Image coordinate system alignment method and system based on 3D recognition

Abstract

The invention relates to the technical field of coordinate system alignment, and particularly discloses an image coordinate system alignment method and system based on 3D recognition, and the method comprises the following steps: S1, constructing a parent object coordinate system through a 2D identification graph, constructing a child object coordinate system, and adjusting the child object coordinate system; s2, acquiring coordinates of the origin of the child object coordinate system in the parent object coordinate system, adding new equipment and generating coordinates; s3, virtual equipment is constructed in the parent object coordinate system, and the position of the virtual equipment is adjusted; and S4, marking the specified equipment as an equipment main body, obtaining the actual height, obtaining the height of virtual equipment in the visual angle of the equipment main body, calculating a scaling ratio, and scaling. Through network synchronization and local correction, space consistency of virtual objects among multiple users is realized, Y-axis height abnormity caused by different data precision dimensions is corrected, and through scaling the height of virtual equipment, picture jitter is reduced, and user experience is improved.

Description

Technical Field

[0001] This invention relates to the field of coordinate system alignment technology, and specifically to an image coordinate system alignment method and system based on 3D recognition. Background Technology

[0002] In the process of using 3D object recognition as an entry point to anchor users from the physical world to virtual reality or augmented reality experiences, a common key technical problem is spatial location registration error, with deviations in the height direction being particularly significant and severely impacting the user experience. After a user or device enters the virtual environment, the virtual ground often does not coincide with the real ground, causing virtual objects to appear to float in the air or sink underground in abnormal states.

[0003] The problem primarily stems from sensor accuracy drift. Determining device height relies on barometers and accelerometers, both of which have inherent errors. Accelerometers are prone to significant drift during double integration of displacement; barometers are highly sensitive to changes in ambient air pressure, causing continuous fluctuations in height estimates and ultimately leading to spatial misalignment. During user movement, this height misalignment can cause severe dizziness, clipping, and interaction failures, severely compromising immersion and comfort. Therefore, an effective method is urgently needed to address the adverse effects caused by inconsistent heights among users. Summary of the Invention

[0004] The purpose of this invention is to provide an image coordinate system alignment method and system based on 3D recognition, thereby solving the above-mentioned technical problems.

[0005] The objective of this invention can be achieved through the following technical solutions: A method and system for aligning image coordinate systems based on 3D recognition, comprising the following steps: S1: Have device A scan the 2D marker image to construct a coordinate system and record it as the parent object coordinate system. The origin of the parent object coordinate system is located at the exact center of the 2D marker image. A coordinate system is reconstructed with device A as the origin and denoted as the sub-object coordinate system. The direction of the X-axis in the sub-object coordinate system is the same as the direction of the X-axis in the parent object coordinate system. The sub-object coordinate system is adjusted based on the X-axis of the sub-object coordinate system. S2: Get the coordinates P of the origin of the child object's coordinate system in the parent object's coordinate system. A (x) A y A , z A ), will y A Let y be the virtual ordinate. A =0; Add device B and generate its corresponding coordinates P using the method described above.B (x) B y B , z B ), will y B Let it be denoted as a virtual ordinate; S3: Let device B and device A exchange coordinates. After device B obtains the coordinates of device A, it constructs a virtual device a corresponding to device A in the parent object's coordinate system. The coordinates of virtual device a are P. a (x) A ,0,z A ); Have device B detect the actual height H of the current device and calculate the deviation value L=Hy B The position of virtual device a is adjusted based on the deviation value L. After adjustment, virtual device a has the correct height in the view of device B. Repeat the above steps to generate virtual device b corresponding to device B in the view of device A. S4: Designate device A as the main body of the device and obtain its current actual height H. A Obtain the height XH of virtual device b from the perspective of device A. B Calculate the scaling ratio L=H A / XH B The height XH of virtual device b from the perspective of device A B Make corrections, and record the corrected height as the corrected height X. B =L×XH B Scale the height of virtual device b to X B Using the above method, device A is designated as the main device, and the height of the virtual device a is scaled.

[0006] As a further aspect of the present invention: in step S3, the method for adjusting the position of the virtual device a based on the deviation value L includes: If the deviation value L > 0, move the virtual device a upward by L units; If the deviation value L=0, stop adjusting the virtual device a; If the deviation value L < 0, move the virtual device a down by |L| units.

[0007] As a further aspect of the present invention: in step S1, the method for adjusting the sub-object coordinate system based on the X-axis of the sub-object coordinate system includes: Let the X-axis of the child object's coordinate system be the rotation axis. Let the child object's coordinate system rotate clockwise around the rotation axis. Stop rotating when the Y-axis of the child object's coordinate system is in the same direction as the Y-axis of the parent object's coordinate system.

[0008] As a further aspect of the present invention: in step S2, when adding device B, ensure that the corresponding coordinate P is... B(x) B y B , z B Satisfy the constraints .

[0009] As a further aspect of the present invention: in step S2, the coordinates P corresponding to device A and device B are... A With coordinate P B All coordinates are obtained from the parent object's coordinate system.

[0010] As a further aspect of the present invention: in step S3, the method for exchanging coordinates between device B and device A includes: After device B sends the coordinates, it starts a timer. When device A receives the coordinates P... B (x) B y B , z B Then, a preset data frame is sent to device B. If device B receives the data frame within the preset waiting time T, the subsequent steps continue. If it does not receive the data frame, the subsequent steps stop and device B is instructed to resend the coordinates P. B (x) B y B , z B ).

[0011] As a further aspect of the present invention: a pre-set test threshold N is defined, when device B resends coordinate P... B (x) B y B , z B If the number of transmissions exceeds the test threshold N, the transmission will stop and a user device malfunction will be indicated.

[0012] An image coordinate system alignment system based on 3D recognition, comprising: Positioning module: Device A scans the 2D marker image to construct a coordinate system and records it as the parent object coordinate system. The origin of the parent object coordinate system is located at the exact center of the 2D marker image. A coordinate system is reconstructed with device A as the origin and denoted as the sub-object coordinate system. The direction of the X-axis in the sub-object coordinate system is the same as the direction of the X-axis in the parent object coordinate system. The sub-object coordinate system is adjusted based on the X-axis of the sub-object coordinate system. Virtual Device Module: Obtains the coordinates P of the origin of the child object's coordinate system in the parent object's coordinate system. A (x) A y A , z A ), will y A Let y be the virtual ordinate. A =0; Add device B and generate its corresponding coordinates P using the method described above. B(x) B y B , z B ), will y B Let it be denoted as a virtual ordinate; Adjustment module: Device B exchanges coordinates with device A. After device B obtains the coordinates of device A, it constructs a virtual device a corresponding to device A in the parent object's coordinate system. The coordinates of virtual device a are P. a (x) A ,0,z A ); Instruct device B to detect the actual height H of the current device and calculate the deviation value L=Hy. B The position of virtual device a is adjusted based on the deviation value L. After adjustment, virtual device a has the correct height in the view of device B. Repeat the above steps to generate virtual device b corresponding to device B in the view of device A. Scaling module: Designates device A as the main body of the device and obtains its current actual height H. A Obtain the height XH of virtual device b from the perspective of device A. B Calculate the scaling ratio L=H A / XH B The height XH of virtual device b from the perspective of device A B Make corrections, and record the corrected height as the corrected height X. B =L×XH B Scale the height of virtual device b to X B Using the above method, device A is designated as the main device, and the height of the virtual device a is scaled.

[0013] The beneficial effects of this invention are as follows: The first step is to create an independent parent object coordinate system and a child object coordinate system. It's important to note the difference between the two: the parent object coordinate system is dynamically instantiated by the application based on the recognition results returned by the AR engine when the device recognizes a preset 2D marker image. The position and rotation of this node are set to the world coordinates indicated by the recognition results and are typically kept static thereafter. In this coordinate system, the X and Z axis coordinates can be accurately expressed, but the Y axis coordinate cannot be accurately measured. The child object coordinate system, on the other hand, is directly driven by the underlying AR engine. Its transformation relationship reflects the six-degree-of-freedom pose of the device's camera in real physical space in real time, thus allowing for more accurate Y-axis coordinates. However, the X and Z axis coordinates cannot be accurately obtained. This step is fundamental to all subsequent processing. High-precision absolute height data sources and high-precision relative horizontal data sources are decoupled. The 3D coordinate system provides a reliable vertical dimension reference, while the 2D coordinate system serves as a stable parent container for all content based on the recognition image, ensuring accurate relative layout relationships between virtual objects.

[0014] The second step is the horizontal alignment of different coordinate systems. During coordinate system initialization, the rotation settings in world space are strictly aligned with the orientation of the recognized image. This ensures that all clients are referenced by the same coordinate system, with the X and Z axes pointing in the same direction as the world space. This means that front, back, left, and right are consistent in the perception of all users, providing a common semantic basis for exchanging relative horizontal position data between different users and eliminating directional ambiguity.

[0015] Then, data is transmitted over the network. Only reliable data dimensions measured in a reliable coordinate system are transmitted between networks, avoiding the propagation of errors at the communication source. Transforming the object from a local coordinate system to a world coordinate system is a crucial preparatory step. Switching the object's positioning reference from a potentially drifting local coordinate system to a globally stable world coordinate system creates the conditions for the next step of individually correcting errors in a specific dimension.

[0016] Finally, localization correction is performed on the height dimension. With the virtual object already positioned in the world coordinate system, the program reads a high-confidence ground height value provided by the local AR engine. Then, the program retains only the accurate X and Z components of the virtual object's world coordinates, while directly overwriting the local true height value with its Y component. At this point, the horizontal position is accurate; only the height needs adjustment. In summary, by authorizing each device to use its most reliable sensor data to ultimately determine the vertical orientation, the problem of inconsistent heights in shared spaces caused by device differences and recognition errors is resolved. Furthermore, by scaling the height of the virtual devices, all virtual devices in the user's view are fixed at the same height as the user, thereby reducing screen jitter caused by height differences and greatly improving the user experience. Attached Figure Description

[0017] The invention will now be further described with reference to the accompanying drawings.

[0018] Figure 1 This is a flowchart illustrating an image coordinate system alignment method and system based on 3D recognition according to the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Please see Figure 1 As shown, the present invention is an image coordinate system alignment method and system based on 3D recognition, comprising the following steps: S1: Have device A scan the 2D marker image to construct a coordinate system and record it as the parent object coordinate system. The origin of the parent object coordinate system is located at the exact center of the 2D marker image. A coordinate system is reconstructed with device A as the origin and denoted as the sub-object coordinate system. The direction of the X-axis in the sub-object coordinate system is the same as the direction of the X-axis in the parent object coordinate system. The sub-object coordinate system is adjusted based on the X-axis of the sub-object coordinate system. S2: Get the coordinates P of the origin of the child object's coordinate system in the parent object's coordinate system. A (x) A y A , z A ), will y A Let y be the virtual ordinate. A =0; Add device B and generate its corresponding coordinates P using the method described above. B (x) B y B , z B ), will y B Let it be denoted as a virtual ordinate; S3: Let device B and device A exchange coordinates. After device B obtains the coordinates of device A, it constructs a virtual device a corresponding to device A in the parent object's coordinate system. The coordinates of virtual device a are P. a (x) A ,0,z A ); Have device B detect the actual height H of the current device and calculate the deviation value L=Hy B The position of virtual device a is adjusted based on the deviation value L. After adjustment, virtual device a has the correct height in the view of device B. Repeat the above steps to generate virtual device b corresponding to device B in the view of device A. S4: Designate device A as the main body of the device and obtain its current actual height H. A Obtain the height XH of virtual device b from the perspective of device A. B Calculate the scaling ratio L=H A / XH B The height XH of virtual device b from the perspective of device A B Make corrections, and record the corrected height as the corrected height X. B =L×XH B Scale the height of virtual device b to X B Using the above method, device A is designated as the main device, and the height of the virtual device a is scaled.

[0021] It's important to note that the first step is to create a parent object coordinate system and a child object coordinate system. The parent object coordinate system dynamically instantiates a dedicated transformation node by recognizing a pre-defined 2D marker image and based on the detailed recognition results returned by the AR engine. The position and rotation angle of this transformation node are set to the world coordinates explicitly indicated by the recognition results. Once this initialization is complete, this node typically remains relatively static during subsequent operation unless there is special intervention or update requirement. It's worth noting that the X and Z axes can be expressed relatively accurately within this specific coordinate system. This is because, based on the recognition of the 2D plane, combined with relevant mathematical models and algorithms, the position information of the object in these two directions can be reliably determined. However, due to the limitations of the 2D marker image itself and the physical limitations of the acquisition device, the Y-axis coordinate cannot be accurately measured. In other words, there is some uncertainty in the position information in the vertical direction, which may affect some applications with high precision requirements.

[0022] The sub-object coordinate system is directly driven by the powerful underlying AR engine, possessing high real-time performance and dynamism. Its transformation relationships can accurately reflect the six degrees of freedom pose of the device's camera in real physical space in real time. The six degrees of freedom include translation along three coordinate axes (X, Y, Z) and rotation around these axes. Thanks to this real-time tracking and feedback mechanism, the sub-object coordinate system can obtain the Y-axis coordinate relatively accurately, providing strong support for vertical positioning. However, on the other hand, because it depends on the camera's viewpoint and motion state, it cannot obtain the X and Z-axis coordinates as accurately as the parent object coordinate system. This is because changes in the camera's viewpoint can cause projection distortion and other problems, resulting in certain errors in the measurements of the horizontal and depth directions.

[0023] Next, horizontal alignment of different coordinate systems is performed. The purpose is to ensure the consistency of subsequent data and the accuracy of interactions. This operation provides a unified and standardized reference base for all clients. Within this common coordinate system framework, the directions of its X and Z axes are consistent with the directions in world space. From a practical application perspective, this feature makes it possible for different users to exchange relative position data in the horizontal direction. In previous systems, due to the lack of such a unified standard, the positional information transmitted between different users was often ambiguous. Horizontal alignment of different coordinate systems is an indispensable part of the entire system. With precise direction definition as its foundation, it builds a unified, efficient, and stable interactive environment, providing strong support for the smooth implementation of various complex applications.

[0024] After completing the coordinate system setup and horizontal alignment, the next crucial step is data transmission over the network. In the complex operating environment of an AR system, various factors can lead to data distortion, such as differences in device performance, environmental interference, and noise during signal transmission. If all unfiltered and unprocessed data is transmitted indiscriminately over the network, these potential errors will spread rapidly throughout the system like a virus, severely impacting the accuracy of the final results.

[0025] Transforming an object from a local coordinate system to a world coordinate system is a crucial preparatory step in this series of operations, with profound and significant implications. Local coordinate systems are often limited by specific scenarios or devices, making them prone to overall drift. A local coordinate system established from the perspective of a particular device may shift due to slight movements, vibrations, or accumulated errors from prolonged operation. This drift not only affects the accurate positioning of the current object but also has a chain reaction on a series of subsequent related calculations and operations, significantly reducing the reliability of the entire system.

[0026] When switching the object's positioning reference from a potentially drifting local coordinate system to a globally stable world coordinate system, the world coordinate system, as a global reference frame, possesses high stability and consistency. It is unaffected by changes in individual devices or local environments, providing the object with a unified and reliable positioning basis.

[0027] Finally, localization corrections are made to the height dimension. At this point, the virtual object is in a stable and unified world coordinate system, providing an ideal framework for subsequent height adjustments. In this crucial stage, the program actively reads high-confidence ground height values ​​provided by the local AR engine. This "high confidence" is based on the reliability guaranteed by the AR engine's advanced algorithms and extensive practical experience. Through the analysis and processing of large amounts of environmental data, combined with information fusion technology from multiple sensors, the engine can accurately capture the ground height information in the real world.

[0028] Next, the program performs a delicate and crucial operation: retaining only the precisely determined X and Z components in the virtual object's world coordinates. This is because, in the preceding steps, through a series of rigorous calibration and alignment operations, the X and Z positions have been determined to an extremely high level of precision; continuing to use these values ​​ensures that the accuracy of the horizontal position remains undisturbed. As for the Y component, which represents the height dimension, the program decisively overwrites the local actual height value with it.

[0029] This strategy was adopted because the horizontal position had already been accurately determined through multiple safeguards; the only aspect requiring further optimization and adjustment was the height dimension. This targeted approach fully utilizes existing precise information while avoiding unnecessary complex calculations and potential errors. More importantly, by authorizing each device to use its most reliable sensor data to ultimately determine the vertical representation, the system cleverly solves the long-standing problem of inconsistent shared spatial heights caused by device differences and recognition errors in AR applications. Different devices have varying built-in sensor performance due to differences in hardware configuration, manufacturing processes, and usage environments. Some devices may have more sensitive gyroscopes, while others may have more accurate accelerometers. By allowing each device to provide the most reliable height data based on its own strengths, the system can fully leverage the potential of each device, achieving complementary advantages.

[0030] In summary, localization correction of the height dimension, as the final step in the entire AR system, cleverly utilizes the sensor advantages of each device to achieve accurate vertical presentation. This provides a unified and realistic shared space for cross-device AR applications, greatly expanding the application scenarios and user experience of AR technology. Furthermore, by scaling the height of virtual devices to match the user's own height from their perspective, it effectively eliminates image jitter caused by height differences. Visually, it places virtual devices on the same horizontal line, clarifying relationships and presenting a harmonious aesthetic. For the user experience, interaction is smoother, and operation is less disruptive; immersion is enhanced, and viewing is seamless.

[0031] In another preferred embodiment of the present invention, the method for adjusting the position of virtual device a based on the deviation value L includes: If the deviation value L > 0, move the virtual device a upward by L units; If the deviation value L=0, stop adjusting the virtual device a; If the deviation value L < 0, move the virtual device a down by |L| units.

[0032] Notably, automated and adaptive height calibration is achieved through real-time calculation of the deviation value L. It supports bidirectional adjustments up and down, covering all possible error scenarios. The system automatically locks the state when L=0 to avoid unnecessary disturbances. Using unit length as the step size ensures that the adjustment amount strictly matches the error, improving positioning accuracy.

[0033] In another preferred embodiment of the present invention, the method for adjusting the coordinate system of a sub-object based on the X-axis of the sub-object coordinate system includes: Let the X-axis of the child object's coordinate system be the rotation axis. Let the child object's coordinate system rotate clockwise around the rotation axis. Stop rotating when the Y-axis of the child object's coordinate system is in the same direction as the Y-axis of the parent object's coordinate system.

[0034] Understandably, horizontal alignment of different coordinate systems is performed to ensure consistency of subsequent data and accuracy of interaction. This operation provides a unified and standardized reference base for all clients. Within this common coordinate system framework, the directions of its X and Z axes are consistent with the directions in world space. From a practical application perspective, this feature enables different users to exchange relative position data in the horizontal direction.

[0035] In another preferred embodiment of the present invention, when adding device B, ensure that the corresponding coordinate P is... B (x) B y B , z B Satisfy the constraints .

[0036] It is important to avoid having device A and device B in the same location, as this could cause system errors.

[0037] In another preferred embodiment of the present invention, the coordinates P corresponding to device A and device B are... A With coordinate P B All coordinates are obtained from the parent object's coordinate system.

[0038] It should be noted that the object's positioning reference was switched from a potentially drifting local coordinate system to a globally stable world coordinate system. As a global reference frame, the world coordinate system possesses high stability and consistency. It is unaffected by changes in individual devices or local environments, providing a unified and reliable positioning basis for the object.

[0039] In another preferred embodiment of the present invention, the method for exchanging coordinates between device B and device A includes: After device B sends the coordinates, it starts a timer. When device A receives the coordinates P... B (x) B y B , z B Then, a preset data frame is sent to device B. If device B receives the data frame within the preset waiting time T, the subsequent steps continue. If it does not receive the data frame, the subsequent steps stop and device B is instructed to resend the coordinates P. B (x) B y B , z B ).

[0040] In a preferred embodiment, a pre-set test threshold N is established when device B resends coordinates P. B (x) B y B , z B If the number of transmissions exceeds the test threshold N, the transmission will stop and a user device malfunction will be indicated.

[0041] An image coordinate system alignment system based on 3D recognition, comprising: Positioning module: Device A scans the 2D marker image to construct a coordinate system and records it as the parent object coordinate system. The origin of the parent object coordinate system is located at the exact center of the 2D marker image. A coordinate system is reconstructed with device A as the origin and denoted as the sub-object coordinate system. The direction of the X-axis in the sub-object coordinate system is the same as the direction of the X-axis in the parent object coordinate system. The sub-object coordinate system is adjusted based on the X-axis of the sub-object coordinate system. Virtual Device Module: Obtains the coordinates P of the origin of the child object's coordinate system in the parent object's coordinate system. A (x) A y A , z A ), will y A Let y be the virtual ordinate. A =0; Add device B and generate its corresponding coordinates P using the method described above. B (x) B y B , z B ), will y B Let it be denoted as a virtual ordinate; Adjustment module: Device B exchanges coordinates with device A. After device B obtains the coordinates of device A, it constructs a virtual device a corresponding to device A in the parent object's coordinate system. The coordinates of virtual device a are P. a (x) A ,0,z A ); Instruct device B to detect the actual height H of the current device and calculate the deviation value L=Hy. B The position of virtual device a is adjusted based on the deviation value L. After adjustment, virtual device a has the correct height in the view of device B. Repeat the above steps to generate virtual device b corresponding to device B in the view of device A. Scaling module: Designates device A as the main body of the device and obtains its current actual height H. A Obtain the height XH of virtual device b from the perspective of device A. B Calculate the scaling ratio L=H A / XH B The height XH of virtual device b from the perspective of device A BMake corrections, and record the corrected height as the corrected height X. B =L×XH B Scale the height of virtual device b to X B Using the above method, device A is designated as the main device, and the height of the virtual device a is scaled.

[0042] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the present invention should still fall within the scope of the present invention.

Claims

1. A method for aligning image coordinate systems based on 3D recognition, characterized in that, Includes the following steps: S1: Have device A scan the 2D marker image to construct a coordinate system and record it as the parent object coordinate system. The origin of the parent object coordinate system is located at the exact center of the 2D marker image. A coordinate system is reconstructed with device A as the origin and denoted as the sub-object coordinate system. The direction of the X-axis in the sub-object coordinate system is the same as the direction of the X-axis in the parent object coordinate system. The sub-object coordinate system is adjusted based on the X-axis of the sub-object coordinate system. S2: Get the coordinates P of the origin of the child object's coordinate system in the parent object's coordinate system. A (x) A y A , z A ), will y A Let y be the virtual ordinate. A =0; Add device B and generate its corresponding coordinates P using the method described above. B (x) B y B , z B ), will y B Let it be denoted as a virtual ordinate; S3: Let device B and device A exchange coordinates. After device B obtains the coordinates of device A, it constructs a virtual device a corresponding to device A in the parent object's coordinate system. The coordinates of virtual device a are P. a (x) A ,0,z A ); Have device B detect the actual height H of the current device and calculate the deviation value L=Hy B The position of virtual device a is adjusted based on the deviation value L. After adjustment, virtual device a has the correct height in the view of device B. Repeat the above steps to generate virtual device b corresponding to device B in the view of device A. S4: Designate device A as the main body of the device and obtain its current actual height H. A Obtain the height XH of virtual device b from the perspective of device A. B Calculate the scaling ratio L=H A / XH B The height XH of virtual device b from the perspective of device A B Make corrections, and record the corrected height as the corrected height X. B =L×XH B Scale the height of virtual device b to X B Using the above method, device A is designated as the main device, and the height of the virtual device a is scaled.

2. The image coordinate system alignment method based on 3D recognition according to claim 1, characterized in that, In step S3, the method for adjusting the position of virtual device a based on the deviation value L includes: If the deviation value L > 0, move the virtual device a upward by L units; If the deviation value L=0, stop adjusting the virtual device a; If the deviation value L < 0, move the virtual device a down by |L| units.

3. The image coordinate system alignment method based on 3D recognition according to claim 1, characterized in that, In step S1, the method for adjusting the sub-object coordinate system based on the X-axis of the sub-object coordinate system includes: Let the X-axis of the child object's coordinate system be the rotation axis. Let the child object's coordinate system rotate clockwise around the rotation axis. Stop rotating when the Y-axis of the child object's coordinate system is in the same direction as the Y-axis of the parent object's coordinate system.

4. The image coordinate system alignment method based on 3D recognition according to claim 1, characterized in that, In step S2, when adding device B, ensure the corresponding coordinates P are correct. B (x) B y B , z B Satisfy the constraints .

5. The image coordinate system alignment method based on 3D recognition according to claim 1, characterized in that, In step S2, the coordinates P corresponding to device A and device B are... A With coordinate P B All coordinates are obtained from the parent object's coordinate system.

6. The image coordinate system alignment method based on 3D recognition according to claim 1, characterized in that, In step S3, the method for exchanging coordinates between device B and device A includes: After device B sends the coordinates, it starts a timer. When device A receives the coordinates P... B (x) B y B , z B Then, a preset data frame is sent to device B. If device B receives the data frame within the preset waiting time T, the subsequent steps continue. If it does not receive the data frame, the subsequent steps stop and device B is instructed to resend the coordinates P. B (x) B y B , z B ).

7. The image coordinate system alignment method based on 3D recognition according to claim 6, characterized in that, A pre-set test threshold N is set when device B resends coordinates P. B (x) B y B , z B If the number of transmissions exceeds the test threshold N, the transmission will stop and a user device malfunction will be indicated.

8. An image coordinate system alignment system based on 3D recognition, characterized in that, include: Positioning module: Device A scans the 2D marker image to construct a coordinate system and records it as the parent object coordinate system. The origin of the parent object coordinate system is located at the exact center of the 2D marker image. A coordinate system is reconstructed with device A as the origin and denoted as the sub-object coordinate system. The direction of the X-axis in the sub-object coordinate system is the same as the direction of the X-axis in the parent object coordinate system. The sub-object coordinate system is adjusted based on the X-axis of the sub-object coordinate system. Virtual Device Module: Obtains the coordinates P of the origin of the child object's coordinate system in the parent object's coordinate system. A (x) A y A , z A ), will y A Let y be the virtual ordinate. A =0; Add device B and generate its corresponding coordinates P using the method described above. B (x) B y B , z B ), will y B Let it be denoted as a virtual ordinate; Adjustment module: Device B exchanges coordinates with device A. After device B obtains the coordinates of device A, it constructs a virtual device a corresponding to device A in the parent object's coordinate system. The coordinates of virtual device a are P. a (x) A ,0,z A ); Have device B detect the actual height H of the current device and calculate the deviation value L=Hy B The position of virtual device a is adjusted based on the deviation value L. After adjustment, virtual device a has the correct height in the view of device B. Repeat the above steps to generate virtual device b corresponding to device B in the view of device A. Scaling module: Designates device A as the main body of the device and obtains its current actual height H. A Obtain the height XH of virtual device b from the perspective of device A. B Calculate the scaling ratio L=H A / XH B The height XH of virtual device b from the perspective of device A B Make corrections, and record the corrected height as the corrected height X. B =L×XH B Scale the height of virtual device b to X B Using the above method, device A is designated as the main device, and the height of the virtual device a is scaled.

Images