Vehicle panoramic view system automatic calibration method, device, medium and equipment

Abstract

The present disclosure relates to a method, device, medium and equipment for automatic calibration of a vehicle panoramic surround view system, including: when the vehicle to be calibrated is in a calibration area, obtaining the panoramic surround view system configuration data corresponding to the vehicle to be calibrated; obtaining the original captured images captured by each camera in the panoramic surround view system; identifying the actual pixel coordinates corresponding to the target detection point in the original captured image; replacing the initial pixel coordinates corresponding to the target detection point in the panoramic surround view system configuration data with the actual pixel coordinates corresponding to the target detection point, so as to calibrate the panoramic surround view system. In this way, when calibrating the panoramic surround view system in the vehicle, it is only necessary to identify the actual pixel coordinates of the target detection point in the captured image, and calibration can be performed according to the actual pixel coordinates. In this way, the computational overhead of the panoramic surround view system calibration can be greatly reduced while ensuring the accuracy of the panoramic image output by the panoramic surround view system, thereby improving the calibration efficiency.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicles, and in particular, to a method, device, medium and equipment for automatically calibrating a vehicle's panoramic surround view system. Background Art

[0002] During the driving process, the driver can only rely on the rearview mirror or windshield and other equipment to observe the surrounding conditions of the vehicle. Therefore, it may be impossible to reasonably judge the distance between the vehicle and the surrounding obstacles, and the surrounding vehicle conditions cannot be known in time. Therefore, most vehicles are usually equipped with a panoramic surround view system that can assist the driver in observing the surrounding conditions of the vehicle. At present, the vehicle visual assistance system equipped on most vehicles is a panoramic surround view system that observes the images around the vehicle through four cameras on the front, back, left and right of the vehicle. It usually uses 4 ultra-wide-angle cameras to process the captured images and splice them to obtain a complete panoramic surround view.

[0003] When the vehicle leaves the factory, due to the installation accuracy of each camera in the panoramic view system, the panoramic view obtained may be inaccurate. Therefore, the panoramic view system needs to be calibrated separately according to the specific situation of the vehicle to ensure the accuracy of the panoramic view obtained. In the prior art, the accuracy of the panoramic view system is usually ensured by calibrating the camera extrinsic parameters. The camera extrinsic parameters are the parameters that determine the relative position relationship between the camera coordinates and the world coordinate system, usually including the rotation matrix and the translation matrix, wherein the rotation matrix describes the direction of the coordinate axis of the world coordinate system relative to the camera coordinate axis, and the translation matrix describes the position of the space origin in the camera coordinate system. By calibrating the camera extrinsic parameters, after each camera captures the corresponding image, the captured images can be processed and spliced ​​according to the camera extrinsic parameters to obtain a complete panoramic view, thereby assisting the driver to observe the surrounding environment of the vehicle body and reducing the occurrence of accidents such as scratches and collisions. Summary of the invention

[0004] The purpose of the present disclosure is to provide a method, device, medium and equipment for automatic calibration of a vehicle panoramic view system, so as to partially solve the above-mentioned problems existing in the related art.

[0005] In order to achieve the above object, the present disclosure provides a method for automatically calibrating a vehicle panoramic view system, wherein the panoramic view system includes a plurality of cameras arranged around the vehicle for capturing images of the environment around the vehicle, and the method includes:

[0006] When the vehicle to be calibrated is in the calibration area, obtaining the panoramic view system configuration data corresponding to the vehicle to be calibrated, wherein calibration plates are laid around the calibration area, the calibration plates correspond to the cameras one by one, each calibration plate includes a plurality of target detection points, and the panoramic view system configuration data includes the target pixel coordinates corresponding to the target detection points in each calibration plate in the target panoramic image output by the panoramic view system, and the initial pixel coordinates corresponding to the target detection points;

[0007] Acquire the original images captured by each camera in the panoramic view system;

[0008] Identify the actual pixel coordinates corresponding to the target detection point in the original captured image;

[0009] The initial pixel coordinates corresponding to the target detection points in the panoramic view system configuration data are replaced with the actual pixel coordinates corresponding to the target detection points to calibrate the panoramic view system.

[0010] Optionally, the calibration plate is a checkerboard calibration plate, and the identifying actual pixel coordinates corresponding to the target detection point in the original captured image includes:

[0011] Identifying all checkerboard corner points included in the original captured image;

[0012] The pixel coordinates of the corner points corresponding to the checkerboard corner points at the target position in the original captured image are used as the actual pixel coordinates corresponding to the target detection points in the original captured image.

[0013] Optionally, the identifying all checkerboard corner points included in the original captured image includes:

[0014] Performing corner point recognition on the original captured image;

[0015] When the number of corner points identified in each original captured image is the target number, the corner points identified in each original captured image are used as the checkerboard corner points included in the original captured image.

[0016] Optionally, the target position is four checkerboard corner points at both ends of the main and secondary diagonals in a corner point matrix composed of all checkerboard corner points included in the checkerboard calibration plate, wherein the positions of the checkerboard corner points in the corner point matrix are determined according to the corner point pixel coordinates corresponding to the checkerboard corner points.

[0017] Optionally, before identifying the actual pixel coordinates corresponding to the target detection point in the original captured image, the method further includes:

[0018] The original captured image is subjected to distortion correction according to the panoramic view system configuration data.

[0019] Optionally, the panoramic surround view system obtains the target panoramic image by the following method:

[0020] Acquire the images to be stitched taken by each camera in the panoramic view system;

[0021] Determine the transformation matrix corresponding to each image to be stitched according to the actual pixel coordinates and the target pixel coordinates corresponding to the actual pixel coordinates;

[0022] The images to be stitched are transformed to the same plane according to the transformation matrix, and stitched in a preset order to obtain the target panoramic image.

[0023] Optionally, the calibration plate is a checkerboard calibration plate, and the recognition module includes:

[0024] A first recognition submodule, used to recognize all checkerboard corner points included in the original captured image;

[0025] The second recognition submodule is used to use the corner point pixel coordinates corresponding to the checkerboard corner points at the target position in the original captured image as the actual pixel coordinates corresponding to the target detection point in the original captured image.

[0026] The present disclosure also provides an automatic calibration device for a vehicle panoramic view system, wherein the panoramic view system includes four cameras arranged around the vehicle, respectively used to capture environmental images around the vehicle, and the device includes:

[0027] A first acquisition module is used to acquire the panoramic view system configuration data corresponding to the vehicle to be calibrated when the vehicle to be calibrated is in the calibration area, wherein corresponding calibration plates are laid around the calibration area, each calibration plate includes a plurality of target detection points, and the panoramic view system configuration data includes target pixel coordinates corresponding to the target detection points in each calibration plate in the target panoramic image output by the panoramic view system;

[0028] A second acquisition module is used to acquire original images captured by each camera in the panoramic view system;

[0029] An identification module, used to identify the actual pixel coordinates corresponding to the target detection points in each calibration plate in the original captured image;

[0030] The calibration module is used to use the actual pixel coordinates corresponding to each target detection point as calibration parameters to calibrate the panoramic surround view system.

[0031] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when executed by a processor.

[0032] The present disclosure also provides an electronic device, comprising:

[0033] a memory having a computer program stored thereon;

[0034] A processor is used to execute the computer program in the memory to implement the steps of the above method.

[0035] Through the above technical solution, when calibrating the panoramic view system in the vehicle, it is only necessary to identify the actual pixel coordinates of the target detection points in the captured image, and then calibrate according to the actual pixel coordinates. This can greatly reduce the computational overhead of calibrating the panoramic view system and improve the calibration efficiency while ensuring the accuracy of the panoramic image output by the panoramic view system.

[0036] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0038] Figure 1 The present invention is a flowchart of a method for automatically calibrating a vehicle panoramic view system according to an exemplary embodiment of the present invention.

[0039] Figure 2 The present invention is a flowchart of a method for automatically calibrating a vehicle panoramic view system according to another exemplary embodiment of the present invention.

[0040] Figure 3 The present invention is a flowchart of a method for automatically calibrating a vehicle panoramic view system according to another exemplary embodiment of the present invention.

[0041] Figure 4 The present invention is a structural block diagram of an automatic calibration device for a vehicle panoramic view system according to an exemplary embodiment of the present invention.

[0042] Figure 5 It is a block diagram of an electronic device according to an exemplary embodiment.

[0043] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0044] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0045] Figure 1 The flowchart of a method for automatically calibrating a vehicle panoramic view system according to an exemplary embodiment of the present disclosure is shown. The panoramic view system includes a plurality of cameras arranged around the vehicle for capturing images of the environment around the vehicle. Figure 1 As shown, the method includes steps 101 to 104.

[0046] In step 101, when the vehicle to be calibrated is in a calibration area, the panoramic view system configuration data corresponding to the vehicle to be calibrated is obtained, wherein calibration plates are laid around the calibration area, the calibration plates correspond to the cameras one-to-one, each calibration plate includes a plurality of target detection points, and the panoramic view system configuration data includes target pixel coordinates corresponding to the target detection points in each calibration plate in the target panoramic image output by the panoramic view system, and initial pixel coordinates corresponding to the target detection points.

[0047] In step 102, original images captured by each camera in the panoramic view system are obtained.

[0048] In step 103, the actual pixel coordinates corresponding to the target detection point in the original captured image are identified.

[0049] In step 104, the initial pixel coordinates corresponding to the target detection points in the panoramic view system configuration data are replaced with the actual pixel coordinates corresponding to the target detection points to calibrate the panoramic view system.

[0050] The calibration area may be any area where the vehicle to be calibrated can be parked.

[0051] The calibration plates laid around the calibration area correspond one-to-one with the cameras included in the panoramic surround view system. For example, if the panoramic surround view system includes four cameras, which are used to capture images in the four directions of the front, back, left, and right of the vehicle, then the calibration plates can also be four, which are laid in the four directions of the front, back, left, and right of the calibration area. Each calibration plate includes multiple target detection points. When the camera in the panoramic surround view system is in the calibration area, the captured image will include the calibration plates laid around the calibration area, and the captured image will be used to form a panoramic view of the surroundings of the vehicle output by the panoramic surround view system. Therefore, the target detection point included in the calibration plate will also correspond to a position in the panoramic view output by the panoramic surround view system, and the position is also the target pixel coordinate.

[0052] Since the calibration plate laid around the calibration area will not change during the vehicle calibration process, the position of the calibration plate in the panoramic view output by the panoramic surround view system should also be fixed, and the target pixel coordinates corresponding to the target detection points on the calibration plate in the panoramic view should also be fixed coordinates. Therefore, after the calibration plate and the target detection points are set, the target pixel coordinates corresponding to each target detection point in the panoramic view output by the panoramic surround view system can also be determined accordingly. The target pixel coordinates can be used as the panoramic surround view system configuration data to configure the panoramic surround view system.

[0053] The number of calibration plates is not necessarily the same as the number of cameras in the panoramic view system. For example, the calibration plate can also be a whole calibration plate laid around the calibration area. In this case, the one-to-one correspondence between the calibration plate and the camera can be expressed as a one-to-one correspondence between the target detection points. For example, if the cameras in the panoramic view system are four cameras that respectively capture images of the front, back, left, and right directions of the vehicle, multiple target detection points can be set in the calibration plate area in the front, back, left, and right directions of the vehicle to be calibrated, so as to represent the calibration plate that corresponds one-to-one with the camera.

[0054] The initial pixel coordinates corresponding to the target detection point are also the positions where the target detection point should be located in the images captured by the cameras in the panoramic view system when the target detection point is set. During the assembly of the vehicle, the installation accuracy of the cameras in the panoramic view system may cause the angles and ranges of the images captured by the cameras to have certain errors compared with the theoretical data. Therefore, the actual pixel coordinates of the pre-set target detection point in the images captured by the cameras in the panoramic view system will have certain deviations from the initial pixel coordinates obtained according to the theoretical data. The calibration method of the panoramic view system provided in the present application is implemented by calibrating the actual pixel coordinates.

[0055] When calibrating a vehicle to be calibrated, the vehicle to be calibrated is placed in the calibration area, at which time a panoramic view system in the vehicle is started, and calibration plates around the calibration area are photographed by a camera in the panoramic view system.

[0056] Each camera will capture a corresponding original image. Since the target detection point is set according to the calibration plate corresponding to the camera one by one, each original image should include the set target detection point. The number of target detection points included in the original image can be determined according to the method of determining the panoramic image by the panoramic view system. For example, if the homography transformation method is used to transform the original image into the panoramic image, the number of target detection points included in each original image can be 4, so that four groups of two-dimensional coordinate pairs are formed according to the actual pixel coordinates and target pixel coordinates corresponding to each target detection point to achieve image transformation; if the affine transformation method is used to transform the original image into the panoramic image, the number of target detection points included in each original image can be 3, so that three groups of two-dimensional coordinate pairs are formed according to the actual pixel coordinates and target pixel coordinates corresponding to each target detection point to achieve image transformation.

[0057] The method for identifying the actual pixel coordinates corresponding to the target detection point in the original captured image may be any image recognition method as long as the preset target detection point can be accurately identified from the original captured image.

[0058] After identifying all target detection points in each original captured image, the actual pixel coordinates corresponding to the target detection points can be used as calibration parameters to replace the initial pixel coordinates in the panoramic view system configuration data to achieve calibration of the panoramic view system.

[0059] Wherein, in the case where there are multiple target detection points included in each original captured image, the correspondence between each target detection point identified in each original captured image and the target pixel coordinates and initial pixel coordinates in the panoramic surround view system configuration data can be determined based on the location of the target detection point and other features. For example, in the case where the number of target detection points in the original captured image captured by each camera should be 4, the four target detection points can be set to be arranged from left to right in sequence on the corresponding calibration plate, and sorted as detection points 1-4, so that they are also presented as four points arranged from left to right in the original captured image. In this way, when identifying the target detection points in the original captured image, it is possible to determine which target detection point each target detection point belongs to from left to right based on the actual pixel coordinates of the identified target detection points, and then determine the correspondence between it and the target pixel coordinates and initial pixel coordinates in the panoramic surround view system configuration data, and finally achieve calibration by replacing the initial pixel coordinates.

[0060] Through the above technical solution, when calibrating the panoramic view system in the vehicle, it is only necessary to identify the actual pixel coordinates of the target detection points in the captured image, and then calibrate according to the actual pixel coordinates. This can greatly reduce the computational overhead of calibrating the panoramic view system and improve the calibration efficiency while ensuring the accuracy of the panoramic image output by the panoramic view system.

[0061] Figure 2 FIG. 1 is a flow chart showing a method for automatically calibrating a vehicle panoramic view system according to another exemplary embodiment of the present disclosure. The calibration board is a checkerboard calibration board. Figure 2 The method further includes step 201 and step 202.

[0062] In step 201, all checkerboard corner points included in the original captured image are identified.

[0063] In step 202, the pixel coordinates of the corner points corresponding to the checkerboard corner points at the target position in the original captured image are used as the actual pixel coordinates corresponding to the target detection points in the original captured image.

[0064] That is, the calibration plate may be a checkerboard calibration plate. In the case where the calibration plate is a checkerboard calibration plate, the target detection point may be determined by directly setting a target position from a plurality of corner points in the checkerboard calibration plate. By setting the target position, after all corner points in the original captured image are identified, the corner point at the target position may be determined as the target detection point.

[0065] Wherein, when the number of target detection points in the calibration plate area corresponding to each camera is set to 4, the target position may be four checkerboard corner points at both ends of the main and secondary diagonals in the corner point matrix composed of all checkerboard corner points included in the checkerboard calibration plate, wherein the positions of the checkerboard corner points in the corner point matrix are determined according to the corner point pixel coordinates corresponding to the checkerboard corner points. That is, after identifying all checkerboard corner points included in the original captured image, the checkerboard corner points may be formed into a corresponding matrix of n×m according to the corner point pixel coordinates corresponding to each corner point, and the target detection point may be determined according to its position in the matrix.

[0066] When identifying all checkerboard corner points included in the original captured image, the identification may be performed using a corner point identification method based on OpenCV.

[0067] In addition, before determining all the checkerboard corner points in the original captured image, the original captured image may be firstly identified; then the number of identified corner points is judged, and only when the number of corner points identified in each original captured image is the target number, the corner points identified in each original captured image are used as the checkerboard corner points included in the original captured image; otherwise, it is judged that the currently identified corner points are incorrect, an error may be reported, and the corner point identification is performed again. For example, if when setting the checkerboard calibration plate, the number of corner points in the calibration plate that can be captured by each camera is 40, then when identifying all the checkerboard corner points in the original captured image, the number of identified corner points in each original captured image is firstly judged, and if the number of identified corner points is not 40, it is judged that the corner point identification of the original captured image is incorrect.

[0068] Figure 3 FIG. 1 is a flow chart showing a method for automatically calibrating a vehicle panoramic view system according to another exemplary embodiment of the present disclosure. Figure 3 As shown, the method further includes step 301.

[0069] In step 301, distortion correction is performed on the original captured image according to the panoramic view system configuration data.

[0070] In the case where the camera equipped in the panoramic surround view system is a camera that needs to be distorted, after each camera in the panoramic surround view system captures the corresponding original captured image, the original captured image will be distorted according to the panoramic surround view system configuration data. The camera internal parameter used for the distortion correction is preset in the panoramic surround view system configuration data. The original captured image used for the target detection point recognition is the new original captured image obtained after the distortion correction.

[0071] In a possible implementation, the panoramic view system disclosed in the present application obtains the target panoramic image by the following method: obtaining the images to be spliced ​​taken by each camera in the panoramic view system; determining the transformation matrix corresponding to each image to be spliced ​​according to the actual pixel coordinates and the target pixel coordinates corresponding to the actual pixel coordinates; transforming each image to be spliced ​​to the same plane according to the transformation matrix, and splicing the target panoramic image in a preset order. Among them, the actual pixel coordinates are also the calibration data obtained by calibration in the calibration method disclosed in the present application. When the target pixel coordinates and the actual pixel coordinates are determined, the transformation method between images is also fixed, so that the transformation matrix corresponding to each image to be spliced ​​can be determined according to the actual pixel coordinates and the target pixel coordinates, and then each image to be spliced ​​can be transformed to the same plane to form the target panoramic image for output. In the case that the image taken by the camera used in the panoramic view system needs to be distorted, the relevant camera internal parameter parameters for distortion correction will be pre-set in the panoramic view system configuration parameters, and the image to be spliced ​​can be the image obtained after the above distortion correction.

[0072] Figure 4 The structure block diagram of an automatic calibration device for a vehicle panoramic view system according to an exemplary embodiment of the present disclosure is shown. The panoramic view system includes four cameras arranged around the vehicle, which are respectively used to capture the environment images around the vehicle, such as Figure 4 As shown, the device includes: a first acquisition module 10, which is used to acquire the panoramic view system configuration data corresponding to the vehicle to be calibrated when the vehicle to be calibrated is in the calibration area, wherein corresponding calibration plates are laid around the calibration area, each calibration plate includes a plurality of target detection points, and the panoramic view system configuration data includes target pixel coordinates corresponding to the target detection points in each calibration plate in the target panoramic image output by the panoramic view system; a second acquisition module 20, which is used to acquire the original captured image captured by each camera in the panoramic view system; an identification module 30, which is used to identify the actual pixel coordinates corresponding to the target detection points in each calibration plate in the original captured image; and a calibration module 40, which is used to use the actual pixel coordinates corresponding to each target detection point as a calibration parameter to calibrate the panoramic view system.

[0073] Through the above technical solution, when calibrating the panoramic view system in the vehicle, it is only necessary to identify the actual pixel coordinates of the target detection points in the captured image, and then calibrate according to the actual pixel coordinates. This can greatly reduce the computational overhead of calibrating the panoramic view system and improve the calibration efficiency while ensuring the accuracy of the panoramic image output by the panoramic view system.

[0074] In a possible implementation, the calibration plate is a checkerboard calibration plate, and the recognition module 30 includes: a first recognition submodule, used to identify all checkerboard corner points included in the original captured image; and a second recognition submodule, used to use the corner point pixel coordinates corresponding to the checkerboard corner points at the target position in the original captured image as the actual pixel coordinates corresponding to the target detection point in the original captured image.

[0075] In a possible implementation, the first recognition submodule is further used to: perform corner point recognition on the original captured image; when the number of corner points recognized in each original captured image is the target number, use the corner points recognized in each original captured image as the checkerboard corner points included in the original captured image.

[0076] In a possible implementation, the target position is four checkerboard corner points at both ends of the main and secondary diagonals in a corner point matrix composed of all checkerboard corner points included in the checkerboard calibration plate, wherein the positions of the checkerboard corner points in the corner point matrix are determined based on the corner point pixel coordinates corresponding to the checkerboard corner points.

[0077] In a possible implementation, before the recognition module 30 recognizes the actual pixel coordinates corresponding to the target detection point in the original captured image, the device further includes a distortion correction module for performing distortion correction on the original captured image according to the panoramic surround view system configuration data.

[0078] In a possible implementation, the panoramic view system obtains the target panoramic image by the following method: acquiring the images to be stitched taken by each camera in the panoramic view system; determining the transformation matrix corresponding to each image to be stitched according to the actual pixel coordinates and the target pixel coordinates corresponding to the actual pixel coordinates; transforming each image to be stitched to the same plane according to the transformation matrix, and stitching them in a preset order to obtain the target panoramic image.

[0079] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0080] Figure 5 FIG. 5 is a block diagram of an electronic device 500 according to an exemplary embodiment. Figure 5 As shown, the electronic device 500 may include: a processor 501 and a memory 502. The electronic device 500 may also include one or more of a multimedia component 503, an input / output (I / O) interface 504, and a communication component 505.

[0081] The processor 501 is used to control the overall operation of the electronic device 500 to complete all or part of the steps in the above-mentioned vehicle panoramic view system automatic calibration method. The memory 502 is used to store various types of data to support the operation of the electronic device 500, and these data may include, for example, instructions for any application or method used to operate on the electronic device 500, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 503 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 502 or sent through the communication component 505. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 504 provides an interface between the processor 501 and other interface modules, and the above-mentioned other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 505 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0082] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned vehicle panoramic view system automatic calibration method.

[0083] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned vehicle panoramic view system automatic calibration method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 502 including program instructions, and the above-mentioned program instructions can be executed by the processor 501 of the electronic device 500 to complete the above-mentioned vehicle panoramic view system automatic calibration method.

[0084] Figure 6 6 is a block diagram of an electronic device 600 according to an exemplary embodiment. For example, the electronic device 600 may be provided as a server. Figure 6 The electronic device 600 includes a processor 622, which may be one or more, and a memory 632 for storing a computer program executable by the processor 622. The computer program stored in the memory 632 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 622 may be configured to execute the computer program to perform the above-mentioned vehicle panoramic view system automatic calibration method.

[0085] In addition, the electronic device 600 may further include a power supply component 626 and a communication component 650. The power supply component 626 may be configured to perform power management of the electronic device 600, and the communication component 650 may be configured to implement communication of the electronic device 600, for example, wired or wireless communication. In addition, the electronic device 600 may further include an input / output (I / O) interface 658. The electronic device 600 may operate based on an operating system stored in the memory 632, such as Windows Server 2000. TM , Mac OSX TM , Unix TM , Linux TM etc.

[0086] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned vehicle panoramic view system automatic calibration method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 632 including program instructions, and the above-mentioned program instructions can be executed by the processor 622 of the electronic device 600 to complete the above-mentioned vehicle panoramic view system automatic calibration method.

[0087] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing the above-mentioned vehicle panoramic view system automatic calibration method when executed by the programmable device.

[0088] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0089] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0090] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for automatic calibration of a vehicle panoramic view system. It is characterized in that The panoramic surround view system includes a plurality of cameras arranged around the vehicle for capturing images of the environment around the vehicle. The method includes: When the vehicle to be calibrated is in the calibration area, obtaining the panoramic view system configuration data corresponding to the vehicle to be calibrated, wherein calibration plates are laid around the calibration area, the calibration plates correspond to the cameras one by one, each calibration plate includes a plurality of target detection points, and the panoramic view system configuration data includes the target pixel coordinates corresponding to the target detection points in each calibration plate in the target panoramic image output by the panoramic view system, and the initial pixel coordinates corresponding to the target detection points; Acquire the original images captured by each camera in the panoramic view system; Identify the actual pixel coordinates corresponding to the target detection point in the original captured image; Replacing the initial pixel coordinates corresponding to the target detection points in the panoramic view system configuration data with the actual pixel coordinates corresponding to the target detection points to calibrate the panoramic view system; The panoramic view system obtains the target panoramic image by the following method: Acquire the images to be stitched taken by each camera in the panoramic view system; Determine the transformation matrix corresponding to each image to be stitched according to the actual pixel coordinates and the target pixel coordinates corresponding to the actual pixel coordinates; The images to be stitched are transformed to the same plane according to the transformation matrix, and stitched in a preset order to obtain the target panoramic image.

2. The method according to claim 1, It is characterized in that The calibration plate is a checkerboard calibration plate, and the identifying the actual pixel coordinates corresponding to the target detection point in the original captured image includes: Identifying all checkerboard corner points included in the original captured image; The pixel coordinates of the corner points corresponding to the checkerboard corner points at the target position in the original captured image are used as the actual pixel coordinates corresponding to the target detection points in the original captured image.

3. The method according to claim 2, It is characterized in that The identifying all checkerboard corner points included in the original captured image comprises: Performing corner point recognition on the original captured image; When the number of corner points identified in each original captured image is the target number, the corner points identified in each original captured image are used as the checkerboard corner points included in the original captured image.

4. The method according to claim 2, It is characterized in that The target position is four checkerboard corner points at both ends of the main and secondary diagonals in the corner point matrix composed of all checkerboard corner points included in the checkerboard calibration plate, wherein the positions of the checkerboard corner points in the corner point matrix are determined according to the corner point pixel coordinates corresponding to the checkerboard corner points.

5. The method according to claim 1, It is characterized in that Before identifying the actual pixel coordinates corresponding to the target detection point in the original captured image, the method further includes: The original captured image is subjected to distortion correction according to the panoramic view system configuration data.

6. An automatic calibration device for a vehicle panoramic view system, It is characterized in that The panoramic surround view system includes four cameras arranged around the vehicle, which are respectively used to capture environmental images around the vehicle. The device includes: The first acquisition module is used to acquire the panoramic view system configuration data corresponding to the vehicle to be calibrated when the vehicle to be calibrated is in the calibration area, wherein corresponding calibration plates are laid around the calibration area, each calibration plate includes a plurality of target detection points, and the panoramic view system configuration data includes target pixel coordinates corresponding to the target detection points in each calibration plate in the target panoramic image output by the panoramic view system, wherein the panoramic view system obtains the target panoramic image by the following method: Acquire the images to be stitched taken by each camera in the panoramic view system; Determine the transformation matrix corresponding to each image to be stitched according to the actual pixel coordinates and the target pixel coordinates corresponding to the actual pixel coordinates; The images to be stitched are transformed to the same plane according to the transformation matrix, and stitched in a preset order to obtain the target panoramic image; A second acquisition module is used to acquire original images captured by each camera in the panoramic view system; An identification module, used to identify the actual pixel coordinates corresponding to the target detection points in each calibration plate in the original captured image; The calibration module is used to use the actual pixel coordinates corresponding to each target detection point as calibration parameters to calibrate the panoramic surround view system.

7. The device according to claim 6, It is characterized in that The calibration plate is a checkerboard calibration plate, and the recognition module includes: A first recognition submodule, used to recognize all checkerboard corner points included in the original captured image; The second recognition submodule is used to use the corner point pixel coordinates corresponding to the checkerboard corner points at the target position in the original captured image as the actual pixel coordinates corresponding to the target detection point in the original captured image.

8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the steps of the method described in any one of claims 1 to 5 are implemented.

9. An electronic device, It is characterized in that include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 5.

Images