and the first correction value corresponding to the correction angle is within the error correction interval corresponding to the correction angle, and the reference vehicle plane and the equipment calibration plane are aligned and coincident; the alignment and coincidence of the reference vehicle plane and the equipment calibration plane at least includes the coincidence of the central axis of the reference vehicle plane and the central axis of the equipment calibration plane.

[0214] It can be seen that in this optional embodiment, by setting multiple correction angles, the calibration equipment can adapt to multi-dimensional calibration requirements, corresponding to the calibration requirements of yaw angle, tilt angle and pitch angle corresponding to front and back, left and right, up and down, thereby helping to improve the fineness and accuracy of centering and calibration operations.

[0215] Embodiment 4

[0216] See also Figure 5 , Figure 5 FIG. 1 is a schematic diagram of another vehicle centerline finding and calibration device based on a binocular camera disclosed in an embodiment of the present invention. Figure 5 As shown, the vehicle centerline finding and calibration device based on a binocular camera may include:

[0217] A memory 401 storing executable program codes;

[0218] a processor 402 coupled to the memory 401;

[0219] The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the vehicle centerline finding and calibration method based on a binocular camera described in the first embodiment of the present invention or the second embodiment of the present invention.

[0220] Embodiment 5

[0221] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps in the vehicle centerline search and calibration method based on a binocular camera described in Embodiment 1 or Embodiment 2 of the present invention.

[0222] Embodiment 6

[0223] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the vehicle centerline search and calibration method based on a binocular camera described in Embodiment 1 or Embodiment 2.

[0224] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0225] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0226] Finally, it should be noted that the vehicle centerline search and calibration method and device based on a binocular camera disclosed in the embodiment of the present invention discloses only a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A vehicle centerline search and calibration method based on a binocular camera, characterized in that: The method comprises: Detecting whether the calibration device currently meets the operating conditions for performing the calibration operation on the vehicle to be calibrated, and when it is detected that the calibration device currently meets the operating conditions for performing the calibration operation, generating a distance measurement instruction for the calibration device, and controlling the calibration device to perform a first recognition operation on a set mobile target according to the distance measurement instruction, and storing a corresponding first recognition result, wherein the first recognition result at least includes a measured distance between the calibration device and the mobile target; The mobile target is removed, and after determining that the first target component and the second target component are mounted at the set recording position, the calibration device is controlled to perform a second recognition operation on the first target component and the second target component to obtain a second recognition result for the first target component and the second target component, wherein the second recognition result includes first component recognition data corresponding to the first target component and second component recognition data corresponding to the second target component; the first target component and the second target component each include at least one binocular camera; According to the first recognition result and the second recognition result, performing parameter calibration on the calibration device to update the second recognition result, until after determining that the second recognition result meets a preset parameter calibration requirement, determining that the centering and calibration operation for the vehicle to be calibrated is completed; The parameter calibration includes vehicle plane construction for the plane where the vehicle to be calibrated is located, device plane construction for the plane corresponding to the calibration device, and plane centering calibration.

2. The vehicle centerline search and calibration method based on a binocular camera according to claim 1, characterized in that: When it is detected that the calibration device currently does not meet the operating conditions for performing the calibration operation, the method further includes: Acquire target calibration parameters corresponding to the calibration device, where the target calibration parameters include current calibration parameters of the calibration device and reference calibration parameters corresponding to the current calibration parameters; Comparing the current calibration parameter with the reference calibration parameter to obtain a difference parameter between the current calibration parameter and the reference calibration parameter; Determining a parameter calibration item corresponding to the difference parameter, wherein the parameter calibration item at least includes a parameter calibration step; According to the parameter calibration matters and in accordance with the parameter calibration steps, a device parameter calibration operation is performed on the calibration device to adjust the calibration device to an operating condition that satisfies the calibration operation.

3. The vehicle centerline search and calibration method based on binocular camera according to claim 2, characterized in that: The target calibration parameter includes at least one of a height from the ground, a device-vehicle offset distance, a calibration position, and a calibration state; The height from the ground is used to indicate the relative distance between the height center of the beam on the calibration device and the ground; The calibration device comprises a first laser emitting component, the first laser emitting component is used to emit an emission light parallel to the body of the vehicle to be calibrated, the direction of the emission light is the direction corresponding to the front and rear wheels on the same side of the vehicle to be calibrated; the device-vehicle offset distance is the distance between the emission light and the body center axis of the vehicle to be calibrated, and the axial direction corresponding to the body center axis is consistent with the direction of the emission light; The calibration device further comprises at least two imaging components; the calibration position is used to indicate the component configuration positions of the two imaging components corresponding to the vehicle to be calibrated; The calibration status is used to indicate the component status of the two imaging components. The calibration status includes a standby state or an operating state opposite to the standby state. The operating state is used to indicate that the two imaging components have completed component initialization operations.

4. The vehicle centerline search and calibration method based on binocular camera according to claim 3 is characterized in that: The step of controlling the calibration device to perform a first recognition operation on a set moving target according to the ranging instruction includes: After determining that the set moving target is at a preset distance measurement starting point and the second laser component on the moving target is switched to an on state, according to the distance measurement instruction, controlling any one of the two imaging components to perform target recognition on the moving target to obtain target recognition data for the moving target; According to the target recognition data, in combination with the configuration position of any imaging component on the vehicle to be calibrated and the ranging starting point, the ranging distance between any imaging component and the ranging starting point is calculated; Determine the configuration position, the ranging starting point, and the ranging distance corresponding to each imaging component as a first recognition result; The straight-line distances between the two imaging components and the distance measurement starting point are the same, and the distance measurement starting point is set right in front of or behind the vehicle to be calibrated.

5. The vehicle centerline search and calibration method based on binocular camera according to claim 3, characterized in that: The two imaging components include a first imaging component and a second imaging component; the first imaging component and the first target component are arranged on the same side; the second imaging component and the second target component are arranged on the same side; the first target component includes a sub-target component; the second target component includes a third imaging component; The controlling the calibration device to perform a second identification operation on the first target component and the second target component to obtain a second identification result for the first target component and the second target component includes: Controlling the first imaging component to perform component recognition on the first target component, and obtaining first position data and first component distance corresponding to the first target component as first component recognition data; Controlling the second imaging component to perform the component identification on the second target component, and obtaining second posture data and second component distance corresponding to the second target component as second component identification data; Controlling the third imaging component to perform the component identification on the sub-target component, and obtaining third posture data and a third component distance corresponding to the sub-target component as third component identification data; The first component identification data, the second component identification data, and the third component identification data are determined as a second identification result.

6. The vehicle centerline search and calibration method based on binocular camera according to claim 5, characterized in that: The performing parameter calibration on the calibration device according to the first recognition result and the second recognition result includes: Determining a reference vehicle plane corresponding to the vehicle to be calibrated according to the first recognition result; determining a device calibration plane corresponding to the calibration device according to the second recognition result; Taking the reference vehicle plane as a calibration target, and combining a plurality of set plane calibration factors, performing plane correction on the device calibration plane to obtain a plane correction result for the device calibration plane; The multiple plane calibration factors include angle values ​​corresponding to multiple correction angles of a device beam on the calibration device relative to the vehicle to be calibrated, and the multiple correction angles include at least one of a yaw angle, a tilt angle, and a pitch angle.

7. The vehicle centerline search and calibration method based on binocular camera according to claim 6, characterized in that: The process of taking the reference vehicle plane as a calibration target and performing plane correction on the device calibration plane in combination with a plurality of set plane calibration factors to obtain a plane correction result for the device calibration plane includes: Determine a first correction angle value corresponding to the reference vehicle plane and each correction angle, and obtain an error correction interval corresponding to each correction angle; Determine a second correction angle value corresponding to the device calibration plane and each correction angle; For each correction angle, based on the first correction angle value corresponding to the correction angle and the error correction interval, perform numerical correction on the second correction angle value corresponding to the correction angle to obtain a numerical correction result corresponding to the correction angle, wherein the numerical correction result corresponding to the correction angle includes a plurality of sub-correction angle values; Determine the numerical correction result corresponding to each correction angle as a plane correction result for the device calibration plane; And, the second recognition result meets the parameter calibration requirement including: The numerical difference between the second correction value corresponding to each correction angle and the first correction value corresponding to the correction angle is within the error correction interval corresponding to the correction angle, and the reference vehicle plane and the equipment calibration plane are aligned and coincident; the alignment and coincidence of the reference vehicle plane and the equipment calibration plane at least includes the coincidence of the central axis of the reference vehicle plane and the central axis of the equipment calibration plane.

8. A vehicle centerline search and calibration device based on a binocular camera, characterized in that: The device comprises: A detection module, used to detect whether the calibration device currently meets the operating conditions for performing a calibration operation on the vehicle to be calibrated; an instruction generating module, configured to generate a distance measurement instruction for the calibration device when the detection module detects that the calibration device currently meets the operating conditions for performing the calibration operation; A first recognition module, configured to control the calibration device to perform a first recognition operation on a set mobile target according to the distance measurement instruction, and store a corresponding first recognition result, wherein the first recognition result at least includes a measured distance between the calibration device and the mobile target; a second identification module, for removing the mobile target, and after determining that the first target component and the second target component are mounted at the set recording position, controlling the calibration device to perform a second identification operation on the first target component and the second target component, and obtaining a second identification result for the first target component and the second target component, wherein the second identification result includes first component identification data corresponding to the first target component and second component identification data corresponding to the second target component; the first target component and the second target component each include at least one binocular camera A calibration processing module is used to perform parameter calibration on the calibration device according to the first recognition result and the second recognition result to update the second recognition result, until it is determined that the second recognition result meets the preset parameter calibration requirements, and then determine that the centering and calibration operations for the vehicle to be calibrated are completed; wherein the parameter calibration includes vehicle plane construction for the plane where the vehicle to be calibrated is located, device plane construction for the plane corresponding to the calibration device, and plane centering calibration.

9. A vehicle centerline search and calibration device based on a binocular camera, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the vehicle centerline finding and calibration method based on a binocular camera as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the vehicle centerline finding and calibration method based on a binocular camera as described in any one of claims 1-7.

Images