Monocular camera offline calibration method and system, storage medium and computer

Abstract

The application provides a monocular camera offline calibration method, system, storage medium and computer, which comprises the following steps: reading the part information of the monocular camera on the vehicle to be calibrated, correcting the part information, and entering the expansion mode if the part information is corrected; writing the vehicle information of the vehicle to be calibrated in the expansion mode, obtaining the corresponding control sequence based on the vehicle information, starting the calibration program of the vehicle to be calibrated by using the control sequence, and obtaining the corresponding calibration result; judging the calibration result, if the calibration result is not equal to the first calibration threshold, judging whether the calibration result is equal to the second calibration threshold; if the calibration result is not equal to the second calibration threshold, obtaining the calibration times of the calibration result; if the calibration times of the calibration result are not greater than the calibration times threshold, recalibrating the vehicle to be calibrated by using the calibration program until the calibration result is equal to the first calibration threshold, so that the vehicle to be calibrated is successfully calibrated.

Description

Offline calibration method, system, storage medium and computer for monocular cameras Technical Field

[0001] This invention relates to the field of vehicle calibration technology, and in particular to a method, system, storage medium, and computer for the offline calibration of a monocular camera. Background Technology

[0002] With the continuous improvement of automotive automation and intelligence, the installation volume of forward-looking monocular cameras is also increasing. A forward-looking monocular camera maps real-world three-dimensional objects onto a two-dimensional plane. During the imaging process, image distortion occurs, requiring appropriate distortion correction to adapt to the algorithm. This series of operations can be called the camera's coordinate transformation. The conversion from real-world three-dimensional coordinates to camera three-dimensional coordinates is called the extrinsic parameter matrix, while the conversion from camera three-dimensional coordinates to two-dimensional coordinate projection is called the intrinsic parameter matrix. Finally, distortion coefficients (distortion correction after two-dimensional imaging) are used for calibration.

[0003] As one of the core sensors in Advanced Driver Assistance Systems (ADAS), the forward-facing monocular camera is crucial for driving safety. Therefore, it must undergo a complex off-line calibration process before the vehicle rolls off the production line. However, existing off-line calibration methods require highly skilled personnel and manual judgment during the calibration process. Manual operation makes it difficult to guarantee the accuracy of the calibration process, resulting in low efficiency and a low pass rate. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a method, system, storage medium and computer for offline calibration of a monocular camera, so as to at least solve the shortcomings of the above-mentioned related technologies.

[0005] This invention proposes a method for offline calibration of a monocular camera, comprising:

[0006] Read the component information of the monocular camera on the vehicle to be calibrated, and verify the component information. If the component information is verified to be qualified, enter the extended mode.

[0007] In the extended mode, the vehicle information of the vehicle to be calibrated is written, the corresponding control sequence is obtained based on the vehicle information, and the calibration program of the vehicle to be calibrated is started using the control sequence to obtain the corresponding calibration result.

[0008] The calibration result is evaluated. If the calibration result is not equal to the first calibration threshold, then it is determined whether the calibration result is equal to the second calibration threshold.

[0009] If the calibration result is not equal to the second calibration threshold, then obtain the number of calibrations for the calibration result;

[0010] If the number of calibrations in the calibration result is not greater than the calibration number threshold, the vehicle to be calibrated is recalibrated using the calibration procedure until the calibration result is equal to the first calibration threshold, so that the vehicle to be calibrated is successfully calibrated.

[0011] Furthermore, the step of using the control sequence to start the calibration program of the vehicle to be calibrated in order to obtain the corresponding calibration result includes:

[0012] The image information collected by the monocular camera under different directions of the vehicle to be calibrated is acquired, and the position data of the geometric elements in each image information are determined by image analysis.

[0013] Construct an image coordinate system, and use the image coordinate system and the position data to determine the actual orientation angle of the monocular camera;

[0014] The actual orientation angle and the preset orientation angle are calibrated to output the orientation angle calibration result of the monocular camera.

[0015] Furthermore, after the step of judging the calibration result, the method further includes:

[0016] If the calibration result is equal to the first calibration threshold, then the calibration procedure is marked as successful.

[0017] Read the calibration results and parse out the calibration tracking domain from the calibration results;

[0018] Upon receiving the successful transmission signal of the calibration tracking domain, exit the extended mode.

[0019] Furthermore, after obtaining the number of calibrations in the calibration result, the method further includes:

[0020] If the number of calibrations in the calibration result is greater than the calibration count threshold, then the current calibration procedure is marked as a calibration failure.

[0021] Obtain the calibration log of the calibration results, and perform data analysis on the calibration log based on the calibration database to obtain the corresponding abnormal information.

[0022] Furthermore, the step of obtaining the corresponding control sequence based on the vehicle information includes:

[0023] Obtain the security algorithm of the monocular camera, and generate the corresponding key message based on the security algorithm;

[0024] The key message is input into the key database for key comparison. If the key message is correct, the ECU hardware sequence message of the monocular camera is obtained and the ECU hardware sequence message is verified.

[0025] If the ECU hardware sequence message is verified to be correct, the corresponding control sequence is obtained based on the ECU hardware sequence message.

[0026] This invention also proposes a post-production calibration system for a monocular camera, comprising:

[0027] The information reading module is used to read the component information of the monocular camera on the vehicle to be calibrated, and to calibrate the component information. If the component information is qualified, it enters the extended mode.

[0028] The vehicle calibration module is used to write the vehicle information of the vehicle to be calibrated in the extended mode, obtain the corresponding control sequence based on the vehicle information, and start the calibration program of the vehicle to be calibrated using the control sequence to obtain the corresponding calibration result.

[0029] The first result judgment module is used to judge the calibration result. If the calibration result is not equal to the first calibration threshold, then it is judged whether the calibration result is equal to the second calibration threshold.

[0030] The calibration count acquisition module is used to acquire the calibration count of the calibration result if the calibration result is not equal to the second calibration threshold.

[0031] The second result judgment module is used to recalibrate the vehicle to be calibrated using the calibration program if the calibration result is not greater than the calibration number threshold, until the calibration result is equal to the first calibration threshold, so that the vehicle to be calibrated is successfully calibrated.

[0032] Furthermore, the vehicle calibration module includes:

[0033] The data acquisition unit is used to acquire image information collected by the monocular camera in different directions of the vehicle to be calibrated, and to use image analysis to determine the position data of geometric elements in each image information.

[0034] An orientation angle calculation unit is used to construct an image coordinate system and determine the actual orientation angle of the monocular camera using the image coordinate system and the position data.

[0035] The vehicle calibration unit is used to calibrate the actual direction angle and the preset direction angle to output the direction angle calibration result of the monocular camera.

[0036] Furthermore, the system also includes:

[0037] The third result judgment module is used to mark the current calibration procedure as successful if the calibration result is equal to the first calibration threshold.

[0038] The calibration result reading module is used to read the calibration result and parse the calibration tracking domain in the calibration result;

[0039] The data transmission module is used to exit the extended mode after receiving the calibration tracking domain transmission success signal.

[0040] Furthermore, the system also includes:

[0041] The fourth result judgment module is used to mark the current calibration procedure as a calibration failure if the number of calibrations of the calibration result is greater than the calibration number threshold.

[0042] The data analysis module is used to obtain the calibration log of the calibration result and perform data analysis on the calibration log based on the calibration database to obtain the corresponding abnormal information.

[0043] Furthermore, the vehicle calibration module also includes:

[0044] An algorithm acquisition unit is used to acquire the security algorithm of the monocular camera and generate a corresponding key message based on the security algorithm.

[0045] The message verification unit is used to input the key message into the key database for key comparison. If the key message is correct, the ECU hardware sequence message of the monocular camera is obtained and the ECU hardware sequence message is verified.

[0046] The sequence generation unit is used to obtain the corresponding control sequence based on the ECU hardware sequence message if the ECU hardware sequence message is verified to be correct.

[0047] The present invention also proposes a storage medium storing a computer program, which, when executed by a processor, implements the above-described method for offline calibration of a monocular camera.

[0048] The present invention also proposes a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for calibrating the offline position of a monocular camera.

[0049] Compared with the prior art, the beneficial effects of the present invention are:

[0050] By calibrating the acquired component information of the monocular camera to ensure that the hardware meets the requirements, and by writing the vehicle information of the vehicle to be calibrated to obtain the corresponding control sequence, the corresponding calibration program is started according to the control sequence. The success of the calibration program is determined by judging the calibration result and the number of calibrations. The systematic operation of the calibration program simplifies the operation steps, reduces the skill requirements of operators, reduces human intervention, and can cover various vehicle models. The automatic calibration method for front-view monocular cameras can significantly improve the efficiency and first-pass yield of vehicle camera calibration. Attached Figure Description

[0051] Figure 1 is a flowchart of the offline calibration method for a monocular camera in the first embodiment of the present invention;

[0052] Figure 2 is a vehicle parameter diagram in the first embodiment of the present invention;

[0053] Figure 3 is a parameter diagram of the black and white checkerboard target in the first embodiment of the present invention;

[0054] Figure 4 is a detailed flowchart of step S102 in Figure 1;

[0055] Figure 5 is a detailed flowchart of another embodiment of step S102 in Figure 1;

[0056] Figure 6 is a structural block diagram of the offline calibration system for a monocular camera in the second embodiment of the present invention;

[0057] Figure 7 is a structural block diagram of the computer in the third embodiment of the present invention.

[0058] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0059] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0060] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0062] Example 1

[0063] Please refer to Figure 1, which shows the offline calibration method for a monocular camera in the first embodiment of the present invention. The method specifically includes steps S101 to S105:

[0064] S101, Read the component information of the monocular camera on the vehicle to be calibrated, and verify the component information. If the component information is verified to be qualified, enter the extended mode.

[0065] The offline calibration method for monocular cameras in this application meets the following conditions in its specific implementation:

[0066] 1) Ambient brightness

[0067] This application provides typical lighting guidance parameters according to Table 1.

[0068] Table 1 Lighting parameters

[0069]

[0070] It should be noted that under the illumination of high-frequency excitation light sources such as pulsed LED lights, there is a certain probability that the static calibration of the camera will not be completed successfully.

[0071] 2) Target brightness requirements: 1. A black and white checkerboard target is recommended for camera calibration. 2. Target area illuminance: 200 lx ~ 35000 lx (without interfering light sources). 3. White area: 60 ~ 10000 cd / m² 2 4. Black area: less than 3% of the white area. 5. Edge area: 3 to 5 times the size of the black area.

[0072] It should be noted that in this embodiment, the target must meet the following conditions: 1. The target illumination must be uniform during calibration; 2. The target cannot be directly illuminated by any light source; 3. The target cannot have shadows; 4. The target cannot be illuminated by vehicle headlights.

[0073] 3) The following requirements apply to the vehicle for calibration in this invention: 1. The vehicle headlights must be off; 2. Ensure that the vehicle has undergone four-wheel alignment before camera calibration; 3. Correct tire pressure; 4. The vehicle's driving axis must be horizontal with the target normal; 5. The vehicle must be unloaded and unoccupied during calibration; 6. The vehicle speed must be 0, and the entire vehicle must be powered on; 7. Ensure that the camera module is correctly configured before calibration (the vehicle configuration DID has been correctly written); 8. The required vehicle parameters for calibration are detailed in Table 2.

[0074] Table 2. Vehicle parameters required for the calibration station cart.

[0075]

[0076] 4) Target Requirements: The target contains multiple geometric elements that contrast sharply with the rest of the target. The target is mounted at a reference position in front of the vehicle, and the camera acquires images from this target. Image analysis then determines the positions of the geometric elements within the image. The forward-looking monocular camera module uses the determined image coordinates and the known target reference position to determine the camera's actual azimuth angle and stores this information in the control unit.

[0077] Figure 3 shows a black and white checkerboard pattern composed of standard black and white squares. This invention provides specific parameter descriptions for the target, where S is the side length of the black and white square, which is related to the camera's parameters and the distance between the vehicle and the target. A larger S value is better; for vehicle-mounted cameras, a value of 100–300 mm is recommended. Wt is the target width, and Ht is the target height. Wt and Ht values ​​are integer multiples of S, with Wt ≥ 3S and Ht ≥ 2S.

[0078] There are two targets, one on the left and one on the right. L is the distance between the center line of the target and the center line of the vehicle. To ensure a high pass rate for calibration, it is recommended that the targets be arranged symmetrically with respect to the vehicle's central axis, i.e., L = 0. Wcl is the center distance between the two targets, and it is recommended that Wcl ≥ 1m. H is the height of the target center above the ground, where H = the height of the center line of the optical axis of the vehicle-mounted calibration camera above the ground.

[0079] 5) Offline calibration:

[0080] In production line mode, static calibration is used to calibrate the forward-looking monocular camera.

[0081] The main task of static calibration is to correctly install the forward-looking monocular camera on the vehicle and calculate the installation errors in three directions to ensure system performance. Therefore, static calibration is a method used to determine the initial deviations during vehicle off-line inspection.

[0082] Static calibration is performed while the vehicle is stationary. The direction angle of the forward-looking monocular camera cannot be directly measured, so a calibration device is used to calculate the direction angle.

[0083] In practice, the diagnostic port of the access system is used to power on the vehicle to be calibrated for 10 seconds at a speed of 0. The system then reads the component information of the monocular camera on the vehicle. This component information includes the part number message "22F1 13" and the camera ECU feedback message "62F1 13xx xx…xx xx". The obtained component information is verified to prevent model mismatch between the vehicle and the camera. If the read component information is incorrect, a "Component assembly error" message is displayed at the calibration station, and the calibration process is exited.

[0084] Furthermore, a message "14FF FF FF" to clear camera fault codes is sent to the monocular camera. The monocular camera ECU responds with a message "54", indicating that the monocular camera initialization was successful. Otherwise, a "Failed to clear camera fault codes" message is displayed at the calibration station.

[0085] In this embodiment, by sending a fault code reading message "19 02 01" to the monocular camera, the monocular camera ECU responds with a message "59 02 8F xx xx…xx xx", indicating that the monocular camera currently has no fault codes. Otherwise, the calibration process exits and displays a "Conditions not met, calibration ended" message at the calibration station. By sending a message "10 03" to the monocular camera to enter the camera ECU extended mode, the camera ECU responds with a message "50 03", indicating that the monocular camera ECU allows the diagnostic tool to enter extended mode. Otherwise, a "Unable to enter extended mode" message is displayed at the calibration station.

[0086] S102, in the extended mode, write the vehicle information of the vehicle to be calibrated, obtain the corresponding control sequence based on the vehicle information, and use the control sequence to start the calibration program of the vehicle to be calibrated in order to obtain the corresponding calibration result.

[0087] Furthermore, referring to Figure 4, step S102 specifically includes steps S1021 to S1023:

[0088] S1021, acquire the image information collected by the monocular camera in different directions of the vehicle to be calibrated, and use image analysis to determine the position data of the geometric elements in each image information;

[0089] S1022, Construct an image coordinate system, and use the image coordinate system and the position data to determine the actual orientation angle of the monocular camera;

[0090] S1023, calibrate the actual direction angle and the preset direction angle to output the direction angle calibration result of the monocular camera.

[0091] In specific implementation, the image information collected by installing a monocular camera in different directions of the vehicle to be calibrated can be understood as the image of the target. There are three different directions. Of course, in other embodiments, there can be multiple directions.

[0092] Furthermore, image analysis is used to determine the positional data of geometric elements in the image information from each direction, and an image coordinate system is constructed. Using the image coordinate system and the positional data, the installation error of the monocular camera in different directions can be determined. Using the installation error, the determined image coordinates, and the known target reference position, the actual azimuth angle of the monocular camera can be confirmed. Calibration is performed based on the actual azimuth angle and the preset azimuth angle to output the azimuth angle calibration result of the monocular camera. By comparing the actual azimuth angle and the preset azimuth angle, it can be determined whether there is any abnormality in the installation position of the monocular camera.

[0093] Furthermore, referring to Figure 5, step S102 also includes steps S1024 to S1026:

[0094] S1024, Obtain the security algorithm of the monocular camera, and generate a corresponding key message based on the security algorithm;

[0095] S1025, the key message is input into the key database for key comparison. If the key message is correct, the ECU hardware sequence message of the monocular camera is obtained and the ECU hardware sequence message is verified.

[0096] S1026, if the ECU hardware sequence message is verified to be correct, then the corresponding control sequence is obtained according to the ECU hardware sequence message.

[0097] In practice, a key message "27 02xx xx xx xx" is sent after being decrypted using a security algorithm based on the camera ECU seed. The camera ECU responds with a key authentication message "67 02", indicating that the key is correct. Otherwise, a message "Key error, unauthorized access" is displayed at the calibration station.

[0098] Furthermore, a message “22F1 8C” is sent to read the hardware serial number of the monocular camera ECU, and the ECU hardware serial number message “62F1 8C xx xx…xx xx” is obtained. The ECU hardware serial number message is then checked. If the ECU hardware serial number message is correct, the corresponding control sequence is obtained from the corresponding control sequence database based on the ECU hardware serial number message.

[0099] S103, perform result judgment on the calibration result; if the calibration result is not equal to the first calibration threshold, then determine whether the calibration result is equal to the second calibration threshold.

[0100] S104, if the calibration result is not equal to the second calibration threshold, then obtain the number of calibrations of the calibration result;

[0101] S105, if the number of calibrations in the calibration result is not greater than the calibration number threshold, then the vehicle to be calibrated is recalibrated using the calibration program until the calibration result is equal to the first calibration threshold, so that the vehicle to be calibrated is successfully calibrated.

[0102] In practice, the camera ECU initiates the calibration routine with the message "31 01 74 00", and the camera ECU responds with the calibration routine initiation message "71 01 74 00xx xx". If xx xx is NRC, it indicates that the calibration conditions are not met and the routine startup fails. The diagnostic tool then sends a message to read the failure reason "22 24 22". Otherwise, it indicates that the calibration routine startup was successful.

[0103] Furthermore, after calibrating the monocular camera of the vehicle to be calibrated, the calibration routine will obtain the corresponding calibration result. The calibration result will be judged. If the calibration result is not equal to the first calibration threshold (in this embodiment, the first calibration threshold is 5), then it will be judged whether the calibration result is equal to the second calibration threshold (in this embodiment, the second calibration threshold is 1).

[0104] Specifically, wait 2 seconds. Send a message "31 03 74 00" requesting the camera ECU calibration result, and the camera ECU will respond with a message "71 03 74 00xx". xx (1 Byte) represents the calibration result of the forward-looking camera (00 = Undefined; 01 = Calibration unfinished; 02 = Calibration fail; 03 = Target not found; 04 = Too many targets; 05 = TAC finished; 06~FF = Reserved). If xx is not equal to 05 and xx is not equal to 01, the calibration process is exited. If xx is not equal to 05 and xx is equal to 01, the calibration steps are repeated. If the calibration fails after 3 repetitions, the calibration process is exited. If xx is equal to 05, the calibration is successful.

[0105] Furthermore, after marking the current calibration procedure as a calibration failure, a message "2224 22" to read the calibration failure reason is sent. The camera ECU responds with a failure reason message "62 24 22xx xx". The system reads this failure reason message "62 2422xx xx" and performs data analysis on it based on the calibration database to obtain the corresponding anomaly information. After the calibration procedure is completed, a calibration routine termination message "31 02 74 00" is sent. The camera ECU responds with a calibration routine termination message "71 02 74 00", exiting the calibration procedure.

[0106] Specifically, after marking the calibration procedure as successful, a message "22 24 22" to read the calibration result from the camera ECU is sent, and the camera ECU responds with a message "62 24 22xx xx". At this time, a message "22 24 23" to read the calibration tracking domain from the camera ECU is sent, and the camera ECU responds with a message "62 24 23xx xx". A message "2E 24 17 00" to close the extended mode is sent, and the camera ECU responds with a message "6E 24 17", thus exiting the extended mode.

[0107] In summary, the offline calibration method for monocular cameras in the above embodiments of the present invention verifies the acquired component information of the monocular camera to ensure that the hardware meets the requirements, obtains the corresponding control sequence by writing the vehicle information of the vehicle to be calibrated, and starts the corresponding calibration program according to the control sequence; the success of the calibration program is determined by judging the calibration result and the number of calibrations. The systematic operation of the calibration program simplifies the operation steps, reduces the skill requirements of operators, reduces human intervention, and can cover various vehicle models. This automatic offline calibration method for front-view monocular cameras can significantly improve the efficiency and first-pass yield of vehicle camera calibration.

[0108] Example 2

[0109] In another aspect, the present invention also proposes a monocular camera offline calibration system. Please refer to Figure 6, which shows the monocular camera offline calibration system in the second embodiment of the present invention, including:

[0110] The information reading module 11 is used to read the component information of the monocular camera on the vehicle to be calibrated and to verify the component information. If the component information is verified to be qualified, it enters the extended mode.

[0111] The vehicle calibration module 12 is used to write the vehicle information of the vehicle to be calibrated in the extended mode, obtain the corresponding control sequence based on the vehicle information, and start the calibration program of the vehicle to be calibrated using the control sequence to obtain the corresponding calibration result.

[0112] Furthermore, the vehicle calibration module 12 includes:

[0113] The data acquisition unit is used to acquire image information collected by the monocular camera in different directions of the vehicle to be calibrated, and to use image analysis to determine the position data of geometric elements in each image information.

[0114] An orientation angle calculation unit is used to construct an image coordinate system and determine the actual orientation angle of the monocular camera using the image coordinate system and the position data.

[0115] The vehicle calibration unit is used to calibrate the actual direction angle and the preset direction angle to output the direction angle calibration result of the monocular camera.

[0116] In some alternative embodiments, the vehicle calibration module 12 further includes:

[0117] An algorithm acquisition unit is used to acquire the security algorithm of the monocular camera and generate a corresponding key message based on the security algorithm.

[0118] The message verification unit is used to input the key message into the key database for key comparison. If the key message is correct, the ECU hardware sequence message of the monocular camera is obtained and the ECU hardware sequence message is verified.

[0119] The sequence generation unit is used to obtain the corresponding control sequence based on the ECU hardware sequence message if the ECU hardware sequence message is verified to be correct.

[0120] The first result judgment module 13 is used to judge the calibration result. If the calibration result is not equal to the first calibration threshold, then it is judged whether the calibration result is equal to the second calibration threshold.

[0121] The calibration count acquisition module 14 is used to acquire the calibration count of the calibration result if the calibration result is not equal to the second calibration threshold.

[0122] The second result judgment module 15 is used to recalibrate the vehicle to be calibrated using the calibration program if the calibration result is not greater than the calibration number threshold, until the calibration result is equal to the first calibration threshold, so that the vehicle to be calibrated is successfully calibrated.

[0123] In other alternative embodiments, the system further includes:

[0124] The third result judgment module is used to mark the current calibration procedure as successful if the calibration result is equal to the first calibration threshold.

[0125] The calibration result reading module is used to read the calibration result and parse the calibration tracking domain in the calibration result;

[0126] The data transmission module is used to exit the extended mode after receiving the calibration tracking domain transmission success signal.

[0127] In other alternative embodiments, the system further includes:

[0128] The fourth result judgment module is used to mark the current calibration procedure as a calibration failure if the number of calibrations of the calibration result is greater than the calibration number threshold.

[0129] The data analysis module is used to obtain the calibration log of the calibration result and perform data analysis on the calibration log based on the calibration database to obtain the corresponding abnormal information.

[0130] The functions or operation steps implemented by the above modules and units are largely the same as those in the above method embodiments, and will not be repeated here.

[0131] The offline calibration system for monocular cameras provided in this embodiment of the invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the system embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0132] Example 3

[0133] The present invention also proposes a computer, as shown in Figure 7, which is a computer in the third embodiment of the present invention. The computer includes a memory 10, a processor 20, and a computer program 30 stored in the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, it implements the above-described method for calibrating the offline status of a monocular camera.

[0134] The memory 10 includes at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10 can be an internal storage unit of a computer, such as the computer's hard disk. In other embodiments, the memory 10 can be an external storage device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Furthermore, the memory 10 can include both internal and external storage units of the computer. The memory 10 can be used not only to store application software and various types of data installed on the computer, but also to temporarily store data that has been output or will be output.

[0135] In some embodiments, the processor 20 may be an electronic control unit (ECU, also known as a vehicle computer), a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip, used to run program code stored in the memory 10 or process data, such as executing access restriction programs.

[0136] It should be noted that the structure shown in Figure 7 does not constitute a limitation on the computer. In other embodiments, the computer may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0137] This invention also proposes a storage medium storing a computer program that, when executed by a processor, implements the above-described method for offline calibration of a monocular camera.

[0138] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer storage medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0139] More specific examples of computer storage media (a non-exhaustive list) include: electrical connections (electronic devices) with one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer storage media can even be paper or other suitable storage media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other storage medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0140] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0141] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0142] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for offline calibration of a monocular camera, characterized in that, include: Read the component information of the monocular camera on the vehicle to be calibrated, and verify the component information. If the component information is verified to be qualified, enter the extended mode. In the extended mode, the vehicle information of the vehicle to be calibrated is written, the corresponding control sequence is obtained based on the vehicle information, and the calibration program of the vehicle to be calibrated is started using the control sequence to obtain the corresponding calibration result. The calibration result is evaluated. If the calibration result is not equal to the first calibration threshold, then it is determined whether the calibration result is equal to the second calibration threshold. If the calibration result is not equal to the second calibration threshold, then obtain the number of calibrations for the calibration result; If the number of calibrations in the calibration result is not greater than the calibration number threshold, the vehicle to be calibrated is recalibrated using the calibration procedure until the calibration result is equal to the first calibration threshold, so that the vehicle to be calibrated is successfully calibrated.

2. The method for calibrating the offline status of a monocular camera according to claim 1, characterized in that, The steps of starting the calibration program of the vehicle to be calibrated using the control sequence to obtain the corresponding calibration results include: acquiring image information collected by the monocular camera in different directions of the vehicle to be calibrated, and determining the position data of geometric elements in each image information using image analysis; constructing an image coordinate system, and determining the actual orientation angle of the monocular camera using the image coordinate system and each position data; calibrating the actual orientation angle and the preset orientation angle to output the orientation angle calibration result of the monocular camera.

3. The method for calibrating the offline status of a monocular camera according to claim 1, characterized in that, After the step of judging the calibration result, the method further includes: if the calibration result is equal to the first calibration threshold, then mark the current calibration procedure as successful; read the calibration result and parse the calibration tracking domain in the calibration result; and exit the extended mode after receiving the calibration tracking domain transmission success signal.

4. The method for calibrating the offline status of a monocular camera according to claim 1, characterized in that, After obtaining the calibration count of the calibration result, the method further includes: if the calibration count of the calibration result is greater than the calibration count threshold, then marking the current calibration procedure as a calibration failure; obtaining the calibration log of the calibration result, and performing data analysis on the calibration log based on the calibration database to obtain the corresponding abnormal information.

5. The method for calibrating the offline status of a monocular camera according to claim 1, characterized in that, The steps for obtaining the corresponding control sequence based on the vehicle information include: obtaining the security algorithm of the monocular camera and generating a corresponding key message based on the security algorithm; inputting the key message into the key database for key comparison; if the key message is correct, obtaining the ECU hardware sequence message of the monocular camera and verifying the ECU hardware sequence message; if the ECU hardware sequence message is correct, obtaining the corresponding control sequence based on the ECU hardware sequence message.

6. A system for calibrating the offline status of a monocular camera, characterized in that, include: The information reading module is used to read the component information of the monocular camera on the vehicle to be calibrated, and to calibrate the component information. If the component information is qualified, it enters the extended mode. The vehicle calibration module is used to write the vehicle information of the vehicle to be calibrated in the extended mode, obtain the corresponding control sequence based on the vehicle information, and start the calibration program of the vehicle to be calibrated using the control sequence to obtain the corresponding calibration result. The first result judgment module is used to judge the calibration result. If the calibration result is not equal to the first calibration threshold, then it is judged whether the calibration result is equal to the second calibration threshold. The calibration count acquisition module is used to acquire the calibration count of the calibration result if the calibration result is not equal to the second calibration threshold. The second result judgment module is used to recalibrate the vehicle to be calibrated using the calibration program if the calibration result is not greater than the calibration number threshold, until the calibration result is equal to the first calibration threshold, so that the vehicle to be calibrated is successfully calibrated.

7. The offline calibration system for a monocular camera according to claim 6, characterized in that, The vehicle calibration module includes: a data acquisition unit, used to acquire image information collected by the monocular camera in different directions of the vehicle to be calibrated, and to determine the position data of geometric elements in each image information using image analysis; a direction angle calculation unit, used to construct an image coordinate system, and to determine the actual direction angle of the monocular camera using the image coordinate system and each position data; and a vehicle calibration unit, used to calibrate the actual direction angle and a preset direction angle to output the direction angle calibration result of the monocular camera.

8. The offline calibration system for a monocular camera according to claim 6, characterized in that, The system further includes: a third result judgment module, used to mark the current calibration procedure as successful if the calibration result is equal to the first calibration threshold; a calibration result reading module, used to read the calibration result and parse out the calibration tracking domain in the calibration result; and a data transmission module, used to exit the extended mode after receiving the calibration tracking domain transmission success signal.

9. A storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the offline calibration method for a monocular camera as described in any one of claims 1 to 5.

10. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the offline calibration method for a monocular camera as described in any one of claims 1 to 5.

Images