A method and system for associating different physical coordinate systems

Abstract

Provided are a method, system, electronic device, and readable medium for associating different physical coordinate systems, wherein the method comprises: establishing a three-dimensional scene model comprising at least a first scene and a second scene, the three-dimensional scene model having a model coordinate system; determining a conversion relationship between a first physical coordinate system where the first scene is located and the model coordinate system, and a conversion relationship between a second physical coordinate system where the second scene is located and the model coordinate system; and based on the conversion relationship between the first physical coordinate system and the model coordinate system, and the conversion relationship between the second physical coordinate system and the model coordinate system, associating the first physical coordinate system with the second physical coordinate system, so as to quickly and accurately complete automatic alignment or association between the two physical coordinate systems.

Description

Technical Field

[0001] The present invention relates to the field of computer vision, and in particular to a method, system, electronic device and storage medium for associating different physical coordinate systems. Background Art

[0002] The statements in this section are merely intended to provide background information related to the technical solution of the present application to aid understanding, and they do not necessarily constitute prior art with respect to the technical solution of the present application.

[0003] Different physical spaces or real-world scenes have different physical coordinate systems (e.g., scene coordinate systems or coordinate systems established with an object in the scene as the origin). Currently, the association or registration of coordinate systems in different physical spaces is generally achieved using manual annotation and mapping methods, resulting in low efficiency and low accuracy.

[0004] Therefore, there is an urgent need for a method and system that can automatically associate different physical coordinate systems. Summary of the Invention

[0005] One aspect of the present invention relates to a method for associating different physical coordinate systems, comprising: establishing a three-dimensional scene model including at least a first scene and a second scene, the three-dimensional scene model having a model coordinate system; determining a conversion relationship between a first physical coordinate system where the first scene is located and the model coordinate system; determining a conversion relationship between a second physical coordinate system where the second scene is located and the model coordinate system; and associating the first physical coordinate system with the second physical coordinate system based on the conversion relationship between the first physical coordinate system and the model coordinate system, and the conversion relationship between the second physical coordinate system and the model coordinate system.

[0006] In one embodiment, a first visual mark is set in the first scene; and / or a second visual mark is set in the second scene.

[0007] In one embodiment, the first scene and the second scene overlap, are adjacent, or are non-adjacent.

[0008] In one embodiment, the establishment of a three-dimensional scene model including at least a first scene and a second scene includes: acquiring a plurality of two-dimensional images containing the first visual sign or the second visual sign through a device, and using the plurality of two-dimensional images to establish a three-dimensional scene model of the first scene or a three-dimensional scene model of the second scene.

[0009] In one embodiment, determining the conversion relationship between the first physical coordinate system where the first scene is located and the model coordinate system includes: selecting at least three two-dimensional images from the multiple two-dimensional images, and obtaining the position information of the devices corresponding to each of the selected two-dimensional images in the first physical coordinate system; for each selected two-dimensional image, determining the position information of the device corresponding to it in the model coordinate system; based on the position information of the devices corresponding to each determined two-dimensional image in the first physical coordinate system and the model coordinate system, determining the conversion relationship between the first physical coordinate system and the model coordinate system.

[0010] In one embodiment, for each selected two-dimensional image, determining the position information of the corresponding device in the model coordinate system includes: selecting at least four feature points from the two-dimensional image, and determining the model coordinates of each feature point in the model coordinate system and the pixel coordinates of the feature point in the two-dimensional image; and calculating the position information of the device corresponding to the two-dimensional image in the model coordinate system based on the model coordinates and the pixel coordinates of each selected feature point.

[0011] In one embodiment, the device positions corresponding to the selected two-dimensional images are not colinear and / or coplanar.

[0012] In one embodiment, acquiring the position information of the device corresponding to each of the selected two-dimensional images in the first physical coordinate system includes: determining the position information of the device in the first physical coordinate system based on the first visual mark.

[0013] In one embodiment, determining the position information of the device in the first physical coordinate system based on the first visual marker includes: collecting a two-dimensional image containing the first visual marker by the device and obtaining identification information of the first visual marker; analyzing the two-dimensional image to determine the position information of the device relative to the first visual marker; and determining the position information of the device in the first physical coordinate system at least partially based on the identification information of the first visual marker and the position information of the device relative to the first visual marker.

[0014] In one embodiment, associating the first physical coordinate system with the second physical coordinate system includes: determining a conversion relationship between the first physical coordinate system and the second physical coordinate system.

[0015] In one embodiment, the use of the multiple two-dimensional images to establish a three-dimensional scene model of the first scene or the three-dimensional scene model of the second scene includes: determining the posture information of the device when shooting the two-dimensional image through imaging of the first visual mark or the second visual mark in the two-dimensional image.

[0016] On the other hand, the present invention provides a system for associating different physical coordinate systems, including: a three-dimensional scene model establishment module, used to establish a three-dimensional scene model including at least a first scene and a second scene, the three-dimensional scene model having a model coordinate system; a transformation relationship determination module, used to determine the transformation relationship between a first physical coordinate system where the first scene is located and the model coordinate system, and to determine the transformation relationship between a second physical coordinate system where the second scene is located and the model coordinate system; and a physical coordinate system association module, used to associate the first physical coordinate system with the second physical coordinate system based on the transformation relationship between the first physical coordinate system and the model coordinate system, and the transformation relationship between the second physical coordinate system and the model coordinate system.

[0017] In one embodiment, a first visual marker is provided in the first scene; and / or a second visual marker is provided in the second scene. Another aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can be used to implement any of the above methods.

[0018] Another aspect of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it can be used to implement any of the above methods.

[0019] The present invention can automatically align or associate the two physical coordinate systems quickly and accurately by using a three-dimensional scene model coordinate system associated with both physical coordinate systems, and therefore has good applicability and flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The embodiments of the present invention are further described below with reference to the accompanying drawings, in which:

[0021] Figure 1 A method for associating different physical coordinate systems according to an embodiment of the present invention is shown;

[0022] Figure 2A An exemplary light tag is shown;

[0023] Figure 2B An exemplary optical tag network is shown;

[0024] Figure 3 A schematic diagram showing a case where no light tag is provided in a third scene between a first scene and a second scene according to an embodiment of the present invention;

[0025] Figure 4 A method for determining a conversion relationship between a first physical coordinate system and a model coordinate system of a three-dimensional scene according to an embodiment of the present invention is shown;

[0026] Figure 5 A schematic diagram showing the camera poses corresponding to each marked two-dimensional image in an example three-dimensional scene;

[0027] Figure 6 A functional module block diagram of a system for associating different physical coordinate systems according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below through specific embodiments in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0029] With the development of science and technology, three-dimensional scene models have been widely used in the field of computer vision. In some applications that use computer vision for positioning or navigation, the real-time positioning and navigation of the moving target in the three-dimensional scene is often achieved by comparing and matching the two-dimensional image captured by the moving target (for example, a robot equipped with a camera) with a pre-established three-dimensional scene model. The three-dimensional scene model itself has its own coordinate system (hereinafter referred to as the model coordinate system), and the physical space or real scene corresponding to the three-dimensional scene model also has a coordinate system (hereinafter referred to as the physical coordinate system). By converting the physical coordinate system into the model coordinate system (for example, displacement, scaling, and rotation), the positioning or navigation of the moving target is achieved.

[0030] In the field of computer vision, three-dimensional scene models are usually constructed based on multiple two-dimensional images of the scene. One way to reconstruct a three-dimensional scene model using two-dimensional images is to use a dedicated camera that can accurately calibrate its own position and posture (hereinafter collectively referred to as pose information) to capture a large number of two-dimensional images of the scene and record the pose information of the dedicated camera when each image is captured. Afterwards, the images can be spatially sorted based on this pose information and the three-dimensional scene can be reconstructed.

[0031] The applicant of this application also disclosed a scene reconstruction method based on two-dimensional images in another Chinese patent application NO.202010758289.9, in which at least one visual mark (for example, an optical communication device, a QR code, a graphic mark, etc.) is pre-arranged in the scene to be reconstructed, and the camera's posture information relative to the visual mark is determined by capturing a scene image including the visual mark and analyzing the scene image, and then the actual posture information of the imaging device when capturing the scene image is determined based on the posture information of the visual mark in the physical coordinate system, thereby spatially sorting multiple scene images based on the imaging device posture information associated with each scene image and establishing a three-dimensional scene model based on the sorted scene images.

[0032] Figure 1 FIG. 4 shows a method for associating different physical coordinate systems according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0033] S110: Establish a three-dimensional scene model including a first scene and a second scene.

[0034] The first scene and the second scene can be any scene or area in the physical world, such as a shopping mall, a building, an underground parking lot, a commercial district, an office, etc. A three-dimensional scene model including the first scene and the second scene can be created using any 3D reconstruction method. For example, a three-dimensional scene model can be constructed using multiple two-dimensional images.

[0035] In one embodiment, in order to establish a three-dimensional scene model, a visual marker can be pre-set in the first scene or the second scene, and a plurality of two-dimensional images including the visual marker can be captured by a device including an image acquisition device, and the position information of the device (hereinafter referred to as the "corresponding device") relative to the visual marker when the two-dimensional image was captured can be determined by analyzing each two-dimensional image, and then the position information of the device in the physical coordinate system can be determined based on the position information of the visual marker in the physical coordinate system, so that the plurality of two-dimensional images can be spatially sorted based on the device position information corresponding to each two-dimensional image, and a three-dimensional scene model of the scene can be established based on the sorted two-dimensional images. Wherein, the physical coordinate system can be a coordinate system with the visual marker as the origin, or it can be a scene coordinate system of the scene.

[0036] Visual signs include any signs that can be recognized by the human eye or electronic devices, which can have various forms. In some embodiments, visual signs can be used to convey information, and the information can be obtained by smart devices (such as mobile phones, smart glasses, etc.). For example, a visual sign can be an optical communication device that can emit coded light information, or a visual sign can be a graphic with coded information, such as a QR code (such as a QR code, a mini-program code), a barcode, etc. The position information of the visual sign in the physical coordinate system can be obtained through its identification information. The identification information of the visual sign can be, for example, any identification corresponding to the visual sign, for example, the number of the visual sign.

[0037] In one embodiment, an optical communication device can be used as a visual marker. An optical communication device is also referred to as an optical tag, and the two terms are used interchangeably herein. Optical tags can transmit information through various light-emitting methods. They have the advantages of long recognition distances and relaxed visible light requirements. Furthermore, the information transmitted by optical tags can change over time, providing large information capacity and flexible configuration capabilities.

[0038] An optical tag generally includes a controller and at least one light source. The controller can drive the light source through different driving modes to transmit different information. Figure 2A An exemplary light tag 200 is shown, which includes three light sources, namely a first light source 201, a second light source 202, and a third light source 203. The light tag 200 also includes a controller (in Figure 2A (not shown in the figure), which is used to select a corresponding driving mode for each light source according to the information to be transmitted. For example, under different driving modes, the controller can use different driving signals to control the light emission mode of the light source, so that when the light tag 200 is photographed using an image acquisition device (such as a camera), the imaging of the light source can present a different appearance (for example, different colors, patterns, brightness, etc.). By analyzing the imaging of the light sources in the light tag 200, the driving mode of each light source at the moment can be parsed, thereby parsing the information transmitted by the light tag 200 at the moment. It can be understood that Figure 2A By way of example only, a light tag may have Figure 2A The examples shown are different shapes and can have Figure 2A The examples shown have different numbers and / or different shapes of light sources.

[0039] In order to provide users with corresponding services based on light tags, each light tag can be configured to transmit an identification information (ID). Typically, a controller in the light tag drives a light source to transmit the identification information. An image acquisition device can capture images of the light tag to obtain one or more images containing the light tag, and analyze the imaging of the light tag (or each light source in the light tag) in the image to identify the identification information transmitted by the light tag. Afterwards, other information associated with the identification information can be obtained, such as the position information of the light tag corresponding to the identification information.

[0040] The information related to each optical tag can be stored in the server. In reality, a large number of optical tags can be constructed into an optical tag network. Figure 2BAn exemplary optical tag network is shown, comprising multiple optical tags and at least one server. The server may store identification information (ID) or other information for each optical tag, such as service information related to the optical tag, descriptive information or attribute information related to the optical tag, such as the optical tag's location information, model information, physical size information, physical shape information, posture or orientation information, etc. The optical tag may also have uniform or default physical size information and physical shape information, etc. A device may use the identification information of an identified optical tag to query the server for other information related to the optical tag. The location information of the optical tag may refer to the actual location of the optical tag in the physical world, which may be indicated by geographic coordinate information. The server may be a software program running on a computing device, a computing device, or a cluster consisting of multiple computing devices. The optical tag may be offline, that is, the optical tag does not need to communicate with the server. Of course, it will be understood that online optical tags capable of communicating with the server are also feasible.

[0041] In one embodiment, the 3D scene model of the first scene may be established first, and then the 3D scene model may be extended to the second scene, or vice versa. In another embodiment, the 3D scene model of the first scene and the 3D scene model of the second scene may also be established simultaneously.

[0042] In one embodiment, the first scene may overlap with, be adjacent to, or be non-adjacent to the second scene. When the first scene and the second scene are non-adjacent, a light tag may or may not be provided between the first scene and the second scene. In one embodiment, when no light tag is provided between the first scene and the second scene, an existing 3D reconstruction technology may be used to establish a three-dimensional scene model between the first scene and the second scene. In one embodiment, when no light tag is provided between the first scene and the second scene, a device having an image acquisition device may determine its initial posture information through the light tags in the first scene or the second scene, and track the posture changes of the device through the built-in sensor of the device, thereby determining the posture information of the device between the first scene and the second scene, and establishing a three-dimensional scene model between the first scene and the second scene through the image captured by the device and the corresponding device posture information.

[0043] Figure 3 FIG. 1 is a schematic diagram showing an embodiment of the present invention in which no light tag is set between the first scene and the second scene. Figure 3As shown, at least one first light tag a is set in the first scene A, at least one second light tag b is set in the second scene B, and no light tags are set between the first scene A and the second scene B. In this case, a 3D scene model of the first scene A can be established based on light tag a, and then a 3D model between the first scene A and the second scene B can be established using the above-mentioned method for scene reconstruction without light tags. Finally, a 3D scene model of the second scene B can be established based on light tag b. Alternatively, 3D models of the first scene A, the second scene B, and the scene between the first scene A and the second scene B can be established simultaneously, and the 3D scene models of these different scenes can be integrated to complete the establishment of a 3D model for a region.

[0044] S120: Determine a conversion relationship between a first physical coordinate system of the first scene and a model coordinate system of the three-dimensional scene.

[0045] Figure 4 FIG1 shows a method for determining the conversion relationship between the first physical coordinate system and the model coordinate system of the three-dimensional scene according to an embodiment of the present invention. Figure 4 As shown, the method includes:

[0046] S410 , selecting at least three two-dimensional images from a plurality of two-dimensional images used to establish a three-dimensional scene model, and obtaining position information of devices corresponding to each of the selected two-dimensional images in a first physical coordinate system.

[0047] As described above, in the process of constructing a three-dimensional scene model using multiple two-dimensional images, the position information of the shooting device corresponding to each two-dimensional image can be obtained. In one embodiment, a first light tag can be pre-set in a first scene, and multiple two-dimensional images of the first scene including the first light tag can be captured using a device. The position information of the corresponding device relative to the first light tag can be determined by analyzing each two-dimensional image. Based on the position information of the first light tag in the first physical coordinate system, the position information of the corresponding device in the first physical coordinate system can be determined.

[0048] In one embodiment, for the selected at least three two-dimensional images, the camera positions corresponding thereto are not collinear. In another embodiment, the camera positions corresponding to the selected two-dimensional images are neither collinear nor coplanar.

[0049] S420: For each selected two-dimensional image, determine the position information of the device corresponding thereto in the three-dimensional scene model coordinate system.

[0050] In one embodiment, for example, at least four feature points can be selected from a two-dimensional image, and the model coordinates of these feature points in the model coordinate system of the three-dimensional scene and the imaging positions (i.e., pixel coordinates) of these feature points in the two-dimensional image can be determined. The model coordinates of these feature points can be obtained by the established three-dimensional scene model, and the pixel coordinates of these feature points are, for example, the positions of these feature points in the two-dimensional coordinate system established with the point in the upper left corner of the image as the coordinate origin. Then, the pose information of the camera corresponding to the two-dimensional image is calculated based on the model coordinates and pixel coordinates of the selected feature points. For example, the PnP (Perspective-n-Point) algorithm can be used to solve the pose of the camera when the image was taken under the condition that the spatial positions of multiple points and their imaging positions on the image are known. Optionally, the BA (Bundle Adjustment) optimization algorithm can also be used at the same time to obtain a more accurate camera pose. In fact, for a three-dimensional scene model created based on multiple two-dimensional images, the above algorithm can be used to mark the position and pose of the camera corresponding to each two-dimensional image in the model coordinate system of the three-dimensional scene model. For example, Figure 5 The three-dimensional scene model shown in FIG. 1 , wherein the pyramid-shaped markers are used to represent the position and posture of the camera corresponding to each two-dimensional image in the model coordinate system of the scene.

[0051] S430: Determine a conversion relationship between the first physical coordinate system and the model coordinate system based on position information of devices corresponding to each selected two-dimensional image in the first physical coordinate system and the model coordinate system.

[0052] That is, the conversion relationship between the two coordinate systems is determined using the corresponding position relationship of the cameras corresponding to the determined two-dimensional images in the two coordinate systems.

[0053] In three-dimensional space, the transformation relationship between two coordinate systems includes displacement (translation), scaling (scaling), and rotation (rotation) between the two coordinate systems, each represented by three parameters, for a total of nine parameters. In other words, the transformation relationship between two coordinate systems in three-dimensional space can be represented by three displacement parameters, three scaling parameters, and three rotation parameters. Typically, to maintain consistency with the real scene, the scaling ratio of a three-dimensional scene model on three axes is the same, so there are a total of seven parameters (three displacement parameters, one scaling parameter, and three rotation parameters). The corresponding positional relationship of at least three points in the two coordinate systems (which cannot be collinear) is required to solve the transformation coefficients of the two coordinate systems (that is, at least three two-dimensional images are required, and the corresponding camera positions are not collinear). In the case of different scaling ratios, the corresponding positional relationship of at least four points is required, and they cannot be coplanar (that is, at least four two-dimensional images are required, and the corresponding camera positions are not coplanar). The specific method of using the known coordinate correspondence of at least three points in the two coordinate systems to solve the rotation, translation, and scaling parameters in the affine transformation matrix formula between the two coordinate systems belongs to the prior art and will not be elaborated here.

[0054] Through the above embodiments, for a three-dimensional scene model constructed using multiple two-dimensional images, the conversion relationship between the model coordinate system and the physical coordinate system of the three-dimensional scene model can be automatically determined simply and quickly, thereby achieving automatic alignment between the model coordinate system and the physical coordinate system.

[0055] In other embodiments of the present invention, manual annotation and surveying methods may be used to determine the conversion relationship between the model coordinate system and the physical coordinate system, or any method known in the art may be used to determine the conversion relationship between the model coordinate system and the physical coordinate system.

[0056] S130: Determine a conversion relationship between a second physical coordinate system where the second scene is located and a coordinate system of the three-dimensional scene model.

[0057] This step is similar to the above step S120 and will not be repeated here.

[0058] S140 , associating the first physical coordinate system with the second physical coordinate system based on the conversion relationship between the first physical coordinate system and the model coordinate system, and the conversion relationship between the second physical coordinate system and the model coordinate system.

[0059] Since the first physical coordinate system associated with the first scene and the second physical coordinate system associated with the second scene have a conversion relationship with the same three-dimensional scene model coordinate system, the conversion relationship between the first physical coordinate system and the second physical coordinate system can be determined, thereby realizing the association between the first physical coordinate system and the second physical coordinate system.

[0060] Figure 6 6 is a block diagram of the functional modules of a system 600 for associating different physical coordinate systems according to one embodiment of the present invention. Although the block diagram depicts components in a functionally separate manner, such depiction is for illustrative purposes only. The components shown in the figure can be arbitrarily combined or separated into independent software, firmware, and / or hardware components. Moreover, regardless of how such components are combined or divided, they can be executed on the same computing device or distributed across multiple computing devices, where the multiple computing devices can be connected by one or more networks.

[0061] like Figure 6 As shown, system 600 includes a 3D scene model establishment module 601, a transformation relationship determination module 602, and a physical coordinate system association module 603. As described above in conjunction with step S110, 3D scene model establishment module 601 establishes a 3D scene model comprising at least a first scene and a second scene, wherein the 3D scene model has a model coordinate system. Transformation relationship determination module 602, as described above in conjunction with steps S120-S130, determines the transformation relationship between a first physical coordinate system for the first scene and the model coordinate system, and determines the transformation relationship between a second physical coordinate system for the second scene and the model coordinate system. Physical coordinate system association module 603, as described above in conjunction with step S140, associates the first physical coordinate system with the second physical coordinate system based on the transformation relationship between the first physical coordinate system and the model coordinate system, and the transformation relationship between the second physical coordinate system and the model coordinate system. In one embodiment, to establish the 3D scene model, a visual marker may be pre-set in the first scene or the second scene. In one embodiment, an optical communication device may be used as the visual marker.

[0062] In one embodiment of the present invention, the present invention may be implemented in the form of a computer program. The computer program may be stored in various computer-readable storage media (e.g., a hard disk, an optical disk, a flash memory, etc.), and when the computer program is executed by a processor, it can be used to implement the method of the present invention.

[0063] In another embodiment of the present invention, the present invention may be implemented in the form of an electronic device, which includes a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method of the present invention can be implemented.

[0064] References herein to "various embodiments," "some embodiments," "one embodiment," or "an embodiment" refer to a particular feature, structure, or property described in connection with the embodiment as being included in at least one embodiment. Thus, the appearances of the phrases "in various embodiments," "in some embodiments," "in one embodiment," or "in an embodiment" throughout this document do not necessarily refer to the same embodiment. Furthermore, particular features, structures, or properties may be combined in any suitable manner in one or more embodiments. Thus, particular features, structures, or properties shown or described in connection with one embodiment may be combined, in whole or in part, with features, structures, or properties of one or more other embodiments without restriction, as long as the combination is not illogical or inoperable. Expressions such as "according to A," "based on A," "through A," or "using A" as used herein are intended to be non-exclusive, meaning that "according to A" may include "according only to A" or "according to A and B," unless specifically stated to mean "according only to A." For clarity, exemplary operational steps are described in a certain order throughout this application, but those skilled in the art will appreciate that not all of these operational steps are essential, and some of these steps may be omitted or replaced by other steps. These operation steps do not have to be executed sequentially in the manner shown; on the contrary, some of these operation steps can be executed in different orders or in parallel according to actual needs, as long as the new execution manner is not illogical or inoperable.

[0065] Having thus described several aspects of at least one embodiment of the present invention, it will be appreciated that various changes, modifications, and improvements will readily occur to those skilled in the art. Such changes, modifications, and improvements are intended to be within the spirit and scope of the present invention. While the present invention has been described with reference to certain embodiments, the present invention is not limited to the embodiments described herein and encompasses various changes and variations that may be made without departing from the scope of the present invention.

Claims

1. A method for associating different physical coordinate systems, comprising: Establishing a three-dimensional scene model including at least a first scene and a second scene, wherein the three-dimensional scene model has a model coordinate system, and a first visual marker is set in the first scene; and / or a second visual marker is provided in the second scene, wherein said establishing a three-dimensional scene model including at least the first scene and the second scene comprises: acquiring, through a device, a plurality of two-dimensional images including the first visual marker or the second visual marker, and establishing a three-dimensional scene model of the first scene or a three-dimensional scene model of the second scene using the plurality of two-dimensional images; Determining a conversion relationship between a first physical coordinate system in which the first scene is located and the model coordinate system, comprising: selecting at least three two-dimensional images from the plurality of two-dimensional images, and obtaining position information of devices corresponding to each of the selected two-dimensional images in the first physical coordinate system; for each selected two-dimensional image, determining position information of the device corresponding thereto in the model coordinate system; and determining a conversion relationship between the first physical coordinate system and the model coordinate system based on the determined position information of the devices corresponding to each of the two-dimensional images in the first physical coordinate system and the model coordinate system; Determining a conversion relationship between a second physical coordinate system where the second scene is located and the model coordinate system; and The first physical coordinate system is associated with the second physical coordinate system based on a conversion relationship between the first physical coordinate system and the model coordinate system, and a conversion relationship between the second physical coordinate system and the model coordinate system.

2. The method according to claim 1, wherein The first scene and the second scene are overlapped, adjacent or non-adjacent.

3. The method according to claim 1, wherein The step of determining, for each selected two-dimensional image, position information of a corresponding device in the model coordinate system includes: Selecting at least four feature points from the two-dimensional image, and determining the model coordinates of each feature point in the model coordinate system and the pixel coordinates of the feature point in the two-dimensional image; The position information of the device corresponding to the two-dimensional image in the model coordinate system is calculated based on the model coordinates and the pixel coordinates of each selected feature point.

4. The method according to claim 1, wherein The device positions corresponding to the selected two-dimensional images are not colinear and / or coplanar.

5. The method according to claim 1, wherein The acquiring the position information of the devices corresponding to the selected two-dimensional images in the first physical coordinate system includes: determining the position information of the devices in the first physical coordinate system based on the first visual mark.

6. The method according to claim 5, wherein: Determining the position information of the device in the first physical coordinate system based on the first visual marker includes: collecting, by the device, a two-dimensional image containing the first visual sign and obtaining identification information of the first visual sign; analyzing the two-dimensional image to determine position information of the device relative to the first visual marker; Position information of the device in the first physical coordinate system is determined based at least in part on the identification information of the first visual marker and the position information of the device relative to the first visual marker.

7. The method according to any one of claims 1 and 3-6, wherein The associating the first physical coordinate system with the second physical coordinate system comprises: A conversion relationship between the first physical coordinate system and the second physical coordinate system is determined.

8. The method according to claim 1, wherein The step of using the plurality of two-dimensional images to establish a three-dimensional scene model of the first scene or a three-dimensional scene model of the second scene includes: The position information of the device when shooting the two-dimensional image is determined by imaging the first visual mark or the second visual mark in the two-dimensional image.

9. A system for relating different physical coordinate systems, comprising: A three-dimensional scene model establishment module, configured to establish a three-dimensional scene model comprising at least a first scene and a second scene, wherein the three-dimensional scene model has a model coordinate system, and a first visual marker is provided in the first scene; and / or a second visual marker is provided in the second scene, wherein said establishing a three-dimensional scene model including at least the first scene and the second scene comprises: acquiring, through a device, a plurality of two-dimensional images including the first visual marker or the second visual marker, and establishing a three-dimensional scene model of the first scene or a three-dimensional scene model of the second scene using the plurality of two-dimensional images; a conversion relationship determination module, configured to determine a conversion relationship between a first physical coordinate system where the first scene is located and the model coordinate system, and to determine a conversion relationship between a second physical coordinate system where the second scene is located and the model coordinate system, comprising: selecting at least three two-dimensional images from the plurality of two-dimensional images, and obtaining position information of devices corresponding to each of the selected two-dimensional images in the first physical coordinate system; determining, for each selected two-dimensional image, position information of the device corresponding thereto in the model coordinate system; and determining a conversion relationship between the first physical coordinate system and the model coordinate system based on the determined position information of the devices corresponding to each of the two-dimensional images in the first physical coordinate system and the model coordinate system; and A physical coordinate system associating module is used to associate the first physical coordinate system with the second physical coordinate system based on a conversion relationship between the first physical coordinate system and the model coordinate system, and a conversion relationship between the second physical coordinate system and the model coordinate system.

10. The system according to claim 9, wherein: A first visual sign is provided in the first scene; and / or A second visual mark is set in the second scene.

11. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the computer program can be used to implement the method according to any one of claims 1 to 8.

12. An electronic device comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the computer program can be used to implement the method according to any one of claims 1 to 8.

Images