Real-time modeling device and method

Through real-time modeling equipment, real-time shooting and 3D modeling of objects is solved, and the problem that 2D display cannot display 3D teaching scenes is realized, real-life 3D teaching scene display is improved, and teaching quality is improved.

CN113808255BActive Publication Date: 2024-11-12GUANGZHOU YIYE ELECTROMECHANICAL EQUIP TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111061366.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-10
Publication Date
2024-11-12
Estimated Expiration
2041-09-10

AI Technical Summary

Technical Problem

The existing 2D picture live broadcast or recording method cannot display realistic 3D teaching scenes, which makes teaching and explanation inconvenient for the communication of knowledge points.

Method used

Provide a real-time modeling device, including a shooting device, a 3D modeling device and a touch display device, by taking an object image in real time, obtaining a left view and a right view, performing feature recognition and matching, establishing a feature point mapping relationship, and calculating the relative displacement amount , generate a 3D stereo model and display it through a touch display device.

Benefits of technology

Real-time 3D modeling and display of objects is realized, and realistic 3D teaching scenarios can be displayed to users in real time, improving teaching quality and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113808255B_ABST
    Figure CN113808255B_ABST
Patent Text Reader

Abstract

The present invention provides an instant modeling device and method, wherein the instant modeling device includes an equipment platform, a shooting device, a 3D modeling device and a touch display device arranged on the equipment platform; the shooting device and the touch display device are electrically connected to the 3D modeling device respectively; the shooting device shoots the object to be shot on the equipment platform, obtains a left view and a right view and transmits them to the 3D modeling device; the 3D modeling device receives the left view and the right view, and performs 3D instant modeling according to the left view and the right view to obtain a 3D display model, generates a display signal according to the 3D display model and sends it to the touch display device; the touch display device receives the display signal and displays the 3D display model. The instant modeling device and method of the present invention have the advantages of being able to shoot objects in real time, perform instant modeling and instant display through the real-time shot object images.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of teaching equipment, and in particular to an instant modeling device and method. Background Art

[0002] With the progress of society and the development of science and technology, digital devices such as electronic whiteboards, smart blackboards, and smart podiums are gradually penetrating into all aspects of teaching. In the process of practical teaching, the general podium is not equipped with real-time image acquisition equipment such as cameras and real-time image processing equipment. It is usually demonstrated to students in the form of 2D live broadcast or 2D recorded broadcast. However, the display method of 2D live broadcast or recorded broadcast cannot show realistic 3D teaching scenes, which is not convenient for teaching and explaining knowledge points. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the embodiments of the present invention provide an instant modeling device and method, which have the advantages of being able to photograph an object in real time and perform instant modeling through the object images photographed in real time.

[0004] According to a first aspect of an embodiment of the present invention, there is provided an instant modeling device, comprising an equipment platform, a shooting device arranged on the equipment platform, a 3D modeling device and a touch display device; the shooting device and the touch display device are electrically connected to the 3D modeling device respectively; the shooting device shoots the object to be shot on the equipment platform, obtains a left view and a right view and transmits them to the 3D modeling device; the 3D modeling device receives the left view and the right view, and performs 3D instant modeling according to the left view and the right view to obtain a 3D display model, specifically: feature recognition is performed on the left view and the right view respectively to obtain a first feature point set and a second feature point set; feature point matching is performed on the first feature point set and the second feature point set to establish a feature point mapping relationship between the left view and the right view; the relative displacement of the left view and the right view is obtained according to the feature point mapping relationship, specifically: a first feature point is determined in the left view, and a first feature point is determined in the right view according to the feature point mapping relationship. A second feature point is determined in the right view, where the second feature point is the feature point in the right view with the greatest correlation with the first feature point; a relative displacement of the left view and the right view is obtained according to the position of the first feature point and the position of the second feature point; wherein the relative displacement includes a horizontal displacement and / or a vertical displacement; the left view and the right view are translated according to the relative displacement to obtain a target image; depth information of each feature point of the first feature point set is obtained, depth information of each feature point of the second feature point set is obtained, the depth information of each feature point is matched with the feature point of the target image, depth information of each feature point of the target image is obtained, and a 3D stereo model is established according to each feature point of the target image and the depth information of each feature point; the 3D modeling device generates a display signal according to the 3D display model and sends it to the touch display device; the touch display device receives the display signal and displays the 3D display model.

[0005] Further, translating the left view and the right view according to the relative displacement to obtain a target image includes:

[0006] According to the relative displacement, the left view is translated to overlap with the right view to obtain a target image, or,

[0007] The right view is translated to overlap with the left view according to the relative displacement to obtain a target image.

[0008] Furthermore, before the step of acquiring the depth information of each feature point of the target image and establishing a 3D stereo model according to the target image and the depth information, the step further includes:

[0009] The screen resolution of the touch display device is obtained, and the image to be cropped that exceeds the screen boundary in the target image is obtained according to the screen resolution, and the image to be cropped is cropped to obtain the target image.

[0010] Furthermore, the instant modeling device is an instant modeling podium, the device platform is a podium body, and the shooting device and the touch display device are installed on the podium body.

[0011] Furthermore, the platform body includes a cabinet and a panel arranged above the cabinet; a plurality of pulleys are installed at the bottom of the cabinet.

[0012] Furthermore, the touch display device comprises a frame, a display and a touch component; the display and the touch component are installed in the frame, and the touch component is located on a side of the display facing a user.

[0013] According to a second aspect of an embodiment of the present invention, there is provided an instant modeling method, comprising the following steps:

[0014] Receiving the left view and the right view sent by the shooting device in real time;

[0015] Performing feature recognition on the left view and the right view respectively to obtain a first feature point set and a second feature point set;

[0016] Performing feature point matching on the first feature point set and the second feature point set to establish a feature point mapping relationship between the left view and the right view;

[0017] Obtaining the relative displacement between the left view and the right view according to the feature point mapping relationship, specifically: determining a first feature point in the left view, and determining a second feature point in the right view according to the feature point mapping relationship, wherein the second feature point is a feature point in the right view that has the greatest correlation with the first feature point; obtaining the relative displacement between the left view and the right view according to the position of the first feature point and the position of the second feature point; wherein the relative displacement includes a horizontal displacement and / or a vertical displacement;

[0018] According to the relative displacement, the left view and the right view are translated to obtain a target image;

[0019] Acquire depth information of each feature point of the first feature point set, and acquire depth information of each feature point of the second feature point set;

[0020] Matching the depth information of each feature point with the feature points of the target image to obtain depth information corresponding to each feature point of the target image;

[0021] A 3D stereo model is established according to each feature point of the target image and the depth information of each feature point.

[0022] The technical solution of the above embodiment of the present application is applied, by setting a shooting device to shoot the object to be shot in real time, obtaining a left view and a right view, and using a 3D modeling device to perform 3D instant modeling based on the left view and the right view to obtain a 3D display model, and generating a display signal based on the 3D display model and sending it to the touch display device, and finally receiving the display signal through the touch display device and displaying the 3D display model for viewing by users and other learners. The technical solution of the present application has the advantage of being able to shoot an object in real time and perform instant modeling through the real-time shot object image.

[0023] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention.

[0024] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a principle block diagram of the instant modeling device according to an embodiment of the present invention;

[0026] Figure 2 A flow chart of a method for real-time modeling of a 3D modeling device according to an embodiment of the present invention;

[0027] Figure 3 A flow chart of a method for obtaining the relative displacement between a left view and a right view according to an embodiment of the present invention;

[0028] Figure 4 A flow chart of a method for establishing a 3D stereoscopic model according to an embodiment of the present invention;

[0029] Figure 5 A schematic diagram of the structure of a podium that facilitates instant modeling according to an embodiment of the present invention;

[0030] Figure 6 A front view of a podium for facilitating instant modeling according to an embodiment of the present invention;

[0031] Figure 7 A rear view of a podium for facilitating instant modeling according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the 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 the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0033] In the process of practical teaching, the general podium is not equipped with real-time image acquisition equipment such as cameras and real-time image processing equipment, and demonstration teaching is usually provided to students in the form of 2D live broadcast or 2D recorded broadcast. However, it is impossible to display realistic 3D teaching scenes through 2D live broadcast or recorded broadcast, which is not convenient for teaching and explaining knowledge points. Based on the above technical problems, the present application provides an instant modeling device that can shoot objects in real time, and perform instant 3D modeling according to the real-time shot object image through a modeling device, and display it in real time through a display device.

[0034] See also Figure 1 , Figure 1 It is a principle block diagram of the real-time modeling device described in an embodiment of the present invention.

[0035] The instant modeling device described in the embodiment of the present invention is a teaching device, that is, a teaching podium capable of instant 3D modeling. The instant modeling device can capture images of objects to be photographed in real time, receive images through a 3D modeling device, and then perform real-time modeling, and generate a display signal that is sent to a touch display device for display.

[0036] The real-time modeling device includes a device platform 10, a shooting device 20, a 3D modeling device 30 and a touch display device 40 arranged on the device platform 10. In this embodiment, the real-time modeling device can be a teaching platform capable of real-time 3D modeling, and the device platform 10 can be a platform body 10, on which the shooting device 20, the 3D modeling device 30 and the touch display device 40 are arranged.

[0037] The photographing device 20 and the touch display device 40 are electrically connected to the 3D modeling device 30 respectively; the photographing device 20 photographs the object to be photographed on the platform body 10, and obtains the image and transmits it to the 3D modeling device 30. The photographing device 20 includes at least a first camera and a second camera, and obtains the left view through the first camera and the right view through the second camera. The 3D modeling device 30 receives the left view and the right view, and performs 3D real-time modeling based on the left view and the right view to obtain a 3D display model, generates a display signal based on the 3D display model and sends it to the touch display device 40; the touch display device 40 receives the display signal to display the 3D display model, so as to show the real-time modeled 3D model to users and learners.

[0038] The technical solution of the above embodiment of the present application is applied, by setting a shooting device to shoot the object to be shot in real time, obtaining a left view and a right view, and using a 3D modeling device to perform 3D instant modeling based on the left view and the right view to obtain a 3D display model, and generating a display signal based on the 3D display model and sending it to the touch display device, and finally receiving the display signal through the touch display device and displaying the 3D display model for viewing by users and other learners. The technical solution of the present application has the advantage of being able to shoot an object in real time and perform instant modeling through the real-time shot object image.

[0039] The 3D instant modeling solution in this application does not require pre-modeling, but instead performs instant modeling based on the acquired object image. The modeling speed is fast, and realistic 3D teaching scenes can be displayed to users in real time to facilitate the teaching and explanation of knowledge points, thereby improving the teaching quality.

[0040] See also Figure 2 , Figure 2 This is a flow chart of the method for real-time modeling of a 3D modeling device according to an embodiment of the present invention.

[0041] In this embodiment, the 3D real-time modeling based on the left view and the right view to obtain the 3D display model includes the following steps:

[0042] S1: receiving the left view and the right view sent by the shooting device in real time.

[0043] The left view and the right view are obtained by photographing the object in real time through the shooting device, so that the 3D modeling device can instantly model according to the current teaching scene and instantly show the realistic teaching scene to the user. The processing speed is fast, there is no delay, and no preset modeling is required, which is more convenient.

[0044] S2: Perform feature recognition on the left view and the right view respectively to obtain a first feature point set and a second feature point set.

[0045] In this embodiment, after obtaining the left view and the right view, the left view and the right view can be input into the feature recognition model for feature recognition to obtain a first feature point set of the left view and a second feature point set of the right view to facilitate subsequent feature point matching, thereby obtaining the difference between the two views.

[0046] In an optional embodiment, the features in the first feature point set include: color, and / or brightness, and / or curvature. When calculating the correlation of the feature points of the left view and the right view, the color correlation, and / or brightness correlation, and / or curvature correlation of the feature points of the left view and the right view may be calculated, and the correlation of multiple parameters may be calculated to accurately calculate the correlation of the feature points of the two views.

[0047] S3: performing feature point matching on the first feature point set and the second feature point set to establish a feature point mapping relationship between the left view and the right view.

[0048] In this embodiment, since the left view is obtained by photographing the object in real time through the first camera, and the right view is obtained by photographing the same object through the second camera, there are corresponding feature points in the left view and the right view. The set of the first feature points in the left view is the first feature point set, and the set of the second feature points in the right view is the second feature point set. By matching the first feature point set with the second feature point set, the feature point mapping relationship between the left view and the right view can be established.

[0049] In an optional embodiment, when performing feature point matching, local feature matching, global feature matching, or a matching method combining local and global features may be used to perform matching.

[0050] When using local feature matching for feature point matching, a faster matching speed can be obtained; when using global feature matching for feature point matching, a higher matching accuracy can be obtained; in order to obtain a matching method with a more appropriate speed and accuracy, a feature matching method that combines local and global features can also be used.

[0051] S4: Obtaining a relative displacement between the left view and the right view according to the feature point mapping relationship.

[0052] Since the left view and the right view are images taken from different angles of the same object, there is a certain relative displacement between the left view and the right view. After obtaining the relative displacement, the left view or the right view can be translated to obtain the target image.

[0053] In an alternative embodiment, see Figure 3 , Figure 3This is a flow chart of a method for obtaining the relative displacement between a left view and a right view according to an embodiment of the present invention.

[0054] The obtaining the relative displacement between the left view and the right view according to the feature point mapping relationship includes:

[0055] S401: determining a first feature point in the left view, and determining a second feature point in the right view according to the feature point mapping relationship, wherein the second feature point is a feature point in the right view with the greatest correlation with the first feature point.

[0056] S402: Obtaining the relative displacement of the left view and the right view according to the position of the first feature point and the position of the second feature point; wherein the relative displacement includes a horizontal displacement and / or a vertical displacement. Setting the maximum correlation position helps to more accurately obtain the horizontal displacement and the vertical displacement, thereby facilitating the translation of the left view and the right view.

[0057] When determining the second feature point in the right view according to the feature mapping relationship, the second feature point in the right view is traversed and searched according to the first feature point. When a feature point with a higher correlation with the first feature point is found, the previous feature point is iterated using the current feature point, and the search is continued until the second feature point with the greatest correlation with the first feature point is found. During the traversal search, if the correlation of the new feature point is greater than the correlation of the previous feature point, the search is continued in this direction and the previously found feature points are iteratively updated. If the correlation of the new feature line is less than the correlation of the previous feature point, the search is continued in the opposite direction until the second feature point with the greatest correlation with the first feature point is found.

[0058] Furthermore, when searching by traversal, an iterative search may be performed by traversing and searching the KD tree or by traversing and searching the R tree.

[0059] S5: translating the left view and the right view according to the relative displacement to obtain a target image.

[0060] In an optional embodiment, the relative displacement includes a horizontal displacement and / or a vertical displacement. Therefore, translating the left view and the right view according to the relative displacement to obtain the target image may include: translating the left view to overlap with the right view according to the relative displacement to obtain the target image; or translating the right view to overlap with the left view according to the relative displacement to obtain the target image.

[0061] S6: Acquire depth information of each feature point of the target image, and establish a 3D stereo model according to the target image and the depth information.

[0062] In an alternative embodiment, see Figure 4 , Figure 4 The figure is a flow chart of a method for establishing a 3D stereoscopic model according to an embodiment of the present invention.

[0063] The step of acquiring the depth information of each feature point of the target image and establishing a 3D stereo model in real time according to the target image and the depth information includes:

[0064] S601: Acquire depth information of each feature point of the first feature point set, and acquire depth information of each feature point of the second feature point set.

[0065] Since the camera is shooting the same object, when the photographed object is imaged in two planes, the coordinates of each pixel of the image will be different, and the depth information carried by each pixel will also be different. Therefore, it is necessary to obtain the depth information of each feature point of the first feature point set in the left view, and to obtain the depth information of each feature point of the second feature point set in the right view, so as to obtain the depth information of each pixel of the synthesized target image according to the triangulation calculation method or other calculation methods, so as to match the depth information of each feature point of the target image.

[0066] S602: Match the depth information of each feature point with the feature point of the target image to obtain the depth information corresponding to each feature point of the target image. Modeling can be performed by obtaining each pixel point of the target image and the depth information corresponding to each pixel point.

[0067] S603: Establishing a 3D stereo model in real time according to each feature point of the target image and the depth information of each feature point.

[0068] In an optional embodiment, before the step of acquiring the depth information of each feature point of the target image and establishing a 3D stereo model according to the target image and the depth information, the step further includes:

[0069] The screen boundary of the touch display device is obtained, and the image to be cropped that exceeds the screen boundary in the target image is obtained according to the screen boundary, and the image to be cropped is cropped to obtain the target image.

[0070] In an optional embodiment, after step S6, the method further includes: generating a display signal according to the 3D stereoscopic model established in real time and sending the signal to the touch display device.

[0071] The following is a description of the structure of each component of the instant modeling device: Figures 5 to 7 , Figure 5 A schematic diagram of the structure of a podium that facilitates instant modeling according to an embodiment of the present invention; Figure 6 A front view of a podium for facilitating instant modeling according to an embodiment of the present invention; Figure 7 A rear view of a podium for facilitating instant modeling according to an embodiment of the present invention.

[0072] The equipment platform is a platform body 10, and the platform body 10 includes a cabinet 11 and a panel 12 arranged above the cabinet 11, and the panel 12 is used to place objects to be photographed or other supplies. The cabinet 11 and the panel 12 cover each other to form a cavity, and the cavity can be used to place power modules, 3D modeling devices, computer equipment, and teaching tools. The cabinet 11 is a stainless steel cabinet, and a plurality of holes are arranged on its outer wall to facilitate heat dissipation or hanging other devices. Specifically, the diameter of the holes on the outer wall of the cabinet 11 is greater than 1 cm. The cabinet 11 has a stainless steel door, which can be opened to put supplies into the cavity.

[0073] In an optional embodiment, a retractable power plug 13 is further provided on the side wall of the cabinet 11, and the retractable power plug 13 is connected to the power module in the cavity, so that the electrical equipment on the podium can obtain power from the outside. When the equipment on the podium needs to be connected to a power source, the retractable plug can be pulled out and plugged into an AC mains socket to obtain power, which is convenient to use. When the power source is not needed, the retractable plug can be retracted and stored in the cavity of the cabinet 11 for easy storage.

[0074] In an optional embodiment, a plurality of pulleys 14 are installed at the bottom of the cabinet 11. The pulleys 14 may be highly wear-resistant casters, so as to facilitate moving the podium to various locations in the classroom, so that students can view the 3D modeling graphics at close range and from multiple angles, thereby improving the teaching quality.

[0075] In an optional embodiment, the podium further includes a camera bracket 50, which is disposed at the edge of the panel 12 of the podium body 10, with the end of the camera bracket 50 disposed toward the central area of ​​the panel 12, and the end of the camera bracket 50 is mounted with the shooting device 20, so that the shooting device 20 can shoot objects on the panel 12. Furthermore, a locking assembly is mounted at the end of the camera bracket 50, and the shooting device 20 is fixed to the camera bracket 50 by the locking assembly. Before shooting, the direction of the shooting device 20 needs to be adjusted to obtain a better shooting angle. After the angle of the shooting device 20 is adjusted, the shooting device 20 can be locked by the locking assembly to prevent shaking from affecting the shooting effect.

[0076] In an optional embodiment, the photographing device 20 includes at least two cameras, and the plurality of cameras are arranged in parallel at the end of the camera bracket 50, so as to facilitate multi-directional photographing of the object to be photographed from different angles, and obtain images and related information at multiple angles. The distance between the plurality of cameras can be adjusted, and the distance between the plurality of cameras is proportional to the viewing angle of the camera, that is, the larger the viewing angle of the camera, the larger the distance between the cameras is set.

[0077] A display support assembly 60 is also provided on the panel 12 ; the touch display device 40 is installed on the panel 12 through the display support assembly 60 , so as to fix the touch display device.

[0078] In an optional embodiment, the display support assembly 60 is provided with a housing cavity, and a power socket 61 and / or a USB socket are provided on the side wall of the housing cavity, wherein the power socket 61 can be a 220V three-prong socket, or a 220V two-prong socket, or a DC power socket, and the power socket 61 is convenient for moving power to other electrical devices. The USB socket is used to connect with other smart devices to realize information interaction, thereby making teaching more flexible and convenient.

[0079] In an optional embodiment, the touch display device 40 includes a frame 41, a display 42 and a touch component; the display 42 and the touch component are installed in the frame 41, and the touch component is located on the side of the display 42 facing the user, so that the user can input relevant information or perform related operations by touch.

[0080] Wherein, the display 42 can be a 3D polarized display, or a 3D shutter display, which is not limited in this application. If the display 42 is a 3D shutter display, the infrared band emitted by the infrared touch component and the band emitted by the shutter 3D display are two different bands that will not cause interference. In this embodiment, the infrared wave band of the infrared touch component can be 850nm, and the infrared wave band emitted by the shutter 3D display can be 1250nm; or the infrared wave band of the infrared touch component can be 1250nm, and the infrared wave band emitted by the shutter 3D display can be 850nm; in other embodiments, the infrared wave band can also have other options, which are not limited here.

[0081] The technical solution of the above-mentioned embodiment of the present application is applied, and a shooting device is set to shoot the object to be shot in real time, and a left view and a right view are obtained. A 3D modeling device is used to perform 3D instant modeling according to the left view and the right view to obtain a 3D display model, and a display signal is generated according to the 3D display model and sent to the touch display device. Finally, the touch display device receives the display signal and displays the 3D display model for viewing by users and other learners. The technical solution of the present application has the advantages of being able to shoot objects in real time and perform instant modeling through the real-time shot object images. It is convenient to show students 3D teaching scenes in a timely manner, and it is convenient to use. At the same time, a pulley is also provided at the bottom of the podium, which is convenient for pushing the podium to various locations in the classroom, so that students can observe 3D modeling graphics at close range and in multiple ranges, which helps to improve the quality of teaching.

[0082] In addition, the present application also provides an instant modeling method, such as Figure 2 As shown, the instant modeling method comprises the following steps:

[0083] S1: receiving the left view and the right view sent by the shooting device in real time;

[0084] S2: performing feature recognition on the left view and the right view respectively to obtain a first feature point set and a second feature point set;

[0085] S3: performing feature point matching on the first feature point set and the second feature point set to establish a feature point mapping relationship between the left view and the right view;

[0086] S4: Obtaining a relative displacement between the left view and the right view according to the feature point mapping relationship;

[0087] S5: translating the left view and the right view according to the relative displacement to obtain a target image;

[0088] S6: Acquire depth information of each feature point of the target image, and establish a 3D stereo model according to the target image and the depth information.

[0089] By applying the technical solution of the above-mentioned embodiment of the present application, 3D real-time modeling can be performed according to the left view and the right view to obtain a 3D display model, and a display signal can be generated according to the 3D display model and sent to the touch display device. Finally, the display signal is received by the touch display device and the 3D display model is displayed for viewing by users and other learners.

[0090] The above-mentioned embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. An instant modeling device, characterized in that: The invention comprises an equipment platform, a shooting device, a 3D modeling device and a touch display device arranged on the equipment platform; the shooting device and the touch display device are electrically connected to the 3D modeling device respectively; the shooting device shoots the object to be shot on the equipment platform, obtains a left view and a right view and transmits them to the 3D modeling device; the 3D modeling device receives the left view and the right view, and performs 3D instant modeling according to the left view and the right view to obtain a 3D display model, specifically: performing feature recognition on the left view and the right view respectively to obtain a first feature point set and a second feature point set; performing feature point matching on the first feature point set and the second feature point set to establish a feature point mapping relationship between the left view and the right view; obtaining a relative displacement of the left view and the right view according to the feature point mapping relationship, specifically: determining a first feature point in the left view, and determining a second feature point in the right view according to the feature point mapping relationship, The second feature point is the feature point in the right view that has the greatest correlation with the first feature point; according to the position of the first feature point and the position of the second feature point, the relative displacement of the left view and the right view is obtained; wherein the relative displacement includes a horizontal displacement and / or a vertical displacement; according to the relative displacement, the left view and the right view are translated to obtain a target image; the depth information of each feature point of the first feature point set is obtained, the depth information of each feature point of the second feature point set is obtained, the depth information of each feature point is matched with the feature point of the target image, the depth information of each feature point of the target image is obtained, and a 3D stereo model is established according to each feature point of the target image and the depth information of each feature point; the 3D modeling device generates a display signal according to the 3D display model and sends it to the touch display device; the touch display device receives the display signal and displays the 3D display model.

2. The instant modeling device according to claim 1, characterized in that: The step of translating the left view and the right view according to the relative displacement to obtain a target image includes: According to the relative displacement, the left view is translated to overlap with the right view to obtain a target image, or, The right view is translated to overlap with the left view according to the relative displacement to obtain a target image.

3. The instant modeling device according to claim 1, characterized in that: Before the step of acquiring the depth information of each feature point of the target image and establishing a 3D stereo model according to the target image and the depth information, the method further includes: The screen boundary of the touch display device is obtained, and the image to be cropped that exceeds the screen boundary in the target image is obtained according to the screen boundary, and the image to be cropped is cropped to obtain the target image.

4. The instant modeling device according to claim 1, characterized in that: The instant modeling device is an instant modeling podium, the device platform is a podium body, and the shooting device and the touch display device are installed on the podium body.

5. The instant modeling device according to claim 4, characterized in that: The platform body comprises a cabinet and a panel arranged above the cabinet; a plurality of pulleys are installed at the bottom of the cabinet.

6. The instant modeling device according to claim 1, characterized in that: The touch display device comprises a frame, a display and a touch component; the display and the touch component are installed in the frame, and the touch component is located on a side of the display facing a user.

7. An instant modeling method, characterized in that: The following steps are involved: Receiving the left view and the right view sent by the shooting device in real time; Performing feature recognition on the left view and the right view respectively to obtain a first feature point set and a second feature point set; Performing feature point matching on the first feature point set and the second feature point set to establish a feature point mapping relationship between the left view and the right view; Obtaining the relative displacement between the left view and the right view according to the feature point mapping relationship, specifically: determining a first feature point in the left view, and determining a second feature point in the right view according to the feature point mapping relationship, wherein the second feature point is a feature point in the right view that has the greatest correlation with the first feature point; obtaining the relative displacement between the left view and the right view according to the position of the first feature point and the position of the second feature point; wherein the relative displacement includes a horizontal displacement and / or a vertical displacement; According to the relative displacement, the left view and the right view are translated to obtain a target image; Acquire depth information of each feature point of the first feature point set, and acquire depth information of each feature point of the second feature point set; Matching the depth information of each feature point with the feature points of the target image to obtain depth information corresponding to each feature point of the target image; A 3D stereo model is established according to each feature point of the target image and the depth information of each feature point.