Vehicle-mounted side-view camera system off-line calibration method and device, storage medium and equipment

Abstract

The application discloses a kind of vehicle-mounted side view camera system offline calibration method, device, storage medium and equipment, the method includes: in the calibration environment of initialization setting, read vehicle configuration information and side view camera system information;According to vehicle configuration information, call corresponding calibration routine;According to calibration routine, clear the fault code of side view camera system;Identity and authority authentication are carried out;Read vehicle configuration information, start calibration routine, obtain routine start result;Whether the same as first calibration result threshold value is judged routine start result;If yes, side view camera system is calibrated, and calibration program execution is completed to read calibration result after waiting;Whether the same as second calibration result threshold value is judged calibration result;If yes, determine that side view camera system calibration is completed and exits calibration program.The technical problem that the prior art is solved to side view camera system in offline calibration process, needs to calibrate each side view camera in turn, so that calibration efficiency is lower.

Description

Technical Field

[0001] This invention relates to the field of vehicle calibration technology, specifically to a method, apparatus, storage medium, and device for calibrating an on-board side-view camera system after it is put into operation. Background Technology

[0002] With the continuous development of the "new four modernizations" of automobiles, higher-level intelligent assisted driving systems such as "navigation-assisted driving" are gradually being mass-produced and implemented. "Navigation-assisted driving" is mainly used in structured scenarios such as highways and urban expressways. It can realize functions such as intelligent entry and exit from ramps, intelligent lane changing, and intelligent avoidance of merging points, and has essentially become a definite future development trend in the industry. To achieve safe intelligent entry and exit from ramps and intelligent lane changing, the typical technical solution for "navigation-assisted driving" is to use four side-view cameras to form a side-view camera system to perceive the surrounding environment on the side of the vehicle body, corresponding to the left front camera, right front camera, left rear camera, and right rear camera. However, due to bracket tolerances, vehicle body tolerances, and installation errors during the production and installation process, dimensional deviations will inevitably occur in the on-board cameras. To compensate for these deviations, off-line calibration is required.

[0003] The common method for calibrating vehicle-mounted cameras is to acquire, compare, and correct images of individual cameras using a black and white checkerboard target to obtain the three directional correction angles of the vehicle-mounted camera: X-axis pitch, Y-axis yaw, and Z-axis roll. However, vehicle-mounted side-view camera systems contain multiple side-view cameras, and calibrating each camera individually is extremely inefficient and severely slows down the production line. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide a method, apparatus, storage medium, and device for calibrating a vehicle-mounted side-view camera system after its production run. This addresses the technical problem in existing technologies where each side-view camera needs to be calibrated sequentially during the production run calibration process, resulting in low calibration efficiency.

[0005] A first aspect of the present invention is to provide a method for calibrating an on-board side-view camera system after it is completed, the method comprising:

[0006] In the initial calibration environment, vehicle configuration information and side-view camera system information are read, and the vehicle information and side-view camera system information are matched to start calibration;

[0007] The corresponding calibration routine is invoked based on the vehicle configuration information;

[0008] The fault codes of the side-view camera system are cleared according to the calibration routine, and then read again to determine whether there are any fault codes that affect the calibration process.

[0009] The control calibration system and the side-view camera system enter an expansion mode to perform identity and authority authentication;

[0010] Reading the vehicle configuration information, starting the calibration routine, and obtaining a routine start result;

[0011] Determining whether the routine start result is the same as a first calibration result threshold value;

[0012] If yes, calibrating the side-view camera system in the calibration environment, waiting for the calibration program to be executed, and reading a calibration result;

[0013] Determining whether the calibration result is the same as a second calibration result threshold value;

[0014] If yes, determining that the side-view camera system is calibrated and exiting the calibration program;

[0015] In the calibration environment, the side-view camera system is calibrated, specifically including:

[0016] Controlling all side-view cameras on the vehicle to simultaneously collect target images in the field of view; obtaining all the collection images of the side-view cameras through an ECU, performing image stitching on the collection images, performing image binarization processing on the stitched images, performing image edge detection, detecting image edges by using a Canny edge detection algorithm to extract edge features, extracting corner point information of the images from the edge features by using a Harris corner point detection algorithm to locate the image positions, solving coordinates of the images in the coordinate system of the side-view cameras by using a linear least square method, obtaining calibration parameters of the side-view cameras through coordinate conversion, and writing the calibration parameters of the side-view cameras into corresponding side-view camera systems to complete the calibration.

[0017] According to an aspect of the above technical solution, the fault codes of the side-view camera system are cleared according to the calibration routine, and the fault codes are read again to determine whether there are fault codes that affect calibration.

[0018] The calibration routine is executed, and the fault codes of the side-view camera system are cleared;

[0019] The calibration routine is executed again, and the fault codes of the side-view camera system are read;

[0020] Determining whether there are fault codes that affect calibration in the side-view camera system.

[0021] According to an aspect of the above technical solution, if there are fault codes that affect calibration after the fault codes of the side-view camera system are cleared, the calibration is exited and the corresponding fault codes are returned and analyzed.

[0022] According to an aspect of the above technical solution, the control calibration system and the side-view camera system enter an extended mode to perform identity and authority authentication, specifically including:

[0023] The control calibration system and the side-view camera system enter an extended mode to perform communication connection of the calibration system and the side-view camera system.

[0024] The key seed sent by the side-view camera system is acquired.

[0025] The key seed is encrypted according to a predetermined encryption algorithm to obtain a target key, and the target key is sent to the side-view camera system to perform identity authentication.

[0026] After identity authentication, the calibration authority of the side-view camera system is acquired.

[0027] According to an aspect of the above technical solution, when the routine start result is different from the first calibration result threshold, the calibration system records and analyzes the start failure reason message of the calibration routine.

[0028] According to an aspect of the above technical solution, when the calibration result is different from the second calibration result threshold, the method further includes:

[0029] The calibration times of the side-view camera system are acquired by the calibration system.

[0030] It is judged whether the calibration times are less than or equal to a preset calibration times threshold.

[0031] If yes, the vehicle configuration information is read again, the calibration routine is started, and a routine start result is acquired.

[0032] According to an aspect of the above technical solution, the calibration environment includes a target image, including nine two-dimensional code patterns to constitute a target image, and the size error is less than ±2mm, the positioning accuracy requirement of the target is that the center point of the target image is taken as the origin, and the XYZ axis error is less than ±5mm, and the XYZ rotation angle deviation is less than ±0.15°.

[0033] The second aspect of the present application provides a vehicle-mounted side-view camera system offline calibration device, the device includes:

[0034] An information acquisition and matching module is used to read vehicle configuration information and side-view camera system information in an initialized set calibration environment, and the vehicle information and the side-view camera system information are matched to start calibration.

[0035] A calibration routine calling module is used to call a corresponding calibration routine according to the vehicle configuration information.

[0036] A fault code clearing module is configured to clear fault codes of the side-view camera system according to the calibration routine and read again to determine whether there is a fault code affecting calibration;

[0037] An identity and permission authentication module is configured to control the calibration system and the side-view camera system to enter an extended mode to perform identity and permission authentication;

[0038] A calibration routine starting module is configured to read the vehicle configuration information, start the calibration routine, and obtain a routine starting result;

[0039] A first judging module is configured to determine whether the routine starting result is the same as a first calibration result threshold value;

[0040] A calibration program executing module is configured to, when the first judging module determines that the routine starting result is the same as the first calibration result threshold value, calibrate the side-view camera system in the calibration environment, wait for calibration program execution to be completed, and read a calibration result;

[0041] A second judging module is configured to determine whether the calibration result is the same as a second calibration result threshold value;

[0042] A calibration result judging module is configured to, when the second judging module determines that the calibration result is the same as the second calibration result threshold value, determine that the side-view camera system is calibrated and exits the calibration program.

[0043] A third aspect of the present application is a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the offline calibration method in the above technical solutions.

[0044] A fourth aspect of the present application is to provide a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the offline calibration method in the above technical solutions.

[0045] Compared with the prior art, the vehicle-mounted side-view camera system offline calibration method, device, storage medium and equipment have the following beneficial effects:

[0046] In the process of offline calibration of the vehicle side-view camera system, the calibration system and the vehicle side-view camera system are authenticated by calling the calibration routine corresponding to the vehicle in the pre-initialized calibration environment, and the vehicle configuration information is read after the authentication is passed, the calibration routine is started, the routine starting result is obtained, and it is judged whether the routine starting result is the same as the first calibration result threshold. Only in the same case, the formal calibration process is entered. In the specific calibration process, image acquisition is carried out for all side-view cameras at the same time, and then a series of image processing is carried out, the coordinates of the image in the side-view camera are solved, and the calibration parameters of the side-view camera are obtained through coordinate conversion, that is, the offline calibration of the side-view camera system can be realized. Compared with the prior art of calibrating each side-view camera in turn, the calibration efficiency is greatly improved, thereby improving the production rhythm of the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0047] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description, taken in conjunction with the following drawings, in which:

[0048] Figure 1 The layout plan view of the side-view camera in the vehicle side-view camera system in an embodiment of the present application;

[0049] Figure 2 The layout side view of the side-view camera in the vehicle side-view camera system in an embodiment of the present application;

[0050] Figure 3 The flow chart of the offline calibration method of the vehicle side-view camera system in an embodiment of the present application;

[0051] Figure 4 The structure block diagram of the offline calibration device of the vehicle side-view camera system in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below. However, the present application can be realized in many different forms, and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0053] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly on the other element or there can be a middle element. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or there can be a middle element. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0054] 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 application belongs. The terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0055] Embodiment one

[0056] The first embodiment of the present application provides a vehicle-mounted side-view camera system offline calibration method, which is applied to a vehicle-mounted side-view camera offline calibration system, including a vehicle system, a vehicle positioning system, a target system, a diagnostic instrument system, a calibration system and a required surrounding environment system.

[0057] Further, as shown in Figure 1 , Figure 2 To obtain a reference image for the side-view camera, the side-view camera field of view (FOV) and the vehicle body need to have a fixed angle, that is, there is a fixed vehicle body feature in the FOV of the side-view camera. In order to splice the images obtained by the four side-view cameras into a complete vehicle body image, the FOV of the side-view camera needs to be overlapped. In order to quickly calibrate the images obtained by the side-view camera, the camera optical axis needs to be parallel to the ground when the side-view camera is arranged.

[0058] The target system is composed of 8 identical targets 1#-8#, which are arranged on the front and rear sides of the vehicle body with the vehicle body center axis as the symmetry axis. The target image is composed of 9 different two-dimensional codes. The image plane of the target is perpendicular to the ground, and the image normal is parallel to the ground and the camera optical axis, so as to reduce the distortion of the target image collected by the side-view camera, improve the image angle comparison efficiency, and improve the first-time calibration pass rate.

[0059] The target is fixed on the calibration station, and the position accuracy needs to meet the following requirements:

[0060] The origin of the target reference coordinate system is the front axle center landing point, and the target positioning point is the center of the two-dimensional code pattern.

[0061] To prevent light reflection, the target surface material is recommended to be matte material. In particular, the target material is not recommended to use cloth materials such as spray-painted cloth, which can easily cause deformation, such as wrinkles or bulging caused by weather.

[0062] As shown in Figure 3 The calibration method shown in the present application includes steps S1-S9:

[0063] Step S1, in the initialization setting of the calibration environment, read the vehicle configuration information and side-view camera system information, match the vehicle information and the side-view camera system information to start calibration.

[0064] In this embodiment, the initialized calibration environment includes the field plan, the lighting plan, the vehicle to be calibrated requirements and vehicle positioning plan, the two-dimensional code target plan and target positioning plan.

[0065] Among them, the qualified calibration environment contains the following contents:

[0066] Flat ground, no vibration influence on the surrounding ground; uniform lighting conditions, ambient illuminance is 400 lux-750 lux, the light intensity difference of the target surface is less than 100 lux or so, which can be observed by the side-view camera to collect target image to observe whether each pixel of the target pattern is clear; the target cannot have shadow, light diffusion plate can be used to make the calibration image uniform, illuminometer can be used to measure whether the actual illuminance of the corner point position of the calibration image meets the above requirements; the calibration site lighting equipment needs to be stable and non-flickering and continuous irradiation, and does not change with the frequency of alternating current, and there should be no other surrounding environmental light changes during the calibration process; the light source cannot make the target pattern reflect or cause the image contrast to decrease, and the color temperature of the light is 5000K-7000K.

[0067] The scheme of the calibration environment is verified by test, the darkroom scheme is used in the calibration station, which can completely avoid the interference of the surrounding environment light, has the best effect, can effectively reduce the calibration time and improve the first-time calibration pass rate.

[0068] In addition, the vehicle speed should be kept at 0 during the calibration process, and the vehicle should be kept stationary; the vehicle needs to be fixed and positioned, and the vehicle body needs to be adjusted without steering wheel angle; after the vehicle is fixed, the horizontal offset of the front and rear wheel shaft centers is ≤±10mm; the longitudinal offset of the front axle center is ≤±10mm; the flatness of each tire standing surface is ±5mm; the target surface material should use matte material. In particular, it is not recommended to use spray cloth and other cloth materials as target material, which can easily cause deformation, such as wrinkles or bulges caused by weather.

[0069] In addition, the target is arranged around the vehicle body and needs to be symmetrically arranged, the target should be perpendicular to the ground, and the image face direction is required to be parallel to the ground; the target adopts nine different two-dimensional code patterns to form an image, and the size error is required to be less than ±2mm; and the positioning accuracy of the target is required to take the center point of the target image as the origin, the XYZ axis error is less than ±5mm, and the XYZ axis rotation angle deviation is less than ±0.15°.

[0070] Specifically, in the embodiment, the information reading module reads the part information of the vehicle-mounted side-view camera and its system, and compares the part information to ensure that the vehicle, the side-view camera system, and the side-view camera part correspond to each other. After the part comparison is qualified, the next step is entered.

[0071] In step S2, the corresponding calibration routine is called according to the vehicle configuration information.

[0072] In the embodiment, the vehicle configuration information of the vehicle to be calibrated is written in the calibration system module. The corresponding calibration routine is called through the vehicle configuration information, and the calibration routine is started, so that the calibration process is carried out through the calibration program.

[0073] Specifically, there are certain structural differences and configuration differences between vehicle models. The existence of the above differences makes the calibration of the vehicle-mounted side-view camera system should be distinguished according to the vehicle model, so the calibration program has multiple calibration routines.

[0074] In step S3, the fault code of the side-view camera system is cleared according to the calibration routine, and the fault code is read again to determine whether there is a fault code affecting the calibration.

[0075] In the embodiment, the calibration system module is used to clear the fault code of the side-view camera system, and then read the part fault code result. If the side-view camera system has a fault code affecting the calibration, the calibration process is exited and the corresponding fault code is returned and analyzed. If there is no fault code affecting the calibration, the next step is performed.

[0076] The fault code is, for example, a fault code output by detecting camera hardware failure, camera system failure, etc. The existence of the fault code indicates that there is a problem with the side-view camera system, and the calibration cannot be carried out smoothly. Therefore, the fault code needs to be analyzed, so that the side-view camera system can be adjusted adaptively, such as replacing the side-view camera.

[0077] In step S4, the calibration system and the side-view camera system are controlled to enter an extended mode for identity and authority authentication.

[0078] In the embodiment, after the side-view camera system does not have any fault code, the calibration system module and the side-view camera system are controlled to enter an extended mode, i.e. an online programming mode, and then the calibration system module and the vehicle-mounted side-view system are authenticated for identity and authority.

[0079] Specifically, the calibration system module requests the side-view camera system to send a secret key seed, i.e. an identity verification code. After receiving the secret key seed file, the calibration system module generates a corresponding secret key through a predetermined encryption algorithm and sends it to the side-view camera system. After verification, the calibration system module is given corresponding calibration authority.

[0080] Step S5, read the vehicle configuration information, start the calibration routine, and obtain the routine start result.

[0081] In this embodiment, the calibration system module will read the vehicle configuration information, obtain the corresponding configuration parameters from the side-view camera system information, start the corresponding calibration routine, and obtain the start result of the corresponding calibration process.

[0082] Step S6, determine whether the routine start result is the same as the first calibration result threshold.

[0083] In this embodiment, the calibration system module will read the routine start result and make a start result determination.

[0084] If the start result is equal to the first calibration threshold, it means that the calibration routine has started successfully, and the method shown in this embodiment proceeds to step S7.

[0085] If the start result is not equal to the first calibration threshold, the calibration routine is exited and the start failure result is returned.

[0086] Further, the calibration system module can record and analyze the start failure reason message in step eight, and the failure reason message contains the following contents:

[0087] 0x01: loss of CAN bus signal; 0x02: abnormal voltage of side-view camera system; 0x03: internal failure of side-view camera system; 0x04: vehicle is not in a stationary state; 0x05: vehicle headlights are not turned off; 0x06: vehicle turn signals are not turned off; 0x08: vehicle handbrake is not released; 0x09: vehicle doors are not closed; 0x0A: vehicle gear is not in N / P gear; 0x0B: left front camera has no signal; 0x0C: right front camera has no signal; 0x0D: left rear camera has no signal; 0x0E: right rear camera has no signal.

[0088] Step S7, calibrate the side-view camera system in the calibration environment, and wait for the calibration program to execute and read the calibration result.

[0089] In this embodiment, the side-view camera system is calibrated by the calibration program in the pre-initialized calibration environment, and then the calibration result is read after the calibration program is executed.

[0090] Specifically, after waiting for several seconds, the calibration system module will read the calibration result of the side-view camera system and make a calibration result determination.

[0091] Step S8, determine whether the calibration result is the same as the second calibration result threshold.

[0092] In the embodiment, if the calibration result is the same as the second calibration result threshold, the method shown in the embodiment enters step S9.

[0093] In step S9, it is determined that the side-view camera system calibration is completed and the calibration program is exited.

[0094] In the embodiment, the side-view camera system is calibrated in the calibration environment, specifically comprising:

[0095] All side-view cameras on the vehicle are controlled to simultaneously capture the target image in the field of view; the ECU acquires the captured images of all side-view cameras, and performs image stitching on the captured images; the stitched images are subjected to image binarization processing, image edge detection, and edge feature extraction by using the Canny edge detection algorithm; the Harris corner detection algorithm is used to extract the corner point information of the image from the edge features to locate the image position, and the linear least square method is used to solve the coordinates of the image in the coordinate system of the side-view camera, so as to obtain the calibration parameters of the side-view camera; and the calibration parameters of the side-view camera are written into the corresponding side-view camera system to complete the calibration.

[0096] The offline calibration of the side-view camera system shown in the embodiment can quickly calibrate all side-view cameras installed on the vehicle during the offline process of the vehicle, and thus it is not necessary to calibrate each side-view camera one by one.

[0097] In the embodiment, the calibration result after successful calibration is stored in the memory [data5]-[data16] of the ECU, specifically:

[0098] [data5] is the pitch angle of the left front camera and the theoretical deviation value;

[0099] [data6] is the yaw angle of the left front camera and the theoretical deviation value;

[0100] [data7] is the roll angle of the left front camera and the theoretical deviation value;

[0101] [data8] is the pitch angle of the right front camera and the theoretical deviation value;

[0102] [data9] is the yaw angle of the right front camera and the theoretical deviation value;

[0103] [data10] is the roll angle of the right front camera and the theoretical deviation value;

[0104] [data11] is the pitch angle of the left rear camera and the theoretical deviation value;

[0105] [data12] is the yaw angle of the left rear camera and the theoretical deviation value;

[0106] [data13] is the left rear camera roll angle and the theoretical deviation value;

[0107] [data14] is the right rear camera pitch angle and the theoretical deviation value;

[0108] [data15] is the right rear camera yaw angle and the theoretical deviation value;

[0109] [data16] is the right rear camera roll angle and the theoretical deviation value.

[0110] Compared with the prior art, the vehicle-mounted side-view camera system offline calibration method shown in the embodiment has the beneficial effects that:

[0111] In the process of calibrating the vehicle-mounted side-view camera system, the calibration system and the vehicle-mounted side-view camera system are authenticated and authorized by calling the calibration routine corresponding to the vehicle in the pre-initialized calibration environment, the vehicle configuration information is read after the authentication is passed, the calibration routine is started to obtain the routine start result, and it is judged whether the routine start result is the same as the first calibration result threshold. Only in the case of being the same, the formal calibration process is entered. In the specific calibration process, images of all side-view cameras are collected at the same time, and then a series of image processing is performed to solve the coordinates of the images in the coordinate system of the side-view camera, so that the calibration parameters of the side-view camera are obtained through coordinate conversion, that is, the offline calibration of the side-view camera system is realized. Compared with the prior art of calibrating each side-view camera in turn, the calibration efficiency is greatly improved, thereby improving the production rhythm of the vehicle.

[0112] Embodiment two

[0113] Please refer to Figure 4 The second embodiment of the present application provides a vehicle-mounted side-view system offline calibration device. The offline calibration device shown in the embodiment comprises an information acquisition and matching module 10, a calibration routine calling module 20, a fault code clearing module 30, an identity and authority authentication module 40, a calibration routine starting module 50, a first judgment module 60, a calibration program execution module 70, a second judgment module 80, and a calibration result judgment module 90.

[0114] The information acquisition and matching module 10 is used to read the vehicle configuration information and the side-view camera system information in the initialized calibration environment, and to match the vehicle information and the side-view camera system information to start calibration.

[0115] In the embodiment, the initialized calibration environment includes a field plan, an illumination scheme, a vehicle positioning scheme, a two-dimensional code target scheme, and a target positioning scheme.

[0116] The qualified calibration environment includes the following:

[0117] A flat ground without vibration influence; uniform light conditions, with an ambient illuminance of 400 lux-750 lux, and a light intensity difference of less than 100 lux on the target surface, which can be observed by a side-view camera to determine whether each pixel of the target pattern is clearly visible; the target cannot have shadows, and a light diffuser plate can be used to ensure that the calibration image is uniformly illuminated, and an illuminance meter can be used to measure the actual illuminance at the corner point of the calibration image to determine whether it meets the above requirements; the light equipment in the calibration site needs to be stable and non-flickering, and should not change with the frequency of alternating current, and there should be no other ambient light interference during the calibration process; the light source cannot cause the target pattern to reflect light or reduce the image contrast, and the color temperature of the light should be 5000K-7000K.

[0118] The scheme shown in the calibration environment is verified by experiments, and the darkroom scheme is used in the calibration station, which can completely avoid the interference of the surrounding light, has the best effect, can effectively reduce the calibration time, and improve the first-time calibration pass rate.

[0119] In addition, the vehicle speed should be kept at 0 during the calibration process, and the vehicle should be kept stationary; the vehicle needs to be fixed and positioned, and the vehicle body should be properly aligned without steering wheel angle; after the vehicle is fixed, the lateral offset of the front and rear wheel shaft centers should be less than or equal to ±10 mm; the longitudinal offset of the front axle center should be less than or equal to ±10 mm; the flatness of each tire standing surface should be ±5 mm; and the target surface material should be matte. In particular, it is not recommended to use cloth materials such as spray-painted cloth for the target material, as these types of materials can easily cause deformation, such as wrinkles or bulges caused by weather.

[0120] In addition, the target is arranged around the vehicle body and needs to be symmetrically arranged, the target should be perpendicular to the ground, and the image normal direction should be parallel to the ground; the target uses nine different two-dimensional code patterns to form an image, and the size error requirement is less than ±2 mm; and the positioning accuracy of the target requires that the target image center point be the origin, the XYZ axis error be less than ±5 mm, and the XYZ axis rotation angle deviation be less than ±0.15°.

[0121] Specifically, in this embodiment, the part information of the vehicle-mounted side-view camera and its system is read by the information reading module, and the part information is compared to ensure that the vehicle, the side-view camera system, and the side-view camera parts correspond one by one. After the part comparison is qualified, the next step is entered.

[0122] The calibration routine calling module 20 is used to call the corresponding calibration routine according to the vehicle configuration information.

[0123] In this embodiment, the vehicle configuration information of the vehicle to be calibrated will be written into the calibration system module. The corresponding calibration routine will be called through the vehicle configuration information to start the calibration routine, thereby carrying out the calibration process through the calibration program.

[0124] Specifically, there are certain structural and configuration differences between vehicle models. The existence of these differences means that the calibration of the vehicle side-view camera system should be differentiated according to the vehicle model. Therefore, the calibration procedure has multiple calibration routines.

[0125] The fault code clearing module 30 is used to clear the fault codes of the side-view camera system according to the calibration routine, and then read them again to determine whether there are any fault codes that affect the calibration process.

[0126] In this embodiment, the side-view camera system control will be cleared of fault codes through the calibration system module, and then the component fault code results will be read. If there are fault codes in the side-view camera system that affect calibration, the calibration process will be exited and the corresponding fault codes will be returned and parsed; if there are no fault codes that affect calibration, the next step will be performed.

[0127] This fault code, such as a camera hardware failure or camera system failure, is a fault code output after testing. The existence of the fault code indicates that there is a certain problem with the side-view camera system, and its calibration cannot be performed smoothly. Therefore, it is necessary to analyze the fault code so that the side-view camera system can be adjusted accordingly, such as replacing the side-view camera.

[0128] The identity and authorization authentication module 40 is used to control the calibration system and the side-view camera system to enter the extended mode for identity and authorization authentication.

[0129] In this embodiment, after the side-view camera system has no fault codes, the control calibration system module and the side-view camera system are put into extended mode, i.e. online programming mode, and then the calibration system module and the vehicle side-view system are subjected to dual identity and authorization authentication.

[0130] Specifically, the calibration system module will request the side-view camera system to send a key seed, i.e., an authentication code. After receiving the key seed file, the calibration system module will generate the corresponding key using an agreed encryption algorithm and send it to the side-view camera system. After successful verification, the calibration system module will be granted the corresponding calibration permissions.

[0131] The calibration routine startup module 50 is used to read the vehicle configuration information, start the calibration routine, and obtain the routine startup result.

[0132] In this embodiment, the calibration system module will read the vehicle configuration information and the side-view camera system information to obtain the corresponding configuration parameters, start the corresponding calibration routine, and obtain the start result of the corresponding calibration process.

[0133] The first judging module 60 is configured to judge whether the routine starting result is the same as the first calibration result threshold.

[0134] In the embodiment, the calibration system module reads the routine starting result and judges the starting result.

[0135] If the starting result is not equal to the first calibration threshold, the calibration routine is exited and the starting failure result is returned.

[0136] Further, the calibration system module can record and analyze the starting failure cause message in step eight, and the failure cause message includes the following contents:

[0137] 0x01: bus CAN signal loss; 0x02: side-view camera system voltage abnormality; 0x03: side-view camera system internal fault; 0x04: vehicle in non-stationary state; 0x05: vehicle headlight not turned off; 0x06: vehicle turn signal not turned off; 0x08: vehicle handbrake not released; 0x09: vehicle door not closed; 0x0A: vehicle gear not in N / P gear; 0x0B: left front camera has no signal; 0x0C: right front camera has no signal; 0x0D: left rear camera has no signal; 0x0E: right rear camera has no signal.

[0138] The calibration program execution module 70 is configured to, when the first judging module 60 judges that the routine starting result is the same as the first calibration result threshold, calibrate the side-view camera system in the calibration environment, and wait for the calibration program to be executed to read the calibration result.

[0139] In the embodiment, the side-view camera system is calibrated by the calibration program in the pre-initialized calibration environment, and then the calibration result is read after the calibration program is executed.

[0140] Specifically, after waiting for several seconds, the calibration system module reads the calibration result of the side-view camera system and judges the calibration result.

[0141] The second judging module 80 is configured to judge whether the calibration result is the same as the second calibration result threshold.

[0142] The calibration result judging module 90 is configured to, when the second judging module judges that the calibration result is the same as the second calibration result threshold, judge that the side-view camera system is calibrated and the calibration program is exited.

[0143] Compared with the prior art, the on-line calibration device for the vehicle-mounted side-view camera system has the following beneficial effects:

[0144] In the process of offline calibration of the vehicle-mounted side-view camera system, the calibration system and the vehicle-mounted side-view camera system are authenticated by calling the calibration routine corresponding to the vehicle in the pre-initialized calibration environment, and the vehicle configuration information is read after the authentication is passed, the calibration routine is started to obtain the routine starting result, and it is judged whether the routine starting result is the same as the first calibration result threshold, and only in the case of the same, the formal calibration process is entered. In the specific calibration process, image acquisition is performed on all side-view cameras at the same time, and then a series of image processing is performed to solve the coordinates of the image in the coordinate system of the side-view camera, so that the calibration parameters of the side-view camera are obtained through coordinate conversion, that is, the offline calibration of the side-view camera system can be realized. Compared with the prior art of calibrating each side-view camera in turn, the calibration efficiency is greatly improved, thereby improving the production rhythm of the vehicle.

[0145] Embodiment three

[0146] The third embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the offline calibration method described in the above embodiments.

[0147] Embodiment four

[0148] The fourth embodiment of the present application provides a computer device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the offline calibration method described in the above embodiments.

[0149] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0150] The above-described embodiments only express several embodiments of the present application, which are described in detail and specifically, but cannot be understood as limiting the scope of the patent of the present application. It should be noted that for ordinary skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which are within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for off-line calibration of a vehicle-mounted side-view camera system, characterized in that, The method comprises: In the initialization setting of the calibration environment, read the vehicle configuration information and the side-view camera system information, match the vehicle information with the side-view camera system information to start the calibration; Call the corresponding calibration routine according to the vehicle configuration information; Clear the fault codes of the side-view camera system according to the calibration routine, and read again to determine whether there are fault codes affecting the calibration; Control the calibration system and the side-view camera system to enter the extended mode to perform identity and authority authentication; Read the vehicle configuration information, start the calibration routine, and obtain the routine start result; Determine whether the routine start result is the same as the first calibration result threshold value; If yes, calibrate the side-view camera system in the calibration environment, wait for the calibration program to be executed, read the calibration result, and determine whether the calibration result is the same as the second calibration result threshold value; If yes, determine that the side-view camera system calibration is completed and the calibration program is exited. In the calibration environment, the calibration of the side-view camera system specifically comprises: Control all side-view cameras on the vehicle to simultaneously collect target images in the field of view; obtain the collected images of all side-view cameras through the ECU, perform image stitching on the collected images, perform image binarization processing on the stitched images, perform image edge detection, detect the image edges by using the Canny edge detection algorithm to extract edge features, extract the corner point information of the image from the edge features by using the Harris corner point detection algorithm to locate the image position, solve the coordinates of the image in the side-view camera by using the linear least squares algorithm, and obtain the calibration parameters of the side-view camera through coordinate conversion; and write the calibration parameters of the side-view camera into the corresponding side-view camera system to complete the calibration. Clear the fault codes of the side-view camera system according to the calibration routine, and read again to determine whether there are fault codes affecting the calibration, specifically comprising:

2. The off-line calibration method of a vehicle side view camera system according to claim 1, wherein Execute the calibration routine to clear the fault codes of the side-view camera system; Execute the calibration routine again to read the fault codes of the side-view camera system; Determine whether there are fault codes affecting the calibration in the side-view camera system. If there are still fault codes affecting the calibration after the fault codes of the side-view camera system are cleared, exit the calibration and return and analyze the corresponding fault codes.

3. The method of claim 2, wherein: Control the calibration system and the side-view camera system to enter the extended mode to perform identity and authority authentication, specifically comprising:

4. The off-line calibration method of a vehicle side view camera system according to claim 1, wherein Control the calibration system and the side-view camera system to enter the extended mode to perform communication connection between the calibration system and the side-view camera system; Obtain the secret key seed sent by the side-view camera system; Encrypt the secret key seed according to the agreed encryption algorithm to obtain a target secret key, and send the target secret key to the side-view camera system to perform identity authentication; After the identity authentication is passed, obtain the calibration authority of the side-view camera system. When the routine start result is not the same as the first calibration result threshold value, record and analyze the start failure reason message of the calibration routine through the calibration system.

5. The method of claim 1, wherein, ​ 6. The method of claim 1, wherein When the calibration result is not the same as the second calibration result threshold, the method further comprises: acquiring a calibration frequency of the side-view camera system through the calibration system; judging whether the calibration frequency is less than or equal to a preset calibration frequency threshold; if yes, reading the vehicle configuration information again, starting the calibration routine, and acquiring a routine start result.

7. The off-line calibration method of a vehicle side view camera system according to any one of claims 1-6, wherein, The calibration environment comprises a target image, and the target image comprises nine two-dimensional code patterns, and the size error is less than ±2 mm. The positioning accuracy of the target is required to take the center point of the target image as the origin, and the XYZ axis error is less than ±5 mm, and the XYZ rotation angle deviation is less than ±0.15°.

8. A calibration device for an on-board side-view camera system, characterized in that, The device comprises: an information acquisition and matching module, configured to read vehicle configuration information and side-view camera system information in an initialized calibration environment, and to match the vehicle information and the side-view camera system information to start calibration; a calibration routine calling module, configured to call a corresponding calibration routine according to the vehicle configuration information; a fault code clearing module, configured to clear fault codes of the side-view camera system according to the calibration routine, and to read again to determine whether there are fault codes affecting calibration; an identity and permission authentication module, configured to control the calibration system and the side-view camera system to enter an extended mode to perform identity and permission authentication; a calibration routine start module, configured to read the vehicle configuration information, start the calibration routine, and acquire a routine start result; a first judging module, configured to judge whether the routine start result is the same as a first calibration result threshold; a calibration program execution module, configured to, when the first judging module determines that the routine start result is the same as the first calibration result threshold, calibrate the side-view camera system in the calibration environment, and to wait for calibration program execution to complete and read a calibration result; a second judging module, configured to judge whether the calibration result is the same as a second calibration result threshold; a calibration result judging module, configured to, when the second judging module determines that the calibration result is the same as the second calibration result threshold, determine that the side-view camera system is calibrated and exits the calibration program.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the offline calibration method of any one of claims 1-7.

10. A computer device comprising a memory, a processor, and a computer program stored on the memory and implementable to run on the processor, characterized in that, The processor executes the computer program to implement the offline calibration method of any one of claims 1-7.

Images