CN120431183A - Calibration method and related device for tracking equipment - Google Patents
Calibration method and related device for tracking equipmentInfo
- Publication number
- CN120431183A CN120431183A CN202510307775.1A CN202510307775A CN120431183A CN 120431183 A CN120431183 A CN 120431183A CN 202510307775 A CN202510307775 A CN 202510307775A CN 120431183 A CN120431183 A CN 120431183A
- Authority
- CN
- China
- Prior art keywords
- displacement
- standard
- rotation
- etalon
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
本申请实施方式提供了一种跟踪设备的标定方法及相关装置。所述跟踪设备的视野中包括旋转标准器和位移标准器，所述旋转标准器对应有旋转标准器标准模型，所述位移标准器对应有位移标准器标准模型，跟踪设备的标定方法包括：基于所述跟踪设备采集的图像数据，重建所述旋转标准器的旋转标准器实测模型，和所述位移标准器的位移标准器实测模型；根据所述旋转标准器实测模型和所述旋转标准器标准模型标定所述跟踪设备的旋转关系表示；根据所述位移标准器实测模型和所述位移标准器标准模型标定所述跟踪设备的位移关系表示。所述跟踪设备的标定方法及相关装置可以实现针对跟踪设备的自动化标定。
The embodiment of the present application provides a calibration method and related apparatus for a tracking device. The field of view of the tracking device includes a rotation standard and a displacement standard. The rotation standard corresponds to a rotation standard standard model, and the displacement standard corresponds to a displacement standard standard model. The calibration method for the tracking device includes: reconstructing a rotation standard measured model of the rotation standard and a displacement standard measured model of the displacement standard based on image data collected by the tracking device; calibrating the rotation relationship representation of the tracking device according to the rotation standard measured model and the rotation standard standard model; calibrating the displacement relationship representation of the tracking device according to the displacement standard measured model and the displacement standard standard model. The calibration method and related apparatus for the tracking device can realize automated calibration for the tracking device.
Description
Technical Field
The embodiment of the application relates to the technical field of computer vision, in particular to a calibration method of tracking equipment and a related device.
Background
With the rapid development of three-dimensional reconstruction technology, three-dimensional scanners are widely used in various application fields, including building modeling, virtual reality, medical imaging, industrial detection, and other scenes. In order to obtain a high-precision three-dimensional reconstruction model, manual assistance is generally required to calibrate a tracking device, and the spatial pose of a three-dimensional scanner is detected based on the calibrated tracking device, so that three-dimensional reconstruction is performed based on the spatial pose and the scanning result of the three-dimensional scanner.
But the related art has a low degree of automation in calibrating the tracking device.
Disclosure of Invention
In view of this, various embodiments of the present application are directed to providing a calibration method and related apparatus for a tracking device, which can implement automatic calibration for the tracking device.
In a first aspect, one embodiment of the application provides a calibration method of tracking equipment, wherein the visual field of the tracking equipment comprises a rotation etalon and a displacement etalon, the rotation etalon corresponds to a rotation etalon standard model, the displacement etalon corresponds to a displacement etalon standard model, the method comprises the steps of reconstructing a rotation etalon actual measurement model of the rotation etalon and a displacement etalon actual measurement model of the displacement etalon based on tracking information acquired by the tracking equipment, calibrating a rotation relation representation of the tracking equipment according to the rotation etalon actual measurement model and the rotation etalon standard model, and calibrating a displacement relation representation of the tracking equipment according to the displacement etalon actual measurement model and the displacement etalon standard model.
Optionally, the rotation etalon and the displacement etalon are respectively provided with marking points; the tracking device comprises a plurality of cameras, the method further comprises triggering the tracking device to acquire tracking information, wherein the tracking information comprises a plurality of frame information, the frame information comprises image frames which are acquired by the plurality of cameras respectively and correspondingly, and at least part of the image frames comprise all marking points of the displacement standard.
Optionally, the image frame included in the frame information includes a partial mark point of the rotation etalon, the step of reconstructing a rotation etalon actual measurement model of the rotation etalon and a displacement etalon actual measurement model of the displacement etalon based on the image data acquired by the tracking device includes reconstructing a rotation etalon actual measurement model of the rotation etalon according to the partial mark point of the rotation etalon included in the frame information, and reconstructing a displacement etalon actual measurement model of the displacement etalon according to the frame information including all mark points of the displacement etalon.
The method comprises the steps of determining a mark point corresponding relation between a rotation standard device standard model and a rotation standard device standard model, acquiring a standard space position relation of the mark point included in the rotation standard device standard model from the rotation standard device standard model based on the mark point corresponding relation, wherein the standard space position relation is used for representing the relative position relation of the mark point on the rotation standard device, and calibrating the rotation relation representation of the tracking device based on the mark point corresponding relation, the standard space position relation, frame information corresponding to the rotation standard device standard model and the rotation standard device standard model.
Optionally, the step of calibrating the rotation relationship representation of the tracking device based on the mark point correspondence, the standard spatial position relationship, frame information corresponding to the rotation etalon actual measurement model, and the rotation etalon actual measurement model includes constructing a constraint model for generating a reference rotation relationship representation of the tracking device based on the mark point correspondence, the standard spatial position relationship, frame information corresponding to the rotation etalon actual measurement model, and the rotation etalon actual measurement model to obtain a reference rotation relationship representation, and adjusting the reference rotation relationship representation based on a minimized distance error algorithm to obtain the rotation relationship representation of the tracking device.
The method comprises the steps of determining a mark point corresponding relation between a displacement etalon actual measurement model and a displacement etalon standard model, acquiring a standard spatial position relation of the displacement etalon actual measurement model comprising the mark point from the displacement etalon standard model based on the mark point corresponding relation, wherein the standard spatial position relation is used for representing a relative position relation of the mark point on the displacement etalon, and calibrating a displacement relation representation of the tracking device based on the rotation relation representation, frame information comprising all the mark points of the displacement etalon, the mark point corresponding relation, the standard spatial position relation, an initial displacement relation representation and the displacement etalon actual measurement model.
Optionally, the step of calibrating the displacement relation representation of the tracking device based on the rotation relation representation, the frame information including all the mark points of the displacement etalon, the mark point correspondence, the standard spatial position relation, the initial displacement relation representation, and the displacement etalon actual measurement model comprises constructing a constraint model for generating a reference displacement relation representation of the tracking device based on the rotation relation, the frame information including all the mark points of the displacement etalon, the mark point correspondence, the standard spatial position relation, the initial displacement relation representation, and the displacement etalon actual measurement model to obtain a reference displacement relation representation, wherein the initial displacement relation representation is an initial value of a specified displacement relation representation, and the reference displacement relation representation is adjusted based on a minimum distance error algorithm to obtain the displacement relation representation of the tracking device.
Optionally, the method further comprises reconstructing a measurement result sent by the measurement device in three dimensions based on the rotation relation representation and the displacement relation representation.
In a second aspect, one embodiment of the application further provides a calibration device of the tracking equipment, the visual field of the tracking equipment comprises a rotation etalon and a displacement etalon, the rotation etalon corresponds to a rotation etalon standard model, the displacement etalon corresponds to a displacement etalon standard model, the device comprises a model reconstruction module, a rotation relation calibration module and a displacement relation calibration module, wherein the model reconstruction module is used for reconstructing a rotation etalon actual measurement model of the rotation etalon and a displacement etalon actual measurement model of the displacement etalon based on tracking information acquired by the tracking equipment, the rotation relation calibration module is used for calibrating a rotation relation representation of the tracking equipment according to the rotation etalon actual measurement model and the rotation etalon standard model, and the displacement relation calibration module is used for calibrating a displacement relation representation of the tracking equipment according to the displacement etalon actual measurement model and the displacement etalon standard model.
In a third aspect, an embodiment of the present application further provides an electronic device, where the electronic device includes a memory and a processor, where at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor, so as to implement a calibration method of a tracking device as described above.
In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, where at least one computer program is stored, where the at least one computer program is capable of implementing a calibration method of a tracking device as described above when executed by a processor.
In a fifth aspect, an embodiment of the present application further provides a computer program product for implementing a calibration method of a tracking device as described above.
In the embodiments provided by the application, the rotation relation of the tracking equipment is calibrated by using the actual measurement model and the standard model of the rotation standard device, and the displacement relation of the tracking equipment is calibrated by using the actual measurement model and the standard model of the displacement standard device, so that the automatic calibration of the tracking equipment can be realized.
Drawings
Fig. 1 is a schematic block diagram of a three-dimensional reconstruction system according to an embodiment of the present application.
Fig. 2 is a schematic diagram illustrating the operation of a three-dimensional reconstruction system according to an embodiment of the present application.
Fig. 3 is a flowchart of a calibration method of a tracking device according to an embodiment of the present application.
Fig. 4 is a schematic block diagram of a calibration device of a tracking device according to an embodiment of the present application.
Fig. 5 is a schematic diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments.
In describing embodiments of the present application, it should be understood that the terms "first," "second," and "second" are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or number of features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the embodiments of the present application, the meaning of "plurality" is two or more, unless explicitly defined otherwise.
Three-dimensional reconstruction systems are widely used in a variety of fields such as building modeling, virtual reality, medical imaging, and industrial detection. The three-dimensional reconstruction system generates a three-dimensional model by scanning the surface of the object, which is helpful for spatial analysis of the object.
The three-dimensional reconstruction system comprises a measurement device and a tracking device. The measuring equipment is used for capturing information of the surface of the object, generating three-dimensional point cloud data, the tracking equipment is used for tracking the space gesture of the measuring equipment, the three-dimensional point cloud data are mapped into a coordinate system of the tracking equipment by combining the space gesture, and global point cloud data for three-dimensional reconstruction can be obtained. In order to achieve accurate three-dimensional reconstruction, not only the measurement equipment but also the tracking equipment are required to be calibrated.
The multi-eye tracking device comprises at least two cameras, and before three-dimensional reconstruction, a rotation relation and a displacement relation between the cameras are usually required to be calibrated, and a measurement result can be accurately mapped into global point cloud data based on the rotation relation and the displacement relation. In the related art, the method for calibrating the tracking equipment is characterized in that the calibration rod is manually moved to a specific position for a plurality of times to trigger the tracking equipment to complete calibration based on the identification of the calibration rod, or the calibration rod is installed on an automatically movable mechanical arm, so that the tracking equipment completes calibration based on the identification of the calibration rod.
It can be seen that the related art has a low degree of automation for the calibration process of the tracking device. Therefore, the embodiment of the application utilizes the actual measurement model and the standard model of the rotary standard device to calibrate the rotation relation of the tracking equipment, and utilizes the actual measurement model and the standard model of the displacement standard device to calibrate the displacement relation of the tracking equipment. The calibration rod is not required to be arranged at a plurality of positions, and the calibration of the tracking equipment can be realized, namely the automatic calibration of the tracking equipment is realized.
Please refer to fig. 1. In various embodiments of the present application, the three-dimensional reconstruction system may include a variety of electronic devices. Specifically, the three-dimensional reconstruction system includes a tracking device and a measuring device. Both the tracking device and the measuring device may be integrated with a computing chip and a memory. So that both the tracking device and the measuring device have a certain data processing capability. In some embodiments, the electronic device of the three-dimensional reconstruction system may further include a host computer, which may receive the data provided by the tracking device and the measuring device, and perform data processing. The upper computer can be a desktop computer, a notebook computer, a tablet personal computer, a workstation or a server, etc.
The measurement devices may include, but are not limited to, optical measurement devices and non-optical measurement devices. The optical measurement device may include, but is not limited to, a visible light scanner, a structured light scanner, a laser scanner, a light pen, etc. Non-optical measurement devices may include, but are not limited to, ultrasonic scanners, X-ray scanners, and the like. For example, a laser scanner can measure the distance of the object surface by emitting a laser beam and detecting the reflection time or phase change of the laser beam, enabling generation of scan data with higher accuracy. Specifically, the scan data may be three-dimensional point cloud data. Structured light scanners can be configured to project a structured light pattern (e.g., a stripe or lattice) onto a surface of an object and to generate scan data by detecting light reflected from the surface of the object. In the present application, the specific type and principle of the measuring apparatus are not particularly limited.
The measuring device has a tracking feature which can be used as a locating feature of the measuring device. The number of tracking features may be multiple and may be deployed at multiple locations on the measurement device, so that tracking the spatial pose of the measurement device may be achieved by tracking the tracking features described above. In some embodiments, tracking features may include, but are not limited to, marker points, encoding points, stereoscopic targets, geometric features of objects, and the like, that may be acquired and identified by a tracking device. The marking point may be a reflective marking point, and the tracking device emits light and receives light reflected by the marking point. In some embodiments, the marker may be a luminescent marker, in which case the tracking device may directly receive the light emitted by the marker.
The tracking device may be used to output tracking information corresponding to the position and pose of the measuring device in space based on stereoscopic tracking principles, which may be used to determine pose information representing the spatial pose of the measuring device. Each tracking device includes a camera. The number of cameras in the tracking device may be one or more. Preferably, the tracking device is a binocular tracking device or a multi-view tracking device. The number of cameras in different tracking devices may be the same or different. The tracking device may form tracking information from images captured by the camera. Specifically, the camera can continuously shoot a plurality of image frames, and a small time interval exists between the plurality of image frames, so that corresponding differences exist between the plurality of image frames in the process of spatial position movement of the measuring equipment. The tracking information may include frame information. Each frame information may include image frames captured by multiple cameras at the same time by the respective tracking device. It is understood that each frame information may include at least one image frame.
The calibration method of the tracking device can be applied to the tracking device in the three-dimensional reconstruction system.
Please refer to fig. 2 and 3. The embodiment of the application provides a calibration method of tracking equipment. The calibration method of the tracking equipment is applied to the electronic equipment of the three-dimensional reconstruction system. The visual field of the tracking equipment comprises a rotation standard device and a displacement standard device, wherein the rotation standard device corresponds to a rotation standard model, the displacement standard device corresponds to a displacement standard model, and the calibration method of the tracking equipment can comprise the following steps.
And step S110, reconstructing a rotation etalon actual measurement model of the rotation etalon and a displacement etalon actual measurement model of the displacement etalon based on the tracking information acquired by the tracking equipment.
And step S120, calibrating the rotation relation representation of the tracking equipment according to the actual measurement model of the rotation standard device and the standard model of the rotation standard device.
And step S130, calibrating the displacement relation representation of the tracking equipment according to the actual measurement model of the displacement etalon and the standard model of the displacement etalon.
In this embodiment, at least two cameras are disposed on the tracking device, and the at least two cameras are disposed at different positions, so that the at least two cameras correspond to different viewing angles, and after the rotation relationship representation and the displacement relationship representation between the calibration cameras, the spatial pose of the scanner can be measured based on a plurality of cameras, thereby obtaining more accurate measurement results. In order to realize automatic calibration of the tracking equipment, the application utilizes a rotary standard device and a displacement standard device to calibrate the tracking equipment, wherein the rotary standard device is a standard device for calibrating the rotation relation expression in the field of view of the tracking equipment, such as a scanner or other devices which can be used for calibrating the rotation relation, and the displacement standard device is a standard device for calibrating the displacement relation expression in the field of view of the tracking equipment, such as a scale or other devices which can be used for calibrating the displacement relation. In some optional embodiments, the scanner can dynamically change the position, the scale is fixed at a specific position in the visual field range of the tracking device, and compared with a scheme which has higher precision requirements on the relative positions of the marking points on the scanner and only uses the position data of the scanner in a local area to calibrate the tracking device, the application does not need to track the high-precision relative position relation between the marking points on the scanner, can also realize the calibration of the tracking device, and reduces the calibration difficulty and the precision maintenance cost for the tracking device. The rotation relation representation represents the rotation relation between two camera coordinate systems on the tracking equipment, the displacement relation representation represents the displacement relation between the two camera coordinate systems on the tracking equipment, the rotation relation representation can be recorded as a rotation matrix, and the displacement relation representation can be recorded as a displacement matrix.
In this embodiment, the rotation etalon and the displacement etalon are provided with any number of tracking features (such as mark points), and the tracking device acquires tracking information corresponding to the rotation etalon and tracking information corresponding to the displacement etalon through a plurality of cameras. Wherein the tracking information corresponding to the rotation etalon can be used for representing the relative position relation of the mark points on the rotation etalon on the two-dimensional plane, and the tracking information of the rotation etalon comprises at least three mark points on the rotation etalon. The tracking information corresponding to the displacement etalon can be used for representing the relative position relation of the mark points on the displacement etalon on the two-dimensional plane, and the tracking information of the displacement etalon comprises at least two mark points on the displacement etalon.
In this embodiment, according to the tracking information acquired by the tracking device and applying the binocular reconstruction principle, the rotation etalon actual measurement model of the rotation etalon and the displacement etalon actual measurement model of the displacement etalon can be reconstructed. The binocular reconstruction principle refers to shooting different angles of the same scene through two cameras, combining the position relation of the two cameras, and recovering the position of an object in the scene in a three-dimensional space through a triangulation method.
In this embodiment, since the tracking device includes a plurality of cameras, the tracking information includes a plurality of frame information, each frame information includes an image frame acquired from each camera at the same time, a rotation etalon actual measurement model including at least three marker points on the rotation etalon can be constructed in the tracking device coordinate system based on the image frame corresponding to the rotation etalon, the rotation etalon actual measurement model can be a three-dimensional model composed of point cloud data, and the rotation etalon actual measurement model characterizes a real-time posture of the rotation etalon in a space constituted by the tracking device coordinate system when the image frame corresponding to the rotation etalon is captured. Similarly, based on the image frame corresponding to the displacement etalon, a displacement etalon actual measurement model containing at least two marking points on the displacement etalon can be constructed in the tracking equipment coordinate system, the displacement etalon actual measurement model can be a three-dimensional model formed by point cloud data, the displacement etalon actual measurement model characterizes the real-time gesture of the displacement etalon in the space formed by the tracking equipment coordinate system when the image frame corresponding to the displacement etalon is shot.
In this embodiment, in order to calibrate the Rotation relation representation of the tracking device, a Rotation etalon standard model (ms_r, modelStandard _rotation) corresponding to the Rotation etalon is preset, and the Rotation etalon standard model (ms_r) and a Rotation etalon actual measurement model (mr_r, modelRealtime _rotation) represent different spatial attitudes of the Rotation etalon under the coordinate system of the tracking device, and the Rotation etalon standard model (ms_r) includes spatial information of all the marker points set on the Rotation etalon. The Rotation relationship representation (R) between cameras in the tracking device may be calibrated based on the marker point correspondence between the Rotation etalon measured model and the Rotation etalon standard model.
In this embodiment, in order to calibrate the displacement relation representation of the tracking device, a displacement etalon standard model (ms_t, modelStandard _transform) corresponding to the displacement etalon is preset, and the displacement etalon standard model (ms_t) and the displacement etalon actual measurement model (mr_t, modelRealtime _transform) represent different spatial attitudes of the displacement etalon under the tracking device coordinate system, where the displacement etalon standard model (ms_t) includes spatial information of all the marker points set on the displacement etalon. Based on the mark point correspondence between the displacement etalon measured model and the displacement etalon standard model, a displacement relation representation (T, transformation_matrix) between cameras in the tracking device can be calibrated.
In the present embodiment, when three or more cameras are provided on the tracking device, the rotation relationship expression and the displacement relationship expression between each two cameras can be calibrated by the method shown in fig. 3.
In this embodiment, the rotation relationship of the tracking device is calibrated by using the actual measurement model and the standard model of the rotation etalon, and the displacement relationship of the tracking device is calibrated by using the actual measurement model and the standard model of the displacement etalon. The calibration rod is not required to be arranged at a plurality of positions, and the calibration of the tracking equipment can be realized, namely the automatic calibration of the tracking equipment is realized.
In some embodiments, the rotation etalon and the displacement etalon are respectively provided with marking points, the tracking equipment comprises a plurality of cameras, a calibration device of the tracking equipment can trigger the tracking equipment to collect tracking information, wherein the tracking information comprises a plurality of frame information, the frame information comprises image frames which are respectively and correspondingly collected by the plurality of cameras, and at least part of the image frames comprise all the marking points of the displacement etalon.
In this embodiment, in order to track the position changes of the tracking features on the rotation etalon and the displacement etalon, at least two cameras are provided on the tracking device, at least three marking points and two marking points are respectively provided on the rotation etalon and the displacement etalon, and the calibration device of the tracking device may trigger each camera to perform a shooting operation, so as to obtain an image frame set corresponding to each camera. In the present application, a plurality of image frames corresponding to the same time are used as frame information. The calibration means of the tracking device may collect a plurality of frame information, wherein if the frame information comprises at least three marker points on the rotation etalon, the frame information is deemed to correspond to the rotation etalon, and the frame information may be used to construct a rotation etalon measured model.
In this embodiment, if the frame information includes at least two mark points on the displacement etalon, the frame information is considered to correspond to the displacement etalon, and the frame information can be used to construct a displacement etalon actual measurement model. If the frame information contains at least two marker points on the rotation etalon and the displacement etalon, the frame information is considered to correspond to both the rotation etalon and the displacement etalon, and the frame information can be used for constructing a rotation etalon actual measurement model and a displacement etalon actual measurement model.
In this embodiment, for frame information, all of the marker points of the rotation etalon, and/or part of the marker points of the rotation etalon, and/or all of the marker points of the displacement etalon, and/or part of the marker points of the displacement etalon, and/or the marker points of the rotation etalon, and/or the marker points of the displacement etalon are included. When generating the rotational etalon measured model, a partial marker point containing the rotational etalon and/or frame information containing all marker points of the displacement etalon may be selected from the plurality of frame information to generate the rotational etalon measured model. When the displacement etalon measured model is generated, frame information including all the mark points of the displacement etalon can be selected from the plurality of frame information to generate the displacement etalon measured model.
In some embodiments, the image frame included in the frame information includes a partial mark point of the rotation etalon, the calibration device of the tracking device may reconstruct a rotation etalon measured model of the rotation etalon according to the partial mark point of the rotation etalon included in the frame information, and reconstruct a displacement etalon measured model of the displacement etalon according to the frame information including all mark points of the displacement etalon.
In this embodiment, in order to obtain the actual measurement model used as the calibration basis, the calibration device of the tracking device may reconstruct the rotation etalon in the tracking device coordinate system according to the frame information including the partial mark point of the rotation etalon to obtain the rotation etalon actual measurement model, and reconstruct the displacement etalon in the tracking device coordinate system according to the frame information including the partial mark point of the displacement etalon to obtain the displacement etalon actual measurement model. Wherein the rotary etalon is a movable device and the displacement etalon is a fixed position device or a movable device.
In this embodiment, when there are a plurality of frame information that can be used to reconstruct the rotation etalon actual measurement model, a rotation etalon actual measurement model can be reconstructed by each frame information, so as to obtain a plurality of rotation etalon actual measurement models, a plurality of rotation relation representations of the tracking device can be obtained by calibrating the rotation etalon actual measurement models and the rotation etalon standard model, respectively, and a rotation relation representation with higher precision can be obtained by fusing the plurality of rotation relation representations.
In this embodiment, when there are a plurality of frame information that can be used to reconstruct the displacement etalon actual measurement model, a displacement etalon actual measurement model can be reconstructed by each frame information, so as to obtain a plurality of displacement etalon actual measurement models, a plurality of displacement relation representations of the tracking device can be obtained by calibrating the plurality of displacement etalon actual measurement models and the displacement etalon standard model, and a rotation relation representation with higher precision can be obtained by fusing the plurality of displacement relation representations. Wherein the plurality of frame information corresponds to different acquisition times.
In some embodiments, a calibration device of the tracking device may determine a corresponding relationship of a marking point between the actually measured model of the rotating etalon and the standard model of the rotating etalon, acquire a standard spatial position relationship of the marking point included in the actually measured model of the rotating etalon from the standard model of the rotating etalon based on the corresponding relationship of the marking point, wherein the standard spatial position relationship is used for representing a relative position relationship of the marking point on the rotating etalon, and calibrate a rotation relationship representation of the tracking device based on the corresponding relationship of the marking point, the standard spatial position relationship, frame information corresponding to the actually measured model of the rotating etalon, and the actually measured model of the rotating etalon.
In this embodiment, since the rotation etalon actual measurement model and the rotation etalon standard model both include the marker points on the rotation etalon, the rotation etalon actual measurement model and the rotation etalon standard model may be subjected to point cloud stitching by a point cloud registration algorithm (e.g., ICP, NDT, etc.), so as to determine the correspondence between the same marker points in the rotation etalon actual measurement model and the rotation etalon standard model, and further obtain the marker point correspondence (S-r_r) including a plurality of correspondence. Based on the above, the standard spatial position relation (ms_r_d) of the marking points included in the rotation standard device actual measurement model in the rotation standard device standard model can be obtained according to the corresponding relation of the marking points, wherein the standard spatial position relation (ms_r_d) refers to the relative position relation between every two marking points, and the relative position relation between every two adjacent marking points can also be obtained. In addition, the position of the marking point included in the actual measurement model of the rotating standard device in the frame information corresponding to the actual measurement model of the rotating standard device can be determined, so that two-dimensional image information of the marking point can be obtained. Furthermore, a rotation relation representation (R) of the tracking device can be calibrated based on the mark point correspondence relation (S-R_R), the standard spatial position relation (MS_R_D), the mark point two-dimensional image information and the rotation standard actual measurement model. Thus, an accurate rotation relation representation (R) can be determined without human intervention.
In some embodiments, the calibration device of the tracking device may construct a constraint model for generating a reference rotation relationship representation of the tracking device based on the corresponding relationship of the mark points, the standard spatial position relationship, frame information corresponding to the actually measured model of the rotation standard, and the actually measured model of the rotation standard, so as to obtain a reference rotation relationship representation, and adjust the reference rotation relationship representation based on a minimized distance error algorithm, so as to obtain a rotation relationship representation of the tracking device.
In this embodiment, based on the mark point correspondence (S-r_r), the standard spatial position relationship (ms_r_d) may be substituted into the rotation etalon actual measurement model (mr_r) to obtain mark point reference two-dimensional image information, where the mark point reference two-dimensional image information indicates correct two-dimensional image information of the rotation etalon that should be included in frame information corresponding to the rotation etalon actual measurement model. A constraint model can be constructed based on the marker point reference two-dimensional image information and the marker point two-dimensional image information, wherein the constraint model can be expressed as x 'T fx=0, and x' and x are respectively used for expressing homogeneous coordinates corresponding to the same marker point in the marker point reference two-dimensional image information and the marker point two-dimensional image information. Due toT=[tx,ty,tz]T、The rotation relation representation (R) can thus be calculated. Where Δx and Δy are pixel dimensions in the horizontal and vertical directions, respectively, f x and f y are representations of the focal length of the camera in a pixel coordinate system, f is the focal length of the camera, and f x and f y depend on f and the pixel dimensions of the camera sensor. Further, c x and c y denote the optical center positions of the cameras, that is, the positions of the image coordinate system origins (0, 0) in the image frames, s is the pixel deviation of the cameras, and t x,ty,tz is used to denote the respective axis offsets between the cameras. Furthermore, a reference rotation relation representation can be obtained based on the constraint model, and a rotation relation representation of tracking equipment with higher precision can be obtained based on the reference rotation relation representation and further based on a minimized distance error algorithm to minimize the distance error between the mark point reference two-dimensional image information and the mark point two-dimensional image information.
In some embodiments, a calibration device of the tracking device can determine a mark point corresponding relation between the displacement etalon measured model and the displacement etalon standard model, acquire a standard spatial position relation of the mark points included in the displacement etalon measured model from the displacement etalon standard model based on the mark point corresponding relation, wherein the standard spatial position relation is used for representing a relative position relation of the mark points on the displacement etalon, and calibrate a displacement relation representation of the tracking device based on the rotation relation representation, frame information including all the mark points of the displacement etalon, the mark point corresponding relation, the standard spatial position relation, an initial displacement relation representation and the displacement etalon measured model.
In this embodiment, since the displacement etalon actual measurement model and the displacement etalon standard model both include the mark points on the displacement etalon, the displacement etalon actual measurement model and the displacement etalon standard model may be subjected to point cloud stitching by a point cloud registration algorithm (such as ICP, NDT, etc.), so as to determine the corresponding relationship of the same mark point in the displacement etalon actual measurement model and the displacement etalon standard model, or determine the corresponding relationship of the same mark point in the displacement etalon actual measurement model and the displacement etalon standard model by a coding point algorithm or an image feature matching algorithm. Further, a mark point correspondence relation (S-R_T) including a plurality of correspondence relations is obtained. Based on the above, the standard spatial position relation (ms_t_d) of the mark points included in the displacement standard device actual measurement model in the displacement standard device standard model can be obtained according to the corresponding relation of the mark points, wherein the standard spatial position relation (ms_t_d) refers to the relative position relation between every two mark points, and the relative position relation between every two adjacent mark points can also be obtained. In addition, the position of the marking point included in the displacement etalon actual measurement model in the frame information corresponding to the displacement etalon actual measurement model can be determined, so that two-dimensional image information of the marking point can be obtained. Furthermore, the displacement relation representation (T) of the tracking device can be calibrated based on the initial displacement relation representation, the corresponding relation (S-R_T) of the mark points, the standard space position relation (MS_T_D), the two-dimensional image information of the mark points and the displacement etalon actual measurement model. The initial displacement relation representation may be a displacement relation representation calculated based on the rotation relation representation (R), a preset rotation relation representation, a random rotation relation representation, or the like. Thus, the accurate displacement relation representation (T) can be determined without manual intervention.
In some embodiments, the calibration device of the tracking device may construct a constraint model for generating a reference displacement relationship representation of the tracking device based on the rotation relationship, frame information including all marker points of the displacement etalon, the marker point correspondence, the standard spatial position relationship, an initial displacement relationship representation, and the displacement etalon actual measurement model to obtain a reference displacement relationship representation, where the initial displacement relationship representation is an initial value of a specified displacement relationship representation, and adjust the reference displacement relationship representation based on a minimized distance error algorithm to obtain the displacement relationship representation of the tracking device.
In this embodiment, based on the initial displacement relationship representation, the displacement etalon standard model (ms_t), the frame information including all the marker points of the displacement etalon, and the marker point correspondence (S-r_t), the standard spatial position relationship (ms_t_d) may be substituted into the displacement etalon actual measurement model (mr_t), so as to confirm the theoretical distance truth between the marker points on the displacement etalon actual measurement model, and further based on the minimized distance error algorithm, the rotation relationship representation obtained by the foregoing and the initial displacement relationship representation to be optimized are utilized, and the error between the distance between the marker points reconstructed based on the epipolar constraint and the triangulation principle and the theoretical distance truth is minimized, so that the displacement relationship representation of the tracking device with higher precision may be obtained.
In some embodiments, the calibration means of the tracking device may reconstruct the measurement results sent by the measurement device in three dimensions based on the rotation relation representation and the displacement relation representation.
In this embodiment, in order to improve the three-dimensional reconstruction efficiency, after the calibration device of the tracking device performs automatic calibration on the tracking device, the three-dimensional reconstruction can be performed on the measurement result sent by the measurement device based on the calibrated rotation relationship representation and displacement relationship representation.
In the embodiment, the three-dimensional reconstruction of the measurement result sent by the measurement device based on the rotation relation representation and the displacement relation representation may be performed by calibrating the measurement device based on the rotation relation representation and the displacement relation representation, mapping the measurement result sent by the measurement device to a tracking device coordinate system based on the displacement relation representation and the rotation relation representation of the measurement device relative to each camera obtained by calibration, obtaining global point cloud data, and generating the global point cloud data into a three-dimensional reconstruction model.
Please refer to fig. 4. The embodiment of the application also provides a calibration device of the tracking equipment. The visual field of the tracking equipment comprises a rotation standard and a displacement standard, the rotation standard corresponds to a rotation standard model, the displacement standard corresponds to a displacement standard model, the calibration device of the tracking equipment can comprise a model reconstruction module, a rotation relation calibration module and a displacement relation calibration module, wherein the model reconstruction module is used for reconstructing a rotation standard actual measurement model of the rotation standard and a displacement standard actual measurement model of the displacement standard based on tracking information acquired by the tracking equipment, the rotation relation calibration module is used for calibrating a rotation relation representation of the tracking equipment according to the rotation standard actual measurement model and the rotation standard model, and the displacement relation calibration module is used for calibrating a displacement relation representation of the tracking equipment according to the displacement standard actual measurement model and the displacement standard model.
In this embodiment, specific functions and effects achieved by the calibration device of the tracking device may be explained in reference to other embodiments of the present application, and are not described herein.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor causes the processor to implement the calibration method of the tracking device as described above.
The embodiments of the present application also provide a computer program product comprising instructions which, when executed by a processor, implement a method of calibrating a tracking device as described above.
Please refer to fig. 5. The embodiment of the application can provide electronic equipment which comprises a memory and one or more processors which are in communication connection with the memory, wherein the memory stores instructions which can be executed by the one or more processors, and the instructions are executed by the one or more processors so as to enable the one or more processors to realize the calibration method of the tracking equipment.
In some implementations, the electronic device may include a processor, a storage medium, and a communication interface connected by a system bus. The storage medium may store a related computer program.
User information or user account information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, etc.) involved in various embodiments of the present application are information and data that are authorized by a user or sufficiently authorized by parties, and the collection, use and processing of relevant data is required to comply with relevant legal regulations and standards of relevant countries and regions, and is provided with corresponding operation portals for the user to select authorization or denial.
It will be appreciated that the specific examples herein are intended only to assist those skilled in the art in better understanding the embodiments of the application and are not intended to limit the scope of the application.
It should be understood that, in various embodiments of the present application, the sequence number of each process does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiments of the present application.
It will be appreciated that the various embodiments described in the present application may be implemented either alone or in combination, and that the embodiments of the present application are not limited in this regard.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It will be appreciated that the processor of an embodiment of the application may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be implemented by integrated logic circuits of hardware in a processor or instructions in software form. The Processor may be a general purpose Processor, a digital signal Processor (DIGITAL SIGNAL Processor, DSP), an Application SPECIFIC INTEGRATED Circuit (ASIC), an off-the-shelf programmable gate array (Field Programmable GATE ARRAY, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in a hardware decoding processor for execution, or in a combination of hardware and software modules in a decoding processor for execution. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
It will be appreciated that the memory in embodiments of the application can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an erasable programmable ROM (erasable PROM, EPROM), an Electrically Erasable Programmable ROM (EEPROM), or a flash memory, among others. The volatile memory may be Random Access Memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system, apparatus and unit may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing an electronic device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. The storage medium includes a U disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (12)
1. A calibration method of tracking equipment is characterized in that the visual field of the tracking equipment comprises a rotation standard device and a displacement standard device, the rotation standard device corresponds to a rotation standard device standard model, the displacement standard device corresponds to a displacement standard device standard model, and the method comprises the following steps:
Reconstructing a rotation etalon actual measurement model of the rotation etalon and a displacement etalon actual measurement model of the displacement etalon based on tracking information acquired by the tracking equipment;
Calibrating a rotation relationship representation of the tracking device according to the rotation etalon measured model and the rotation etalon standard model;
And calibrating the displacement relation representation of the tracking equipment according to the displacement standard actual measurement model and the displacement standard model.
2. The method of claim 1, wherein the rotation etalon and the displacement etalon are each provided with a marker point, wherein the tracking device comprises a plurality of cameras, and wherein the method further comprises:
The tracking equipment is triggered to acquire tracking information, wherein the tracking information comprises a plurality of pieces of frame information, the frame information comprises image frames which are acquired by a plurality of cameras respectively and correspondingly, and at least part of the image frames comprise all marking points of the displacement standard.
3. The method of claim 2, wherein the frame information includes an image frame including a partial marker point of the rotation etalon, wherein reconstructing a rotation etalon measured model of the rotation etalon and a displacement etalon measured model of the displacement etalon based on the image data acquired by the tracking device comprises:
Reconstructing a rotation etalon actual measurement model of the rotation etalon according to part of marking points of the rotation etalon included in the frame information;
And reconstructing a displacement etalon actual measurement model of the displacement etalon according to frame information of all marking points comprising the displacement etalon.
4. The method of claim 2, wherein calibrating the rotational relationship representation of the tracking device based on the rotational etalon measured model and the rotational etalon standard model comprises:
determining a mark point corresponding relation between the rotation standard device actual measurement model and the rotation standard device standard model;
Based on the corresponding relation of the marking points, acquiring a standard spatial position relation of the marking points included in the actual measurement model of the rotary standard from the standard model of the rotary standard, wherein the standard spatial position relation is used for representing the relative position relation of the marking points on the rotary standard;
And calibrating the rotation relation representation of the tracking equipment based on the corresponding relation of the marking points, the standard spatial position relation, frame information corresponding to the actual measurement model of the rotation standard device and the actual measurement model of the rotation standard device.
5. The method of claim 4, wherein calibrating the rotation relationship representation of the tracking device based on the marker point correspondence, the standard spatial location relationship, frame information corresponding to the rotation etalon measured model, the rotation etalon measured model comprises:
Constructing a constraint model for generating a reference rotation relation representation of the tracking equipment based on the corresponding relation of the marking points, the standard spatial position relation, frame information corresponding to the rotation standard actual measurement model and the rotation standard actual measurement model so as to obtain the reference rotation relation representation;
The reference rotation relationship representation is adjusted based on a minimized distance error algorithm to obtain a rotation relationship representation of the tracking device.
6. The method of claim 2, wherein calibrating the displacement relationship representation of the tracking device based on the displacement etalon measured model and the displacement etalon standard model comprises:
Determining a mark point corresponding relation between the displacement etalon actual measurement model and the displacement etalon standard model;
Based on the corresponding relation of the marking points, acquiring a standard spatial position relation of the marking points included in the actually measured displacement standard model from the standard displacement standard model, wherein the standard spatial position relation is used for representing the relative position relation of the marking points on the displacement standard;
calibrating the displacement relation representation of the tracking equipment based on the rotation relation representation, frame information comprising all marking points of the displacement etalon, the corresponding relation of the marking points, the standard spatial position relation, the initial displacement relation representation and the actual measurement model of the displacement etalon.
7. The method of claim 6, wherein calibrating the displacement relationship representation of the tracking device based on the rotation relationship representation, frame information including all marker points of the displacement etalon, the marker point correspondence, the standard spatial position relationship, an initial displacement relationship representation, the displacement etalon measured model comprises:
Constructing a constraint model for generating a reference displacement relation representation of the tracking equipment based on the rotation relation, frame information of all mark points comprising the displacement etalon, the corresponding relation of the mark points, the standard spatial position relation, an initial displacement relation representation and the actually measured displacement etalon model to obtain the reference displacement relation representation, wherein the initial displacement relation representation is an initial value of a designated displacement relation representation;
And adjusting the reference displacement relation representation based on a minimized distance error algorithm to obtain a displacement relation representation of the tracking device.
8. The method according to any one of claims 1-7, further comprising:
and carrying out three-dimensional reconstruction on the measurement result sent by the measurement device based on the rotation relation representation and the displacement relation representation.
9. The calibration device of the tracking equipment is characterized in that the visual field of the tracking equipment comprises a rotation standard device and a displacement standard device, the rotation standard device corresponds to a rotation standard device standard model, the displacement standard device corresponds to a displacement standard device standard model, and the device comprises:
the model reconstruction module is used for reconstructing a rotation standard device actual measurement model of the rotation standard device and a displacement standard device actual measurement model of the displacement standard device based on tracking information acquired by the tracking equipment;
The rotation relation calibration module is used for calibrating the rotation relation representation of the tracking equipment according to the rotation standard actual measurement model and the rotation standard model;
and the displacement relation calibration module is used for calibrating the displacement relation representation of the tracking equipment according to the displacement standard actual measurement model and the displacement standard model.
10. An electronic device comprising a memory and a processor, wherein the memory stores at least one computer program, the at least one computer program being loaded and executed by the processor to implement the method of calibrating a tracking device according to any of claims 1 to 8.
11. A computer-readable storage medium, characterized in that at least one computer program is stored in the computer-readable storage medium, which, when being executed by a processor, enables a calibration method of a tracking device according to any one of claims 1 to 8.
12. Computer program product, characterized in that the computer program product is adapted to implement a calibration method of a tracking device as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510307775.1A CN120431183A (en) | 2025-03-14 | 2025-03-14 | Calibration method and related device for tracking equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510307775.1A CN120431183A (en) | 2025-03-14 | 2025-03-14 | Calibration method and related device for tracking equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN120431183A true CN120431183A (en) | 2025-08-05 |
Family
ID=96556700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510307775.1A Pending CN120431183A (en) | 2025-03-14 | 2025-03-14 | Calibration method and related device for tracking equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120431183A (en) |
-
2025
- 2025-03-14 CN CN202510307775.1A patent/CN120431183A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7716712B2 (en) | Three-dimensional model generation method, information processing device and program | |
| CN113532329B (en) | Calibration method with projected light spot as calibration point | |
| CN113379822B (en) | Method for acquiring 3D information of target object based on pose information of acquisition equipment | |
| JP5467404B2 (en) | 3D imaging system | |
| Bouguet et al. | 3D photography using shadows in dual-space geometry | |
| EP1364226B1 (en) | Apparatus and method for obtaining three-dimensional positional data from a two-dimensional captured image | |
| JP5583761B2 (en) | 3D surface detection method and apparatus using dynamic reference frame | |
| CN112254670B (en) | 3D information acquisition equipment based on optical scanning and intelligent vision integration | |
| CN113327291B (en) | Calibration method for 3D modeling of remote target object based on continuous shooting | |
| CN111445529B (en) | Calibration equipment and method based on multi-laser ranging | |
| WO2004044522A1 (en) | Three-dimensional shape measuring method and its device | |
| KR102546346B1 (en) | Apparatus and method for omni-directional camera calibration | |
| CN110419208B (en) | Imaging system, imaging control method, image processing apparatus, and computer readable medium | |
| CN118781207B (en) | Target determining method, device and equipment based on multiple cameras | |
| WO2023095375A1 (en) | Three-dimensional model generation method and three-dimensional model generation device | |
| JP2003006618A (en) | Method and device for generating three-dimensional model and computer program | |
| CN120431183A (en) | Calibration method and related device for tracking equipment | |
| WO2024252781A1 (en) | Reliability calculating device, three-dimensional information creating device, and reliability calculating method | |
| US11978161B2 (en) | 3D modelling method and system | |
| JP3637416B2 (en) | Three-dimensional measurement method, three-dimensional measurement system, image processing apparatus, and computer program | |
| KR102684986B1 (en) | Device for 3D image reconstruction using rectangular grid projection | |
| Detchev et al. | Image matching and surface registration for 3D reconstruction of a scoliotic torso | |
| CN119810207B (en) | Calibration and Point Cloud Fusion Methods for Multi-Camera Single-Projector 3D Reconstruction Systems | |
| CN119103992A (en) | Laser projection system calibration method, three-dimensional reconstruction method and electronic device | |
| Hemmati et al. | A study on the refractive effect of glass in vision systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |