WO2021254324A1

WO2021254324A1 - Method and apparatus for acquiring display element information of tiled screen

Info

Publication number: WO2021254324A1
Application number: PCT/CN2021/100099
Authority: WO
Inventors: 石炳川
Original assignee: 京东方科技集团股份有限公司
Priority date: 2020-06-15
Filing date: 2021-06-15
Publication date: 2021-12-23
Also published as: CN111694534A

Abstract

Disclosed are a method and apparatus for acquiring spatial information of a display element of a tiled screen. The method comprises: display elements of a tiled screen respectively displaying a calibration image, wherein the calibration image comprises an identification code and at least one positioning label located at a preset position; collecting a tiled screen image including calibration images displayed by the display elements; and performing image identification on the tiled screen image to acquire identification codes displayed by the display elements and coordinates of the displayed positioning labels under an image coordinate system, and determining spatial information of the display elements according to the coordinates of the positioning labels displayed by the display elements under the image coordinate system.

Description

Method and device for acquiring display element information of splicing screen

Cross-references to related applications

This application claims the priority of Chinese patent application No. 202010540737.8 filed on June 15, 2020, the disclosure of which is incorporated herein by reference.

Technical field

This application relates to the field of display technology. More specifically, it relates to a method and device for acquiring spatial information of display elements of a splicing screen.

Background technique

At present, the existing splicing display technology mainly adopts matrix splicing, using multiple rectangular display elements of the same model (meaning the same size) to be spliced into a large-size rectangular splicing screen. In the existing splicing display technology, each display element has high installation and positioning accuracy, and the size of the seam between the display elements is strictly controlled. Therefore, the video signal can be divided based on the equal division mode of rectangular splicing. Since the video inputs of the display elements are independent of each other, the overall display control of the splicing screen is realized by the splicing controller. The main function of the splicing controller is to divide the input overall video signal into the regional video signals corresponding to each display element. The main basis for completing this process is the recognition and positioning results of each display element. The positioning, installation and signal control of the existing matrix splicing technology all require strict and professional design, which greatly limits the user's design space.

As the splicing display technology is more widely used in exhibitions and other fields, users have higher requirements for the flexibility of splicing display, for example: non-rectangular splicing screens need to be arranged; each display element no longer has an alignment relationship but It can be rotated; the display element models are diversified, and the display elements of different shapes and sizes are used. These scenes greatly increase the complexity of the identification and positioning of the display elements, thereby increasing the complexity of the splicing screen configuration, which is difficult to achieve by the existing splicing display technology.

Summary of the invention

The first aspect of the present application provides a method for acquiring spatial information of display elements of a splicing screen, including:

Each display element of the splicing screen respectively displays a calibration image, and the calibration image includes an identification code and at least one positioning mark;

Acquiring a spliced screen image including the calibration image displayed by each display element;

Perform image recognition on the spliced screen image to obtain the identification code displayed by each display element and the coordinates of the displayed positioning mark in the image coordinate system, and according to the coordinates of the positioning mark displayed by each display element in the image coordinate system Determine the spatial information of each display element.

In an embodiment, the calibration image includes a plurality of positioning marks located at different positions.

In an embodiment, the plurality of positioning marks at different preset positions includes at least one main positioning mark with a different pattern from other positioning marks in the plurality of positioning marks.

In an embodiment, the plurality of positioning marks are uniformly distributed at the edge position of the display area of the display element.

In an embodiment, before the image recognition is performed on the spliced screen image, the method further includes:

Distortion correction is performed on the spliced screen image.

In an embodiment, the display planes of the display elements are parallel, and the imaging optical axis when collecting the spliced screen image is perpendicular to the display plane.

In an embodiment, the determining the spatial information of each display element according to the coordinates of the positioning mark displayed by each display element in the image coordinate system includes:

Performing perspective transformation correction on the spliced screen image to determine the coordinates of the positioning marks displayed by each display element in the world coordinate system according to the coordinates of the positioning marks displayed by each display element in the image coordinate system;

The spatial information of each display element is determined according to the coordinates of the positioning mark displayed by each display element in the world coordinate system.

In an embodiment, the performing perspective transformation correction on the spliced screen image to determine the coordinates of the positioning mark displayed by each display element in the world coordinate system according to the coordinates of the positioning mark displayed by each display element in the image coordinate system includes :

Select a display element as a reference display element, set a positioning mark displayed by the reference display element as the origin of the world coordinate system, and set the display plane of the reference display element to be a plane formed by the X axis and the Y axis of the world coordinate system;

Determine the coordinates of the positioning mark displayed by the reference display element in the world coordinate system according to the position of the positioning mark displayed by the reference display element and the actual physical size of the reference display element, and according to the positioning displayed by the reference display element Mark the coordinates in the image coordinate system and the coordinates in the world coordinate system to determine the homography matrix;

According to the homography matrix, the coordinates of the positioning marks displayed by each display element in the image coordinate system are transformed into the coordinates in the world coordinate system.

In an embodiment, the spatial information of the display element includes: the rotation angle information of the display element and the position of the frame of the display element.

In an embodiment, the method further includes: storing the displayed identification code of each display element, the coordinates of the displayed positioning mark in the world coordinate system, the rotation angle, and the position of the frame in the data table.

In an embodiment, the identification code is used to distinguish each display element.

In an embodiment, the identification code includes a barcode or a two-dimensional code.

In an embodiment, the calibration image includes an identification code located in the middle of the calibration image and four positioning marks located around the identification code.

In an embodiment, the calibration image has a rectangular shape, and the four positioning marks are respectively located at four vertices of the rectangular shape.

In an embodiment, the coordinates of the displayed positioning mark in the image coordinate system are determined based on the pixel position of the positioning mark in the stitched image.

A second aspect of the present application provides a device for acquiring spatial information of display elements of a splicing screen, which is used to implement the method provided in the first aspect of the present application. The device includes a processor, an image collector, and a memory.

The image collector is used to collect a spliced screen image including the calibration image displayed by each display element when each display element of the spliced screen displays the calibration image, wherein the calibration image includes an identification code and at least one positioning mark; and

The processor is used to perform image recognition on the splicing screen image to obtain the identification code displayed by each display element and the coordinates of the displayed positioning mark in the image coordinate system, and according to the positioning mark displayed by each display element in the image coordinate system The coordinates below determine the spatial information of each display element.

In an embodiment, the processor is further configured to perform distortion correction on the spliced screen image collected by the image collector.

In an embodiment, distortion correction is performed on the spliced screen image according to the calibration result of the image collector.

Description of the drawings

The specific implementation manners of the present application will be described in further detail below in conjunction with the accompanying drawings.

FIG. 1 shows a schematic flowchart of a method for acquiring spatial information of display elements of a splicing screen provided by an embodiment of the present application.

Figure 2 shows a schematic diagram of a calibration image.

FIG. 3 shows a schematic diagram of a spliced screen image collected when the method for obtaining display element information of a spliced screen provided by an embodiment of the present application is applied to a common spliced screen.

FIG. 4 shows a schematic diagram of a spliced screen image collected when the method for acquiring display element information of a spliced screen provided by an embodiment of the present application is applied to a special-shaped spliced screen.

FIG. 5 shows a schematic structural diagram of a device for acquiring spatial information of display elements of a splicing screen provided by an embodiment of the present application.

detailed description

In order to explain the application more clearly, the application will be further explained below in conjunction with embodiments and drawings. Similar components in the drawings are denoted by the same reference numerals. Those skilled in the art should understand that the content described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of this application.

As shown in FIG. 1, an embodiment of the present application provides a method for obtaining spatial information of display elements of a splicing screen, including steps S10 to S30.

In an embodiment, the display element may be various display screens or display modules to be spliced.

In step S10, each display element of the splicing screen respectively displays a calibration image, and the calibration image includes an identification code and at least one positioning mark located at a preset position.

In some embodiments, the calibration image includes a plurality of positioning marks located at different preset positions. The more positioning marks, the more accurate the subsequent positioning of the display element can be guaranteed.

In some embodiments, the plurality of positioning marks at different preset positions includes at least one main positioning mark with a different shape from other positioning marks in the plurality of positioning marks. As a result, the accuracy and efficiency of the identification and positioning of the display elements can be improved, and errors in identification and positioning can be avoided when the display elements are relatively close or even partially overlapped.

In some embodiments, the multiple positioning marks are evenly distributed at the edge of the display area of the display element. The positioning marks are evenly distributed at the edge of the display area to facilitate the accuracy of the positioning of the display element.

For example, the display element is a rectangular display element, and the displayed calibration image is, for example, the rectangular image shown in FIG. 2. In an embodiment, the rectangular image includes a barcode located in the middle of the rectangular image and four positioning marks located at the four corners of the rectangular image. In the embodiment, the positioning mark at the upper left corner of the rectangular image is used as the main positioning mark, which is different in shape or pattern from the remaining three positioning marks. Suppose the height of the rectangular display element is h, the width is w, and the vertex of the upper left corner of the rectangular display element is the origin, as shown in Figure 2. When the rectangular display element displays the calibration image on the full screen, the preset positions of the four positioning marks are: the coordinates of the positioning mark in the upper left corner are (x ₀ , y ₀ ), and the coordinates of the positioning mark in the lower left corner are (x ₃ , y ₃ ), The coordinates of the positioning mark in the upper right corner are (x ₁ , y ₁ ), and the coordinates of the positioning mark in the lower right corner are (x ₂ , y ₂ ), where x ₀ ＝x ₃ ＝0.15w, x ₁ ＝x ₂ =0.85w, y ₀ =y ₁ =0.15h, y ₂ =y ₃ =0.85h.

For another example, the calibration image displayed by the rectangular display element may also include only one positioning mark, or more positioning marks than four. It is understandable that no matter how many positioning marks are included in the calibration image, each positioning mark has a preset position, or in other words, the display position of each positioning mark should be known.

For another example, the identification code may also be of other types, such as a two-dimensional code, etc., as long as the display element can be uniquely identified.

For the calibration image displayed by each display element, for example, when the display element is shipped from the factory, a calibration image containing a unique barcode and four positioning marks is generated according to the unique serial number of the display element, and the calibration image is stored in the storage space of the display element . When each display element of the splicing screen is required to respectively display the calibration image, the control signal is sent to the control interface of each display element, so that each display element displays the stored calibration image on the full screen.

In this embodiment, the display element may be a rectangular display element, and the splicing screen formed by splicing a plurality of rectangular display elements may be a rectangular splicing screen as shown in FIG. 3 or a special-shaped splicing screen as shown in FIG. 4. The display element may also be a non-rectangular display element, and the spliced screen is not limited to a rectangular spliced screen. The display elements in the spliced screen may be of different sizes and shapes. The shape of the display element is various shapes such as a circle, a trapezoid, etc. Taking a circle as an example, the position of the main positioning mark in the calibration image displayed by the circular display element can be preset at a position close to the left end point on the horizontal diameter. Display elements of different shapes and sizes that can be arbitrarily selected according to the needs of the scene form a splicing screen.

In step S20, a spliced screen image including the calibration image displayed by each display element is collected.

In a specific example, the image collector (such as a CCD camera) used to collect the spliced screen image containing the calibration image displayed by each display element should have sufficient field of view and resolution to ensure that all display elements can be covered during collection. The displayed calibration image, and the calibration image displayed by each display element in the collected splicing screen image is sufficiently clear. For example, the image collector uses a small-distortion fixed-focus lens to prevent changes in lens parameters from affecting subsequent image processing. The image collector needs to be calibrated to determine the focal length, distortion coefficient and other parameters before image acquisition.

In some embodiments, the display planes of the display elements are parallel, and the imaging optical axis when the spliced screen image is collected is perpendicular to the display plane. In the embodiment, the display plane of each display element is located in the same plane.

Although this embodiment is used as an application solution for the special-shaped splicing screen, it no longer limits the translation and rotation of each display element, but in order to ensure the accuracy of subsequent recognition and positioning of the display element, it is preferable to set the display plane of each display element to be parallel. In this way, Collecting spliced screen images when the imaging optical axis is perpendicular to the display plane of each display element can guarantee accuracy.

In step S30, image recognition is performed on the spliced screen image to obtain the identification code displayed by each display element and the coordinates of the displayed positioning mark in the image coordinate system, and according to the positioning mark displayed by each display element in the image The coordinates in the coordinate system determine the spatial information of each display element.

In an embodiment, the coordinates of the positioning mark in the image coordinate system may be determined based on the pixel position of the positioning mark in the spliced screen image.

In some embodiments, before the image recognition is performed on the spliced screen image, the method further includes:

Distortion correction is performed on the spliced screen image.

In an embodiment, distortion correction may be performed on the spliced screen image according to the calibration result of the image collector before image acquisition, so as to eliminate the radial distortion, tangential distortion, etc. caused by the parameters of the image collector.

In an embodiment, performing image recognition on the spliced screen image to obtain the identification code displayed by each display element and the coordinates of the displayed positioning mark in the image coordinate system includes the following processing.

As shown in Figures 3 and 4, since the spliced screen image includes barcodes displayed by multiple display elements, multiple barcodes need to be extracted separately.

For example, a pre-trained barcode detection network such as a deep learning network is used to detect barcode features in the spliced screen image to obtain multiple barcode regions.

Cut out the sub-images of each barcode area and input the barcode reading program or barcode reader to obtain the serial number of each display element.

Identify the positioning marks on the periphery of each barcode area, obtain the coordinates p ₀ , p ₁ , p ₂ , and p ₃ of the four positioning marks around each barcode area in the image coordinate system, and determine the main position based on the shape difference of the positioning marks The positioning point can be used to determine which of the four positioning marks are top left, bottom left, top right, and bottom right, where the origin of the image coordinate system can be set as the top left corner of the spliced screen image, for example.

Recording the coordinates of each display element, and four serial number of a given mark is displayed in the image coordinate system, and for example, data stored in the list L _1.

In some embodiments, the determining the spatial information of each display element according to the coordinates of the positioning mark displayed by each display element in the image coordinate system includes:

In some embodiments, the perspective transformation correction is performed on the spliced screen image to determine the coordinates of the positioning marks displayed by each display element in the world coordinate system according to the coordinates of the positioning marks displayed by each display element in the image coordinate system include:

Determine the coordinates of the positioning mark displayed by the reference display element in the world coordinate system according to the preset position of the positioning mark displayed by the reference display element and the actual physical size of the reference display element, and display it according to the reference display element The coordinates of the positioning mark in the image coordinate system and the coordinates in the world coordinate system are used to determine the homography matrix;

In some embodiments, the spatial information of the display element includes: the rotation angle of the display element and the position of the frame of the display element.

Since it is difficult to ensure that the imaging optical axis is absolutely perpendicular to the display plane of each display element during image acquisition, it is difficult to avoid tilt during acquisition. Therefore, the calibration image displayed by each display element contained in the spliced screen image may be captured by the image The external parameters of the detector cause a certain degree of perspective transformation. Therefore, there may be a certain deviation in positioning directly using the coordinates of the positioning mark displayed by the display element in the image coordinate system. At this time, the correction of the perspective transformation can be performed to ensure the accuracy of the positioning of the display element.

In order to correct the perspective transformation, select display element C as the reference display element, for example, select the display element in the upper left corner of all display elements as the reference display element, and set a positioning mark of display element C, for example, the upper left corner positioning mark as the origin of the world coordinate system , The display screen of the display element C is taken as the plane (z=0 plane) formed by the X axis and the Y axis of the world coordinate system. According to the preset positions of the four positioning marks displayed by the display element C in the calibration image and the actual physical size of the display element C, determine the coordinates w _c0 , w _c1 , w of the four positioning marks displayed by the display element C in the world coordinates _c2 , w _c3 . _{Combining the coordinates p c0} , p _c1 , p _c2 , and p _c3 of the four positioning marks displayed by the display element C obtained above in the image coordinate system, the homography matrix H of the perspective transformation is obtained.

For example, the homography transformation is defined as the projection mapping from one plane to another. The homography matrix has the following form:

The homography matrix can be obtained by solving the four pairs of corresponding coordinate points. In this example, the coordinates p _c0 , p _c1 , p _c2 , and p _c3 of the four positioning marks displayed by the display element C in the image coordinate system correspond to the world coordinate system The coordinates of w _c0 , w _c1 , w _c2 , w _c3 .

In the image coordinate system, p _c0 = (x ₀ `,y ₀ `), p _c1 = (x ₁ `,y ₁ `), p _c2 = (x ₂ `,y ₂ `), p _c3 = (x ₃ `,y ₃ `);

In the world coordinate system: the height of the rectangular display element is h, the width is w, and the preset positions of the four positioning marks are obtained: the coordinates of the positioning mark in the upper left corner are (x ₀ , y ₀ ), and the coordinates of the positioning mark in the lower left corner Is (x ₃ , y ₃ ), the coordinates of the positioning mark in the upper right corner are (x ₁ , y ₁ ), and the coordinates of the positioning mark in the lower right corner are (x ₂ , y ₂ ), where x ₀ =x ₃ =0.15w, x ₁ =x ₂ =0.85w, y ₀ =y ₁ =0.15h, y ₂ =y ₃ =0.85h, we can see that w _c0 =(0.15w,0.15h), w _c1 =(0.85w,0.15h), w _c2 = (0.85w, 0.85h), w _c3 = (0.15w, 0.85h);

Then, the four pairs of corresponding coordinate points have the following correspondence:

According to the above corresponding relationship, the homography matrix H can be solved.

After the homography matrix H is determined, the coordinates of the positioning marks displayed by each display element in the image coordinate system are transformed into the coordinates in the world coordinate system based on the homography matrix H.

For example: when the homography matrix H has been determined, any point (x`,y`) in the spliced screen image can be converted to coordinates (w _x ,w _y ) in the world coordinate system:

After determining the coordinates of the four positioning marks displayed by each display element in the world coordinate system, the position of the frame of the display element and the rotation angle around the Z axis of the world coordinate system can be calculated based on it. In the embodiment, the position of the frame of the display element and the rotation angle around the Z axis of the world coordinate system can be calculated from the relative position relationship of the coordinates of the four positioning marks in the world coordinate system. It is understandable that if the image is calibrated Only one positioning mark is included, and the rotation angle information and the position of the frame can also be calculated according to the relative position relationship between it and the identification code at the preset position.

So far, the serial number of each display element, the coordinates of the upper left corner positioning mark in the world coordinate system, the position of the frame and the rotation angle around the Z axis of the world coordinate system have been obtained, and the identification and recognition of each display element in the splicing screen has been achieved. positioning, according to these data, that can automate the configuration fight control system, may be used when information is stored in the data table L _1, for subsequent configuration of the mosaic screen.

As shown in FIG. 5, another embodiment of the present application provides a device for acquiring spatial information of display elements of a splicing screen, including: an image collector 100 and an information acquiring element 300.

The image collector 100 is configured to collect a spliced screen image including the calibration image displayed by each display element when each display element of the spliced screen displays the calibration image. In an embodiment, the calibration image includes an identification code and at least one positioning mark at a preset position;

The information acquisition element 300 is used to perform image recognition on the spliced screen image to obtain the identification code displayed by each display element and the coordinates of the displayed positioning mark in the image coordinate system, and according to the positioning mark displayed by each display element The coordinates in the image coordinate system determine the spatial information of each display element.

In some embodiments, the calibration image includes a plurality of positioning marks located at different preset positions.

In some embodiments, the plurality of positioning marks at different preset positions includes at least one main positioning mark with a different shape from other positioning marks in the plurality of positioning marks.

In some embodiments, the multiple positioning marks are evenly distributed at the edge of the display area of the display element.

In some embodiments, as shown in FIG. 5, the device further includes a distortion correction element 200 for performing distortion correction on the spliced screen image collected by the image collector 100.

In a specific example, the distortion correction element 200 and the information acquisition element 300 may be arranged in the splicing controller, and the image collector 100 and the distortion correction element 200 communicate through a network, and the network may include various connection types, such as wired and wireless. Communication link or fiber optic cable, etc.

In an embodiment, the processor may be used as the distortion correction element 200 and the information acquisition element 300.

In some embodiments, the display planes of the display elements are parallel, and the imaging optical axis when the image collector 100 collects the spliced screen image is perpendicular to the display plane.

In some embodiments, the information acquisition element 300 for determining the spatial information of each display element according to the coordinates of the positioning marks displayed by the display elements in the image coordinate system includes: performing perspective transformation on the spliced screen image Correction to determine the coordinates of the positioning mark displayed by each display element in the world coordinate system according to the coordinates of the positioning mark displayed by each display element in the image coordinate system; according to the positioning mark displayed by each display element in the world coordinate system The coordinates determine the spatial information of each display element.

In some embodiments, the information acquisition element 300 is used to perform perspective transformation correction on the spliced screen image to determine the positioning mark displayed by each display element according to the coordinates of the positioning mark displayed by each display element in the image coordinate system The coordinates in the world coordinate system include: selecting a display element as the reference display element, setting a positioning mark displayed by the reference display element as the origin of the world coordinate system, and setting the display plane of the reference display element to the world coordinate system The plane formed by the X axis and the Y axis;

In some embodiments, the spatial information of the display element includes: the rotation angle of the display element and the position of the frame on the display element.

In some embodiments, as shown in FIG. 5, the device further includes a storage element 400 for storing the displayed identification code of each display element, the coordinates and rotation of the displayed positioning mark in the world coordinate system in the form of a data table. Angle and border position. In an embodiment, the storage element 400 may be a memory.

It should be noted that the principle and work flow of the device for acquiring spatial information of display elements of the splicing screen provided in this embodiment are similar to the method of acquiring spatial information of the display elements of the splicing screen. For related details, please refer to the above description. No longer.

In the description of this application, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", etc. are based on the orientation or positional relationship shown in the drawings, which is only for the convenience of describing the application and simplifying the description. It does not indicate or imply that the pointed device or element must have a specific orientation, be configured and operated in a specific orientation, and therefore cannot be understood as a limitation of the present application. Unless otherwise clearly specified and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, It can also be an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the internal communication between two components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

It should also be noted that in the description of this application, 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 these There is any such actual relationship or sequence between entities or operations. Moreover, the terms "including", "including" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also those that are not explicitly listed Other elements of, or also include elements inherent to this process, method, article or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, article, or equipment that includes the element.

Obviously, the above-mentioned embodiments of this application are merely examples to clearly illustrate this application, and are not meant to limit the implementation of this application. For those of ordinary skill in the art, they can also do on the basis of the above description. Other changes or changes in different forms cannot be exhaustively listed here. Any obvious changes or changes derived from the technical solutions of this application are still within the scope of protection of this application.

Claims

A method for obtaining spatial information of display elements of a splicing screen, including:

Each display element of the splicing screen respectively displays a calibration image, and the calibration image includes an identification code and at least one positioning mark;

Acquiring a spliced screen image including the calibration image displayed by each display element;

Perform image recognition on the spliced screen image to obtain the identification code displayed by each display element and the coordinates of the displayed positioning mark in the image coordinate system, and according to the coordinates of the positioning mark displayed by each display element in the image coordinate system Determine the spatial information of each display element.
The method according to claim 1, wherein the calibration image includes a plurality of positioning marks located at different positions.
The method according to claim 2, wherein the plurality of positioning marks includes at least one main positioning mark having a different pattern from other positioning marks in the plurality of positioning marks.
3. The method according to claim 3, wherein the plurality of positioning marks are uniformly distributed at the edge positions of the display area of the display element.
The method according to claim 1, wherein, before said performing image recognition on the spliced screen image, the method further comprises:

Distortion correction is performed on the spliced screen image.
The method according to claim 1, wherein the display planes of the display elements are parallel, and the imaging optical axis when the spliced screen image is collected is perpendicular to the display plane.
The method according to claim 6, wherein the determining the spatial information of each display element according to the coordinates of the positioning marks displayed by the display elements in the image coordinate system comprises:

Perform perspective transformation correction on the spliced screen image to determine the coordinates of the positioning marks displayed by each display element in the world coordinate system according to the coordinates of the positioning marks displayed by each display element in the image coordinate system;

The spatial information of each display element is determined according to the coordinates of the positioning mark displayed by each display element in the world coordinate system.
The method according to claim 7, wherein the perspective transformation correction is performed on the spliced screen image to determine that the positioning mark displayed by each display element is in the world according to the coordinates of the positioning mark displayed by each display element in the image coordinate system. The coordinates in the coordinate system include:

Select a display element as a reference display element, set a positioning mark displayed by the reference display element as the origin of the world coordinate system, and set the display plane of the reference display element to be a plane formed by the X axis and the Y axis of the world coordinate system;

Determine the coordinates of the positioning mark displayed by the reference display element in the world coordinate system according to the position of the positioning mark displayed by the reference display element and the actual physical size of the reference display element, and according to the positioning displayed by the reference display element Mark the coordinates in the image coordinate system and the coordinates in the world coordinate system to determine the homography matrix;

According to the homography matrix, the coordinates of the positioning marks displayed by each display element in the image coordinate system are transformed into the coordinates in the world coordinate system.
The method according to claim 7 or 8, wherein the spatial information of the display element includes: the rotation angle of the display element and the position of the frame of the display element.
The method according to claim 9, further comprising: storing the displayed identification code of each display element, the coordinates of the displayed positioning mark in the world coordinate system, the rotation angle and the position of the frame in a data table.
The method according to claim 10, wherein the identification code is used to distinguish each display element.
The method according to claim 11, wherein the identification code comprises a barcode or a two-dimensional code.
The method according to claim 1, wherein the calibration image includes an identification code located in the middle of the calibration image and four positioning marks located around the identification code.
The method according to claim 13, wherein the calibration image has a rectangular shape, and the four positioning marks are respectively located at four vertices of the rectangular shape.
The method according to claim 11, wherein the coordinates of the displayed positioning mark in the image coordinate system are determined based on the pixel position of the positioning mark in the stitched image.
A device for acquiring spatial information of display elements of a splicing screen, including a processor and an image collector, wherein

The image collector is configured to collect a spliced screen image including the calibration image displayed by each display element when each display element of the spliced screen displays a calibration image, wherein the calibration image includes an identification code and at least one positioning mark; and

The processor is configured to perform image recognition on the spliced screen image to obtain the identification code displayed by each display element and the coordinates of the displayed positioning mark in the image coordinate system, and according to the positioning mark displayed by each display element in the image The coordinates in the coordinate system determine the spatial information of each display element.
The device of claim 16, wherein:

The processor is also used to perform distortion correction on the spliced screen image collected by the image collector.
18. The device according to claim 17, wherein distortion correction is performed on the spliced screen image according to a calibration result of the image collector.
The apparatus according to claim 16, wherein the calibration image includes a plurality of positioning marks located at different positions.
The device according to claim 19, wherein the plurality of positioning marks comprise at least one main positioning mark having a different pattern from other positioning marks of the plurality of positioning marks.