Method and system for constructing digital virtual reality scene

Abstract

The present invention relates to the field of virtual reality technology, and in particular to a method for constructing a digital virtual reality scene and a construction system thereof. The present invention obtains a plurality of images of a real scene, extracts a plurality of virtual features to be digitized according to the images, uses a depth camera and a laser radar to obtain spatial information of each virtual feature to be digitized, calculates a spatial information difference value, divides the real scene area category according to the spatial information difference value, and selects a construction strategy, including dividing each area into a plurality of sub-areas, calculating the spatial information difference value of each sub-area, determining whether to divide the sub-area again, or constructing a digital virtual reality scene according to the spatial information of each virtual feature to be digitized. The present invention can further divide the area that is more prone to errors by classifying different areas, and directly digitize the area that is more accurately digitized, thereby improving the accuracy and reliability of the digital virtual reality scene.

Description

Technical Field

[0001] The present invention relates to the field of virtual reality technology, and in particular to a method for constructing a digital virtual reality scene and a construction system thereof. Background Art

[0002] In the construction, engineering and manufacturing industries, virtual reality technology can help designers and engineers monitor products in real time and identify potential problems. In the medical field, virtual reality technology can be used for surgical simulation, patient rehabilitation and psychological treatment. It can also help doctors better understand the patient's condition and develop more effective treatment plans, so the accuracy and reliability of digital virtual reality scenes are crucial.

[0003] In the prior art, Chinese patent publication number: CN113223162A discloses a method and device for constructing a digital twin scene of an inland waterway, which involves the fields of transportation informatization and virtual reality technology to solve the problems of video fragmentation, separation of multi-source IoT data, and lack of correlation in the current supervision of inland waterways. The method for constructing a digital twin scene of an inland waterway includes: multi-scale waterway scene construction, three-dimensional real-time fusion of multi-channel videos, three-dimensional annotation of digital assets, and convergence and fusion of IoT sensor data. The method and device for constructing a digital twin scene of an inland waterway provided by the present invention are used to create a digital twin scene of a real inland waterway scene in a digital manner using digital twin technology, which greatly improves the precise positioning capability and emergency response efficiency of the intelligent management of inland waterways. However, in the prior art, due to the different light conditions and different difficulty levels of image acquisition in different areas in the real scene, the digital virtual accuracy of different areas is different in the process of digitizing the virtual reality scene, and the problem of low precision and reliability.

[0004] Therefore, there is an urgent need for a construction method and system for digital virtual reality scenes that can solve the problems of different lighting conditions and different levels of difficulty in image acquisition in different areas of the real scene, and adopt different construction strategies to construct different areas, thereby improving the accuracy and reliability of digital virtual reality scenes. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for constructing a digital virtual reality scene, which classifies different areas in a real scene based on analysis of collected spatial information, adopts different construction strategies to construct different areas, and thus improves the accuracy and reliability of the digital virtual reality scene.

[0006] The present invention provides a method for constructing a digital virtual reality scene, the method comprising:

[0007] Step S1, acquiring a number of images of a real scene through an image acquisition unit, and extracting a number of virtual features to be digitized according to the images;

[0008] Step S2, using a depth camera and a laser radar to respectively obtain the virtual feature space information to be digitized;

[0009] Step S3, dividing the real scene into several areas, obtaining the virtual feature space information to be digitized obtained by the depth camera and the laser radar in each area, calculating the spatial information difference value, and classifying the real scene area categories according to the spatial information difference value;

[0010] Step S4, selecting a construction strategy according to the real scene area category, including:

[0011] Divide each area into a number of sub-areas, calculate the spatial information difference value of each sub-area, determine whether to divide the sub-area again, and divide the sub-area again according to the spatial information difference value of the sub-area, and construct a digital virtual reality scene according to each virtual feature space information to be digitized;

[0012] Or, a digital virtual reality scene is constructed according to each virtual feature space information to be digitized.

[0013] Furthermore, in step S1, the process of extracting a plurality of virtual features to be digitized according to the image includes:

[0014] Identifying virtual parts of the image to be digitized;

[0015] The edge contour and center point of each virtual part to be digitized are obtained as each virtual feature to be digitized.

[0016] Furthermore, in step S2, a depth camera and a laser radar are used to respectively obtain spatial information of each virtual feature to be digitized, and the spatial information is the three-dimensional position coordinates of several points on the edge contour of the virtual feature to be digitized and the three-dimensional position coordinates of the center point.

[0017] Furthermore, in step S3, the real scene is divided into a number of areas, wherein each area is equal in size.

[0018] Furthermore, in step S3, the process of obtaining the virtual feature space information to be digitized respectively obtained by the depth camera and the laser radar in each area and calculating the difference value of the space information includes:

[0019] Obtaining virtual features to be digitized included in each area;

[0020] Arbitrarily select a number of points and a center point on the edge contour of the virtual feature to be digitized;

[0021] Acquire the three-dimensional position coordinates of several points on the edge contour and the center point through a depth camera, and acquire the three-dimensional position coordinates of several points on the edge contour and the center point through a laser radar;

[0022] Calculate the Euclidean distance between the three-dimensional position coordinates of the plurality of points on the edge contour and the center point obtained by the depth camera and the corresponding three-dimensional position coordinates of the plurality of points on the edge contour and the center point obtained by the laser radar;

[0023] Get the average Euclidean distance of the three-dimensional position coordinate pair;

[0024] The average Euclidean distance is recorded as the spatial information difference value.

[0025] Furthermore, in step S3, the process of dividing the real scene area categories according to the spatial information difference value includes:

[0026] Compare the spatial information difference value of each area with a preset spatial information difference value comparison threshold;

[0027] If the spatial information difference value of the area is less than the preset spatial information difference value comparison threshold, the real scene area category is classified as a strong precision tendency area category;

[0028] If the spatial information difference value of the area is greater than or equal to the preset spatial information difference value comparison threshold, the real scene area category is classified as a weak precision tendency area category.

[0029] Furthermore, in step S4, a construction strategy is selected according to the category of the real scene area, wherein:

[0030] If the real scene area category is a strong precision tendency area category, a digital virtual reality scene is constructed according to each virtual feature space information to be digitized;

[0031] If the area category of the real scene is a weak precision tendency area category, each area is divided into several sub-areas, the spatial information difference value of each sub-area is calculated, and it is determined whether to divide the sub-area again, and the sub-area is divided again according to the spatial information difference value of the sub-area, and a digital virtual reality scene is constructed according to the virtual feature space information to be digitized.

[0032] Furthermore, in step S4, the process of determining whether to divide the sub-region again includes:

[0033] Obtain the spatial information difference value of each sub-region;

[0034] Compare the spatial information difference value of each sub-region with a preset sub-region spatial information difference value comparison threshold;

[0035] If the spatial information difference value of the sub-region is greater than a preset sub-region spatial information difference value comparison threshold, it is determined that the sub-region is to be divided again.

[0036] Furthermore, in the step S4, the sub-regions are divided again according to the spatial information difference values ​​of the sub-regions, wherein the spatial information difference values ​​are inversely proportional to the sizes of the sub-regions after the division.

[0037] A system for constructing a digital virtual reality scene is also provided, comprising:

[0038] An information acquisition module, including an image acquisition unit for acquiring images of real scenes, a depth camera and a laser radar for acquiring spatial information of digital virtual features;

[0039] A region division module, connected to the information acquisition module, is used to divide the real scene into several regions, obtain the virtual feature space information to be digitized obtained by the depth camera and the laser radar in each region, calculate the spatial information difference value, and classify the real scene region category according to the spatial information difference value;

[0040] The construction strategy selection module is connected to each of the information collection modules and the area division module respectively, and is used to select the construction strategy according to the area category of the real scene, including.

[0041] Divide each area into a number of sub-areas, calculate the spatial information difference value of each sub-area, determine whether to divide the sub-area again, and divide the sub-area again according to the spatial information difference value of the sub-area, and construct a digital virtual reality scene according to each virtual feature space information to be digitized;

[0042] Or, a digital virtual reality scene is constructed according to each virtual feature space information to be digitized.

[0043] The beneficial effects of the present invention are:

[0044] The present invention provides a method for constructing a digitized virtual reality scene and a construction system thereof, which combines the three-dimensional position coordinates obtained by a depth camera with the three-dimensional position coordinates obtained by a laser radar for calculation, and can characterize the difficulty and accuracy of obtaining virtual feature space information to be digitized in each area to a certain extent, so that real scene areas with different degrees of difficulty in digitization and virtualization can be identified, thereby improving the accuracy and reliability of the digitized virtual reality scene. By classifying different areas, areas that are more prone to errors can be further divided, and areas that are more accurately digitized and virtualized can be directly digitized and virtualized, thereby ensuring high efficiency and low computing power while improving the accuracy and reliability of the digitized virtual reality scene.

[0045] Furthermore, the present invention obtains the spatial information of each virtual feature to be digitized obtained by using a depth camera and a lidar in each area, and calculates the spatial information difference value. In actual situations, the depth camera may not be able to accurately measure the distance under dim or too bright light conditions. If the measuring point is located at the edge of the field of view of the camera or the lidar, the acquired coordinate information may be inaccurate due to the low edge resolution. The three-dimensional position coordinates obtained by the depth camera are combined with the three-dimensional position coordinates obtained by the lidar for calculation, which can characterize the difficulty and accuracy of obtaining the spatial information of the virtual features to be digitized in each area to a certain extent, thereby identifying real scene areas with different degrees of digitization difficulty, thereby improving the accuracy and reliability of the digitized virtual reality scene.

[0046] Furthermore, the present invention classifies the real scene area according to the spatial information difference value. In actual situations, if the light in the real scene area is too dark or too bright, and the virtual feature to be digitized is located at the edge of the image, it may cause errors in the digitized virtualization of the area, thereby making the accuracy and reliability of the digitized virtual reality scene low. By classifying different areas, the areas that are more prone to errors can be further divided, and the areas that are more accurately digitized can be directly digitized, thereby ensuring high efficiency and low computing power while improving the accuracy and reliability of the digitized virtual reality scene.

[0047] Furthermore, the present invention determines whether to divide the sub-region again by calculating the spatial information difference value of each sub-region. In actual situations, when the light is too dark or too bright, by reducing the area where the depth camera image is acquired, the signal-to-noise ratio can be improved in the local image due to the reduction of the background, so that the camera sensor can more accurately capture the reflected light from the depth camera transmitter, thereby improving the accuracy and reliability of the digitized virtual reality scene. Moreover, when the area is divided into several sub-regions, the position of the virtual feature to be digitized originally located at the edge of the image can be changed, thereby improving the accuracy and reliability of the digitized virtual reality scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A diagram showing the steps of a method for constructing a digital virtual reality scene in an embodiment of the present invention;

[0049] Figure 2 A logical decision diagram for classifying real scene regions according to spatial information difference values ​​in an embodiment of the present invention;

[0050] Figure 3 A logical decision diagram for selecting a construction strategy according to the category of a real scene area in an embodiment of the present invention;

[0051] Figure 4This is a structural diagram of a system for constructing a digital virtual reality scene in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] In the description of the present invention, it should be noted that the orientations or positional relationships indicated by the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. Among them, the terms "first position" and "second position" are two different positions, and the first feature "above", "above" and "above" the second feature include the first feature being directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. The first feature "below", "below" and "below" the second feature include the first feature being directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0054] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" 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 or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0056] See also Figure 1-Figure 4 As shown, Figure 1 is a step diagram of a method for constructing a digital virtual reality scene in an embodiment of the present invention, Figure 2This is a logic decision diagram for classifying real scene regions according to spatial information difference values ​​in an embodiment of the present invention. Figure 3 The strategy logic decision diagram is selected according to the real scene area category in the embodiment of the present invention. Figure 4 : is a structural diagram of a system for constructing a digital virtual reality scene in an embodiment of the present invention. This embodiment provides a method for constructing a digital virtual reality scene. The method for constructing a digital virtual reality scene includes:

[0057] Step S1, acquiring a number of images of a real scene through an image acquisition unit, and extracting a number of virtual features to be digitized according to the images;

[0058] Step S2, using a depth camera and a laser radar to respectively obtain the virtual feature space information to be digitized;

[0059] Step S3, dividing the real scene into several areas, obtaining the virtual feature space information to be digitized obtained by the depth camera and the laser radar in each area, calculating the spatial information difference value, and classifying the real scene area categories according to the spatial information difference value;

[0060] Step S4, selecting a construction strategy according to the real scene area category, including:

[0061] Divide each area into a number of sub-areas, calculate the spatial information difference value of each sub-area, determine whether to divide the sub-area again, and divide the sub-area again according to the spatial information difference value of the sub-area, and construct a digital virtual reality scene according to each virtual feature space information to be digitized;

[0062] Or, a digital virtual reality scene is constructed according to each virtual feature space information to be digitized.

[0063] The present invention does not limit the specific structure of the image acquisition unit, which may be an industrial CCD camera that can acquire images of multiple angles in each area of ​​a real scene.

[0064] Specifically, in step S1, the process of extracting a number of virtual features to be digitized according to the image includes:

[0065] Identifying virtual parts of the image to be digitized;

[0066] The edge contour and center point of each virtual part to be digitized are obtained as each virtual feature to be digitized.

[0067] Specifically, in step S2, a depth camera and a laser radar are used to respectively obtain spatial information of each virtual feature to be digitized, and the spatial information is the three-dimensional position coordinates of several points on the edge contour of the virtual feature to be digitized and the three-dimensional position coordinates of the center point.

[0068] The present invention does not limit the specific method of identifying each virtual part to be digitized in the image, and each virtual part to be digitized in the image can be identified by image analysis software. In this embodiment, the image recognition software can be matlab.

[0069] Specifically, in step S3, the real scene is divided into a number of areas, wherein each area is equal in size.

[0070] Specifically, in step S3, the process of obtaining the virtual feature space information to be digitized respectively obtained by the depth camera and the laser radar in each area and calculating the difference value of the space information includes:

[0071] Obtaining virtual features to be digitized included in each area;

[0072] Arbitrarily select a number of points and a center point on the edge contour of the virtual feature to be digitized;

[0073] Acquire the three-dimensional position coordinates of several points on the edge contour and the center point through a depth camera, and acquire the three-dimensional position coordinates of several points on the edge contour and the center point through a laser radar;

[0074] Calculate the Euclidean distance between the three-dimensional position coordinates of the plurality of points on the edge contour and the center point obtained by the depth camera and the corresponding three-dimensional position coordinates of the plurality of points on the edge contour and the center point obtained by the laser radar;

[0075] Get the average Euclidean distance of the three-dimensional position coordinate pair;

[0076] The average Euclidean distance is recorded as the spatial information difference value.

[0077] In this embodiment, the depth camera captures images of each area and detects several points on the edge contour and the center point in the image. For the several points on the edge contour and the center point, the depth camera can provide corresponding depth values, which represent the straight-line distance from the camera to the point. The two-dimensional pixel coordinates in the image are converted into three-dimensional space coordinates, and the three-dimensional points in the camera coordinate system are converted into the world coordinate system.

[0078] In this embodiment, a data set of spatial points scanned by a laser radar device is obtained, and each point cloud contains three-dimensional position coordinates, and the data in the laser radar coordinate system is converted into the world coordinate system.

[0079] It can be understood that the three-dimensional position coordinates of the same point obtained by the depth camera and the three-dimensional position coordinates obtained by the lidar are a three-dimensional position coordinate pair, and the Euclidean distance of each three-dimensional position coordinate pair is calculated, and the average Euclidean distance of the three-dimensional position coordinate pair is obtained.

[0080] Specifically, the present invention obtains the spatial information of each virtual feature to be digitized obtained by using a depth camera and a lidar in each area, and calculates the difference value of the spatial information. In actual situations, the depth camera may not be able to accurately measure the distance under dim or too bright light conditions. If the measuring point is located at the edge of the field of view of the camera or the lidar, the acquired coordinate information may be inaccurate due to the low edge resolution. The three-dimensional position coordinates obtained by the depth camera are combined with the three-dimensional position coordinates obtained by the lidar for calculation. The difficulty and accuracy of obtaining the spatial information of the virtual features to be digitized in each area can be characterized to a certain extent, thereby identifying real scene areas with different degrees of digitized virtual difficulty, thereby improving the accuracy and reliability of the digitized virtual reality scene.

[0081] Specifically, in step S3, the process of dividing the real scene area categories according to the spatial information difference value includes:

[0082] Compare the spatial information difference value of each area with a preset spatial information difference value comparison threshold;

[0083] If the spatial information difference value of the area is less than the preset spatial information difference value comparison threshold, the real scene area category is classified as a strong precision tendency area category;

[0084] If the spatial information difference value of the area is greater than or equal to the preset spatial information difference value comparison threshold, the real scene area category is classified as a weak precision tendency area category.

[0085] In this embodiment, the preset spatial information difference value comparison threshold is selected within the range of [1 mm, 5 mm].

[0086] Specifically, the present invention classifies the real scene area according to the spatial information difference value. In actual situations, if the light in the real scene area is too dark or too bright, and the virtual feature to be digitized is located at the edge of the image, it may cause errors in the digitized virtualization of the area, thereby making the accuracy and reliability of the digitized virtual reality scene low. By classifying different areas, the areas that are more prone to errors can be further divided, and the areas that are more accurately digitized can be directly digitized, thereby ensuring high efficiency and low computing power while improving the accuracy and reliability of the digitized virtual reality scene.

[0087] Specifically, in step S4, a construction strategy is selected according to the category of the real scene area, wherein:

[0088] If the real scene area category is a strong precision tendency area category, a digital virtual reality scene is constructed according to each virtual feature space information to be digitized;

[0089] If the area category of the real scene is a weak precision tendency area category, each area is divided into several sub-areas, the spatial information difference value of each sub-area is calculated, and it is determined whether to divide the sub-area again, and the sub-area is divided again according to the spatial information difference value of the sub-area, and a digital virtual reality scene is constructed according to the virtual feature space information to be digitized.

[0090] Specifically, in step S4, the process of determining whether to divide the sub-region again includes:

[0091] Obtain the spatial information difference value of each sub-region;

[0092] Compare the spatial information difference value of each sub-region with a preset sub-region spatial information difference value comparison threshold;

[0093] If the spatial information difference value of the sub-region is greater than a preset sub-region spatial information difference value comparison threshold, it is determined that the sub-region is to be divided again.

[0094] In this embodiment, the preset sub-region spatial information difference value comparison threshold is selected within the range of [1 mm, 5 mm].

[0095] Specifically, in step S4, the sub-regions are divided again according to the spatial information difference values ​​of the sub-regions, wherein the spatial information difference values ​​are inversely proportional to the sizes of the sub-regions after the division.

[0096] It is understandable that if the spatial information difference value of the sub-region is still large, the sub-region should be further divided, and the larger the spatial information difference value of the sub-region is, the smaller the size of the sub-region after further division should be.

[0097] Specifically, the present invention determines whether to divide the sub-region again by calculating the spatial information difference value of each sub-region. In actual situations, when the light is too dark or too bright, by reducing the area where the depth camera image is acquired, the signal-to-noise ratio can be improved in the local image due to the reduction of the background, so that the camera sensor can more accurately capture the reflected light from the depth camera transmitter, thereby improving the accuracy and reliability of the digitized virtual reality scene. Moreover, when the area is divided into several sub-regions, the position of the virtual feature to be digitized originally located at the edge of the image can be changed, thereby improving the accuracy and reliability of the digitized virtual reality scene.

[0098] Specifically, a system for constructing a digital virtual reality scene is also provided, comprising:

[0099] An information acquisition module, including an image acquisition unit for acquiring images of real scenes, a depth camera for acquiring spatial information of digital virtual features, and a laser radar;

[0100] A region division module, connected to the information acquisition module, is used to divide the real scene into several regions, obtain the virtual feature space information to be digitized obtained by the depth camera and the laser radar in each region, calculate the spatial information difference value, and classify the real scene region category according to the spatial information difference value;

[0101] The construction strategy selection module is connected to each of the information collection modules and the area division module respectively, and is used to select the construction strategy according to the area category of the real scene, including.

[0102] Divide each area into a number of sub-areas, calculate the spatial information difference value of each sub-area, determine whether to divide the sub-area again, and divide the sub-area again according to the spatial information difference value of the sub-area, and construct a digital virtual reality scene according to each virtual feature space information to be digitized;

[0103] Or, a digital virtual reality scene is constructed according to each virtual feature space information to be digitized.

[0104] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the device, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based device that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0105] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for constructing a digital virtual reality scene, characterized in that: include: Step S1, acquiring a number of images of a real scene through an image acquisition unit, and extracting a number of virtual features to be digitized according to the images; Step S2, using a depth camera and a laser radar to respectively obtain the virtual feature space information to be digitized; Step S3, dividing the real scene into several areas, obtaining the virtual feature space information to be digitized obtained by the depth camera and the laser radar in each area, calculating the spatial information difference value, and classifying the real scene area categories according to the spatial information difference value; The process of calculating the spatial information difference value includes: Obtaining virtual features to be digitized included in each area; Arbitrarily select a number of points and a center point on the edge contour of the virtual feature to be digitized; Acquire the three-dimensional position coordinates of several points on the edge contour and the center point through a depth camera, and acquire the three-dimensional position coordinates of several points on the edge contour and the center point through a laser radar; Calculate the Euclidean distance between the three-dimensional position coordinates of the plurality of points on the edge contour and the center point obtained by the depth camera and the corresponding three-dimensional position coordinates of the plurality of points on the edge contour and the center point obtained by the laser radar; Get the average Euclidean distance of the three-dimensional position coordinate pair; The average Euclidean distance is recorded as the spatial information difference value; Compare the spatial information difference value of each area with a preset spatial information difference value comparison threshold; If the spatial information difference value of the area is less than the preset spatial information difference value comparison threshold, the real scene area category is classified as a strong precision tendency area category; If the spatial information difference value of the area is greater than or equal to the preset spatial information difference value comparison threshold, the real scene area category is classified as a weak precision tendency area category; Step S4, selecting a construction strategy based on the real scene area category, include, If the real scene area category is a weak precision tendency area category, each area is divided into several sub-areas, the spatial information difference value of each sub-area is calculated, and it is determined whether to divide the sub-area again, and the sub-area is divided again according to the spatial information difference value of the sub-area, and a digital virtual reality scene is constructed according to each virtual feature space information to be digitized; If the real scene area category is a strong precision tendency area category, a digitized virtual reality scene is constructed according to each virtual feature space information to be digitized.

2. The method for constructing a digital virtual reality scene according to claim 1, characterized in that: In step S1, the process of extracting a number of virtual features to be digitized according to the image includes: Identifying virtual parts of the image to be digitized; The edge contour and center point of each virtual part to be digitized are obtained as each virtual feature to be digitized.

3. The method for constructing a digital virtual reality scene according to claim 1, characterized in that: In step S2, a depth camera and a laser radar are used to respectively obtain spatial information of each virtual feature to be digitized, and the spatial information is the three-dimensional position coordinates of several points on the edge contour of the virtual feature to be digitized and the three-dimensional position coordinates of the center point.

4. The method for constructing a digital virtual reality scene according to claim 1, characterized in that: In step S3, the real scene is divided into a number of regions, wherein each region is equal in size.

5. The method for constructing a digital virtual reality scene according to claim 1, characterized in that: In step S4, the process of determining whether to divide the sub-region again includes: Obtain the spatial information difference value of each sub-region; Compare the spatial information difference value of each sub-region with a preset sub-region spatial information difference value comparison threshold; If the spatial information difference value of the sub-region is greater than a preset sub-region spatial information difference value comparison threshold, it is determined that the sub-region is to be divided again.

6. The method for constructing a digital virtual reality scene according to claim 5, characterized in that: In the step S4, the sub-regions are divided again according to the spatial information difference values ​​of the sub-regions, wherein the spatial information difference values ​​are inversely proportional to the sizes of the sub-regions after the division.

7. A construction system using the construction method of a digital virtual reality scene according to any one of claims 1 to 6, characterized in that: include, An information acquisition module, including an image acquisition unit for acquiring images of real scenes, a depth camera for acquiring spatial information of virtual features to be digitized, and a laser radar; A region division module, connected to the information acquisition module, is used to divide the real scene into several regions, obtain the virtual feature space information to be digitized obtained by the depth camera and the laser radar in each region, calculate the spatial information difference value, and classify the real scene region category according to the spatial information difference value; The construction strategy selection module is connected to the information collection module and the area division module respectively, and is used to select the construction strategy according to the area category of the real scene, including: Divide each area into a number of sub-areas, calculate the spatial information difference value of each sub-area, determine whether to divide the sub-area again, and divide the sub-area again according to the spatial information difference value of the sub-area, and construct a digital virtual reality scene according to each virtual feature space information to be digitized; Or, a digital virtual reality scene is constructed according to each virtual feature space information to be digitized.

Images