Camera adjusting method and device in optical positioning field and storage medium

Abstract

The invention relates to a camera adjusting method and device in an optical positioning field and a storage medium. The method comprises the steps that at least one frame of picture collected by at least one camera for a reference object is acquired, the position of the reference object in a world coordinate system is fixed, the at least one camera comprises a target camera, and the at least one frame of picture comprises a first picture collected by the target camera after pose adjustment; based on the at least one frame of picture, camera external parameters of the target camera when the first picture is collected are determined, and the camera external parameters comprise the position and / or posture of the camera. According to the embodiment of the invention, the adjustment time can be greatly saved, and reworking and poor optical positioning effect caused by deviation in the adjustment process are avoided. Meanwhile, according to the scheme provided by the embodiment of the invention, the external parameters of the camera can be determined in real time after the camera is adjusted, and the target camera does not need to keep the pose unchanged in the process, so that the requirements of an optical positioning field on real-time performance and efficiency are met.

Description

Technical Field

[0001] The present disclosure relates to the field of computer vision technology, and in particular to a camera adjustment method, device and storage medium in an optical positioning field. Background Art

[0002] In an optical positioning site, several cameras are usually required to shoot the objects to be positioned in the site. Therefore, the placement and posture of the camera are particularly important. The position and posture of the camera are usually collectively referred to as the camera extrinsic parameters. When the size of the site and the positioning requirements change, the direction and position of the camera often need to be adjusted accordingly.

[0003] When adjusting the camera in an optical positioning site, the usual solution requires an operation process similar to "scanning the site". Specifically, the camera must maintain its position and posture unchanged after adjustment until the recalibration of the camera's external parameters after adjustment is completed, in order to restore the normal site positioning function. If the camera moves unexpectedly during the adjustment process, it will cause deviations in the external parameter calibration, which may require rework; in addition, errors caused by insufficient adjustment accuracy will also cause the optical positioning effect to deteriorate. It is unable to meet the real-time requirements of camera adjustment in optical positioning sites, and there are efficiency and accuracy limitations. Summary of the invention

[0004] In view of this, the present disclosure proposes a camera adjustment method, device and storage medium in an optical positioning field.

[0005] According to one aspect of the present disclosure, a method for adjusting a camera in an optical positioning field is provided. The method comprises:

[0006] Acquire at least one frame of picture captured by at least one camera for a reference object, where the position of the reference object in the world coordinate system is fixed, the at least one camera includes a target camera, and the at least one frame of picture includes a first picture captured by the target camera after the position and posture are adjusted;

[0007] Based on at least one frame, camera extrinsic parameters of the target camera when capturing the first frame are determined, where the camera extrinsic parameters include a position and / or posture of the camera.

[0008] In a possible implementation, determining the camera extrinsic parameters of the target camera when capturing the first picture based on at least one frame includes:

[0009] Performing feature point detection on at least one frame of images captured by each camera to obtain a plurality of feature points respectively included in each image, wherein the feature points are associated with a reference object;

[0010] Based on a plurality of feature points respectively included in each picture, a camera extrinsic parameter of the target camera when capturing the first picture is determined.

[0011] In a possible implementation, determining the camera extrinsic parameters of the target camera when capturing the first picture based on a plurality of feature points respectively included in each picture includes:

[0012] Matching is performed between the plurality of feature points respectively included in each picture to obtain a preset number of target feature points corresponding to the same world coordinate system position in each picture, and the positions of the target feature points in the world coordinate system;

[0013] Based on the position of the target feature point in the image coordinate system corresponding to the first picture, the position of the target feature point in the world coordinate system, and the camera intrinsic parameters of the target camera, the camera extrinsic parameters of the target camera when capturing the first picture are calculated.

[0014] In a possible implementation, at least one frame of the picture also includes pictures captured by at least two cameras other than the target camera.

[0015] Matching is performed between multiple feature points respectively included in each picture to obtain a preset number of target feature points corresponding to the same world coordinate system position in each picture, and the position of the target feature points in the world coordinate system, including:

[0016] Using binocular stereo vision technology, feature points included in the images captured by at least two cameras other than the target camera are matched to obtain target feature points;

[0017] Based on the target feature points, the positions of the target feature points in the world coordinate system are obtained.

[0018] In a possible implementation, the preset number is not less than three, and the preset number of target feature points includes not less than three feature points that are asymmetrically distributed; the method further includes:

[0019] In response to the number of target feature points being less than a preset number, a prompt message is displayed, where the prompt message is used to instruct to re-perform feature point detection.

[0020] In a possible implementation, at least one frame of the picture also includes a second picture captured by the target camera before the posture adjustment, and based on the at least one frame of the picture, determining the camera extrinsic parameters of the target camera when capturing the first picture includes:

[0021] Performing feature point detection in the first picture and the second picture respectively to obtain feature points corresponding to the reference object at the same world coordinate system position;

[0022] Based on the offset of the feature points corresponding to the reference object from the second picture to the first picture and the camera intrinsic parameters of the target camera, the posture of the target camera when capturing the first picture is calculated.

[0023] In a possible implementation, the reference object includes a preset area in the optical positioning field and / or a rigid body of any fixed size in the optical positioning field;

[0024] In response to the reference object being a preset area in the optical positioning site, at least one frame of the picture includes a picture of the optical positioning site having a texture feature;

[0025] In response to the camera being an infrared camera and the optical positioning field being an outdoor field, the rigid body does not include a rigid body for emitting infrared light.

[0026] In a possible implementation, the target camera is mounted on a stepper motor, and the posture of the target camera is determined by control parameters of the stepper motor; or, the target camera is equipped with a posture positioning module, and the posture of the target camera is determined based on measurement parameters of the posture positioning module.

[0027] In a possible implementation, the method further includes:

[0028] The camera extrinsic parameters of the target camera when capturing the first image are visualized.

[0029] According to another aspect of the present disclosure, a device for adjusting a camera in an optical positioning field is provided. The device comprises:

[0030] An acquisition module, configured to acquire at least one frame of an image captured by at least one camera for a reference object, wherein the position of the reference object in a world coordinate system is fixed, the at least one camera includes a target camera, and the at least one frame of an image includes a first image captured by the target camera after posture adjustment;

[0031] The determination module is used to determine the camera extrinsic parameters of the target camera when capturing the first picture based on at least one frame of the picture, where the camera extrinsic parameters include the position and / or posture of the camera.

[0032] In a possible implementation, a module is determined to:

[0033] Performing feature point detection on at least one frame of images captured by each camera to obtain a plurality of feature points respectively included in each image, wherein the feature points are associated with a reference object;

[0034] Based on a plurality of feature points respectively included in each picture, a camera extrinsic parameter of the target camera when capturing the first picture is determined.

[0035] In a possible implementation, determining the camera extrinsic parameters of the target camera when capturing the first picture based on a plurality of feature points respectively included in each picture includes:

[0036] Matching is performed between the plurality of feature points respectively included in each picture to obtain a preset number of target feature points corresponding to the same world coordinate system position in each picture, and the positions of the target feature points in the world coordinate system;

[0037] Based on the position of the target feature point in the image coordinate system corresponding to the first picture, the position of the target feature point in the world coordinate system, and the camera intrinsic parameters of the target camera, the camera extrinsic parameters of the target camera when capturing the first picture are calculated.

[0038] In a possible implementation, at least one frame of the picture also includes pictures captured by at least two cameras other than the target camera.

[0039] Matching is performed between multiple feature points respectively included in each picture to obtain a preset number of target feature points corresponding to the same world coordinate system position in each picture, and the position of the target feature points in the world coordinate system, including:

[0040] Using binocular stereo vision technology, feature points included in the images captured by at least two cameras other than the target camera are matched to obtain target feature points;

[0041] Based on the target feature points, the positions of the target feature points in the world coordinate system are obtained.

[0042] In a possible implementation, the preset number is not less than three, and the preset number of target feature points includes not less than three feature points that are asymmetrically distributed; the device further includes:

[0043] The first display module is used to display prompt information in response to the number of target feature points being less than a preset number, where the prompt information is used to instruct to re-perform feature point detection.

[0044] In a possible implementation, at least one frame of the picture also includes a second picture captured by the target camera before the posture is adjusted, and the determination module is used to:

[0045] Performing feature point detection in the first picture and the second picture respectively to obtain feature points corresponding to the reference object at the same world coordinate system position;

[0046] Based on the offset of the feature points corresponding to the reference object from the second picture to the first picture and the camera intrinsic parameters of the target camera, the posture of the target camera when capturing the first picture is calculated.

[0047] In a possible implementation, the reference object includes a preset area in the optical positioning field and / or a rigid body of any fixed size in the optical positioning field;

[0048] In response to the reference object being a preset area in the optical positioning site, at least one frame of the picture includes a picture of the optical positioning site having a texture feature;

[0049] In response to the camera being an infrared camera and the optical positioning field being an outdoor field, the rigid body does not include a rigid body for emitting infrared light.

[0050] In a possible implementation, the target camera is mounted on a stepper motor, and the posture of the target camera is determined by control parameters of the stepper motor; or, the target camera is equipped with a posture positioning module, and the posture of the target camera is determined based on measurement parameters of the posture positioning module.

[0051] In a possible implementation, the device further includes:

[0052] The second display module is used to visualize the camera extrinsic parameters of the target camera when capturing the first image.

[0053] According to another aspect of the present disclosure, a camera adjustment device in an optical positioning field is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0054] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0055] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0056] According to an embodiment of the present disclosure, at least one frame of picture captured by at least one camera including a target camera for a reference object is obtained, wherein the position of the reference object in the world coordinate system is fixed, and at least one frame of picture includes the first picture captured by the target camera after the posture is adjusted. Based on the at least one frame of picture, the camera extrinsics of the target camera when capturing the first picture are determined. The camera extrinsics include the position and / or posture of the camera. This can achieve accurate determination of the camera extrinsics after the camera adjusts its posture, greatly saving adjustment time and avoiding rework and deterioration of the optical positioning effect caused by deviations during the adjustment process. At the same time, according to the solution of an embodiment of the present disclosure, the camera extrinsics can be determined in real time after the camera is adjusted. During this process, the target camera does not need to keep its posture unchanged, thereby meeting the requirements of the optical positioning site for real-time performance and efficiency.

[0057] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0059] Figure 1 A schematic diagram showing an application scenario according to an embodiment of the present disclosure.

[0060] Figure 2 A flowchart of a method for adjusting a camera in an optical positioning field according to an embodiment of the present disclosure is shown.

[0061] Figure 3 A structural diagram of a camera adjustment device in an optical positioning field according to an embodiment of the present disclosure is shown.

[0062] Figure 4 It is a block diagram of a device 1900 for adjusting a camera in an optical positioning field according to an exemplary embodiment. DETAILED DESCRIPTION

[0063] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0064] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0065] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0066] In an optical positioning site, several cameras are usually required to shoot the objects to be positioned in the site. Therefore, the placement and posture of the camera are particularly important. The position and posture of the camera are usually collectively referred to as the camera extrinsic parameters. When the size of the site and the positioning requirements change, the direction and position of the camera often need to be adjusted accordingly.

[0067] When adjusting the camera in an optical positioning site, the usual solution requires an operation process similar to "scanning the site". Specifically, the camera must maintain its position and posture unchanged after adjustment until the recalibration of the camera's external parameters after adjustment is completed, in order to restore the normal site positioning function. If the camera moves unexpectedly during the adjustment process, it will cause deviations in the external parameter calibration, which may require rework; in addition, errors caused by insufficient adjustment accuracy will also cause the optical positioning effect to deteriorate. It is unable to meet the real-time requirements of camera adjustment in optical positioning sites, and there are efficiency and accuracy limitations.

[0068] In view of this, the present disclosure provides a camera adjustment method, device and storage medium in an optical positioning site. The method of the embodiment of the present disclosure obtains at least one frame of picture captured by at least one camera including a target camera for a reference object, wherein the position of the reference object in the world coordinate system is fixed, and at least one frame of picture includes the first picture captured by the target camera after the posture is adjusted. Based on the at least one frame of picture, the camera extrinsic parameters of the target camera when capturing the first picture are determined. The camera extrinsic parameters include the position and / or posture of the camera, which can achieve accurate determination of the camera extrinsic parameters after the camera adjusts its posture, greatly saving adjustment time and avoiding rework and deterioration of the optical positioning effect caused by deviations during the adjustment process. At the same time, according to the solution of the embodiment of the present disclosure, the camera extrinsic parameters can be determined in real time after the camera is adjusted. During this process, the target camera does not need to keep the posture unchanged, thereby meeting the requirements of the optical positioning site for real-time and efficiency.

[0069] Figure 1 The schematic diagram of the application scenario according to the embodiment of the present disclosure is shown. The camera adjustment method of the embodiment of the present disclosure can be applied to the scene of positioning the target object in the optical positioning field, such as Figure 1 As shown, the optical positioning site is a physical environment or area that uses optical technology to achieve accurate positioning of objects in a specific space. A plurality of cameras (such as cameras 1 to 4, distributed around the optical positioning site) can be arranged in the optical positioning site to locate the target object in the optical positioning site. Reference objects can also be arranged in the optical positioning site. In one example, before locating the target object, it is first necessary to move the camera to a posture that meets the positioning requirements, and use the reference object to calibrate the camera extrinsic parameters of cameras 1 to 4. After the camera extrinsic parameters of cameras 1 to 4 are calibrated, cameras 1 to 4 can be used to perform optical positioning operations on the target object.

[0070] In another example, when the size of the optical positioning site or the positioning requirements change (for example, the target object to be positioned changes or the positioning accuracy needs to be further improved), it is usually necessary to move the position and posture of the camera (any one or more of camera 1 to camera 4) in the optical positioning site, and then it is necessary to use a reference object to recalibrate the camera extrinsic parameters of the moved camera before the optical positioning function for the target object can be continued.

[0071] In the above example, the position and posture of the camera may change continuously. However, by using the method of the embodiment of the present disclosure, the change of the camera posture can be acquired in real time by using a reference object, and the updated camera extrinsic parameters can be calculated quickly and accurately without restricting the movement of the camera.

[0072] In one possible implementation, the camera adjustment method of the disclosed embodiment can also be applied to virtual shooting scenes. For example, in a virtual shooting scene for video special effects production, the target object can be a model of a virtual character. In order to make the actor's movements and positions match the model of the virtual character when performing in the optical positioning venue, multiple cameras (such as the above-mentioned cameras 1 to 4) need to be used to continuously optically position the model of the virtual character during the shooting process.

[0073] Before using the camera to optically locate the model of the virtual character, it is necessary to first adjust the position and posture of each camera so that the model of the virtual character can be accurately located later and the blind spot of the camera field of view can be reduced, thereby meeting the requirements of the virtual shooting scene. In this process, the method of the embodiment of the present disclosure can be used to quickly and accurately calibrate the camera extrinsic parameters of the camera in the process of adjusting the position and posture of each camera in the virtual shooting environment, thereby significantly improving the adjustment efficiency.

[0074] It should be noted that, in the virtual shooting scene, the target object may also be other objects to be located, such as a video recorder used for virtual shooting, and the embodiments of the present disclosure are not limited to this.

[0075] The camera adjustment method in the optical positioning field of the embodiment of the present disclosure can be used for a terminal device or a server, and the terminal device can be any one or more of a mobile phone, a foldable electronic device, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, and a vehicle-mounted device. The embodiment of the present disclosure does not impose any special restrictions on the specific type of the terminal device, and it can have a wired or wireless communication function. The server can be located locally or in the cloud, and can be a physical device or a virtual device, such as a virtual machine, a container, etc., with a wireless communication function, wherein the wireless communication function can be set in the chip (system) or other parts or components of the server. The wireless communication function can be realized, for example, by mobile communication technologies such as 2G / 3G / 4G / 5G, as well as Wi-Fi, Bluetooth, frequency modulation (FM), digital radio, satellite communication, etc. Communication can also be carried out by wired connection to achieve interaction with other devices.

[0076] Figure 2 A flowchart of a method for adjusting a camera in an optical positioning field according to an embodiment of the present disclosure is shown. The method can be used in the above-mentioned terminal device or server, such as Figure 2 As shown, the method may include:

[0077] Step S201: acquiring at least one frame of image captured by at least one camera with respect to a reference object.

[0078] At least one camera can be a camera arranged in an optical positioning field (such as Figure 1 Any one or more cameras in camera 1 to camera 4) can be arranged at any position in the optical positioning site as long as all or part of the image of the reference object can be captured. Among them, at least one camera includes a target camera, and the target camera can be any one or more cameras in at least one camera whose camera extrinsic parameters are to be calibrated. The disclosed embodiment does not limit the type of the above-mentioned camera, which can be an infrared camera, an ordinary camera, etc.

[0079] Since the camera adjustment method of the embodiment of the present invention can be used to adjust the camera in the optical positioning site to a posture that meets the positioning requirements before positioning the target object, step S201 can usually be performed once every preset time period (for example, 1 second) within a period of time (for example, 2 minutes or other duration) before fixing the camera posture, that is, at least one frame of image captured by at least one camera for a reference object is obtained and subsequent steps are performed to calibrate the camera extrinsic parameters of the target camera once every preset time period.

[0080] In a possible implementation, the target camera can be controlled to capture a picture every preset time (for example, 1 second). When the picture captured by the target camera changes compared to the last captured picture (the change is, for example, when the position of a reference object in the picture changes), it can be considered that the position of the target camera is updated, and step S201 and subsequent steps are executed to calibrate the camera extrinsic parameters of the target camera in real time.

[0081] The reference object may be an object used to calibrate the camera extrinsic parameters in the embodiments of the present disclosure. Compared to the existing "field scanning" method for determining camera extrinsic parameters, the position of the reference object in the embodiments of the present disclosure may be fixed rather than mobile in the world coordinate system, thereby eliminating the need for complex adjustments to the reference object position and simplifying the process of determining camera extrinsic parameters. The reference object may include a preset area in the optical positioning site and / or a rigid body of any fixed size in the optical positioning site. The reference object in the embodiments of the present disclosure may be selected as needed, wherein one or more reference objects may be set as needed to meet the needs of different scenarios and improve adjustment performance and user experience.

[0082] Among them, the preset area in the optical positioning site can be set as needed, and can be an area of ​​any size in the optical positioning site. The embodiments of the present disclosure are not limited to this, as long as the camera can obtain a picture containing texture features when capturing the preset area. In response to the reference object being a preset area in the optical positioning site, at least one frame of the picture includes a picture of the optical positioning site with texture features. Among them, texture features generally refer to unique patterns, shapes, color distributions or other visual characteristics in the preset area serving as a reference object that can be used for subsequent feature point extraction and matching.

[0083] Any rigid body of fixed size in the optical positioning field can also be called an anchor point. For example, it can be a scanning pole, a ground ruler, an ice ball, etc. When the camera is an infrared camera, the rigid body can also be an object used to emit or reflect infrared light, etc.

[0084] The above-mentioned optical positioning site can be an indoor site or an outdoor site. Indoor sites can represent closed or semi-enclosed spaces with stable lighting conditions and less environmental interference, which is convenient for subsequent accurate detection of feature points, so that the determined camera extrinsic parameters are more accurate; outdoor sites can represent open spaces, whose lighting conditions and environmental factors (such as natural light changes, weather influences, etc.) are more complex. In response to the camera being an infrared camera and the optical positioning site being an outdoor site, the rigid body may not include a rigid body for emitting infrared light. In this way, it is possible to avoid affecting the accuracy of subsequent camera extrinsic calibration due to interference with infrared signals under complex lighting conditions.

[0085] The at least one frame of image captured by the camera for the reference object may include images captured in whole or in part by multiple cameras for the reference object, including at least the first image captured by the target camera after the posture is adjusted.

[0086] The first picture may be one frame or multiple frames, and thus, the camera extrinsic parameters of the target camera when capturing the first picture may be determined subsequently.

[0087] When the camera only includes the target camera, at least one frame of the picture may also include a second picture collected by the target camera before the posture adjustment. The second picture may be one or more frames of pictures.

[0088] The camera may also include at least two other cameras arranged in the optical positioning field in addition to the target camera. The at least one frame of the image captured by the camera for the reference object may also include images captured by at least two other cameras for the reference object, wherein each camera may capture one or more frames of images, and the camera extrinsics of the other cameras when capturing the images may be known.

[0089] by Figure 1 For example, if camera 1 is the target camera, in one example, at least one frame of images captured by the camera for the reference object may include one or more frames of second images captured by camera 1 for the reference object before the posture adjustment, and one or more frames of first images captured by camera 1 for the reference object after the posture adjustment, so that the posture of camera 1 when capturing the first image can be determined later; in another example, at least one frame of images captured by the camera for the reference object may include one or more frames of first images captured by camera 1 for the reference object after the posture adjustment, and one or more frames of images captured by any at least two of cameras 2 to 4 for the reference object. Thus, the position and posture of camera 1 when capturing the first image can be determined later.

[0090] Step S202: determining the camera extrinsic parameters of the target camera when capturing the first frame based on at least one frame.

[0091] According to an embodiment of the present disclosure, at least one frame of picture captured by at least one camera including a target camera for a reference object is obtained, wherein the position of the reference object in the world coordinate system is fixed, and at least one frame of picture includes the first picture captured by the target camera after the posture is adjusted. Based on the at least one frame of picture, the camera extrinsics of the target camera when capturing the first picture are determined. The camera extrinsics include the position and / or posture of the camera. This can achieve accurate determination of the camera extrinsics after the camera adjusts its posture, greatly saving adjustment time and avoiding rework and deterioration of the optical positioning effect caused by deviations during the adjustment process. At the same time, according to the solution of an embodiment of the present disclosure, the camera extrinsics can be determined in real time after the camera is adjusted. During this process, the target camera does not need to keep its posture unchanged, thereby meeting the requirements of the optical positioning site for real-time performance and efficiency.

[0092] Camera extrinsics can be used to realize the mutual conversion between the world coordinate system and the camera coordinate system. The camera coordinate system can be a three-dimensional coordinate system with the camera optical center (i.e., the geometric center of the camera lens) as the origin, where the camera optical axis is the Z axis of the coordinate system, the X axis is the horizontal axis, and the Y axis is the vertical axis. The world coordinate system is a coordinate system in real three-dimensional space.

[0093] The camera extrinsics may include the position and / or attitude of the camera. The position of the camera may be the three-dimensional coordinate position of the optical center of the camera in the world coordinate system, which may be represented by a translation vector; the attitude of the camera may represent the direction in which the camera coordinate system rotates relative to the world coordinate system, which may be represented by a rotation matrix. By determining the translation vector and the rotation matrix, the mapping relationship between the camera coordinate system and the world coordinate system may be described.

[0094] The solution of the embodiment of the present disclosure may be used to determine the position and posture of the target camera when capturing the first picture, or to determine only one of the position and posture.

[0095] In a possible implementation, the camera may include a target camera and at least two other cameras arranged in the optical positioning field other than the target camera. At least one frame of the image captured by the camera for the reference object may include the first image and the images captured by the other at least two cameras for the reference object, so that the real-time calibration of the target camera posture can be achieved by using multiple cameras in the optical positioning field. In step S202, it is possible to:

[0096] Feature point detection is performed on at least one frame of images captured by each camera to obtain a plurality of feature points respectively included in each image; based on the plurality of feature points respectively included in each image, the camera extrinsic parameters of the target camera when capturing the first image are determined.

[0097] By using images captured by multiple cameras to detect feature points to calibrate the extrinsic parameters of the target camera, the camera extrinsic parameter calibration process can be made faster and more accurate.

[0098] The at least one frame of the picture also includes pictures collected by at least two other cameras other than the target camera. The at least two other cameras other than the target camera may be cameras other than the target camera arranged in the optical positioning site.

[0099] The method for detecting feature points in each picture can be implemented based on the existing technology, and the present disclosure does not limit this. Among them, the feature point can be associated with a reference object. For example, when the reference object is an anchor point, the feature point detected in the picture can be a point corresponding to a certain position on the anchor point, or a point corresponding to the infrared light emitted or reflected by the anchor point; when the reference object is a preset area in the optical positioning site, the feature point can be a point associated with a certain texture feature in the preset area, such as a point corresponding to an edge, a high gradient transformation, and other areas in the preset area. Thereby, it is convenient to perform subsequent operations such as feature point matching and improve the calibration accuracy. The detected feature points may also include points that are not related to the reference object.

[0100] In the process of determining the camera extrinsic parameters of the target camera when capturing the first picture based on the plurality of feature points respectively included in each picture, it is possible to:

[0101] Matching is performed between multiple feature points respectively included in each picture to obtain a preset number of target feature points corresponding to the same world coordinate system position in each picture, and the position of the target feature points in the world coordinate system; based on the position of the target feature point in the image coordinate system corresponding to the first picture, the position of the target feature point in the world coordinate system, and the camera intrinsic parameters of the target camera, the camera extrinsic parameters of the target camera when capturing the first picture are calculated.

[0102] In the process of matching multiple feature points respectively included in each picture to obtain a preset number of target feature points corresponding to the same world coordinate system position in each picture, it is possible to: use binocular stereo vision technology to match feature points included in the pictures captured by at least two cameras other than the target camera to obtain target feature points; based on the target feature points, obtain the position of the target feature points in the world coordinate system.

[0103] In this way, other cameras in the optical positioning site can be used to assist in the calibration of the camera extrinsic parameters of the target camera, so that the calibration result of the camera extrinsic parameters of the target camera is more accurate and meets the needs of the optical positioning scene.

[0104] Among them, at least two frames of pictures collected from at least two different other cameras can be used to match the feature points in the pictures based on binocular stereo vision technology to determine the target feature points. The target feature points corresponding to the same world coordinate system position in different pictures can also be called points of the same name. The embodiment of the present disclosure does not limit the implementation method of the binocular stereo vision technology, and can be any binocular stereo vision method (such as a method using a sliding window, etc.). In the process of obtaining the position of the target feature point in the world coordinate system based on the target feature point, the position of the target feature point in the world coordinate system can be obtained by using the existing triangulation principle or other methods, and the embodiment of the present disclosure does not limit this. In the embodiment of the present disclosure, in order to ensure the calibration accuracy of the camera extrinsic parameters, the minimum number of target feature points, that is, the preset number, can be pre-set as needed, wherein the preset number can be no less than three, and the preset number of target feature points obtained includes no less than three feature points that are asymmetrically distributed, so that the camera extrinsic parameters of the target camera when collecting the first picture can be further determined later. In order to make the accuracy of the subsequent determination of the camera extrinsic parameters higher, a higher preset number can also be set.

[0105] In a possible implementation, the method may further include:

[0106] In response to the number of target feature points being less than a preset number, a prompt message is displayed.

[0107] Among them, the prompt information can be displayed in any visual form on the user interface. For example, the user interface can display a screen captured by a camera for a reference object, and the prompt information can be displayed on the screen in the form of a prompt box or other controls. The prompt information indicates that the number of determined target feature points is insufficient, and the prompt information can be used to instruct to re-detect feature points. Alternatively, based on the prompt information, other cameras can be controlled to re-capture the screen for the reference object to re-detect feature points. Thereby, the accuracy of the external parameters of the target camera determined subsequently can be guaranteed.

[0108] In the process of calculating the camera external parameters of the target camera when collecting the first picture based on the position of the target feature point in the image coordinate system corresponding to the first picture, the position of the target feature point in the world coordinate system, and the camera internal parameters of the target camera, the shape formed by connecting multiple target feature points can be matched with the feature points in the first picture. For example, the shape can be combined with the feature points in the first picture to obtain a combination of several feature points, and the shape obtained by connecting the feature points in the combination of several feature points can be compared with the shape formed by connecting the above multiple target feature points to determine the feature points corresponding to the same or similar shapes in the combination of several feature points as the matched feature points. Through this matching process, the corresponding feature points of multiple target feature points in the first picture are determined, so as to obtain the positions of these target feature points in the image coordinate system corresponding to the first picture.

[0109] The image coordinate system of the first picture can represent a two-dimensional coordinate system with any vertex of the picture (usually the upper left vertex) as the origin and directions parallel to the sides of the picture as coordinate axes in the picture captured by the target camera. Based on the position of the target feature point in the image coordinate system corresponding to the first picture, the position of the target feature point in the world coordinate system, and the camera intrinsic parameters of the target camera, the camera extrinsic parameters of the target camera when capturing the first picture can be calculated using relevant technologies such as the PnP (Perspective-n-Point) algorithm.

[0110] The intrinsic parameters of the target camera may be parameters representing the internal properties of the camera, including focal length, principal point (optical center) coordinates, distortion coefficients, etc. The intrinsic parameters of the target camera may be predetermined. The intrinsic parameters of the target camera may be used to convert the camera coordinate system of the target camera to the image coordinate system corresponding to the image captured by the target camera. Therefore, based on the camera intrinsic parameters of the target camera, the position of the target feature point in the image coordinate system corresponding to the first screen may be converted to the position of the target feature point in the camera coordinate system of the target camera. Furthermore, the PnP algorithm may be used to solve the translation vector and rotation matrix of the target camera when capturing the first screen through the correlation relationship between the positions of more than three pairs of asymmetrically distributed target feature points in the camera coordinate system of the target camera and the positions in the world coordinate system, as the camera extrinsic parameters of the target camera when capturing the first screen obtained by the solution.

[0111] In a possible implementation, if only the change in the posture of the camera extrinsic parameters needs to be determined, the posture of the target camera when capturing the first picture can be determined only by the first picture captured by the target camera after the posture adjustment of the reference object and the second picture captured before the posture adjustment. In step S202, it is possible to:

[0112] Feature point detection is performed in the first picture and the second picture respectively to obtain feature points corresponding to the reference object at the same world coordinate system position; based on the offset of the feature points corresponding to the reference object from the second picture to the first picture and the camera intrinsic parameters of the target camera, the posture of the target camera when capturing the first picture is calculated.

[0113] In this way, the diverse needs of users in different scenarios can be further met, and the determination of the target camera posture can be achieved more flexibly and conveniently.

[0114] Among them, the method of detecting feature points in the first picture and the second picture can be consistent with the above, based on the existing technology, and the present disclosure is not limited to this. At least one feature point is detected in the first picture and the second picture respectively. The feature points corresponding to the reference object at the same world coordinate system position can be obtained by matching the feature points detected in the first picture and the second picture. Among them, the matching method can be implemented based on the existing technology, as long as at least one feature point can be determined in the first picture and the second picture respectively, and the two feature points correspond to the same world coordinate system position. The offset of the feature point corresponding to the reference object from the second picture to the first picture can represent the pixel coordinate offset of the feature point corresponding to the reference object between the image coordinate system of the second picture and the image coordinate system of the first picture. The pixel coordinate offset can be converted into the displacement in the camera coordinate system of the target camera through the camera intrinsic parameter of the target camera. Based on the relevant technology, the change in the attitude of the target camera when collecting the first picture relative to the second picture can be solved based on the displacement in the camera coordinate system of the target camera. Since the attitude of the target camera when collecting the second picture is known, the attitude of the target camera when collecting the first picture can be calculated.

[0115] In a possible implementation, the position of the target camera can be determined only by the method in the above steps S201-S202, and the posture of the target camera can be determined by the measurement parameters or control parameters alone, so that the posture of the target camera can be obtained more quickly and accurately. The target camera can be installed on a stepper motor, and the posture of the target camera can be determined by the control parameters of the stepper motor; or the target camera can be equipped with a posture positioning module, and the posture of the target camera is determined based on the measurement parameters of the posture positioning module.

[0116] Among them, the stepper motor can be a motor used to accurately control the rotation angle, and the above control parameters can include the rotation angle, the number of rotation steps, etc., so that the posture of the current target camera can be determined through the control parameters.

[0117] The attitude positioning module may be a sensor, such as a gyroscope, an accelerometer, a magnetometer, etc. The measurement parameters of the attitude positioning module may represent parameters measured by the sensor to determine the position and posture of the target camera in real time.

[0118] In order to facilitate the user to monitor the adjustment process in real time and determine the effect of the camera adjustment in real time, the method may also include: visually displaying the camera extrinsic parameters of the target camera when capturing the first picture.

[0119] The visual display method may include any one or more methods such as text, charts, videos, etc. For example, it can be visualized in the form of a heat map. In one possible implementation method, the camera extrinsics of all cameras in the optical positioning site can be visualized in a heat map. When there is a camera with posture adjustment, the adjusted camera extrinsics are determined based on the method of the embodiment of the present disclosure and updated in the heat map, wherein the color of the camera whose posture is adjusted in real time can be made darker (for example, red) in the heat map, and the camera extrinsics determined in real time are displayed on the corresponding camera.

[0120] Figure 3 The structure diagram of the camera adjustment device in the optical positioning field according to the embodiment of the present disclosure is shown. The device can be used in a server or a terminal device, such as Figure 3 As shown, the device may include:

[0121] An acquisition module 301 is used to acquire at least one frame of an image captured by at least one camera for a reference object, where the position of the reference object in the world coordinate system is fixed, the at least one camera includes a target camera, and the at least one frame of the image includes a first image captured by the target camera after the position and posture are adjusted;

[0122] The determination module 302 is used to determine the camera extrinsic parameters of the target camera when capturing the first picture based on at least one frame, where the camera extrinsic parameters include the position and / or posture of the camera.

[0123] In a possible implementation, the determination module 302 is configured to:

[0124] Performing feature point detection on at least one frame of images captured by each camera to obtain a plurality of feature points respectively included in each image, wherein the feature points are associated with a reference object;

[0125] Based on a plurality of feature points respectively included in each picture, a camera extrinsic parameter of the target camera when capturing the first picture is determined.

[0126] In a possible implementation, determining the camera extrinsic parameters of the target camera when capturing the first picture based on a plurality of feature points respectively included in each picture includes:

[0127] Matching is performed between the plurality of feature points respectively included in each picture to obtain a preset number of target feature points corresponding to the same world coordinate system position in each picture, and the positions of the target feature points in the world coordinate system;

[0128] Based on the position of the target feature point in the image coordinate system corresponding to the first picture, the position of the target feature point in the world coordinate system, and the camera intrinsic parameters of the target camera, the camera extrinsic parameters of the target camera when capturing the first picture are calculated.

[0129] In a possible implementation, at least one frame of the picture also includes pictures captured by at least two cameras other than the target camera.

[0130] Matching is performed between multiple feature points respectively included in each picture to obtain a preset number of target feature points corresponding to the same world coordinate system position in each picture, and the position of the target feature points in the world coordinate system, including:

[0131] Using binocular stereo vision technology, feature points included in the images captured by at least two cameras other than the target camera are matched to obtain target feature points;

[0132] Based on the target feature points, the positions of the target feature points in the world coordinate system are obtained.

[0133] In a possible implementation, the preset number is not less than three, and the preset number of target feature points includes not less than three feature points that are asymmetrically distributed; the device further includes:

[0134] The first display module is used to display prompt information in response to the number of target feature points being less than a preset number, where the prompt information is used to instruct to re-perform feature point detection.

[0135] In a possible implementation, at least one frame of the picture further includes a second picture captured by the target camera before the posture is adjusted, and the determination module 302 is used to:

[0136] Performing feature point detection in the first picture and the second picture respectively to obtain feature points corresponding to the reference object at the same world coordinate system position;

[0137] Based on the offset of the feature points corresponding to the reference object from the second picture to the first picture and the camera intrinsic parameters of the target camera, the posture of the target camera when capturing the first picture is calculated.

[0138] In a possible implementation, the reference object includes a preset area in the optical positioning field and / or a rigid body of any fixed size in the optical positioning field;

[0139] In response to the reference object being a preset area in the optical positioning site, at least one frame of the picture includes a picture of the optical positioning site having a texture feature;

[0140] In response to the camera being an infrared camera and the optical positioning field being an outdoor field, the rigid body does not include a rigid body for emitting infrared light.

[0141] In a possible implementation, the target camera is mounted on a stepper motor, and the posture of the target camera is determined by control parameters of the stepper motor; or, the target camera is equipped with a posture positioning module, and the posture of the target camera is determined based on measurement parameters of the posture positioning module.

[0142] In a possible implementation, the device further includes:

[0143] The second display module is used to visualize the camera extrinsic parameters of the target camera when capturing the first image.

[0144] According to an embodiment of the present disclosure, at least one frame of picture captured by at least one camera including a target camera for a reference object is obtained, wherein the position of the reference object in the world coordinate system is fixed, and at least one frame of picture includes the first picture captured by the target camera after the posture is adjusted. Based on the at least one frame of picture, the camera extrinsics of the target camera when capturing the first picture are determined. The camera extrinsics include the position and / or posture of the camera. This can achieve accurate determination of the camera extrinsics after the camera adjusts its posture, greatly saving adjustment time and avoiding rework and deterioration of the optical positioning effect caused by deviations during the adjustment process. At the same time, according to the solution of an embodiment of the present disclosure, the camera extrinsics can be determined in real time after the camera is adjusted. During this process, the target camera does not need to keep its posture unchanged, thereby meeting the requirements of the optical positioning site for real-time performance and efficiency.

[0145] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0146] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0147] The embodiment of the present disclosure also proposes a camera adjustment device in an optical positioning field, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0148] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0149] Figure 41 is a block diagram of an apparatus 1900 for adjusting a camera in an optical positioning field according to an exemplary embodiment. For example, the apparatus 1900 may be provided as a server or a terminal device. Figure 4 , the apparatus 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions, such as an application, that can be executed by the processing component 1922. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0150] The device 1900 may also include a power supply component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input / output interface 1958 (I / O interface). The device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2000. TM , MacOS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.

[0151] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the device 1900 to perform the above method.

[0152] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0153] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0154] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0155] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0156] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0157] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0158] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0159] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0160] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A camera adjustment method in an optical positioning site, characterized in that: The method comprises: Acquire at least one frame of picture captured by at least one camera for a reference object, wherein the position of the reference object in the world coordinate system is fixed, the at least one camera includes a target camera, and the at least one frame of picture includes a first picture captured by the target camera after posture adjustment; Based on the at least one frame, camera extrinsic parameters of the target camera when capturing the first frame are determined, where the camera extrinsic parameters include a position and / or posture of the camera.

2. The method according to claim 1, characterized in that The step of determining the camera extrinsic parameters of the target camera when capturing the first picture based on the at least one frame of picture includes: Performing feature point detection on at least one frame of images captured by each camera to obtain a plurality of feature points respectively included in each image, wherein the feature points are associated with the reference object; Based on a plurality of feature points respectively included in each picture, a camera extrinsic parameter of the target camera when capturing the first picture is determined.

3. The method according to claim 2, characterized in that The determining, based on a plurality of feature points respectively included in each picture, the camera extrinsic parameters of the target camera when acquiring the first picture includes: Matching is performed between the plurality of feature points respectively included in each picture to obtain a preset number of target feature points corresponding to the same world coordinate system position in each picture, and the positions of the target feature points in the world coordinate system; Based on the position of the target feature point in the image coordinate system corresponding to the first picture, the position of the target feature point in the world coordinate system, and the camera intrinsic parameters of the target camera, the camera extrinsic parameters of the target camera when capturing the first picture are calculated.

4. The method according to claim 3, characterized in that The at least one frame of picture also includes pictures captured by at least two cameras other than the target camera, The matching between the multiple feature points respectively included in each picture to obtain a preset number of target feature points corresponding to the same world coordinate system position in each picture, and the position of the target feature points in the world coordinate system, includes: Using binocular stereo vision technology, feature points included in the images captured by at least two cameras other than the target camera are matched to obtain the target feature points; Based on the target feature point, the position of the target feature point in the world coordinate system is obtained.

5. The method according to claim 3, characterized in that: The preset number is not less than three, and the preset number of target feature points includes not less than three feature points that are asymmetrically distributed; the method further includes: In response to the number of the target feature points being less than the preset number, a prompt message is displayed, wherein the prompt message is used to instruct to re-perform feature point detection.

6. The method according to claim 1, characterized in that The at least one frame also includes a second frame captured by the target camera before the posture adjustment, and the determining, based on the at least one frame, the camera extrinsic parameters of the target camera when capturing the first frame includes: Performing feature point detection in the first picture and the second picture respectively to obtain feature points corresponding to the reference object at the same world coordinate system position; Based on the offset of the feature point corresponding to the reference object from the second picture to the first picture and the camera intrinsic parameter of the target camera, the posture of the target camera when capturing the first picture is calculated.

7. The method according to any one of claims 1 to 6, characterized in that: The reference object includes a preset area in the optical positioning field and / or a rigid body of any fixed size in the optical positioning field; In response to the reference object being a preset area in the optical positioning site, the at least one frame of the picture includes a picture of the optical positioning site having texture features; In response to the camera being an infrared camera and the optical positioning field being an outdoor field, the rigid body does not include a rigid body for emitting infrared light.

8. The method according to claim 1, characterized in that The target camera is mounted on a stepper motor, and the posture of the target camera is determined by the control parameters of the stepper motor; or, The target camera is equipped with a posture positioning module, and the posture of the target camera is determined based on the measurement parameters of the posture positioning module.

9. The method according to claim 1, characterized in that: The method further comprises: The camera extrinsic parameters of the target camera when capturing the first picture are visualized.

10. A camera adjustment device in an optical positioning field, characterized in that: The device comprises: An acquisition module, configured to acquire at least one frame of an image captured by at least one camera for a reference object, wherein the position of the reference object in a world coordinate system is fixed, the at least one camera comprises a target camera, and the at least one frame of an image comprises a first image captured by the target camera after posture adjustment; A determination module is used to determine the camera extrinsic parameters of the target camera when capturing the first picture based on the at least one frame, wherein the camera extrinsic parameters include the position and / or posture of the camera.

11. A camera adjustment device in an optical positioning field, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method described in any one of claims 1 to 9 when executing the instructions stored in the memory.

12. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product, comprising a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code, wherein when the computer-readable code is executed in an electronic device, a processor in the electronic device executes the method according to any one of claims 1 to 9.

Images