Video AR lofting method and device, electronic equipment and storage medium

Abstract

The invention discloses a video AR lofting method and device, electronic equipment and a storage medium, and belongs to the technical field of computer vision and surveying and mapping. The video AR lofting method comprises the following steps: acquiring high-precision position and attitude information of RTK (Real-Time Kinematic) equipment; matching the position and attitude information of the RTK equipment with design coordinates; the design coordinates are converted into AR image coordinates through conversion between coordinate systems; and overlapping and displaying the target point to be lofted in the video stream in real time. The RTK lofting method solves the problem that an existing RTK lofting method needs professionals to frequently move equipment and depends on numerical value comparison for navigation. According to the method, by introducing the AR technical means, the lofting point is displayed in the video in real time, so that an operator is guided to find the target point, when the operator is within one meter away from the target point, the target point can be positioned through a virtual position and one rod displayed by the video, and the usability and efficiency of lofting can be greatly improved by the method.

Description

Technical Field

[0001] The present invention relates to the technical fields of computer vision and surveying and mapping, and specifically provides a video AR lofting method, device, electronic device and storage medium. Background Technique

[0002] In the traditional RTK lofting process, it mainly relies on the high-precision coordinate data provided by the RTK device. The operator determines the forward direction and distance by observing the difference between the coordinates output by the measuring device and the designed target point, and gradually approaches the target point. This method not only requires professional technicians to be very familiar with the working area, but also it is difficult to achieve efficient and accurate lofting in complex environments. Specifically: The traditional method requires the operator to have rich experience and professional knowledge to correctly interpret the coordinate data and guide the construction. Since the position of the RTK device needs to be continuously adjusted, the whole process takes a long time, especially in the case of large-area or multi-point lofting. Moreover, multiple device movements may cause cumulative errors, affecting the accuracy of the final lofting. Summary of the Invention

[0003] The purpose of the present invention is to provide a video AR lofting method, device, electronic device and storage medium. By introducing AR technical means, the lofting points are displayed in the video in real time, so as to guide the operator to find the target point. When the operator is within 1 meter of the target point, the target point can be located with one rod through the virtual position displayed in the video. This method can greatly improve the usability and efficiency of lofting and solve the problems raised in the above background technique.

[0004] To achieve the above purpose, the present invention provides the following technical solutions: A video AR lofting method includes the following steps: S1. Obtain the high-precision position and attitude information of the RTK device; S2. Match the position and attitude information of the RTK device with the designed coordinates; S3. Convert the designed coordinates into corresponding coordinates in the AR image through the conversion between multiple coordinate systems; S4. In the video stream, superimpose and display the virtual points to be lofted, that is, the target points, in real time. Guide the operator to find and mark the actual position according to the displayed target points, and adjust the position and angle of the lofting device, so as to accurately calibrate the target points in reality.

[0005] Preferably, for S3 described above, the conversion order of the designed coordinates is specifically: Transfer from the geodetic coordinate system G (B, L, H) to the projection coordinate system W (x, y, h); Transfer from the projection coordinate system W to the local coordinate system L (E, N, U); Transfer from the local geocentric coordinate system L to the RTK device coordinate system r (X, Y, Z); Transfer from the RTK device coordinate system r to the IMU device coordinate system i (X, Y, Z); Transfer from the IMU device coordinate system i to the camera coordinate system c (X, Y, Z); Transfer from the camera coordinate system c to the image space coordinate system S (x, y, z); Transfer from the image space coordinate system S to the image plane coordinate system O (x, y); Add distortion parameters to compensate for the influence of lens distortion, and obtain the frame coordinate Q (x, y).

[0006] Preferably, the conversion process of the design objective is specifically as follows: S31. During the process of transferring from the geodetic coordinate system G to the projection coordinate system W, the RTK coordinate G1 (B, L, H) of the RTK device phase center is obtained through projection calculation to get the coordinate W1 (x, y, h) in the local projection coordinate system, and the geodetic coordinate G2 (B, L, H) of the target point is obtained through projection calculation to get the coordinate W2 (x, y, h) in the local projection coordinate system; S32. During the process of transferring from the projection coordinate system W to the local geocentric coordinate system L, according to the RTK device projection coordinate and the projection method, calculate the rotation and translation conversion relationship between the projection coordinate system W and the local geocentric coordinate system L, that is and ; S33. During the process of transferring from the local geocentric coordinate system L to the RTK device coordinate system r, set the attitude angles roll (r), pitch (p) and yaw (h) of the RTK device, and obtain the rotation conversion relationship between the r system and the L system through the rotation matrix, that is , , ; S34. During the process of transferring from the device coordinate system r to the IMU coordinate system i, obtain the rotation and translation conversion relationship between the IMU device and the RTK device through IMU calibration, that is and ; S35. During the process of transferring from the IMU device coordinate system i to the camera coordinate system c, obtain the external parameter rotation and translation conversion relationship between the camera coordinate system and the IMU device through camera external parameter calibration, that is and ; S36. The image space coordinate S is converted to the image plane coordinate O through the camera internal parameters c x , c y , f and according to the collinearity equation; S37. The image plane coordinate O is converted to the image point coordinate through the camera internal parameters cx, cy, f; S38. Use the distortion parameter k1 , k 2 , k 3 , p 1 , p 2 Increase the distortion variable.

[0007] Preferably, for S33, the calculation formula of the rotation matrix is as follows: ; .

[0008] Preferably, the target conversion formulas of S31 to S36 can be combined to obtain the coordinates of the target point 2 in the image space coordinate S as follows: ; The image plane coordinates are obtained through internal parameter conversion: ; Among them, u represents the pixel position along the horizontal direction (X-axis) of the image, and v represents the pixel position along the vertical direction (Y-axis); The increased radial formula is distortion: ; The increased tangential formula is distortion: ; Among them, k 1 , k 2 , k 3 are the quadratic term, quartic term, and sextic term distortions respectively, and p 1 , p 2 represent the two components of the tangential distortion respectively.

[0009] Preferably, when the elevation is not available in the target point design coordinates, the elevation of the rod tip is used as the elevation of the target design point. If the difference between the elevation of the design point and the rod tip exceeds a certain threshold, the elevation of the rod tip is used as the elevation of the target point to calculate the AR layout image point coordinates.

[0010] A video AR layout device, comprising: An AR camera device for capturing videos of the real world and generating augmented reality views; A positioning module for obtaining RTK position and attitude information; A data processing module for calculating and processing position information and executing coordinate conversion algorithms; A display module for real-time displaying the position and information of the points to be laid out on the AR image.

[0011] Preferably, the AR camera device includes a ranging module for real-time detecting the depth of the space in the central area of the screen and correcting the AR display points.

[0012] An electronic device for video AR lofting, comprising a processor and a memory, the memory storing machine-readable instructions executable by the processor, and when the machine-readable instructions are executed, they are used to implement the video AR lofting method according to any one of claims 1 to 6.

[0013] A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it executes the video AR lofting method.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Through the augmented reality technology, the present invention superimposes and displays virtual points to be lofted in real time in the video stream, replacing the traditional numerical comparison navigation method. Operators no longer rely on complex numerical calculations and frequent movements of professional equipment to determine the target position. The AR image provides an intuitive visual guidance, enabling even non-professionals to quickly and accurately find and mark the target points, greatly improving work efficiency and usability.

[0015] 2. By introducing an automatic conversion mechanism between multiple coordinate systems, including the geodetic coordinate system, local projection coordinate system, and station-centered coordinate system, etc., the present invention ensures that the design coordinates can be accurately mapped into the video image, reduces the dependence on professional skills, and avoids error accumulation caused by improper manual operations. The automated coordinate conversion process guarantees high precision for each lofting, improving the overall project quality control level.

[0016] 3. By adding a ranging module, the present invention can sense the actual surface height in the central area of the measurement image in real time and adjust the display position of the AR point accordingly, solving the error problem caused by inaccurate elevation information of the design point or complex terrain in the traditional RTK method. The intelligent compensation mechanism ensures high-precision lofting results even under complex terrain conditions, improving the reliability and accuracy of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is the first AR lofting schematic diagram of the present invention; Figure 2 It is the second AR lofting schematic diagram of the present invention; Figure 3 It is the third AR lofting schematic diagram of the present invention; Figure 4 It is the schematic diagram of the ranging and camera module of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] To solve the problem that the traditional RTK layout method requires professionals to frequently move the device and rely on numerical comparison for navigation, the following technical solutions are provided in this embodiment: A video AR layout method includes the following steps: S1. Obtain the high-precision position and attitude information of the RTK device; S2. Match the position and attitude information of the RTK device with the design coordinates; S3. Convert the design coordinates into corresponding coordinates in the AR image through the conversion between multiple coordinate systems; S4. In the video stream, the target points to be laid out are superimposed and displayed in real time, and the position and angle of the layout device are adjusted according to the displayed target points, so as to accurately calibrate the real target points.

[0020] Among them, the coordinate conversion mentioned in S3 is a key step in AR layout, which involves the conversion between multiple coordinate systems and needs to be selected and converted according to actual requirements. Through reasonable coordinate conversion, accurate AR layout can be achieved. During the AR layout coordinate conversion process, the conversion between multiple coordinate systems is involved, and there are a total of 9 coordinate systems. These coordinate systems can be roughly divided into the following three categories: The object space coordinate system is used to describe the position of ground points and includes the WGS84 coordinate system, the local projection coordinate system, and the station-centered coordinate system; the device coordinate system is used to describe the relative position with the device and includes the RTK device coordinate system, the IMU coordinate system, and the camera coordinate system; the image space coordinate system is used to describe the position of image points and includes the photo frame coordinate system, the image plane coordinate system, and the image space coordinate system.

[0021] (1) Geodetic coordinate system G(B, L, H): A coordinate system established with the reference ellipsoid as the reference surface in geodesy. The position of a ground point is represented by geodetic longitude (B), geodetic latitude (L), and geodetic height (H). The establishment of the geodetic coordinate system includes selecting an ellipsoid, positioning the ellipsoid, and determining the geodetic starting data. An earth ellipsoid with a determined shape, size, positioning, and orientation is called a reference ellipsoid. Commonly used geodetic coordinate systems include WGS84 and CGCS2000.

[0022] (2)Local projection coordinate system W(x, y, h): Also known as the ground survey coordinate system, usually referring to the map projection coordinate system, that is, the plane rectangular coordinate system and elevation system of the Gauss-Krüger projection used in national mapping. The spatial rectangular coordinate system composed of the two conforms to the left-hand rule.

[0023] (3)Station-centered coordinate system L(E, N, U): Also known as the ground photogrammetric coordinate system, it is a transitional coordinate system for the mutual conversion between photogrammetric coordinates and ground survey coordinates, and it conforms to the right-hand rule. The origin is usually selected at a certain ground control point; the axis is the plumb line passing through this point, with the upward direction being positive and parallel to the axis of the ground survey coordinate system; the axis is consistent with the flight line direction.

[0024] (4)RTK device coordinate system r(X, Y, Z): Used to describe the special moving coordinate system of the RTK device; its origin coincides with the phase center of the RTK device.

[0025] (5)IMU device coordinate system i(X, Y, Z): Used to describe the special moving coordinate system of the IMU device; its origin coincides with the sensor center of the IMU device.

[0026] (6)Camera coordinate system c(X, Y, Z): Used to describe the special moving coordinate system of the IMU device; its origin coincides with the photographic center of the camera device.

[0027] (7)Image space coordinate system S(x, y, z): To describe the position of the image point in space, it is necessary to convert the image plane rectangular coordinate system into an image space rectangular coordinate system. Take the projection center S as the coordinate origin of the image space rectangular coordinate system, the z-axis coincides with the photographic direction, and the upward direction is the positive direction of the Z-axis; the z-axis and the y-axis are respectively parallel to the corresponding axes of the image plane coordinates, with the same direction. The positive direction of the axis system is still determined according to the right-hand rule. In this coordinate system, the z coordinate of each image point is equal to -f, and the x and y coordinates are the image plane coordinates of the image point. Therefore, the image space coordinates of the image point are expressed as (x, y, -f). The image space coordinate system is determined by the spatial position of the photo. So the image space rectangular coordinate systems of each photo are independent of each other.

[0028] (8)Image plane coordinate system O(x, y): The scanning coordinate system is also called the image coordinate system or the image plane coordinate system. Taking the center of the CCD image plane as the coordinate origin, the X-axis and the Y-axis are respectively parallel to the two perpendicular sides of the image plane, and its coordinate values are represented by (x, y). Among them, Q(u, v) is the pixel coordinate system with the upper left corner as the origin (unit: pixel), and O(x, y) is generally the image plane rectangular coordinate system centered on the principal point of the image (unit: pixel).

[0029] (9) Photo Frame Coordinate System Q(x, y): The internal parameter calibration of the camera is one of the basic contents of photogrammetry work. Its essence is to determine the conversion parameters between the fiducial mark coordinate system and the scanning coordinate system. The fiducial mark coordinate system is an image coordinate system in pixels, also known as the pixel coordinate system. Taking the upper left vertex of the CCD image plane as the origin, the X-axis and Y-axis are respectively parallel to the X-axis and Y-axis of the image coordinate system, and its coordinate values are represented by (u, v).

[0030] For S3, the specific conversion order of coordinates is as follows: Convert from the geodetic coordinate system G(B, L, H) to the projection coordinate system W(x, y, h); Convert from the projection coordinate system W to the local tangent coordinate system L(E, N, U); Convert from the local tangent coordinate system L to the RTK device coordinate r(X, Y, Z); Convert from the RTK device coordinate r to the IMU device coordinate i(X, Y, Z); Convert from the IMU device coordinate i to the camera coordinate c(X, Y, Z); Convert from the camera coordinate c to the image space coordinate S(x, y, z); Convert from the image space coordinate S to the image plane coordinate O(x, y); Add distortion parameters to compensate for the influence of lens distortion to obtain the photo frame coordinate Q(x, y).

[0031] The specific conversion process of the design objective is as follows: S31. In the process of converting from the geodetic coordinate system G to the projection coordinate system W, the RTK coordinate G1(B, L, H) of the RTK device phase center is obtained through projection calculation to get the coordinate W1(x, y, h) in the local projection coordinate system, and the geodetic coordinate G2(B, L, H) of the target point is obtained through projection calculation to get the coordinate W2(x, y, h) in the local projection coordinate system; S32. In the process of converting from the projection coordinate system W to the local tangent coordinate system L, according to the RTK device projection coordinate and the projection method, calculate the rotation and translation conversion relationship between the projection coordinate system W and the local tangent coordinate system L, that is and ; S33. In the process of converting from the local tangent coordinate system L to the RTK device coordinate system r, set the attitude angles roll(r), pitch(p) and yaw(h) of the RTK device, and obtain the rotation conversion relationship between the r system and the L system through the rotation matrix calculation, that is . . ; The calculation formula of the rotation matrix is as follows: ; 。

[0032] S34. During the process of converting from the device coordinate system r to the IMU coordinate system i, the rotation and translation transformation relationships between the IMU device and the RTK device are obtained through IMU calibration, that is and ; S35. During the process of converting from the IMU device coordinate i to the camera coordinate c, the external parameter rotation and translation transformation relationships between the camera coordinate system and the IMU device are obtained through camera external parameter calibration, that is and ; S36. The image space coordinate S is converted to the image plane coordinate O through the camera internal parameters c x 、c y 、f and according to the collinearity equation; S37. The image plane coordinate O is converted to the image point coordinate through the camera internal parameters cx, cy, f; S38. The distortion parameters k 1 、k 2 、k 3 、p 1 、p 2 are used to increase the distortion amount.

[0033] The target transformation formulas of S31 to S36 can be combined to obtain the coordinates of the target point 2 in the image space coordinate S as follows: ; The image plane coordinate is obtained through internal parameter conversion: ; Among them, u represents the pixel position along the horizontal direction (X-axis) of the image, and v represents the pixel position along the vertical direction (Y-axis); The radial formula is added as distortion: ; The tangential formula is added as distortion: ; Among them, k 1 、k 2 、k 3 are the quadratic term, quartic term, and sextic term distortions respectively, and p 1 、p 2 represent the two components of the tangential distortion respectively.

[0034] In actual AR layout, the designed coordinates of the target point may not have an elevation, or the designed elevation is generally not on the terrain surface. In this case, if there is no elevation, the elevation of the tip of the rod is usually used as the elevation of the target design point. If the difference between the designed point elevation and the tip of the rod exceeds a certain threshold, the elevation of the tip of the rod is also used as the elevation of the target point to calculate the AR layout image point coordinates. The reason for this is that the greater the error in the designed elevation, the greater the AR display error will be.

[0035] As Figure 1 shown, point A in the figure is the designed target point, point C is the AR image display position, and point B is the designed expected layout point. When the designed point is exactly on the ground surface, A, B, and C coincide, and the AR display is accurate. Usually within 1 meter, the display accuracy can reach within 5 cm.

[0036] As Figure 2 shown, when the designed point is below the ground surface, the image point calculated by the collinearity equation will be displayed at point C. At this time, if the gap between AB is larger, the display error BC will be larger.

[0037] As Figure 3 shown, when the designed point is above the ground surface, the image point calculated by the collinearity equation will be displayed at point C. At this time, if the gap between AB is larger, the display error BC will be larger.

[0038] To solve the problem that the larger the gap between AB, the larger the display error BC, a ranging module is added to the RTK device to real-time sense the actual ground surface height in the central area of the measurement image, thereby correcting the AR point display position and making the AR layout display more accurate.

[0039] A video AR layout device, comprising: An AR camera device for capturing videos of the real world and generating augmented reality views; As Figure 4 shown, the AR camera device includes a ranging module for real-time detecting the depth of the space in the central area of the screen and correcting the AR display point; A positioning module for obtaining RTK position and attitude information; A data processing module for calculating and processing the position information and the design data and executing a coordinate transformation algorithm; A display module for real-time displaying the position and information of the point to be laid out on the AR image.

[0040] An electronic device for video AR layout, comprising a processor and a memory. The memory stores machine-readable instructions executable by the processor. When the machine-readable instructions are executed, they are used to execute the video AR layout method.

[0041] A computer-readable storage medium stores a computer program thereon, and when the program is executed by a processor, the described video AR lofting method is implemented.

[0042] Working principle: First, use an RTK (Real-Time Kinematic) device to obtain position information with centimeter-level accuracy, and capture the attitude data of the device through a built-in IMU (Inertial Measurement Unit) sensor. This information provides the basis for subsequent coordinate conversions, ensuring the accurate positioning of virtual points in the real world.

[0043] Next, the system performs conversions between multiple coordinate systems, including the geodetic coordinate system, local projection coordinate system, topocentric coordinate system, RTK device coordinate system, IMU device coordinate system, camera coordinate system, etc. Through reasonable coordinate conversions, an accurate mapping from design coordinates to video image coordinates can be achieved.

[0044] Then, use a camera to collect the on-site video stream, and convert the design coordinates into positions in the video image through computer vision algorithms. The system will overlay and display the virtual points to be lofted in the video in real time to help the operator visually find the target position. To ensure the accuracy of the display, the system also adopts distortion correction parameters to eliminate the image distortion caused by the lens.

[0045] Finally, considering that the design points may not have accurate elevation information or there is a large difference between their elevations and the actual terrain surface, this solution introduces a ranging module to sense and measure the actual surface height in the central area of the measurement image in real time. Through the display screen and the image processing unit, real-time video feedback with virtual lofting points is provided to the user. The user can approach and finally locate the target point step by step according to the prompts on the screen to complete the precise lofting operation.

[0046] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0047] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention.

Claims

1. A video AR lofting method, characterized in that: The steps include: S1. Obtain high-precision position and attitude information of RTK equipment; S2, matching the position and attitude information of the RTK device with the design coordinates; S3, converting the design coordinates into corresponding coordinates in the AR image through conversion between multiple coordinate systems; S4. The target point to be staked out is displayed in real time in the video stream, and the position and angle of the stakeout device are adjusted according to the displayed target point.

2. A video AR lofting method according to claim 1, characterized in that: According to S3, the conversion order of the design coordinates is as follows: Convert from the geodetic coordinate system G (B, L, H) to the projected coordinate system W (x, y, h); From the projection coordinate system W to the station center coordinate system L (E, N, U); Convert from the station center coordinate system L to the RTK device coordinate system r (X, Y, Z); Convert from RTK device coordinates r to IMU device coordinates i (X, Y, Z); Convert from IMU device coordinates i to camera coordinates c (X, Y, Z); Convert from camera coordinates c to image space coordinates S (x, y, z); Convert from image space coordinates S to image plane coordinates O (x, y); The distortion parameters are added to compensate for the influence of lens distortion and the frame coordinates Q (x, y) are obtained.

3. A video AR lofting method according to claim 2, characterized in that: The conversion process of the design target is specifically as follows: S31. In the process of transferring from the geodetic coordinate system G to the projection coordinate system W, the RTK coordinates G1 (B, L, H) of the phase center of the RTK device are projected and calculated to obtain the coordinates W1 (x, y, h) in the local projection coordinate system, and the geodetic coordinates G2 (B, L, H) of the target point are projected and calculated to obtain the coordinates W2 (x, y, h) in the local projection coordinate system. S32, in the process of transferring from the projection coordinate system W to the station center coordinate system L, according to the projection coordinates of the RTK equipment and the projection method, the rotation and translation transformation relationship between the projection coordinate system W and the station center coordinate system L is calculated, that is, and ; S33, in the process of converting from the station center coordinate system L to the RTK device coordinate system r, set the attitude angles roll (r), pitch (p) and yaw (h) of the RTK device, and obtain the rotation transformation relationship between the r system and the L system through the rotation matrix calculation, that is, , , ; S34, in the process of converting from the device coordinate system r to the IMU coordinate system i, the rotation and translation transformation relationship between the IMU device and the RTK device is obtained through IMU calibration, that is, and ; S35, in the process of converting the IMU device coordinate i to the camera coordinate c, the extrinsic parameter rotation and translation transformation relationship between the camera coordinate system and the IMU device is obtained through the camera extrinsic parameter calibration, that is, and ; S36, image space coordinates S through the camera internal parameter c x 、c y , f and transform to image plane coordinates O according to the collinear equation; S37, the image plane coordinate O is converted to the image point coordinate through the camera internal parameters cx, cy, f; S38. Use distortion parameters k1, k2, k3, p1, and p2 to increase the distortion amount.

4. A video AR lofting method according to claim 3, characterized in that: As described in S33, the calculation formula of the rotation matrix is ​​as follows: ； 。 5. A video AR lofting method according to claim 4, characterized in that: The target conversion formulas of S31 to S36 can be combined to obtain the coordinates of the target point 2 in the image space coordinate S as follows: ; After the internal parameter transformation, the image plane coordinates are obtained: ; Among them, u represents the pixel position along the horizontal direction of the image, and v represents the pixel position along the vertical direction; Add the radial formula for distortion: ; Add the tangential formula for distortion: ; Among them, k1, k2, k3 are quadratic, quartic, and sextic distortions, respectively, and p1 and p2 represent two components of tangential distortion, respectively.

6. A video AR lofting method according to claim 5, characterized in that: If the target point design coordinates have no elevation, the rod tip elevation is used as the target design point elevation. If the difference between the design point elevation and the rod tip is higher than a certain threshold, the rod tip elevation is used as the target point to calculate the AR lofting image point coordinates.

7. A video AR placement device, characterized in that: include: AR camera devices that capture video of the real world and generate an augmented reality view; Positioning module, used to obtain RTK position and attitude information; A data processing module, used to calculate and process the position information and execute a coordinate conversion algorithm; The display module is used to display the position and information of the points to be staked out in real time on the AR image.

8. The video AR layout device according to claim 7, characterized in that: The AR camera device includes a ranging module for detecting the depth of the space in the center area of ​​the picture in real time and correcting the AR display point.

9. An electronic device for video AR projection, comprising a processor and a memory, characterized in that: The memory stores machine-readable instructions executable by a processor, and the machine-readable instructions are used to implement the video AR placement method according to any one of claims 1 to 6 when executed.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the video AR placement method according to any one of claims 1 to 6 is implemented.

Images