A rapid automatic calibration method for vehicle-mounted surround-view panoramic imaging system

By utilizing the partitioned calibration area and checkerboard calibration board jointly observed by adjacent vehicle cameras in the vehicle surround-view panoramic imaging system, the vehicle surround-view panoramic imaging system is automatically calibrated, solving the problems of high dependence on calibration area and poor accuracy in the existing technology, and achieving efficient and low-cost calibration results.

CN117372546BActive Publication Date: 2026-11-17DALIAN CHENGSI TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202311389449.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-10-24
Publication Date
2026-11-17
Estimated Expiration
2043-10-24

AI Technical Summary

Technical Problem

The calibration of existing vehicle-mounted surround-view panoramic imaging systems requires a pre-prepared standard calibration area on the ground, which results in high initial costs and poor calibration accuracy, and cannot be calibrated anytime and anywhere.

Method used

By setting up a partitioned calibration area jointly observed by adjacent vehicle cameras in the vehicle surround-view panoramic imaging system, and using a checkerboard calibration board and orientation marks, the projection matrix and local coordinate system of the camera are obtained, and a transformation matrix from the local coordinate system to the global coordinate system is established to achieve automatic calibration.

Benefits of technology

It enables high-precision calibration of in-vehicle surround-view panoramic imaging systems without the need for additional calibration area preparation, simplifying the calibration process, reducing initial costs, and improving calibration accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117372546B_ABST
    Figure CN117372546B_ABST
Patent Text Reader

Abstract

This invention discloses a rapid and automatic calibration method for an in-vehicle surround-view panoramic imaging system. By defining a calibration region that can be jointly observed by two adjacent in-vehicle cameras, first and second photos taken by the two cameras within the calibration region are acquired. Orientation markers visible to all in-vehicle cameras in the surround-view panoramic imaging system are set on a checkerboard calibration board. The local coordinates of the checkerboard corner points within the calibration region are determined. Based on the pixel coordinates of the checkerboard corner points within the first and second photos in the calibration region, the transformation matrices from the local coordinate system to the global coordinate system of the calibration region and from the local coordinate system to the global coordinate system of the in-vehicle cameras are obtained to complete the calibration of the in-vehicle surround-view panoramic imaging system. This invention uses only one calibration board to calibrate the system, and the calibration process requires no additional alignment or other interventions, resulting in high calibration accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of vehicle camera calibration technology, and in particular to a rapid automatic calibration method for a vehicle surround-view panoramic imaging system. Background Technology

[0002] Currently, the calibration of in-vehicle surround-view imaging systems typically involves drawing a fixed calibration area on the ground (including the vehicle's position and the position of the calibration template), then driving the vehicle to a designated position within the calibration area. Using pre-defined knowledge of the calibration template and its projection onto the cameras, the extrinsic parameters of each camera are calibrated, thus stitching together a surround-view panoramic image centered on the vehicle. These calibration methods require a pre-prepared standard calibration area on the ground, resulting in high initial costs, poor calibration accuracy, and an inability to perform calibration anytime, anywhere without restrictions. Summary of the Invention

[0003] This invention provides a rapid automatic calibration method for an in-vehicle surround-view panoramic imaging system to overcome the above-mentioned technical problems.

[0004] To achieve the above objectives, the technical solution of the present invention is as follows: A rapid automatic calibration method for an in-vehicle surround-view panoramic imaging system includes the following steps: S1: Calibrate the intrinsic parameters of the vehicle-mounted cameras in the vehicle-mounted surround-view panoramic imaging system and determine the projection matrix of the cameras; the vehicle-mounted cameras in the vehicle-mounted surround-view panoramic imaging system are arranged sequentially and connected end to end; S2: Place the checkerboard calibration board on the ground of the calibration area. The area that can be jointly observed by two adjacent vehicle-mounted cameras forms a partitioned calibration area. Obtain the first and second photos within the partitioned calibration area to obtain the pixel coordinates of the checkerboard corner points in the first and second photos within the partitioned calibration area. The first and second photos within the partitioned calibration area are respectively taken by the two vehicle-mounted cameras that form the partitioned calibration area. S3: Orientation markers that can be observed by all onboard cameras in the vehicle surround-view panoramic imaging system are set on the chessboard calibration plate. , To establish a local coordinate system for the partitioned calibration area, the local coordinates of the corner points of the chessboard grid within the partitioned calibration area are determined. S4: Based on the local coordinates of the checkerboard corner points in the partition calibration area and the projection matrix of the camera, and based on the pixel coordinates of the checkerboard corner points in the first and second photos in the partition calibration area, obtain the transformation matrix from the local coordinate system to the global coordinate system of the partition calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera, so as to complete the calibration of the vehicle surround view panoramic imaging system.

[0005] Furthermore, in S4, the method for obtaining the transformation matrix from the local coordinate system to the global coordinate system of the partition calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera is as follows: S41: Obtain the... The coordinates of the corner points of the chessboard within each partitioned area in the global coordinate system ; in, Indicates the first The transformation matrix from the local coordinate system to the global coordinate system of each partition calibration region; Indicates the corner point of the chessboard at the 1st position. Local coordinates in the local coordinate system of each partitioned calibration area; S42: Based on the first The coordinates of the corner points of the chessboard grid within each partition's calibration area in the global coordinate system are obtained. The corner points of the chessboard grid within the designated area of ​​each partition are at the first... Coordinates in the local coordinate system of an onboard camera and the The corner points of the chessboard grid within the designated area of ​​each partition are at the first... The coordinates in the local coordinate system of the vehicle-mounted camera are ; in, Indicates the first The transformation matrix from the local coordinate system to the global coordinate system of a vehicle-mounted camera; This represents the inverse operation; S43: Based on the projection matrix of the camera, obtain the corner points of the chessboard grid at the 1st... The pixel coordinates corresponding to the first / second photos of the partitioned area and the corner points of the checkerboard are described in the... Mapping relationship between local coordinates of each partition calibration area: S44. Based on the mapping relationship, obtain the transformation matrix from the local coordinate system to the global coordinate system of the partition calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera.

[0006] Furthermore, in S43, the corner points of the chessboard grid are in the... The pixel coordinates corresponding to the first / second photos of the partitioned area and the corner points of the checkerboard are described in the... The mapping relationship between the local coordinates of each partition calibration area is obtained as follows: (1) (2) in, Indicates the corner point of the chessboard at the 1st position. The coordinates of the corresponding pixel in the first photo within the partitioned area; Indicates the corner point of the chessboard at the 1st position. The coordinates of the corresponding pixel in the second photo within the calibrated area of ​​each partition; Indicates the first The scaling factor of the first photo within each zone's calibration area; Indicates the first The scaling factor of the second photo within each zone's calibration area; Indicates the first Projection matrix of a vehicle-mounted camera; Indicates the first Projection matrix of a vehicle-mounted camera; By solving equations (1) and (2) simultaneously, we can obtain the transformation matrix from the local coordinate system to the global coordinate system of the partitioned calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera.

[0007] Furthermore, in S2, the area that can be jointly observed by two adjacent vehicle-mounted cameras forms the partition calibration area, including the area that can be jointly observed by the first vehicle-mounted camera and the second vehicle-mounted camera forming the first partition calibration area. ;…;No. The vehicle-mounted camera and the first The area that can be jointly observed by the vehicle-mounted cameras forms the first... Partitioning and calibration area ;…;No. The vehicle-mounted camera and the first The area that can be jointly observed by the vehicle-mounted cameras forms the first... Partitioning and calibration area ;No. The vehicle-mounted camera and the first The area that can be jointly observed by the vehicle-mounted cameras forms the first... Partitioning and calibration area .

[0008] Furthermore, the center origin of the orientation mark is the origin of the coordinate system, and the direction pointed to by the orientation mark is taken as the 45° direction in the coordinate system.

[0009] Beneficial Effects: This invention provides a rapid automatic calibration method for an in-vehicle surround-view panoramic imaging system. By defining a calibration area that can be jointly observed by two adjacent in-vehicle cameras, first and second photos taken by the two cameras within the calibration area are acquired. Orientation markers visible to all in-vehicle cameras in the panoramic imaging system are set on a checkerboard calibration plate, determining the local coordinates of the checkerboard corner points within the calibration area. Based on the camera's projection matrix and the corresponding pixel coordinates of the checkerboard corner points in the first and second photos within the calibration area, the transformation matrices from the local coordinate system to the global coordinate system of the calibration area and from the local coordinate system to the global coordinate system of the in-vehicle cameras are obtained, thus completing the calibration of the in-vehicle surround-view panoramic imaging system. This invention uses only one calibration plate to calibrate the in-vehicle surround-view panoramic imaging system, and the calibration process requires no additional alignment or other interventions, resulting in high calibration accuracy. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart of the calibration method of the present invention; Figure 2 This is a schematic diagram of the orientation mark in an embodiment of the present invention. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0013] This embodiment provides a rapid automatic calibration method for an in-vehicle surround-view panoramic imaging system, such as... Figure 1 It includes the following steps: S1: Calibrate the intrinsic parameters of the vehicle-mounted cameras in the vehicle-mounted surround-view panoramic imaging system and determine the projection matrix of the cameras; the vehicle-mounted cameras in the vehicle-mounted surround-view panoramic imaging system are arranged sequentially adjacent to each other and connected end to end; Specifically, the first vehicle-mounted camera, the second vehicle-mounted camera, ..., the third vehicle-mounted camera in the vehicle surround-view panoramic imaging system. One vehicle-mounted camera, ..., the first A number of vehicle-mounted cameras are sequentially and adjacently installed around the vehicle, the first... The vehicle-mounted camera is adjacent to the first vehicle-mounted camera; This represents the total number of vehicle-mounted cameras. The serial number of the vehicle-mounted camera; S2: Place the checkerboard calibration board on the ground of the calibration area. The area that can be jointly observed by two adjacent vehicle-mounted cameras forms a partitioned calibration area. Obtain the first and second photos within the partitioned calibration area to obtain the pixel coordinates of the checkerboard corner points in the first and second photos within the partitioned calibration area. The first and second photos within the partitioned calibration area are respectively taken by the two vehicle-mounted cameras that form the partitioned calibration area. Specifically, the area jointly observed by the first and second vehicle-mounted cameras forms the first zone calibration area. ;…;No. The vehicle-mounted camera and the first The area that can be jointly observed by the vehicle-mounted cameras forms the first... Partitioning and calibration area ;…;No. The vehicle-mounted camera and the first The area that can be jointly observed by the vehicle-mounted cameras forms the first... Partitioning and calibration area ;No. The vehicle-mounted camera and the first The area that can be jointly observed by the vehicle-mounted cameras forms the first... Partitioning and calibration area ; Specifically, to obtain the first The first photograph within the calibration area and the The second photo within the calibration area To obtain the first The corner points of the chessboard within the marked area are at the 1st Pixel coordinates in the first image within the calibration area and the The corner points of the chessboard within the marked area are at the 1st Pixel coordinates in the second photo within the calibration area The first The first photograph within the calibration area is the one described above. The first vehicle-mounted camera acquires the information, the first... The second photograph within the calibration area is the one described above. Acquired by a vehicle-mounted camera; S3: The checkerboard calibration plate is equipped with orientation markers that can be observed by all onboard cameras in the vehicle surround-view panoramic imaging system, such as... Figure 2 As shown; the orientation marker is used to establish a local coordinate system for the partitioned calibration area, so as to determine the local coordinates of the chessboard corner points within the partitioned calibration area; specifically, to determine the first Local coordinates of corner points within the calibration area ; Specifically, in this embodiment, before calibration, a calibration target, also called a calibration board, is prepared (without loss of generality). The calibration board is in the form of a checkerboard pattern; the checkerboard calibration board is placed on the ground of the calibration area, so that the first... Each camera device can observe the orientation mark; a local coordinate system for the zoned calibration area can be established based on the orientation mark; specifically, a unique local coordinate system, unaffected by projection, can be established based on the orientation mark, and the three-dimensional coordinates of the checkerboard corner points are represented by local coordinates. The checkerboard calibration plate can be rigid or flexible, as long as it is easy to flatten. The calibration plate coordinate system (i.e., the local coordinate system of the zoned calibration area) is determined by the orientation mark. A simple yet general method is: The center origin of the orientation mark is the origin of the coordinate system. The direction pointed to by the orientation mark is used as the horizontal coordinate, vertical coordinate, or 45° direction in the coordinate system, or any other direction. Based on the method of this embodiment, the positions of the checkerboard corner points in the local coordinate system of each partitioned area are uniform.

[0014] S4: Based on the local coordinates of the checkerboard corner points in the partition calibration area and the projection matrix of the camera, and based on the pixel coordinates of the checkerboard corner points in the first and second photos within the partition calibration area, obtain the transformation matrix from the local coordinate system to the global coordinate system of the partition calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera, so as to complete the calibration of the vehicle surround view panoramic imaging system.

[0015] Preferably, the method for obtaining the transformation matrix from the local coordinate system to the global coordinate system of the partitioned calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle-mounted camera is as follows: S41: Obtain the... The coordinates of the corner points within each partition calibration area in the global coordinate system ; in, Indicates the first The transformation matrix from the local coordinate system to the global coordinate system of each partition calibration region; Indicates the first The local coordinates of the corner points within each calibrated area in the local coordinate system of the respective calibrated area; S42: Based on the first The coordinates of the corner points within the first partition calibration area in the global coordinate system are obtained. The corner points within the zonal calibration area are at the 1st The coordinates in the local coordinate system of the vehicle-mounted camera are ; in, Indicates the first The transformation matrix from the local coordinate system to the global coordinate system of a vehicle-mounted camera; This represents the inverse operation; S43: Based on the projection matrix of the camera, obtain the corner points of the chessboard grid at the 1st... The pixel coordinates of the corresponding points in the first / second photo within the 1st partitioned area are related to the corner points of the checkerboard pattern in the 1st... Mapping relationship between the local coordinates of each partition calibration region: (1) (2) in, Indicates the first The pixel coordinates of the corner points within the calibrated area of ​​each partition in the first image; Indicates the first The pixel coordinates of the corner points within the first partitioned area in the second photo; Indicates the first The scaling factor of the first photo within each zone's calibration area; Indicates the first The scaling factor of the second photo within each zone's calibration area; Indicates the first Projection matrix of a vehicle-mounted camera; Indicates the first Projection matrix of a vehicle-mounted camera; S44. Based on the mapping relationship, obtain the transformation matrix from the local coordinate system to the global coordinate system of the partition calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera.

[0016] Specifically, by solving formulas (1) and (2) simultaneously, we can obtain the transformation matrix from the local coordinate system to the global coordinate system of the partitioned calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera.

[0017] Specifically, in this embodiment, the surrounding cameras are arranged in the following order: C 1, C 2, ... C IEach pair of adjacent cameras forms a calibration zone. The pose of the calibration target within the calibration zone is unrestricted, as long as both cameras can observe the complete orientation marker image of the checkerboard. Then, these two cameras are used to take pictures of the checkerboard in this calibration zone, and so on. C 1, C 2. Take and obtain photos of the first zone marking area. P 1_ r , P 2_ l , C 2, C 3. Take and obtain photos of the second zone's designated area. P 2_ r , P 3_ l ,…, camera C I-1 , C I Shoot and obtain the first I -1 Zone Marking Area Photo PI -1_ r , PI _ l ,camera C I , C 1. Shoot and obtain the first I Photographs of the partitioned area PI _ r , P 1_ l A total of 2× I Two photos were taken by each camera.

[0018] Specifically, in this embodiment, two adjacent vehicle-mounted cameras form a calibration group, and the common shooting area of ​​the two cameras forms a partitioned calibration area; The first camera C Camera 1 and Camera 2 C 2. As the first calibration group, acquire the first image of the first calibration region. P 1_ r The second photograph of the first zone marking area. P 2_ l ; the second camera C 2 and 3 cameras C 3, as the second calibration group, acquires the first image of the second calibration region. P 2_ r The second photograph of the second zone marking area. P 3_ l ; ...; and so on, the number of -1 cameraC I-1 and the One camera C N As the first -1 calibration group, obtain the first The first photograph of the -1 zone marking area. P I-1 _ r , No. The second photo of the -1 zone marking area. P I _ l ; will the first One camera C I And the first camera C 1 as the first Calibration group, obtain the first The first photograph of the zoned area P I _ r , No. The second photo of the zoned area P 1_ l ; Specifically, this embodiment uses the first partition marking area as an example, but this is not without generality: Use the first zone calibration area to calibrate the camera. C 1, C 2. The coordinate transformation that transforms the local coordinate system of the first partition calibration area to the global coordinate system is called... TransformB 1, TransformB 1 describes the translation and rotation of the calibration target in the y=0 plane. TransformB 1. To be solved.

[0019] camera C 1. The transformation from a local coordinate system to a global coordinate system is denoted as... TransformC 1. Describes the rigid body transformation of the camera in three-dimensional space. TransformC 1. To be solved.

[0020] camera C The first photograph obtained by taking the first zone marking area. P 1_ r In the photo P 1_ r It can detect the projection points of the checkerboard corner points on a series of calibration targets (checkerboard calibration plates) onto the photograph, that is, the projection points of the checkerboard corner points onto the photograph. P 1_ r The pixels in the image, assuming the local coordinates of one of the checkerboard corner points in the first partition of the calibration region.P 1. The corner points of the chessboard in the photo P 1_ r The pixels on are p 11 According to the orientation markings on the calibration target and... P The vector relationships between points can be determined regardless of how the origin and coordinate axes of the coordinate system are chosen. P The local coordinates of point 1, and unaffected by confusion with the positional relationships of other corner points (due to incomplete or insufficiently clear corner points, or non-unique positional relationships caused by rotation or overlap), are still denoted as . P 1. Pixel p 11 Its position on the image is also known, and is still denoted as... p 11 The camera's projection matrix is ​​determined by the camera's intrinsic parameters. Since the camera's intrinsic parameters are known, the camera's projection matrix is ​​also known, denoted as [equation missing]. TransformP 1. Therefore: the local coordinates of the upper corner of the calibrated target are as follows: P 1. The global coordinates of the top corner of the calibrated target are: TransformB 1 P 1.

[0021] Specifically, set up a camera C 1. The transformation from the camera's local coordinate system to the global coordinate system is TrasnsformC 1. The inverse of this matrix, inv( TransformC 1) describes the transformation from the actual coordinate system to the camera coordinate system. The expression inv( TransformC 1) TransformB 1 P 1. Transform the corner points of the chessboard grid to the camera's local coordinate system.

[0022] Consider the projection of the checkerboard corner points onto the imaging plane in the camera's local coordinate system to obtain the pixels in the image. Since this is a 3D to 2D process, there will be an unknown scaling factor. = TransformT 1 inv( TransformC 1) TransformB 1 P 1; Similarly, for cameras C The second photo obtained by taking the first zone marking area. P 1_l The pixels in the image are: = TransformT 2 inv( TransformC 2) TransformB 1 P 1; These two equations hold true for all detected corner points of all camera and calibration area combinations. Therefore, a series of equations corresponding to pixels and checkerboard corner points can be obtained. By solving the system of these equations, the solution can be obtained. , , .

[0023] The calibration method in this embodiment is simple, does not require the prior establishment of a standard calibration area, and does not have too many requirements on the position and number of the collected checkerboard corner points. As long as the corner points facing the surrounding marks can be collected by the vehicle-mounted camera, it is sufficient. Specifically, under the condition of ensuring the accuracy of the collected images, collecting more corner points can help improve the projection calculation results.

[0024] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A rapid automatic calibration method for a vehicle-mounted surround-view panoramic imaging system, characterized in that, Includes the following steps: S1: Calibrate the intrinsic parameters of the vehicle-mounted cameras in the vehicle surround-view panoramic imaging system and determine the camera projection matrix; the vehicle-mounted cameras in the vehicle surround-view panoramic imaging system are arranged sequentially and connected end to end. S2: Place the checkerboard calibration board on the ground of the calibration area. The area that can be jointly observed by two adjacent vehicle-mounted cameras forms a partitioned calibration area. Obtain the first and second photos within the partitioned calibration area to obtain the pixel coordinates of the checkerboard corner points in the first and second photos within the partitioned calibration area. The first and second photos within the partitioned calibration area are respectively taken by the two vehicle-mounted cameras that form the partitioned calibration area. S3: Orientation markers that can be observed by all onboard cameras in the vehicle surround-view panoramic imaging system are set on the chessboard calibration plate. , A local coordinate system for the partitioned calibration area is established to determine the local coordinates of the checkerboard corner points within the partitioned calibration area; the center origin of the orientation mark is taken as the origin of the coordinate system, and the direction pointed to by the orientation mark is taken as the horizontal coordinate, vertical coordinate, or 45° direction in the coordinate system to establish a local coordinate system for the partitioned calibration area. S4: Based on the local coordinates of the checkerboard corner points in the partition calibration area and the projection matrix of the camera, and based on the pixel coordinates of the checkerboard corner points in the first and second photos in the partition calibration area, obtain the transformation matrix from the local coordinate system to the global coordinate system of the partition calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera, so as to complete the calibration of the vehicle surround view panoramic imaging system.

2. The rapid automatic calibration method for a vehicle-mounted surround-view panoramic imaging system according to claim 1, characterized in that, In step S4, the method for obtaining the transformation matrix from the local coordinate system to the global coordinate system of the partition calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera is as follows: S41: Obtain the... The coordinates of the corner points of the chessboard within each partitioned area in the global coordinate system ; in, Indicates the first The transformation matrix from the local coordinate system to the global coordinate system of each partition calibration region; Indicates the corner point of the chessboard at the 1st position. Local coordinates in the local coordinate system of each partitioned calibration area; S42: Based on the first The coordinates of the corner points of the chessboard grid within each partition's calibration area in the global coordinate system are obtained. The corner points of the chessboard grid within the designated area of ​​each partition are at the first... The coordinates in the local coordinate system of the vehicle-mounted camera are ; in, Indicates the first The transformation matrix from the local coordinate system to the global coordinate system of a vehicle-mounted camera; This represents the matrix inversion operation; S43: Based on the projection matrix of the camera, obtain the corner points of the chessboard grid at the 1st... The pixel coordinates corresponding to the first / second photos of the partitioned area and the corner points of the checkerboard are described in the... Mapping relationship between local coordinates of each partition calibration area: S44. Based on the mapping relationship, obtain the transformation matrix from the local coordinate system to the global coordinate system of the partition calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera.

3. The rapid automatic calibration method for a vehicle-mounted surround-view panoramic imaging system according to claim 2, characterized in that, In S43, the corner points of the chessboard grid are at the... The pixel coordinates corresponding to the first / second photos of the partitioned area and the corner points of the checkerboard are described in the... The mapping relationship between the local coordinates of each partition calibration area is obtained as follows: (1) (2) in, Indicates the corner point of the chessboard at the 1st position. The coordinates of the corresponding pixel in the first photo within the partitioned area; Indicates the corner point of the chessboard at the 1st position. The coordinates of the corresponding pixel in the second photo within the calibrated area of ​​each partition; Indicates the first The scaling factor of the first photo within each zone's calibration area; Indicates the first The scaling factor of the second photo within each zone's calibration area; Indicates the first Projection matrix of a vehicle-mounted camera; Indicates the first Projection matrix of a vehicle-mounted camera; This represents the total number of vehicle-mounted cameras. The serial number of the vehicle-mounted camera; By solving equations (1) and (2) simultaneously, we can obtain the transformation matrix from the local coordinate system to the global coordinate system of the partitioned calibration area and the transformation matrix from the local coordinate system to the global coordinate system of the vehicle camera.

4. The rapid automatic calibration method for a vehicle-mounted surround-view panoramic imaging system according to claim 1, characterized in that, In step S2, the area that can be jointly observed by two adjacent vehicle-mounted cameras forms a partitioned calibration area, including the area that can be jointly observed by the first vehicle-mounted camera and the second vehicle-mounted camera forming a first partitioned calibration area. ;…;No. The vehicle-mounted camera and the first The area that can be jointly observed by the vehicle-mounted cameras forms the first... Partitioning and calibration area ;…;No. The vehicle-mounted camera and the first The area that can be jointly observed by the vehicle-mounted cameras forms the first... Partitioning and calibration area ;No. The vehicle-mounted camera and the first The area that can be jointly observed by the vehicle-mounted cameras forms the first... Partitioning and calibration area .

Citation Information

Patent Citations

  • All-round view splicing method of vehicle-mounted all-round view system

    CN111435540A

  • Rapid and automatic calibration method and apparatus for vehicle-mounted surround-view camera

    WO2023103679A1