Calibration method of panoramic surround view system, storage medium, electronic device and vehicle

Abstract

The application discloses a kind of calibration methods of panoramic surround view system and storage medium, electronic equipment, vehicle, panoramic surround view system includes multiple cameras, each camera in multiple cameras corresponds multiple candidate calibration points, multiple candidate calibration points are distributed in the two fusion regions and one non-fusion region corresponding to corresponding camera, fusion region is the field of view overlapping region of adjacent two cameras, calibration method includes: for each camera, the original image photographed by each camera is obtained;Multiple target calibration points are extracted from the original image, and the parameters of the corresponding camera are calibrated based on multiple target calibration points, wherein multiple target calibration points are at least part of multiple candidate calibration points, and multiple target calibration points include at least one candidate calibration point distributed in each fusion region of the corresponding camera.The calibration method improves the calibration accuracy, stability and success rate of panoramic surround view system.

Description

Calibration methods and storage media for panoramic surround view systems, electronic devices, and vehicles. Technical Field

[0001] This invention relates to the field of calibration technology, specifically to a calibration method for a panoramic surround view system, as well as a storage medium, electronic device, and vehicle. Background Technology

[0002] The panoramic surround view system sets up 4 to 8 wide-angle cameras around the car to cover the entire field of view around the vehicle. It processes multiple video images captured at the same time into a 360-degree top view of the vehicle's surroundings and finally displays it on the screen of the center console. This allows the driver to clearly see whether there are obstacles around the vehicle and understand the relative position and distance of the obstacles, helping the driver to park the vehicle easily.

[0003] However, the calibration of the panoramic surround view system using related technologies results in significant discrepancies when the vehicle enters the calibration site twice, failing to meet the requirements of the panoramic surround view system for calibration success rate and effectiveness. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in related technologies. Therefore, one objective of this invention is to propose a calibration method for a panoramic surround-view system, which has the advantages of high calibration accuracy, high stability, and high success rate.

[0005] A second objective of this invention is to provide a computer-readable storage medium.

[0006] The third objective of this invention is to provide an electronic device.

[0007] The fourth objective of this invention is to provide a vehicle.

[0008] To achieve the above objectives, a first aspect of the present invention provides a calibration method for a panoramic surround-view system. The panoramic surround-view system includes multiple cameras, each of which has multiple candidate calibration points. The multiple candidate calibration points are distributed in two fusion regions and one non-fusion region corresponding to the respective camera. The fusion region is the overlapping area of ​​the field of view of two adjacent cameras. The calibration method includes: acquiring an original image captured by each camera for each camera; extracting multiple target calibration points from the original image; and calibrating the parameters of the corresponding camera based on the multiple target calibration points. The multiple target calibration points are at least a portion of the multiple candidate calibration points, and the multiple target calibration points include at least one candidate calibration point distributed in each fusion region of the respective camera.

[0009] According to the calibration method of the panoramic surround view system of the present invention, during calibration, candidate calibration points and target calibration points are distributed in each fusion region and non-fusion region of the corresponding camera, and the parameters of the corresponding camera are calibrated based on multiple target calibration points, which can improve the calibration accuracy, stability and success rate.

[0010] In addition, the calibration method for the panoramic surround view system proposed in the above embodiments of the present invention may also have the following additional technical features:

[0011] According to one embodiment of the present invention, for each camera, the number of candidate calibration points distributed in each fusion region of the corresponding camera is greater than the number of candidate calibration points distributed in the non-fusion region, and the candidate calibration points of two adjacent cameras partially overlap in the fusion region.

[0012] According to one embodiment of the present invention, for each camera, the number of the plurality of candidate calibration points is 8, wherein the number of candidate calibration points distributed in each fusion region is 3, and the number of candidate calibration points distributed in the non-fusion region is 2.

[0013] According to one embodiment of the present invention, the step of extracting multiple target calibration points from the original image includes: extracting two candidate calibration points from the non-fused regions and extracting at least one candidate calibration point from each fused region to extract the multiple target calibration points, wherein the number of the multiple target calibration points is greater than or equal to 6.

[0014] According to one embodiment of the present invention, each fused region and the non-fused region are provided with a calibration pattern, and the plurality of candidate calibration points are distributed on the calibration pattern.

[0015] According to one embodiment of the present invention, the calibration pattern is a polygonal pattern, and the plurality of candidate calibration points are distributed at the corners of the polygonal pattern.

[0016] According to one embodiment of the present invention, the step of extracting multiple target calibration points from the original image and calibrating the parameters of the corresponding camera based on the multiple target calibration points includes: firstly, extracting a first number of multiple target calibration points from the original image and calibrating the parameters of the corresponding camera based on the first number of multiple target calibration points; if calibrating the parameters of the corresponding camera based on the first number of multiple target calibration points fails, then extracting a second number of multiple target calibration points from the original image and calibrating the parameters of the corresponding camera based on the second number of multiple target calibration points, until a preset condition is met, wherein the second number is less than the first number.

[0017] According to one embodiment of the present invention, the preset condition is: the number of multiple target calibration points extracted from the original image is less than a preset number or the parameters of the corresponding camera are successfully calibrated.

[0018] According to an embodiment of the present invention, the step of extracting multiple target calibration points from the original image includes: extracting multiple regions of interest from the original image, wherein the multiple regions of interest include regions of interest corresponding to each fused region of the corresponding camera and regions of interest corresponding to the non-fused regions; performing binarization processing on the multiple regions of interest; and extracting the multiple target calibration points from the binarized multiple regions of interest.

[0019] According to one embodiment of the present invention, the plurality of cameras are disposed around the target object. After calibrating the parameters of the corresponding cameras based on the plurality of target calibration points, the method further includes: unifying the parameters of the plurality of cameras to the world coordinate system based on the parameters of the plurality of cameras and the coordinate system of the target object.

[0020] To achieve the above objectives, a second aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements a calibration method for a panoramic surround-view system according to a first aspect of the present invention.

[0021] To achieve the above objectives, a third aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements a calibration method for a panoramic surround-view system proposed in a first aspect of the present invention.

[0022] To achieve the above objectives, a fourth aspect of the present invention provides a vehicle comprising electronic equipment as provided in a third aspect of the present invention.

[0023] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0024] Figure 1 is a flowchart of a calibration method for a panoramic surround view system according to an embodiment of the present invention;

[0025] Figure 2 is a schematic diagram of a calibration site according to an embodiment of the present invention;

[0026] Figure 3 is a flowchart of calibrating the parameters of a corresponding camera according to an embodiment of the present invention;

[0027] Figure 4 is a flowchart of calibrating the parameters of a corresponding camera according to a specific embodiment of the present invention;

[0028] Figure 5 is a schematic diagram of the calibration results using the calibration method provided in the embodiments of the present invention;

[0029] Figure 6 is a flowchart of extracting multiple target calibration points according to an embodiment of the present invention;

[0030] Figure 7 is a schematic diagram of multiple regions of interest in the original image according to an embodiment of the present invention;

[0031] Figure 8 is a schematic diagram of an electronic device according to an embodiment of the present invention;

[0032] Figure 9 is a schematic diagram of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0033] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0034] The calibration method, storage medium, electronic device, and vehicle of the panoramic surround view system of the present invention will be described in detail below with reference to Sections 1-9 and specific implementation methods.

[0035] In an embodiment of the present invention, the panoramic surround view system may include multiple cameras, each of which has multiple candidate calibration points. The multiple candidate calibration points are distributed in two fusion regions and one non-fusion region corresponding to the respective cameras. The fusion region is the overlapping area of ​​the field of view of two adjacent cameras.

[0036] As a specific embodiment, the panoramic surround view system may include four cameras distributed at the four locations of the target object, such as a vehicle: a front camera, a rear camera, a left camera, and a right camera. The front, rear, left, and right cameras are used to capture images of the target object from the front, rear, left, and right.

[0037] It should be noted that adjacent cameras have overlapping fields of view. The overlapping area between adjacent cameras is called the fusion region, and the non-overlapping area is called the non-fusion region. Each camera corresponds to multiple candidate calibration points, from which target calibration points are selected to calibrate the parameters of the corresponding camera. In the embodiments of this invention, the multiple candidate calibration points are distributed across two fusion regions and one non-fusion region corresponding to the corresponding camera. That is, when selecting candidate calibration points, both the fusion and non-fusion regions on both sides must be selected to ensure the quality of the obtained panoramic image and prevent significant ghosting in the fusion region.

[0038] Figure 1 is a flowchart of a calibration method for a panoramic surround view system according to an embodiment of the present invention. As shown in Figure 1, the calibration method for the panoramic surround view system may include:

[0039] S1: For each camera, acquire the raw image captured by each camera.

[0040] S2, extract multiple target calibration points from the original image, and calibrate the parameters of the corresponding camera based on the multiple target calibration points, wherein the multiple target calibration points are at least a portion of multiple candidate calibration points, and the multiple target calibration points include at least one candidate calibration point distributed in each fusion region of the corresponding camera.

[0041] When calibrating a panoramic surround-view system, the target object, such as a vehicle, needs to be driven into the calibration area. Figure 2 is a schematic diagram of the calibration area according to an embodiment of the present invention. The vehicle must be positioned as shown in Figure 2 above. Each camera captures an image (original image) of the calibration area in the corresponding direction. Multiple target calibration points are extracted from the original images. When extracting multiple target calibration points, there must be a calibration point determined from multiple candidate calibration points, and at least one candidate calibration point in each fusion region of the corresponding camera must be a target calibration point to ensure the quality of the panoramic image and improve the calibration success rate. After extracting multiple target calibration points, the parameters of the corresponding cameras can be calibrated using the OpenCV (OpenCV is a cross-platform computer vision and machine learning software library) extrinsic calibration algorithm based on the multiple target calibration points.

[0042] In an embodiment of the present invention, for each camera, the number of candidate calibration points distributed in each fusion region of the corresponding camera is greater than the number of candidate calibration points distributed in the non-fusion region, and the candidate calibration points of two adjacent cameras partially overlap in the fusion region.

[0043] To prevent significant ghosting in the fused region even after successful calibration, and to ensure at least one point is within the fused region, a feasible approach is to determine multiple candidate calibration points for each camera from the two fused regions (i.e., the overlapping areas of the four cameras' fields of view) and one non-fused region (i.e., the non-overlapping areas of the four cameras' fields of view). The number of candidate calibration points in each fused region for each camera is greater than the number of candidate calibration points distributed in the non-fused region, and the candidate calibration points of adjacent cameras in the fused region must partially overlap. Placing more candidate calibration points in the fused region (i.e., the overlapping areas of the four cameras' fields of view) increases the weight of the fused region, improving the stability and effectiveness of the calibration.

[0044] In one embodiment of the present invention, for each camera, there are a total of 8 candidate calibration points, of which 3 candidate calibration points are distributed in each fusion region and 2 candidate calibration points are distributed in the non-fusion region.

[0045] Specifically, each camera corresponds to 8 candidate calibration points, the fusion areas on both sides have 3 candidate calibration points, and the non-fusion area in the middle has 2 candidate calibration points.

[0046] In one embodiment of the present invention, extracting multiple target calibration points from the original image may include:

[0047] Two candidate calibration points are extracted from the non-fusion region, and at least one candidate calibration point is extracted from each fusion region to extract multiple target calibration points, and the number of multiple target calibration points is greater than or equal to 6.

[0048] Specifically, when extracting multiple target calibration points, two candidate calibration points are extracted from the non-fused region, and two candidate calibration points are extracted from each fused region. These six candidate calibration points are then selected as the target calibration points. Alternatively, three candidate calibration points can be extracted from each fused region, and these eight candidate calibration points are then selected as the target calibration points.

[0049] In one embodiment of the present invention, each fused region and non-fused region is provided with a calibration pattern, and multiple candidate calibration points are distributed on the calibration pattern.

[0050] Because the calibration environment (original image) captured by the camera contains many highlights and areas that affect calibration, the accuracy and stability of the calibration method are severely impacted. A feasible solution is to set a calibration pattern in each fused and non-fused region, and select multiple candidate calibration points from the calibration pattern. This prevents interference environments with the same shape as the calibration pattern in the original image from being identified as the calibration pattern when selecting multiple candidate calibration points, thereby improving the accuracy and stability of the calibration method.

[0051] In one embodiment of the present invention, the calibration pattern is a polygonal pattern, and multiple candidate calibration points are distributed on the corners of the polygonal pattern.

[0052] As a specific embodiment, taking a vehicle as the target object, refer to Figure 2. The calibration patterns in the fused and non-fused regions are polygonal patterns, with multiple candidate calibration points located at the corners of the polygonal patterns. Eight gray polygonal regions are located on the outer side of the vehicle. The polygonal regions on the left and right sides of the front of the vehicle are in the fused region, while the polygonal region in the middle of the front of the vehicle is in the non-fused region. The polygonal regions on the left and right sides of the rear of the vehicle are in the fused region, while the polygonal region in the middle of the rear of the vehicle is in the non-fused region. The polygonal regions on the upper and lower left sides of the vehicle are in the fused region, while the polygonal region in the middle of the left side of the vehicle is in the non-fused region. The polygonal regions on the upper and lower right sides of the vehicle are in the fused region, while the polygonal region in the middle of the right side of the vehicle is in the non-fused region. Figure 2 shows the positions of the eight candidate calibration points corresponding to the front, rear, left, and right cameras. The black numbers 1-8 on the three polygonal calibration patterns from left to right at the front of the vehicle represent the eight candidate calibration points corresponding to the front camera. The white numbers 1-8 on the three polygonal calibration patterns from right to left behind the vehicle represent the eight candidate calibration points corresponding to the rear camera. The circled numbers 1-8 on the three polygonal calibration patterns from bottom to top on the left side of the vehicle represent the eight candidate calibration points corresponding to the rear camera. The triangular numbers 1-8 on the three polygonal calibration patterns from right to left behind the vehicle represent the eight candidate calibration points corresponding to the rear camera.

[0053] In one embodiment of the present invention, as shown in FIG3, extracting multiple target calibration points from the original image and calibrating the parameters of the corresponding camera based on the multiple target calibration points may include:

[0054] S21, first extract a first number of multiple target calibration points from the original image, and calibrate the parameters of the corresponding camera based on the first number of multiple target calibration points;

[0055] S22, if the parameters of the corresponding camera are not successfully calibrated based on the first number of multiple target calibration points, a second number of multiple target calibration points are extracted from the original image, and the parameters of the corresponding camera are calibrated based on the second number of multiple target calibration points, until the preset condition is met, wherein the second number is less than the first number.

[0056] In one embodiment of the present invention, the preset condition may be: the number of multiple target calibration points extracted from the original image is less than a preset number or the parameters of the corresponding camera are successfully calibrated.

[0057] As a specific embodiment, as shown in Figure 4, each camera corresponds to 8 candidate calibration points and the number of target calibration points is 6. When calibrating the parameters of the corresponding camera, all 8 candidate calibration points are first extracted as target calibration points, i.e., 8 target calibration points are extracted, and the parameters of the corresponding camera are calibrated based on these 8 target calibration points. If calibrating the parameters of the corresponding camera based on these 8 target calibration points fails, 7 target calibration points can be extracted from the 8 candidate calibration points, and the parameters of the corresponding camera can be calibrated based on these 7 target calibration points. If calibrating the parameters of the corresponding camera based on these 7 target calibration points also fails, 6 target calibration points can be extracted from the 8 candidate calibration points, and the parameters of the corresponding camera can be calibrated based on these 6 target calibration points.

[0058] It should be noted that when using the 8-to-8, 8-to-7, or 8-to-6 selection scheme, if the 8-to-8 calibration is successful, the program will not enter the 8-to-7 or 8-to-6 selection process. The program only enters the 8-to-7 selection process if the 8-to-8 calibration fails. If the 8-to-7 calibration succeeds at this point, the program still will not enter the 8-to-6 selection process. The program only enters the 8-to-6 selection process if both 8-to-8 and 8-to-7 selections fail simultaneously. This is to prevent the problem of partial ghosting in the fused area when a candidate calibration point has an error within the pixel range and the calibration is successful using that candidate point. The calibration results using the calibration method provided in this embodiment can be seen in Figure 5.

[0059] In one embodiment of the present invention, as shown in FIG6, extracting multiple target calibration points from the original image may include:

[0060] S31, extract multiple regions of interest from the original image, wherein the multiple regions of interest include the regions of interest corresponding to each fused region of the corresponding camera and the regions of interest corresponding to the non-fused regions;

[0061] S32 performs binarization on multiple regions of interest;

[0062] S33 extracts multiple target calibration points from multiple regions of interest after binarization.

[0063] The calibration environment contains various regions that can interfere with calibration. To prevent the environment surrounding the calibration pattern from affecting the calibration success rate, multiple regions of interest (ROIs) are extracted from the original image. As an example, referring to Figure 7, when the front camera corresponds to the aforementioned three polygonal calibration patterns, four ROIs can be selected from the original image captured by the front camera: ROI 1 contains the calibration patterns of the three polygons in the original image; ROI 2 contains only the calibration pattern of the left polygon in the original image; ROI 3 contains only the calibration pattern of the middle polygon in the original image; and ROI 4 contains only the calibration pattern of the right polygon in the original image. Then, each of the four ROIs is binarized, and multiple target calibration points are extracted from the binarized ROIs. Multiple target calibration points are also extracted from the original images captured by other cameras using the same method. This effectively avoids the influence of pixels outside the calibration pattern area on the extraction of the calibration pattern contour, improving the accuracy of calibration pattern extraction and increasing the calibration success rate.

[0064] In one embodiment of the present invention, multiple cameras are arranged around the target object. After calibrating the parameters of the corresponding cameras based on multiple target calibration points, the panoramic surround view system method further includes: unifying the parameters of the multiple cameras to the world coordinate system based on the parameters of the multiple cameras and the coordinate system of the target object.

[0065] Specifically, after obtaining the parameters of the corresponding cameras, the parameters of multiple cameras are unified into the world coordinate system based on the parameters of multiple cameras and the coordinate system of the target object.

[0066] The calibration method of the panoramic surround view system in this embodiment of the invention optimizes the selection of candidate calibration points, the application of candidate calibration points and target calibration points in the original image, the extraction of calibration pattern contours, and the application of regions of interest in the original image when the inherent properties of the camera intrinsic parameters cannot be optimized. This effectively improves the calibration effect.

[0067] This invention provides a computer-readable storage medium.

[0068] In this embodiment, a program is stored on a computer-readable storage medium, and when the program is executed by a processor, it implements the calibration method of the panoramic surround view system as described above.

[0069] This invention provides an electronic device.

[0070] In this embodiment, as shown in FIG8, the electronic device 100 includes a memory 10, a processor 20, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the calibration method of the panoramic surround view system as described above.

[0071] This invention provides a vehicle.

[0072] Figure 9 is a schematic diagram of a vehicle according to an embodiment of the present invention. As shown in Figure 9, the vehicle 200 includes the electronic device 100 as described above.

[0073] In an embodiment of the present invention, when calibrating, the vehicle 200 is driven into the calibration area shown in Figure 2. The distance from the perimeter of the vehicle body to the edge of the polygonal calibration pattern is 500 mm.

[0074] In this embodiment of the invention, the vehicle 200 is calibrated using the calibration method of the panoramic surround view system in the electronic device 100. If calibration fails, a calibration failure screen can be displayed on the central control screen, and the extrinsic parameters of the corresponding camera are not saved. If calibration succeeds, a calibration success screen can be displayed on the central control screen, and the extrinsic parameters of the corresponding camera are saved. After successful calibration, a panoramic view can be displayed on the central control screen, and the panoramic view can be checked. Specifically, it is detected whether there is ghosting in the fusion area of ​​the panoramic view, whether the degree of ghosting is within a preset range, or whether it is acceptable to the user. If there is no ghosting, or the degree of ghosting is within the preset range, or it is acceptable to the user, then the check is complete. If the degree of ghosting exceeds the preset range, or it is unacceptable to the user, calibration can be performed again to make the panoramic view meet the user's needs.

[0075] The computer-readable storage medium, electronic device, and vehicle of this invention are calibrated using the calibration method described above, thereby improving the accuracy, stability, and success rate of panoramic surround view system calibration.

[0076] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0077] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0078] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0079] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0080] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0081] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0082] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0083] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A calibration method for a panoramic surround view system, characterized in that, The panoramic surround view system includes multiple cameras, each of which corresponds to multiple candidate calibration points. These candidate calibration points are distributed across two fusion regions and one non-fusion region corresponding to the respective camera. The fusion region is the overlapping area of ​​the fields of view of two adjacent cameras. The calibration method includes: acquiring an original image captured by each camera; extracting multiple target calibration points from the original image; and calibrating the parameters of the corresponding camera based on the multiple target calibration points. The multiple target calibration points are at least a portion of the multiple candidate calibration points, and the multiple target calibration points include those distributed across the respective cameras. At least one candidate calibration point for each fusion region; the step of extracting multiple target calibration points from the original image and calibrating the parameters of the corresponding camera based on the multiple target calibration points includes: firstly, extracting a first number of multiple target calibration points from the original image and calibrating the parameters of the corresponding camera based on the first number of multiple target calibration points; if calibrating the parameters of the corresponding camera based on the first number of multiple target calibration points is unsuccessful, then extracting a second number of multiple target calibration points from the original image and calibrating the parameters of the corresponding camera based on the second number of multiple target calibration points, until a preset condition is met, wherein the second number is less than the first number.

2. The method according to claim 1, characterized in that, For each camera, the number of candidate calibration points distributed in each fusion region of the corresponding camera is greater than the number of candidate calibration points distributed in the non-fusion region, and the candidate calibration points of two adjacent cameras partially overlap in the fusion region.

3. The method according to claim 2, characterized in that, For each camera, there are 8 candidate calibration points, of which 3 are distributed in each fusion region and 2 are distributed in the non-fusion region.

4. The method according to claim 3, characterized in that, The step of extracting multiple target calibration points from the original image includes: extracting two candidate calibration points from the non-fused regions and extracting at least one candidate calibration point from each fused region to extract the multiple target calibration points, and the number of the multiple target calibration points is greater than or equal to 6.

5. The method according to claim 1, characterized in that, Each fused region and the non-fused region are provided with a calibration pattern, and the plurality of candidate calibration points are distributed on the calibration pattern.

6. The method according to claim 5, characterized in that, The calibration pattern is a polygonal pattern, and the multiple candidate calibration points are distributed at the corners of the polygonal pattern.

7. The method according to claim 1, characterized in that, The preset conditions are: the number of multiple target calibration points extracted from the original image is less than a preset number or the parameters of the corresponding camera are successfully calibrated.

8. The method according to any one of claims 1-6, characterized in that, The step of extracting multiple target calibration points from the original image includes: extracting multiple regions of interest from the original image, wherein the multiple regions of interest include the regions of interest corresponding to each fused region of the corresponding camera and the regions of interest corresponding to the non-fused regions; performing binarization processing on the multiple regions of interest; and extracting the multiple target calibration points from the binarized multiple regions of interest.

9. The method according to any one of claims 1-6, characterized in that, The multiple cameras are positioned around the target object. After calibrating the parameters of the corresponding cameras based on the multiple target calibration points, the method further includes: unifying the parameters of the multiple cameras to the world coordinate system based on the parameters of the multiple cameras and the coordinate system of the target object.

10. A computer-readable storage medium, characterized in that, It stores a program that, when executed by a processor, implements the calibration method for the panoramic surround view system according to any one of claims 1-9.

11. An electronic device, characterized in that, include: The system includes a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the calibration method for the panoramic surround view system according to any one of claims 1-9.

12. A vehicle, characterized in that, The vehicle includes the electronic equipment as described in claim 11.

Images