Camera pose estimation method and device, storage medium and electronic device

Abstract

This disclosure provides a camera pose estimation method, apparatus, storage medium, and electronic device. The method includes: acquiring an image of at least one calibration board within a preset space using a camera mounted on a mobile device to obtain a calibration image; extracting the positions of multiple calibration objects on the preset calibration board based on the at least one calibration board included in the calibration image to obtain at least two first straight lines and at least two second straight lines; determining the positional relationship between a first plane containing the preset calibration board and the camera coordinate system corresponding to the camera based on the at least two first straight lines, the at least two second straight lines, and the origin corresponding to the camera; and determining at least one attitude angle corresponding to the camera based on the positional relationship.

Description

Technical Field

[0001] This disclosure relates to the field of computer vision technology, and in particular to a camera pose estimation method, apparatus, storage medium, and electronic device. Background Technology

[0002] Visual perception plays a crucial role in current autonomous driving scenarios, providing vehicles with information about their surroundings. To ensure the proper functioning of these perception functions, automakers typically calibrate visual sensors on production lines / in factories to obtain better camera extrinsic parameters (primarily camera pose information). Most production line / in-factory calibrations require speed and accuracy, making markers indispensable. Therefore, adapting calibration algorithms to different markers is essential. Current camera calibration schemes mainly rely on regular-shaped markers such as checkerboard patterns and April tags. When the marker shape is irregular, it becomes impossible to determine the camera pose. Summary of the Invention

[0003] To address the aforementioned technical problems, this disclosure is proposed. Embodiments of this disclosure provide a camera pose estimation method, apparatus, storage medium, and electronic device.

[0004] According to one aspect of the present disclosure, a camera pose estimation method is provided, comprising:

[0005] The calibration image is obtained by capturing images of at least one calibration board in a preset space using a camera set on a mobile device.

[0006] Based on at least one calibration board included in the calibration image, the positions of multiple calibration objects in the preset calibration board are extracted to obtain at least two first straight lines and at least two second straight lines; wherein, the preset calibration board is one of the at least one calibration board, the at least two first straight lines are parallel to each other, the at least two second straight lines are parallel to each other, and each first straight line is perpendicular to each second straight line.

[0007] Based on at least two first straight lines, at least two second straight lines, and the origin corresponding to the camera, determine the positional relationship between the first plane where the preset calibration plate is located and the camera coordinate system corresponding to the camera.

[0008] Based on the positional relationship, at least one attitude angle corresponding to the camera is determined.

[0009] According to another aspect of the embodiments of this disclosure, a camera pose estimation apparatus is provided, comprising:

[0010] The image acquisition module is used to acquire images of at least one calibration board in a preset space based on a camera set on a mobile device, and obtain a calibration image.

[0011] A straight line extraction module is used to extract the positions of multiple calibration objects in a preset calibration plate based on at least one calibration plate contained in the calibration image acquired by the image acquisition module, to obtain at least two first straight lines and at least two second straight lines; wherein, the preset calibration plate is one of the at least one calibration plate, the at least two first straight lines are parallel to each other, the at least two second straight lines are parallel to each other, and each first straight line is perpendicular to each second straight line.

[0012] The direction determination module is used to determine the positional relationship between the first plane where the preset calibration plate is located and the camera coordinate system corresponding to the camera, based on at least two first lines and at least two second lines determined by the line extraction module and the origin corresponding to the camera.

[0013] The pose determination module is used to determine at least one pose angle corresponding to the camera based on the positional relationship determined by the direction determination module.

[0014] According to another aspect of the present disclosure, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the camera pose estimation method described in any of the above embodiments.

[0015] According to another aspect of the embodiments of this disclosure, an electronic device is provided, the electronic device comprising:

[0016] processor;

[0017] Memory used to store the processor's executable instructions;

[0018] The processor is configured to read the executable instructions from the memory and execute the instructions to implement the camera pose estimation method described in any of the above embodiments.

[0019] Based on the camera pose estimation method, apparatus, storage medium and electronic device provided in the above embodiments of this disclosure, this embodiment extracts the position of the calibration object without limiting the shape of the calibration object. As long as the distribution of the calibration object meets the conditions for straight line extraction, at least two first straight lines and at least two second straight lines for estimating the pose can be abstracted, which reduces the difficulty of configuring the calibration board.

[0020] The technical solutions of this disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0021] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0022] Figure 1 This is a schematic flowchart of a camera pose estimation method provided in an exemplary embodiment of this disclosure;

[0023] Figure 2a This is a schematic diagram of a calibration board provided in an exemplary embodiment of this disclosure;

[0024] Figure 2b This is a schematic diagram of another calibration board provided in an exemplary embodiment of this disclosure;

[0025] Figure 3a For example Figure 2a A schematic diagram of the straight line obtained by position extraction from the calibration plate shown;

[0026] Figure 3b For example Figure 2b A schematic diagram of the straight line obtained by position extraction from the calibration plate shown;

[0027] Figure 4 This is a public announcement Figure 1 A flowchart illustrating step 104 in the illustrated embodiment;

[0028] Figure 5a This is a public announcement Figure 1 A flowchart illustrating step 106 in the illustrated embodiment;

[0029] Figure 5b This is a schematic diagram illustrating the determination of positional relationships provided by an exemplary embodiment of this disclosure;

[0030] Figure 6a This is a public announcement Figure 1 A flowchart illustrating step 108 in the illustrated embodiment;

[0031] Figure 6b right Figure 5b The diagram shows the coordinate representation of the direction vector in the camera coordinate system.

[0032] Figure 6c right Figure 6b The illustrated embodiment is a coordinate representation of the pitch and roll angles after alignment.

[0033] Figure 6d right Figure 6c The illustrated embodiment is a coordinate representation of the yaw angle after alignment.

[0034] Figure 7 This is a flowchart illustrating a camera pose estimation method provided in another exemplary embodiment of this disclosure;

[0035] Figure 8 This is a public announcement Figure 7 A flowchart illustrating step 702 in the illustrated embodiment;

[0036] Figure 9a This is a schematic diagram of the structure of a camera pose estimation device provided in an exemplary embodiment of the present disclosure;

[0037] Figure 9b This is a schematic diagram of the structure of a camera pose estimation device provided in another exemplary embodiment of this disclosure;

[0038] Figure 10 This is a structural diagram of an electronic device provided in an exemplary embodiment of this disclosure. Detailed Implementation

[0039] Hereinafter, exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present disclosure, and not all embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0040] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0041] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0042] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0043] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0044] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0045] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0046] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0047] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0048] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0049] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0050] The embodiments disclosed herein can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0051] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0052] Application Overview

[0053] In the process of realizing this disclosure, the inventors discovered that in existing camera pose calibration methods, the calibration objects on the calibration board need to have regular shapes, such as checkerboard patterns, April tags, etc. However, the existing technology has at least the following problems: pose estimation depends on the shape of the calibration objects. When the shape of the calibration objects changes, the original calibration algorithm needs to be redeveloped to adapt.

[0054] Exemplary methods

[0055] Figure 1 This is a schematic flowchart of a camera pose estimation method provided in an exemplary embodiment of this disclosure. This embodiment can be applied to electronic devices, such as... Figure 1 As shown, it includes the following steps:

[0056] Step 102: Acquire images of at least one calibration board within a preset space using a camera mounted on a mobile device to obtain a calibration image.

[0057] The mobile device can be a vehicle, ship, aircraft, or similar equipment. Before image acquisition, the mobile device can be moved to a designated space and fixed in place, for example, by using a limiting device (e.g., a limiting guide rail) to constrain the position and orientation of the mobile device. The mobile device is then fixed in the designated position, and an image is acquired from at least one calibration plate using a camera. The resulting calibration image contains at least one calibration plate. For example, in an optional example, an image is acquired from any one calibration plate in the preset space, resulting in an image like... Figure 2a The calibration image shown; or, for example, in another alternative example, an image is acquired from any calibration board in a preset space, resulting in the following: Figure 2b The calibration image shown, and, by Figure 2b As can be seen, this embodiment does not limit the angle between the camera and the calibration plate, and they can be in a positive orientation (the plane of the calibration plate is parallel to the plane of the camera, such as...). Figure 2a ), or there is a certain tilt angle (the plane where the calibration plate is located has a certain angle with the camera plane, such as Figure 2b The angle between the calibration board and the camera does not affect the pose estimation result, reducing the difficulty of setting up the calibration board and limiting the position of the mobile device.

[0058] In one optional embodiment, the mobile device is a vehicle. The vehicle is moved into a set space, and its orientation is constrained by a limiting guide rail. After aligning the vehicle with a preset standard orientation, image acquisition is performed. The preset standard orientation is that the ground point at the center of the rear or front axle of the vehicle coincides with the origin of the spatial coordinate system corresponding to the set space. Furthermore, the x-axis and y-axis of the vehicle coordinate system coincide with the x-axis and y-axis of the spatial coordinate system, respectively. The camera position can be quickly located in the preset standard orientation (the position of the camera relative to the vehicle is known and determined at the factory). After fixing the vehicle's orientation relative to the preset space, the position of the camera relative to the preset space can be quickly located, accelerating the speed of camera pose estimation. However, the preset standard orientation is not a necessary condition for pose estimation.

[0059] Step 104: Based on at least one calibration plate contained in the calibration image, extract the positions of multiple calibration objects in the preset calibration plate to obtain at least two first straight lines and at least two second straight lines.

[0060] The preset calibration plate is one of at least one calibration plate, at least two first straight lines are parallel to each other, at least two second straight lines are parallel to each other, and each first straight line is perpendicular to each second straight line.

[0061] Optionally, in this embodiment, all calibration objects included in each calibration plate typically have the same shape. This embodiment does not limit the shape of the calibration objects; they can be any shape, such as circles, rectangles, pentagrams, triangles, other irregular shapes, etc. This embodiment determines the distribution of multiple calibration objects by extracting their positions from a preset calibration plate. Based on the distribution of the multiple calibration objects, at least two first straight lines and at least two second straight lines can be extracted. For example, for... Figure 2a Position extraction is performed on the calibration plate shown, and the result can be obtained from the calibration image as follows. Figure 3a The multiple straight lines shown can be used to determine multiple first straight lines in the calibration plate under the world coordinate system based on all horizontally distributed straight lines, and multiple second straight lines in the calibration plate under the world coordinate system based on all vertically distributed straight lines; for example, for such... Figure 2b Position extraction is performed on the calibration plate shown, and the result can be obtained from the calibration image as follows. Figure 3b The multiple straight lines shown can be used to determine multiple first straight lines in the calibration plate under the world coordinate system based on all straight lines with a horizontal tilt distribution, and multiple second straight lines in the calibration plate under the world coordinate system based on all straight lines with a vertical tilt distribution. In this embodiment, all first straight lines and all second straight lines are distribution lines of calibration objects in the calibration plate determined based on straight lines in the calibration image. The relationship between the first straight lines and the second straight lines is determined by the distribution of calibration objects in the calibration plate.

[0062] Step 106: Based on at least two first straight lines, at least two second straight lines and the origin corresponding to the camera, determine the positional relationship between the first plane where the preset calibration plate is located and the camera coordinate system corresponding to the camera.

[0063] In this embodiment, given that at least two first straight lines, at least two second straight lines, and the origin corresponding to the camera are known, the x-axis and y-axis corresponding to the calibration plate can be transformed to the camera coordinate system using spatial geometric relationships. Since the preset calibration plate corresponds to only one first plane in the world coordinate system, the positional relationship between the first plane and the camera coordinate system can be determined after transforming the x-axis and y-axis to the camera coordinate system.

[0064] Step 108: Based on the positional relationship, determine at least one attitude angle corresponding to the camera.

[0065] In this embodiment, after determining the positional relationship, the offset between the first plane where the calibration plate is located and at least one coordinate axis of the camera coordinate system can be known. Based on the offset of at least one coordinate axis, at least one attitude angle of the camera relative to the calibration plate can be determined.

[0066] The present invention discloses a camera pose estimation method according to the above embodiments. This embodiment extracts the position of the calibration object without limiting the shape of the calibration object. As long as the distribution of the calibration object meets the conditions for straight line extraction, at least two first straight lines and at least two second straight lines for posing estimation can be abstracted, which reduces the difficulty of calibration plate configuration.

[0067] like Figure 4 As shown above, in the above Figure 1 Based on the illustrated embodiment, step 104 may include the following steps:

[0068] Step 1041: Based on at least one calibration plate contained in the calibration image, determine the feature points of each calibration object among the multiple calibration objects arrayed in the preset calibration plate.

[0069] Each calibration object corresponds to a feature point, which can optionally be a corner point or center point of the calibration object.

[0070] In this embodiment, by performing feature point recognition on the calibration image (the location of the feature points in the calibration image can be determined using deep learning technology or image recognition technology such as corner recognition), multiple feature points corresponding to the preset calibration plate in the calibration image can be determined. Combining the camera intrinsic parameters (known) and multiple feature points in the image, as well as the position information of the preset calibration plate in the world coordinate system, the position of the feature point of each calibration object in the preset calibration plate in the world coordinate system can be determined based on the feature points in the image (corresponding to the image coordinate system) through coordinate system transformation.

[0071] Step 1042: Determine multiple straight lines based on the connections between multiple feature points.

[0072] Since the multiple calibration objects in the preset calibration board are distributed in an array, and each feature point represents the position of a calibration object, multiple straight lines can be obtained by connecting every two adjacent feature points.

[0073] Step 1043: Classify the multiple straight lines to obtain at least two first straight lines and at least two second straight lines.

[0074] In this embodiment, after determining multiple straight lines, a group of parallel straight lines are identified as multiple first straight lines based on their perpendicular and parallel relationships. Multiple straight lines that are perpendicular to and parallel to the first straight lines are identified as multiple second straight lines. This embodiment extracts the distribution of calibration objects in a preset calibration board. As long as the distribution of calibration objects in the calibration board conforms to an array distribution, multiple first straight lines and multiple second straight lines can be extracted. Since the shape of the calibration objects is not limited, it can cover various calibration object design schemes, making implementation easier.

[0075] Optionally, in some alternative embodiments, before performing step 104, the following may also be included:

[0076] Based on the camera's intrinsic parameters, a distortion correction operation is performed on the calibration image to obtain the distortion-corrected calibration image.

[0077] Optionally, since the camera intrinsic parameters include an intrinsic parameter matrix and a distortion parameter matrix, and the camera intrinsic parameters in this embodiment are known, the distortion parameter matrix is ​​known. By performing a distortion removal operation on the calibration image using the distortion parameter matrix, a distortion-removed calibration image can be obtained.

[0078] In this embodiment, step 104 includes:

[0079] Based on at least one calibration plate contained in the distortion-free calibration image, the positions of multiple calibration objects in the preset calibration plate are extracted to obtain at least two first straight lines and at least two second straight lines.

[0080] In this embodiment, straight line extraction is performed on the calibrated image after distortion correction, which improves the accuracy of the first and second straight lines obtained, and thus improves the accuracy of the camera's attitude angle estimated based on the first and second straight lines.

[0081] like Figure 5a As shown above, in the above Figure 1 Based on the illustrated embodiment, step 106 may include the following steps:

[0082] Step 1061: Based on two of the at least two first straight lines, determine two second planes with respect to the origin, and determine the first direction vector of the first coordinate axis in the first plane where the preset calibration plate is located in the camera coordinate system based on the intersection line between the two second planes.

[0083] Optionally, such as Figure 5b As shown, at least two of the first straight lines are the first straight line AB and the first straight line CD. A second plane OAB is formed based on the first straight line AB and the origin O, and a second plane OCD is formed based on the first straight line CD and the origin O. The intersection line OV between the second plane OAB and the second plane OCD is the first direction vector, which represents the first direction vector of the first coordinate axis (e.g., the x-axis) of the first plane in the camera coordinate system.

[0084] Step 1062: Based on two of the at least two second straight lines, determine two third planes with respect to the origin, and determine the second direction vector of the second coordinate axis in the first plane corresponding to the preset calibration plate in the camera coordinate system based on the intersection line between the two third planes.

[0085] Optionally, such as Figure 5b As shown, at least two of the two second lines are the second line AC and the second line BD. A third plane OAC is formed based on the second line AC and the origin O, and a third plane OBD is formed based on the second line BD and the origin O. The intersection line OU between the third plane OAC and the third plane OBD is the second direction vector, which represents the second direction vector of the second axis (e.g., the y-axis) of the first plane in the camera coordinate system.

[0086] In this embodiment, the first direction vector and the second direction vector are respectively the direction vectors of the two coordinate axes of the first plane where the calibration plate is located (i.e., the rectangular coordinate system corresponding to the calibration plate). By transforming the first direction vector and the second direction vector to the camera coordinate system, at least one attitude angle of the camera can be determined by the angle between the first direction vector and the second direction vector and at least one coordinate axis in the camera coordinate system. This embodiment realizes the estimation of attitude angle using only geometric analytical operations, with low computing power requirements, and can be applied to more systems and scenarios with lower computing power.

[0087] In this embodiment, Figure 5a This illustration only shows one embodiment of step 106 including steps 1061 and 1062. In addition, step 106 may also include only step 1061, or step 106 may include only step 1062.

[0088] like Figure 6a As shown above, in the above Figure 1 Based on the illustrated embodiment, step 108 may include the following steps:

[0089] Step 1081: Project the first direction vector onto the yoz plane in the camera coordinate system to obtain the third line corresponding to the first direction vector; determine the roll angle of the camera based on the angle between the third line and the y-axis of the camera coordinate system.

[0090] In this embodiment, the first direction vector represents the direction of the y-axis of the calibration board in the camera coordinate system. When the roll angle and yaw angle of the camera match the preset attitude corresponding to the calibration board, the first direction vector should coincide with the y-axis of the camera coordinate system. Therefore, by projecting the first direction vector onto the yoz plane, the offset of the roll angle can be determined, and by projecting the first direction vector onto the xoy plane, the offset of the yaw angle can be determined. In this embodiment, the components of the first direction vector in the yoz plane are determined by projection to obtain the third straight line. The angle between the third straight line and the y-axis of the camera coordinate system can represent the offset of the camera relative to the preset attitude corresponding to the mobile device. That is, the angle is the roll angle corresponding to the camera.

[0091] Step 1082: Project the second direction vector onto the xoz plane in the camera coordinate system to obtain the fourth line corresponding to the second direction vector; determine the pitch angle of the camera based on the angle between the fourth line and the x plane of the camera coordinate system.

[0092] In this embodiment, the second direction vector represents the direction of the calibration board's x-axis in the camera coordinate system. When the camera's pitch and yaw angles match the preset attitude corresponding to the calibration board, the second direction vector should coincide with the x-axis of the camera coordinate system. Therefore, projecting the second direction vector onto the xoz plane determines the pitch angle offset, and projecting it onto the xoy plane determines the yaw angle offset. In this embodiment, the components of the second direction vector in the xoz plane are determined by projection to obtain a fourth straight line. The angle between this fourth straight line and the x-axis of the camera coordinate system represents the offset of the camera relative to the preset attitude corresponding to the mobile device; that is, this angle is the pitch angle corresponding to the camera. For example, in an optional example, the second direction vector is... Figure 5b Normalizing OV and OU in the coordinate system and transforming them to the camera coordinate system yields the following: Figure 6b The coordinate representation diagram shown ( Figure 5b The OV and OU in the conversion are represented as Figure 6b The ov and ou in the coordinate system are used; the pitch and roll angles of the camera can be solved through planar coordinate transformation; finally, the yaw angle to be calibrated can be obtained by aligning the principal directions of the coordinate system. The diagram of the aligned coordinate system is shown in the figure. Figure 6c As shown, this embodiment can determine the roll angle and / or pitch angle of the camera through geometric analysis, which requires low computing power and speeds up the estimation of attitude angles.

[0093] In this embodiment, Figure 6aThis illustration only shows one embodiment of step 108 including steps 1081 and 1082. In addition, step 108 may also include only step 1081 or only step 1082.

[0094] In some alternative embodiments, step 108 may further include:

[0095] The first direction vector is projected onto the xoy plane in the camera coordinate system to obtain the third straight line; based on the angle between the third straight line and the x-axis in the xoy plane, the corresponding yaw angle of the camera is determined.

[0096] Based on the above Figure 6c As shown in the embodiment, after adjusting the roll and pitch angles, the first and second coordinate axes in the calibration plate still deviate from the x and y axes of the camera coordinate system in the xoy plane. To achieve the desired result after calibration... Figure 6d The coordinate system alignment diagram shown in this embodiment uses a third straight line (such as...) Figure 6d (ov) and the x-axis in the xoy plane (e.g. Figure 6d The angle between the line and the xoy plane is used as the camera's yaw angle, or the angle between the fourth line and the y-axis in the xoy plane is used as the camera's yaw angle.

[0097] Alternatively, the second direction vector can be projected onto the xoy plane in the camera coordinate system to obtain the fourth line; based on the angle between the fourth line and the y-axis in the xoy plane, the corresponding yaw angle of the camera can be determined.

[0098] The fourth line is perpendicular to the third line.

[0099] In this embodiment, since the fourth line is perpendicular to the third line, and the x-axis and y-axis in the camera coordinate system are perpendicular to each other, the result of determining the yaw angle based on the third line or the fourth line is the same. Either method can be used to determine the yaw angle. This embodiment only determines the camera's yaw angle based on the angle between a simple line in the plane and the coordinate axis, which greatly simplifies the yaw angle estimation process, makes it easier to quickly estimate the camera's attitude angle, and enables the estimation of the camera's attitude angle based on devices with low computing power.

[0100] Figure 7 This is a flowchart illustrating a camera pose estimation method provided in another exemplary embodiment of this disclosure. In this embodiment, there are multiple cameras, such as... Figure 7 As shown, the method provided in this embodiment may further include:

[0101] Step 701: Predict the pose information of multiple cameras set on the mobile device.

[0102] The pose information includes at least one pose angle, and each pose information corresponds to a camera.

[0103] This embodiment can be based on the above. Figure 1 -6 The pose estimation method provided in any embodiment determines the pose information corresponding to each camera among multiple cameras.

[0104] Step 702: Based on the overlapping portion between the calibration images acquired by every two adjacent cameras in the multiple cameras, the pose information corresponding to one of the two adjacent cameras is corrected to obtain a pose combination composed of the corrected pose information corresponding to multiple cameras.

[0105] In this embodiment, when there are multiple cameras, there will be overlapping parts between the images captured by adjacent cameras. This overlapping part indicates that the calibration plate will appear in the calibration images captured by two adjacent cameras at the same time. Due to the overlapping part, given that the pose information corresponding to one camera is determined, the pose information corresponding to other cameras can be corrected based on the pose information of that camera. After correcting multiple cameras, the corrected pose combination can be obtained. In this embodiment, since the correction process only requires one accurate pose information, the prior knowledge only needs to determine the position of one calibration plate. Compared with the prior art, which requires determining the position of each calibration plate to realize the pose estimation of multiple cameras, this embodiment only needs to know the position of one calibration plate, does not rely on too much known information, can be applied to most calibration spaces, and realizes a general solution for multi-camera production line calibration.

[0106] Another scenario exists in this embodiment: the pose information of a camera is determined based on a standard calibration board with a known position; the position information of a calibration board in the overlapping part with another camera is determined based on the pose information of the camera; the pose information of another camera is determined by determining the position information of the calibration board; and so on, to obtain multiple pose information corresponding to multiple cameras. In this case, only the position information of one calibration board needs to be known, which is easier to implement.

[0107] like Figure 8 As shown above, in the above Figure 7 Based on the illustrated embodiment, at least one calibration board includes a standard calibration board, which has known position information; step 702 may include the following steps:

[0108] Step 7021: Determine that each pair of adjacent cameras in the multiple cameras is a camera group.

[0109] Each camera group includes a first camera and a second camera.

[0110] In this embodiment, for ease of correction, every two adjacent cameras are defined as a camera group. Since multiple cameras are usually arranged in a ring relative to the mobile device, the ring arrangement enables the acquisition of images from all around the mobile device, which is more conducive to improving the safety of the mobile device during movement. Therefore, the number of camera groups is the same as the number of cameras. For example, there are 6 cameras: camera a, camera b, camera c, camera d, camera e, and camera f. The camera groups based on these cameras include: first camera group: camera a and camera b, second camera group: camera b and camera c, third camera group: camera c and camera d, fourth camera group: camera d and camera e, fifth camera group: camera e and camera f, and sixth camera group: camera f and camera a.

[0111] Step 7022: Based on the standard calibration board, determine the reference pose information corresponding to the reference camera.

[0112] Among them, the reference camera is a camera whose calibration images acquired by multiple cameras include a standard calibration plate and at least one other calibration plate.

[0113] In this embodiment, the position of the standard calibration board is known, and the pose information determined based on the standard calibration board is accurate. Therefore, the camera that includes the standard calibration board in the acquired image is used as the reference camera, and subsequent adjustments to other pose information are based on the pose information of this reference information.

[0114] Step 7023: Based on the reference pose information, determine the position information of at least one other calibration plate in the calibration image corresponding to the reference camera, and adjust the pose information of the second camera in the camera group with the reference camera as the first camera based on the position information.

[0115] After determining the reference pose information, the position information of other calibration plates corresponding to the reference camera can be determined based on the reference pose information. Based on the calibration plates with determined positions, the pose information of the second camera that simultaneously acquires the pose information of the calibration plate can be adjusted to obtain relatively accurate pose information of the second camera.

[0116] Step 7024 determines whether the second camera in the camera group that uses the second camera corresponding to the adjusted pose information as the first camera is a reference camera; if the second camera in the camera group is a reference camera, the correction ends; otherwise, proceed to step 7025.

[0117] During the process of correcting the pose information of the second camera in each camera group, when the second camera to be adjusted is used as a reference camera, for example, in the example above, when adjusting to the sixth camera group, the second camera is camera a, and camera a is the reference camera. At this time, there is no need to adjust the pose information of this camera, and the correction ends, obtaining the corrected pose information of all cameras.

[0118] Step 7025: Based on the adjusted pose information, determine the position information of all calibration plates corresponding to the calibration image acquired by the first camera in the camera group, adjust the pose information corresponding to the second camera in the camera group based on the position information, and return to execute step 7024.

[0119] When the second camera in the camera group whose pose information needs to be corrected is not the reference camera, for example, in the above example, during the process of adjusting from the second camera group to the fifth camera group, the pose information corresponding to the second camera is corrected by the adjusted pose information. The specific process is the same as the process of adjusting the pose information of the second camera in the corresponding camera group based on the reference pose, and will not be described again here.

[0120] This embodiment establishes constraints by using the common viewing area between adjacent cameras (represented by the overlapping portion in the images captured by the two cameras) to jointly optimize the pose information of multiple cameras, thereby solving for a better combination of pose information. Of course, the pose information combination obtained through correction may not necessarily meet the requirements. After correction, it can be verified to determine whether the pose information combination meets the requirements. This verification method may include, but is not limited to, stitching verification. For example, in step 7024 above, when the second camera in the camera group is identified as the reference camera, the position information of all calibration plates is determined by the pose information corresponding to the first camera in the camera group. Based on the position information, the pose information of the reference camera is adjusted. When the difference between the adjusted pose information and the original pose information of the reference camera is within a set range (which can be set according to the actual scene), it can be considered that the images corresponding to multiple cameras can be stitched together, that is, the pose information combination corresponding to the camera group meets the requirements; otherwise, the pose information combination corresponding to the camera group does not meet the requirements, and an error message can be sent.

[0121] Any camera pose estimation method provided in this disclosure can be executed by any suitable device with data processing capabilities, including but not limited to: terminal devices and servers. Alternatively, any camera pose estimation method provided in this disclosure can be executed by a processor, such as by a processor executing any of the camera pose estimation methods mentioned in this disclosure by calling corresponding instructions stored in memory. Further details will not be elaborated below.

[0122] Exemplary device

[0123] Figure 9a This is a schematic diagram of the structure of a camera pose estimation device provided in an exemplary embodiment of this disclosure. Figure 9a As shown, the apparatus provided in this embodiment includes:

[0124] The image acquisition module 91 is used to acquire images of at least one calibration board in a preset space based on a camera set on a mobile device, and obtain a calibration image.

[0125] The line extraction module 92 is used to extract the positions of multiple calibration objects in the preset calibration plate based on at least one calibration plate contained in the calibration image acquired by the image acquisition module 91, and obtain at least two first lines and at least two second lines.

[0126] The preset calibration plate is one of at least one calibration plate, at least two first straight lines are parallel to each other, at least two second straight lines are parallel to each other, and each first straight line is perpendicular to each second straight line.

[0127] The direction determination module 93 is used to determine the positional relationship between the first plane where the preset calibration plate is located and the camera coordinate system corresponding to the camera, based on at least two first lines and at least two second lines determined by the line extraction module 92 and the origin corresponding to the camera.

[0128] The pose determination module 94 is used to determine at least one pose angle corresponding to the camera based on the positional relationship determined by the orientation determination module 93.

[0129] The present invention discloses a camera pose estimation device according to the above embodiments. In this embodiment, by extracting the position of the calibration object, there is no need to limit the shape of the calibration object. As long as the distribution of the calibration object meets the conditions for straight line extraction, at least two first straight lines and at least two second straight lines for posing estimation can be abstracted, which reduces the difficulty of calibration plate configuration.

[0130] Figure 9b This is a schematic diagram of the structure of a camera pose estimation device provided in another exemplary embodiment of this disclosure.

[0131] like Figure 9b As shown, in this embodiment, the straight line extraction module 92 includes:

[0132] The feature point extraction unit 921 is used to determine the feature points of each of the multiple calibration objects distributed in an array in the preset calibration plate based on at least one calibration plate contained in the calibration image; wherein each calibration object corresponds to one feature point;

[0133] The straight line extraction unit 922 is used to determine multiple straight lines based on the connections between multiple feature points;

[0134] The straight line classification unit 923 is used to classify the multiple straight lines to obtain at least two first straight lines and at least two second straight lines.

[0135] Optionally, it also includes:

[0136] The distortion correction module 95 is used to perform distortion correction operation on the calibration image based on the intrinsic parameter information of the camera to obtain the distortion-corrected calibration image;

[0137] At this time, the straight line extraction module 92 is used to extract the positions of multiple calibration objects in the preset calibration plate based on at least one calibration plate contained in the distortion-free calibration image, so as to obtain the at least two first straight lines and the at least two second straight lines.

[0138] The direction determination module 93 includes at least one of the following units:

[0139] The first direction unit 931 is used to determine two second planes based on two of the first straight lines among at least two first straight lines and the origin, and to determine the first direction vector of the first coordinate axis in the first plane where the preset calibration plate is located in the camera coordinate system based on the intersection line between the two second planes.

[0140] The second direction unit 932 is used to determine two third planes based on two of the two second straight lines and the origin, respectively, and to determine the second direction vector of the second coordinate axis in the first plane corresponding to the preset calibration plate in the camera coordinate system based on the intersection line between the two third planes.

[0141] Optionally, the pose determination module 94 includes at least one of the following units:

[0142] The roll angle determination unit 941 is used to project the first direction vector onto the yoz plane in the camera coordinate system to obtain the third straight line corresponding to the first direction vector; and to determine the roll angle corresponding to the camera based on the angle between the third straight line and the y-axis of the camera coordinate system.

[0143] The pitch angle determination unit 942 is used to project the second direction vector onto the xoz plane in the camera coordinate system to obtain the fourth straight line corresponding to the second direction vector; and to determine the pitch angle corresponding to the camera based on the angle between the fourth straight line and the x plane of the camera coordinate system.

[0144] Optionally, the pose determination module 94 further includes:

[0145] The yaw angle determination unit 943 is used to project the first direction vector onto the xoy plane in the camera coordinate system to obtain a third straight line; and determine the yaw angle corresponding to the camera based on the angle between the third straight line and the x-axis in the xoy plane; or, project the second direction vector onto the xoy plane in the camera coordinate system to obtain a fourth straight line; and determine the yaw angle corresponding to the camera based on the angle between the fourth straight line and the y-axis in the xoy plane; wherein the fourth straight line is perpendicular to the third straight line.

[0146] In some optional examples, the number of cameras is multiple, and the apparatus in this embodiment also includes:

[0147] The pose prediction module 96 is used to predict the pose of multiple cameras installed on the mobile device to obtain multiple pose information; wherein the pose information includes at least one pose angle, and each pose information corresponds to one camera;

[0148] The pose correction module 97 is used to correct the pose information of one of the two adjacent cameras based on the overlapping part between the calibration images acquired by each pair of the multiple cameras, so as to obtain a pose combination composed of the corrected pose information of the multiple cameras.

[0149] Optionally, at least one calibration plate includes a standard calibration plate having known position information;

[0150] The pose correction module 97 is specifically used to determine that every two adjacent cameras in the plurality of cameras form a camera group; wherein each camera group includes a first camera and a second camera; based on the standard calibration board, determine the reference pose information corresponding to the reference camera; wherein the reference camera is a camera in the calibration image acquired by the plurality of cameras that includes the standard calibration board and at least one other calibration board; based on the reference pose information, determine the position information of at least one other calibration board in the calibration image corresponding to the reference camera, and adjust the pose information corresponding to the second camera in the camera group with the reference camera as the first camera based on the position information; determine whether the second camera in the camera group with the second camera corresponding to the adjusted pose information as the first camera is the reference camera; in response to the second camera in the camera group being the reference camera, end the correction; in response to the second camera in the camera group not being the reference camera, based on the adjusted pose information, determine the position information of all calibration boards corresponding to the calibration image acquired by the first camera in the camera group, and adjust the pose information corresponding to the second camera in the camera group based on the position information.

[0151] Exemplary electronic devices

[0152] Below, for reference Figure 10 This describes an electronic device according to embodiments of the present disclosure. The electronic device may be either or both of a first device 100 and a second device 200, or a standalone device independent of them, which may communicate with the first and second devices to receive acquired input signals from them.

[0153] Figure 10 A block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0154] like Figure 10 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0155] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0156] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute the program instructions to implement the camera pose estimation methods of the various embodiments of this disclosure described above and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0157] In one example, the electronic device 10 may also include an input device 13 and an output device 14, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0158] For example, when the electronic device is a first device 100 or a second device 200, the input device 13 can be the aforementioned microphone or microphone array for capturing the input signal from the sound source. When the electronic device is a standalone device, the input device 13 can be a communication network connector for receiving the acquired input signals from the first device 100 and the second device 200.

[0159] In addition, the input device 13 may also include, for example, a keyboard, a mouse, etc.

[0160] The output device 14 can output various information to the outside, including determined distance information, direction information, etc. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0161] Of course, for the sake of simplicity, Figure 10 Only some of the components of the electronic device 10 relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 10 may include any other suitable components depending on the specific application.

[0162] Exemplary computer program products and computer-readable storage media

[0163] In addition to the methods and apparatus described above, embodiments of this disclosure may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the camera pose estimation methods according to various embodiments of this disclosure as described in the "Exemplary Methods" section of this specification.

[0164] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0165] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the camera pose estimation methods according to various embodiments of this disclosure as described in the "Exemplary Methods" section above.

[0166] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0167] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0168] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0169] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0170] The methods and apparatus of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0171] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0172] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0173] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A camera pose estimation method, comprising: The calibration image is obtained by capturing images of at least one calibration board in a preset space using a camera set on a mobile device. Based on at least one calibration board included in the calibration image, the positions of multiple calibration objects in the preset calibration board are extracted to obtain at least two first straight lines and at least two second straight lines; wherein, the preset calibration board is one of the at least one calibration board, the at least two first straight lines are parallel to each other, the at least two second straight lines are parallel to each other, and each first straight line is perpendicular to each second straight line. Based on at least two first straight lines, at least two second straight lines, and the origin corresponding to the camera, determine the positional relationship between the first plane where the preset calibration plate is located and the camera coordinate system corresponding to the camera. Based on the positional relationship, at least one attitude angle corresponding to the camera is determined; The step of determining the positional relationship between the first plane where the preset calibration plate is located and the camera coordinate system corresponding to the camera, based on at least two first straight lines, at least two second straight lines, and the origin corresponding to the camera, includes: Based on two of the at least two first straight lines, two second planes are determined with respect to the origin; and based on the intersection of the two second planes, a first direction vector of the first coordinate axis in the first plane where the preset calibration plate is located is determined in the camera coordinate system; and / or Based on two of the two second straight lines, two third planes are determined with respect to the origin. Based on the intersection of the two third planes, the second direction vector of the second coordinate axis in the first plane corresponding to the preset calibration plate in the camera coordinate system is determined.

2. The method according to claim 1, wherein, The step of extracting the positions of multiple calibration objects in a preset calibration plate based on at least one calibration plate contained in the calibration image to obtain at least two first straight lines and at least two second straight lines includes: Based on at least one calibration board contained in the calibration image, feature points of each calibration object among a plurality of calibration objects arrayed in the preset calibration board are determined; wherein, each calibration object corresponds to one feature point; Multiple straight lines are determined based on the lines connecting the multiple feature points; The multiple straight lines are classified to obtain at least two first straight lines and at least two second straight lines.

3. The method according to claim 1, before extracting the positions of multiple calibration objects in a preset calibration plate based on at least one calibration plate included in the calibration image to obtain at least two first straight lines and at least two second straight lines, further comprising: Based on the camera's intrinsic parameter information, a distortion correction operation is performed on the calibration image to obtain a distortion-corrected calibration image; The step of extracting the positions of multiple calibration objects in a preset calibration plate based on at least one calibration plate contained in the calibration image to obtain at least two first straight lines and at least two second straight lines includes: Based on at least one calibration plate contained in the distortion-free calibration image, the positions of multiple calibration objects in the preset calibration plate are extracted to obtain at least two first straight lines and at least two second straight lines.

4. The method according to any one of claims 1-3, wherein, Determining at least one attitude angle corresponding to the camera based on the positional relationship includes: Project the first direction vector onto the yoz plane in the camera coordinate system to obtain the third straight line corresponding to the first direction vector; determine the roll angle of the camera based on the angle between the third straight line and the y-axis of the camera coordinate system; and / or, The second direction vector is projected onto the xoz plane in the camera coordinate system to obtain the fourth line corresponding to the second direction vector; based on the angle between the fourth line and the x plane of the camera coordinate system, the pitch angle corresponding to the camera is determined.

5. The method according to any one of claims 1-3, wherein, The step of determining at least one attitude angle corresponding to the camera based on the positional relationship further includes: Project the first direction vector onto the xoy plane in the camera coordinate system to obtain a third straight line; determine the yaw angle corresponding to the camera based on the angle between the third straight line and the x-axis in the xoy plane; or... The second direction vector is projected onto the xoy plane in the camera coordinate system to obtain the fourth straight line; the yaw angle corresponding to the camera is determined based on the angle between the fourth straight line and the y-axis in the xoy plane; wherein the fourth straight line is perpendicular to the third straight line.

6. The method according to any one of claims 1-3, wherein the number of cameras is multiple, and the method further comprises: Multiple pose information is obtained by predicting the pose information of multiple cameras installed on the mobile device; wherein, the pose information includes at least one pose angle, and each pose information corresponds to one camera; Based on the overlapping portion between the calibration images acquired by every two adjacent cameras, the pose information corresponding to one of the two adjacent cameras is corrected to obtain a pose combination composed of the corrected pose information corresponding to multiple cameras.

7. The method according to claim 6, wherein the at least one calibration plate includes a standard calibration plate having known position information; The step of correcting the pose information corresponding to one of the two adjacent cameras based on the overlapping portion between the calibration images acquired by each pair of adjacent cameras includes: Each pair of adjacent cameras in the plurality of cameras is defined as a camera group; wherein each camera group includes a first camera and a second camera; Based on the standard calibration board, the reference pose information corresponding to the reference camera is determined; wherein, the reference camera is the camera whose calibration image acquired by the plurality of cameras includes the standard calibration board and at least one other calibration board; Based on the reference pose information, determine the position information of at least one other calibration plate in the calibration image corresponding to the reference camera, and adjust the pose information of the second camera in the camera group with the reference camera as the first camera based on the position information. Determine whether the second camera in the camera group, in which the second camera corresponding to the adjusted pose information is used as the first camera, is the reference camera; The correction ends when the second camera in the camera group is the reference camera. In response to the fact that the second camera in the camera group is not the reference camera, the position information of all calibration plates corresponding to the calibration image acquired by the first camera in the camera group is determined based on the adjusted pose information, and the pose information corresponding to the second camera in the camera group is adjusted based on the position information.

8. A camera pose estimation device, comprising: The image acquisition module is used to acquire images of at least one calibration board in a preset space based on a camera set on a mobile device, and obtain a calibration image. A straight line extraction module is used to extract the positions of multiple calibration objects in a preset calibration plate based on at least one calibration plate contained in the calibration image acquired by the image acquisition module, to obtain at least two first straight lines and at least two second straight lines; wherein, the preset calibration plate is one of the at least one calibration plate, the at least two first straight lines are parallel to each other, the at least two second straight lines are parallel to each other, and each first straight line is perpendicular to each second straight line. The direction determination module is used to determine the positional relationship between the first plane where the preset calibration plate is located and the camera coordinate system corresponding to the camera, based on at least two first lines and at least two second lines determined by the line extraction module and the origin corresponding to the camera. The pose determination module is used to determine at least one pose angle corresponding to the camera based on the positional relationship determined by the direction determination module. The direction determination module includes: A first direction unit is configured to determine two second planes based on two of at least two first straight lines, respectively, with respect to the origin; and to determine a first direction vector of the first coordinate axis in the first plane where the preset calibration plate is located, in the camera coordinate system, based on the intersection line between the two second planes; and / or... The second direction unit is used to determine two third planes based on two of the two second straight lines and the origin, respectively, and to determine the second direction vector of the second coordinate axis in the first plane corresponding to the preset calibration plate in the camera coordinate system based on the intersection line between the two third planes.

9. A computer-readable storage medium storing a computer program for performing the camera pose estimation method according to any one of claims 1-7.

10. An electronic device, the electronic device comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the camera pose estimation method according to any one of claims 1-7.

Images