Around-looking calibration method and system and storage medium thereof

Abstract

The invention provides a look-around calibration method and system and a storage medium thereof.The look-around calibration method comprises the steps that firstly, project parameters are confirmed, initial calibration configuration parameters are confirmed based on the project parameters, then the initial calibration configuration parameters are debugged until project calibration succeeds, and final calibration configuration parameters are obtained. The invention also provides a look-around calibration system based on the method. The look-around calibration system comprises an algorithm debugging module, a parameter acquisition module, a calibration configuration module, a calibration tool background service system and a folder generation module. According to the look-around calibration method and system and the storage medium thereof, the look-around calibration requirements of different projects can be realized at the cloud, and manual parameter configuration according to documents or experience is not needed, so that the quality and efficiency of look-around calibration work are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent vehicle technology, and in particular to a surround view calibration method, system and storage medium thereof. Background Art

[0002] Nowadays, the application of in-vehicle intelligent terminal equipment has become more and more extensive, the complexity of the projects has become higher and higher, and the project cycle has become shorter and shorter. Therefore, higher requirements are placed on the efficiency of the development of in-vehicle intelligent terminal equipment.

[0003] Surround view calibration algorithm is an important technology in the development of vehicle-mounted intelligent terminal equipment. In its existing development process, there is no unified service application platform, and the actual performance of the project cannot be verified, which brings inconvenience to mass production application and service support, and directly or indirectly affects the R&D efficiency, which is manifested in:

[0004] The application development colleagues of each project manually configure the vehicle host according to the documents or experience. Due to insufficient understanding of the algorithm, the randomness of the algorithm-related configuration parameters, the poor generalization of the configuration parameters, and insufficient understanding of the product solution, some product-related problems and potential risks are easily overlooked.

[0005] When facing product-related problems and potential risks, if you directly seek help from the relevant algorithm engineers, it will take up more of the algorithm engineers' working time and waste more manpower costs. Summary of the invention

[0006] To solve the above technical problems, the present application provides a surround view calibration method, system and storage medium thereof.

[0007] In a first aspect, the present application proposes a surround view calibration method, the method comprising the following steps:

[0008] The specific steps include:

[0009] S1: Get the project parameters of the target system.

[0010] S2: Acquire calibration configuration parameters according to the project parameters.

[0011] S3: Based on the calibration configuration parameters, a calibration result is calculated by a calibration algorithm, and then the process goes to step S4.

[0012] S4: Determine whether the calibration result meets the preset requirements. If so, proceed to step S5. If not, recalculate the calibration result.

[0013] S5: Generate a calibration configuration folder based on the calibration result, and output the calibration configuration folder to the target system through an output interface for calibration.

[0014] The surround view calibration method proposed in the present application first obtains the project parameters of the target system, and obtains the calibration configuration parameters according to the project parameters. Then, calibration is performed based on the calibration configuration parameters, and the calibration configuration parameters are debugged according to the calibration results, and finally the final calibration configuration parameters are obtained.

[0015] Furthermore, the project parameters include: project name parameters, platform parameters, vehicle model parameters, camera installation parameters and project images; the platform parameters include: the internal parameter type used by the camera used in the project, the distortion model and the number of vehicle suspensions.

[0016] Furthermore, the step S1 specifically includes the steps of:

[0017] S11: Get the project name parameter.

[0018] S12: Obtain platform parameters.

[0019] S13: Obtain vehicle model parameters.

[0020] S14: Obtain camera installation parameters.

[0021] S15: Based on the project parameters obtained in the steps S11 to S14, corresponding historical surround view calibration configuration parameters are selected in the historical database as initial surround view calibration configuration parameters.

[0022] Different surround view calibration projects have different project parameters. The surround view calibration system proposed in this application can identify and confirm different project parameters, and obtain corresponding initial calibration configuration parameters based on historical calibration configuration parameters stored in the historical database according to different project parameters.

[0023] The initial calibration configuration parameters obtained in step S1 are only calibration configuration parameters estimated for the project calibration parameters input for this calibration project. For different projects, the obtained initial calibration configuration parameters need to be further debugged to ensure the accuracy of the calibration configuration parameters.

[0024] Furthermore, the step S3 specifically includes:

[0025] S31: Obtaining a project image including calibrated feature points from the project parameters.

[0026] S32: Extracting the RIO region of the image using an image segmentation algorithm.

[0027] S33: Detect corner points in the RIO area using a corner point detection algorithm, and extract coordinates of the corner points to obtain calibration results.

[0028] Furthermore, the determining whether the calibration result meets the preset requirements also includes:

[0029] The error log information is generated when the error position is determined, and the correct log information is generated when the correct position is determined.

[0030] By generating corresponding log information, the location of the calibration anomaly can be quickly and accurately obtained, which is helpful for the subsequent debugging of the calibration configuration parameters.

[0031] Furthermore, the step S4 also includes: when the calibration result does not meet the preset requirements for a number of times greater than or equal to a preset number of times, sending an email to a preset engineer requesting the engineer to log in to the system to assist in debugging.

[0032] The surround view calibration method further comprises the steps of:

[0033] The obtained evaluation results and debugging process are recorded in the log module.

[0034] When the engineer logs into the system through the email, the log module pushes the evaluation result and debugging process record to the engineer or makes it available to the engineer.

[0035] The obtained evaluation results and debugging process are recorded in the log module;

[0036] When the engineer logs into the system through the email, the log module pushes the evaluation result and debugging process record to the engineer or makes it available to the engineer.

[0037] After obtaining accurate calibration configuration parameters, they need to be input into the host for on-machine verification. After on-machine verification, this surround calibration project is completed. On-machine verification can further improve the accuracy of calibration configuration parameters to prevent errors in calibration configuration parameters during actual application.

[0038] Furthermore, the most suitable historical calibration configuration parameters are obtained from the historical database according to the project parameters as calibration configuration parameters.

[0039] When determining the calibration configuration parameters, the most suitable historical calibration configuration parameters are obtained from the historical database according to the project parameters as the calibration configuration parameters.

[0040] Furthermore, the calibration result includes final calibration configuration parameters obtained in this debugging, and after step S5, the step further includes: storing the final calibration configuration parameters in the calibration result.

[0041] In a second aspect, the present application provides a surround view calibration system, the surround view calibration system comprising:

[0042] A parameter acquisition module is used to obtain the project parameters of the target system through an input interface;

[0043] A calibration configuration module, used to obtain calibration configuration parameters according to the project parameters;

[0044] An algorithm debugging module, used to calculate based on the calibration configuration parameters through a calibration algorithm to obtain a calibration result and debug the calibration configuration parameters;

[0045] The calibration tool backend service system is used to determine whether the calibration results meet the preset requirements;

[0046] The folder generation module is used to generate a calibration configuration folder based on the final calibration configuration parameters, and output the calibration configuration folder to the target system through an output interface for calibration.

[0047] Furthermore, the surround view calibration system further includes:

[0048] A log module, used to store the evaluation results and debugging process records of the surround view calibration system;

[0049] Message discussion module, used to collect user feedback;

[0050] When the engineer logs into the system through the email, the log module pushes the evaluation results and debugging process records of the surround view calibration system to the engineer or makes them available to the engineer.

[0051] When the engineer logs into the system through the email, the log module pushes the evaluation results and debugging process records of the surround view calibration system to the engineer or makes them available to the engineer.

[0052] Furthermore, the surround view calibration system further includes:

[0053] A historical database for storing the final calibration configuration parameters generated historically;

[0054] When determining the calibration configuration parameters, the calibration configuration module obtains the most suitable historical calibration configuration parameters from the historical database according to the project parameters as the calibration configuration parameters.

[0055] Through the historical database, calibration configuration parameters can be obtained in the historical database.

[0056] By setting up a log module, the modification records of the calibration configuration parameters can be stored during the debugging process of the calibration configuration parameters, thereby further improving the functions of the surround view calibration system.

[0057] By setting up a message discussion module, user feedback can be collected to further improve the functions of the surround view calibration system.

[0058] When the calibration tool backend service system obtains an evaluation result of failure of surround calibration for a number greater than or equal to a preset number of times, it sends an email to a preset engineer through an email system, requesting the engineer to log in to the system to assist in debugging.

[0059] The above-mentioned surround view calibration system design also includes a user system for storing user information. After logging into the surround view calibration system through the user system, the project parameters are uploaded to the main system. Combined with the evaluation function provided by the calibration tool background service system, accurate surround view calibration configuration parameters can be obtained in the cloud without manual configuration based on documents or experience, saving labor costs.

[0060] Furthermore, the calibration tool background service system is used to obtain and evaluate the initial calibration configuration parameters from the calibration configuration module, and is also used to obtain and evaluate the intermediate calibration configuration parameters from the algorithm debugging module. If the evaluation result is that the surround view calibration is successful, the initial calibration configuration parameters or the intermediate calibration configuration parameters of this evaluation are determined as the final calibration configuration parameters and output through the output interface. If the evaluation result is that the surround view calibration fails, the initial calibration configuration parameters or the intermediate calibration configuration parameters of this evaluation are sent to the algorithm debugging module for debugging;

[0061] After the calibration tool background service system determines the final calibration configuration parameters, the folder generation module first encapsulates the final calibration configuration parameters into a calibration configuration file package, and then outputs it through the output interface.

[0062] In a third aspect, based on the same inventive concept, the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a control processor, the surround view calibration method as described is implemented.

[0063] It should be noted that since the computer-readable storage medium in this embodiment and the surround view calibration method in the above embodiment are based on the same inventive concept, the corresponding contents in the method embodiment are also applicable to this embodiment and will not be described in detail here.

[0064] In summary, the present application proposes a surround view calibration method, system and storage medium thereof. The surround view calibration method first confirms the project parameters, and confirms the initial calibration configuration parameters based on the project parameters, and then debugs the initial calibration configuration parameters until the project calibration is successful and the final calibration configuration parameters are obtained. The present application also proposes a surround view calibration system based on the method, and the surround view calibration system includes: an algorithm debugging module, a parameter acquisition module, a calibration configuration module, a calibration tool background service system and a folder generation module.

[0065] Compared with the prior art, this application has at least the following beneficial effects:

[0066] The surround view calibration method, system and storage medium proposed in this application can realize the surround view calibration requirements of different projects in the cloud, without the need for manual parameter configuration based on documents or experience, which significantly improves the quality and efficiency of the surround view calibration work. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Attached Figure 1 A flow chart of a surround view calibration method shown in an embodiment of the application.

[0068] Attached Figure 2 A bird's-eye view displayed during the surround view calibration process shown in an embodiment of the present application.

[0069] Attached Figure 3 A schematic diagram of the system structure of the surround view calibration method shown in an embodiment of the present application. DETAILED DESCRIPTION

[0070] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0071] Embodiment 1:

[0072] As attached Figure 1 As shown, the present application also proposes a surround view calibration method, which specifically includes the following steps:

[0073] A surround view calibration method, characterized in that the surround view calibration method specifically comprises the following steps:

[0074] S1: Get the project parameters of the target system.

[0075] S2: Acquire calibration configuration parameters according to the project parameters.

[0076] S3: Based on the calibration configuration parameters, a calibration result is calculated by a calibration algorithm, and then the process goes to step S4.

[0077] S4: Determine whether the calibration result meets the preset requirements. If so, proceed to step S5. If not, recalculate the calibration result.

[0078] S5: Generate a calibration configuration folder based on the calibration result, and output the calibration configuration folder to the target system through an output interface for calibration.

[0079] In a preferred embodiment of a surround view calibration project, a user logs in to the surround view calibration system, uploads the project parameters, and then the vehicle camera corresponding to the surround view calibration project obtains a calibration image. Subsequently, based on the project parameters, the surround view calibration system obtains initial calibration configuration parameters, and then debugs the initial calibration configuration parameters to obtain final calibration configuration parameters.

[0080] In an embodiment of the present invention, optionally, the project parameters include: project name parameters, platform parameters, vehicle model parameters, camera installation parameters and project images; the platform parameters include: the internal parameter type used by the camera used in the project, the distortion model and the number of vehicle suspensions.

[0081] In the embodiment of the present invention, optionally, the step S1 specifically includes the steps of:

[0082] S11: Get the project name parameter.

[0083] S12: Obtain platform parameters.

[0084] S13: Obtain vehicle model parameters.

[0085] S14: Obtain camera installation parameters.

[0086] S15: Based on the project parameters obtained in the steps S11 to S14, corresponding historical surround view calibration configuration parameters are selected in the historical database as initial surround view calibration configuration parameters.

[0087] Different surround view calibration projects have different project parameters. The surround view calibration system proposed in this application can identify and confirm different project parameters, and obtain corresponding initial calibration configuration parameters based on historical calibration configuration parameters stored in the historical database according to different project parameters.

[0088] Each surround view calibration project has a different project name parameter, which is used to distinguish different surround view calibration projects; vehicle model parameters specifically include basic vehicle parameters, such as body size, vehicle brand and model, vehicle type, vehicle level and body structure; camera installation parameters are the specific installation positions of the cameras required in the surround view calibration process; the platform parameters include: the number of cameras and suspensions installed in the vehicle used in the project, and the internal reference models of each camera installed in the vehicle used in the project. The internal reference types of the camera can include: fisheye isometric model, omni model and MEI model.

[0089] Platform parameters are key information within project parameters. The surround view calibration information comes from the camera system installed in the vehicle. Different camera systems will obtain different calibration configuration parameters when facing the same vehicle and the same site. Therefore, the platform parameters specify the camera system of the surround view calibration project and are used for subsequent surround view calibration work.

[0090] In the embodiment of the present invention, optionally, the step S2 specifically includes:

[0091] According to the project parameters, the most suitable historical calibration configuration parameters are obtained in the historical database as calibration configuration parameters.

[0092] In a preferred embodiment of the surround view calibration project, after the user uploads the project parameters to the surround view calibration system, the surround view calibration obtains the closest historical calibration configuration parameters corresponding to the project parameters in the historical database based on the project parameters and uses them as the initial calibration configuration parameters.

[0093] The initial calibration configuration parameters obtained in step S1 are only calibration configuration parameters estimated for the project calibration parameters input for this calibration project. For different projects, the obtained initial calibration configuration parameters need to be further debugged to ensure the accuracy of the calibration configuration parameters.

[0094] The calculation process of the calibration results is as follows:

[0095] 1. Determine the ROI area of ​​the calibration image

[0096] 1.1 Prepare the image:

[0097] Acquire an image that contains a calibration plate. The calibration plate typically has known geometric features such as a checkerboard, array of dots, or other pattern.

[0098] 1.2 Preprocessing images:

[0099] Grayscale: Convert the image to grayscale to simplify subsequent corner detection.

[0100] Denoising: Apply filters (such as Gaussian blur) to remove noise from the image and improve the accuracy of corner detection.

[0101] 1.3 Extract ROI:

[0102] Image segmentation: Use edge detection (such as Canny edge detection) or threshold segmentation to extract the boundaries of the calibration plate.

[0103] Shape detection: Use shape detection algorithms (such as Hough transform) to find the outline of the calibration plate.

[0104] ROI selection: Define the region of interest (ROI) based on the contour of the calibration plate or the position of the detected corners. Usually the ROI is the entire area of ​​the calibration plate or a part of it.

[0105] 2. Corner Detection

[0106] 2.1 Corner Detection:

[0107] Select algorithm: Use corner detection algorithm, such as Harris corner detection, Shi-Tomasi corner detection, or other suitable methods to detect corners in the ROI area.

[0108] Parameter adjustment: Adjust parameters according to the needs of the algorithm, such as the corner response threshold, to ensure that the final corner points are detected.

[0109] 2.2 Corner point coordinate extraction:

[0110] Corner point position: Record the pixel coordinates (x, y) of each detected corner point.

[0111] The process of debugging and calibrating configuration parameters is as follows:

[0112] 3. Optimize calibration configuration parameters

[0113] 3.1 Error calculation:

[0114] Reprojection error: Calculate the error between the actual world coordinates of the corner points on the calibration plate and their reprojected positions on the image.

[0115] 3.2 Nonlinear Optimization:

[0116] Optimization algorithm: Apply nonlinear optimization algorithms (such as the Levenberg-Marquardt algorithm) to minimize the reprojection error and thus optimize the calibration configuration parameters.

[0117] 3.3 Update configuration parameters

[0118] 4. Verify the calibration results

[0119] 4.1 Reprojection:

[0120] Verify reprojection: Reproject the real world coordinates onto the image plane and check how well the projected points match the actual corner locations.

[0121] 4.2 Accuracy Evaluation

[0122] Error analysis: Evaluate the accuracy of the calibration results and verify the accuracy of the calibration by calculating the statistics of the reprojection error (such as the mean square error).

[0123] 4.3 Result adjustment:

[0124] Tuning Parameters: Depending on the validation results, additional tuning may be necessary to improve accuracy.

[0125] In a preferred embodiment of the surround view calibration project, a risk assessment of the calibration configuration parameters can be obtained through the surround view calibration system and the project parameters imported by the user, and abnormalities or risk prompts of the surround view calibration are given in a visual manner based on B / S system highlights.

[0126] The evaluation process includes the following functions:

[0127] After receiving the calibration configuration parameters, the calibration tool backend service system performs simulation verification and evaluation, as shown in the attached Figure 2 The above is a bird's-eye view shown by the calibration tool background service system, and at the same time, the meaning of the calibration parameters is described or schematically expressed, such as: corner point order, grid aspect ratio and other parameters, which are used to screen and sort the calibration algorithm grids, and provide visual step-by-step guidance.

[0128] During the assessment process, high-risk or error parameters are highlighted, analyzed, or schematically presented.

[0129] In an embodiment of the present invention, optionally, the method of outputting the final calibration configuration parameters through the output interface includes:

[0130] The final calibration configuration parameters are packaged into a calibration configuration file package, and then output through the output interface.

[0131] In the embodiment of the present invention, optionally, step S4 further includes: when the calibration result does not meet the preset requirements for a number of times greater than or equal to a preset number of times, sending an email to a preset engineer requesting the engineer to log in to the system to assist in debugging.

[0132] The surround view calibration method further comprises the steps of:

[0133] The obtained evaluation results and debugging process are recorded in the log module.

[0134] When the engineer logs into the system through the email, the log module pushes the evaluation result and debugging process record to the engineer or makes it available to the engineer.

[0135] In the embodiment of the present invention, optionally, the calibration result includes final calibration configuration parameters obtained in this debugging, and the step S5 further includes: storing the final calibration configuration in the calibration result.

[0136] After obtaining accurate calibration configuration parameters, they need to be input into the host for on-machine verification. After on-machine verification, this surround calibration project is completed. On-machine verification can further improve the accuracy of calibration configuration parameters to prevent errors in calibration configuration parameters during actual application.

[0137] Embodiment 2:

[0138] As attached Figure 3 As shown, an embodiment of the present invention provides a surround view calibration system, the surround view calibration system comprising:

[0139] The surround view calibration system comprises:

[0140] The parameter acquisition module is used to obtain the project parameters of the target system through the input interface.

[0141] The calibration configuration module is used to obtain calibration configuration parameters according to the project parameters.

[0142] The algorithm debugging module is used to calculate based on the calibration configuration parameters through the calibration algorithm to obtain the calibration results and debug the calibration configuration parameters.

[0143] The calibration tool backend service system is used to determine whether the calibration results meet the preset requirements.

[0144] The folder generation module is used to generate a calibration configuration folder based on the final calibration configuration parameters, and output the calibration configuration folder to the target system through an output interface for calibration.

[0145] In the embodiment of the present invention, optionally, the surround view calibration system further includes:

[0146] The log module is used to store the evaluation results and debugging process records of the surround view calibration system.

[0147] Message discussion module, used to collect user feedback.

[0148] When the engineer logs into the system through the email, the log module pushes the evaluation results and debugging process records of the surround view calibration system to the engineer or makes them available to the engineer.

[0149] Through the historical database, calibration configuration parameters can be obtained in the historical database.

[0150] The above-mentioned surround view calibration system design also includes a user system for storing user information. After logging into the surround view calibration system through the user system, the project parameters are uploaded to the main system. Combined with the evaluation function provided by the calibration tool background service system, accurate surround view calibration configuration parameters can be obtained in the cloud without manual configuration based on documents or experience, saving labor costs.

[0151] In an embodiment of the present invention, the user system is used to store the account and password of the system user, receive user information (account and password) entered by the user, verify the user information, allow the user to access other functional modules after verification, store the user's login information, etc.

[0152] The calibration tool background service system includes at least one calibration algorithm. In an embodiment of the present invention, the calibration tool background service system also includes: a data acquisition and storage unit, a data processing unit and a deep learning unit. The calibration tool background service system performs simulation evaluation on the calibration configuration parameters.

[0153] The surround view calibration system contains three core modules: algorithm debugging module, parameter acquisition module, and calibration configuration module.

[0154] In a preferred surround view calibration project process, after the user logs in to the surround view calibration system, he inputs the project calibration parameters into the parameter acquisition module. The parameter acquisition module confirms the project parameters shown and sends them to the calibration configuration module. Based on the project calibration parameters, the calibration configuration module obtains the corresponding historical calibration configuration parameters in the historical database as calibration configuration parameters and outputs them to the algorithm debugging module and the calibration tool background service system.

[0155] In the embodiment of the present invention, a solid state drive 1 is provided in the parameter acquisition module for storing calibration parameters of items that need to be quickly accessed and processed and need to be confirmed, but the present invention is not limited thereto.

[0156] In an embodiment of the present invention, a memory 2 and a processor 1 are provided in the calibration configuration module. The memory 2 is used to receive the project parameters sent by the parameter acquisition module. The processor 1 is provided with a communication connection with the historical database, and is used to obtain corresponding historical calibration configuration parameters in the historical database as initial calibration configuration parameters based on the project parameters, but is not limited to this.

[0157] In an embodiment of the present invention, a processor 2 is provided in the algorithm debugging module, a communication connection is provided between the processor 2 and the calibration tool background service system, and a debugging algorithm is built in, for receiving the evaluation results sent by the calibration tool background service system and performing debugging according to the debugging algorithm.

[0158] When determining the initial calibration configuration parameters, the calibration configuration module obtains the most suitable calibration configuration parameters from the historical database according to the project parameters as the initial calibration configuration parameters.

[0159] In the embodiment of the present invention, optionally, the surround view calibration system further includes:

[0160] A historical database for storing the final calibration configuration parameters generated historically;

[0161] When determining the calibration configuration parameters, the calibration configuration module obtains the most suitable historical calibration configuration parameters from the historical database according to the project parameters as the calibration configuration parameters.

[0162] Through the historical database, initial calibration configuration parameters can be obtained in the historical database.

[0163] In an embodiment of the present invention, optionally, the historical database is used to store historical calibration configuration parameters, which is implemented based on a server, such as a physical or virtual server running a database management system (such as MySQL, PostgreSQL, MongoDB, etc.). The database server is responsible for storing and managing data, executing queries and processing requests. The parameter data used in the process of the panoramic calibration project will be uploaded to the database for subsequent query maintenance.

[0164] When the engineer logs into the system through the email, the log module pushes the evaluation results and debugging process records of the surround view calibration system to the engineer or makes them available to the engineer.

[0165] The log module and the message discussion module are auxiliary modules, mainly used to record, solve and feedback problems encountered in the environmental calibration project. The log module is provided with a memory 3, and each calibration project configuration folder has a dedicated log folder for saving the modification history of the calibration configuration parameters in the project; the message discussion module and the email module are used to discuss and feedback problems encountered in the calibration project in the cloud.

[0166] In an embodiment of the present invention, optionally, the calibration tool background service system is used to obtain and evaluate the initial calibration configuration parameters from the calibration configuration module, and is also used to obtain and evaluate the intermediate calibration configuration parameters from the algorithm debugging module. If the evaluation result is that the surround view calibration is successful, the initial calibration configuration parameters or the intermediate calibration configuration parameters of this evaluation are determined as the final calibration configuration parameters and output through the output interface. If the evaluation result is that the surround view calibration fails, the calibration configuration of this evaluation is sent to the algorithm debugging module for debugging.

[0167] After determining the final calibration configuration parameters, the calibration tool background service system first encapsulates the final calibration configuration parameters into a calibration configuration file package, and then outputs it through the output interface.

[0168] The third aspect:

[0169] The present application also proposes a computer-readable storage medium, which stores computer-executable instructions, and is characterized in that when the computer-executable instructions are executed by a control processor, the assisted driving method as described is implemented.

[0170] The computer readable storage medium comprises:

[0171] The computer-readable storage medium stores computer-executable instructions.

[0172] The computer executable instructions implement the reversing video signal processing method when executed by the control processor.

[0173] In the computer-readable storage medium, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk SolidState Disk (SSD)), etc.

[0174] It should be noted that since the computer-readable storage medium in this embodiment and the assisted driving method in the above embodiment are based on the same inventive concept, the corresponding contents in the method embodiment are also applicable to the system embodiment and will not be described in detail here.

[0175] In summary, this application proposes a surround view calibration method, system and storage medium thereof. The surround view calibration method first confirms the project parameters, and confirms the initial calibration configuration parameters based on the project parameters, and then debugs the initial calibration configuration parameters until the project calibration is successful and the final calibration configuration parameters are obtained. This application also proposes a surround view calibration system based on the method, and the surround view calibration system includes: an algorithm debugging module, a parameter acquisition module, a calibration configuration module, a calibration tool background service system and a folder generation module.

[0176] The surround view calibration method, system and storage medium proposed in this application can realize the surround view calibration requirements of different projects in the cloud, without the need for manual parameter configuration based on documents or experience, which significantly improves the quality and efficiency of the surround view calibration work.

[0177] In several embodiments provided in the present application, it is understood that each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.

[0178] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling an electronic device to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0179] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A surround calibration method, characterized in that: The surround view calibration method specifically comprises the following steps: S1: Get the project parameters of the target system; S2: Obtain calibration configuration parameters according to the project parameters; S3: Based on the calibration configuration parameters, a calibration result is obtained by calculating the calibration algorithm, and then proceeding to step S4; S4: Determine whether the calibration result meets the preset requirements. If so, proceed to step S5. If not, recalculate the calibration result. S5: Generate a calibration configuration folder based on the calibration result, and output the calibration configuration folder to the target system through an output interface for calibration.

2. The surround view calibration method according to claim 1, characterized in that: The project parameters include: project name parameters, platform parameters, vehicle model parameters, camera installation parameters and project images; the platform parameters include: the internal parameter type used by the camera used in the project, the distortion model and the number of vehicle suspensions.

3. The surround view calibration method according to claim 1, characterized in that: The step S3 specifically includes: S31: Obtaining a project image including calibration feature points from the project parameters; S32: extracting the RIO region of the image using an image segmentation algorithm; S33: Detect corner points in the RIO area using a corner point detection algorithm, and extract coordinates of the corner points to obtain a calibration result.

4. The surround view calibration method according to claim 1, characterized in that: The step S4 also includes: when the number of times that the calibration result does not meet the preset requirements is greater than or equal to the preset number of times, sending an email to a preset engineer to request the engineer to log in to the system to assist in debugging.

5. The surround view calibration method according to claim 4, characterized in that: Further comprising the steps of: The obtained evaluation results and debugging process are recorded in the log module; When the engineer logs into the system through the email, the log module pushes the evaluation result and debugging process record to the engineer or makes it available to the engineer.

6. The surround view calibration method according to claim 1, characterized in that: Acquire the most suitable historical calibration configuration parameters as calibration configuration parameters according to the project parameters; The calibration result includes the final calibration configuration parameters obtained in this debugging, and after step S5, the further step includes: storing the final calibration configuration in the calibration result.

7. A surround view calibration system based on the surround view calibration method according to any one of claims 1 to 6, characterized in that: The surround view calibration system comprises: A parameter acquisition module is used to obtain the project parameters of the target system through an input interface; A calibration configuration module, used to obtain calibration configuration parameters according to the project parameters; An algorithm debugging module, used to calculate based on the calibration configuration parameters through a calibration algorithm to obtain a calibration result and debug the calibration configuration parameters; The calibration tool backend service system is used to determine whether the calibration results meet the preset requirements; The folder generation module is used to generate a calibration configuration folder based on the final calibration configuration parameters, and output the calibration configuration folder to the target system through an output interface for calibration.

8. The surround view calibration system according to claim 7, wherein: The surround view calibration system also includes: A log module, used to store the evaluation results and debugging process records of the surround view calibration system; Message discussion module, used to collect user feedback; When the engineer logs into the system through the email, the log module pushes the evaluation results and debugging process records of the surround view calibration system to the engineer or makes them available to the engineer.

9. The surround view calibration system according to claim 7, characterized in that: The surround view calibration system also includes: A historical database for storing the final calibration configuration parameters generated historically; When determining the calibration configuration parameters, the calibration configuration module obtains the most suitable historical calibration configuration parameters from the historical database according to the project parameters as the calibration configuration parameters.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that: When the computer executable instructions are executed by the control processor, the surround view calibration method as described in claims 1-6 is implemented.

Images