Digital field domain space virtual avatar differentiation generation method and system

Abstract

The invention relates to a digitalized field domain space virtual avatar differentiation generation method and system. The method comprises the steps that three-dimensional point cloud scanning data and image data of an object are acquired; constructing a virtual space model belonging to the object by using the three-dimensional point cloud scanning data, wherein the virtual space model consists of a plurality of surfaces; cutting the image data to obtain sub-image data; matching the sub-image data with the surface, adjusting the sub-image data after successful matching, and endowing the sub-image data to the surface; and fusing gaps of adjacent surface time to obtain a virtual avatar. According to the digitalized field domain space virtual avatar differentiation generation method and system disclosed by the invention, the virtual avatar of the user in the digitalized field domain space is created in a mode of constructing the three-dimensional space model and endowing the image based on the user, so that the virtual avatar has obvious difference.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for generating differentiated virtual avatars in a digital field space. Background Art

[0002] Digital field space refers to the electronic recording or operation of specific areas (such as cultural and tourist attractions, urban areas, industrial parks, etc.) at different levels in a digital way. It uses modern information technology, such as 3D modeling, virtual reality (VR), augmented reality (AR), Internet of Things (IoT), big data, cloud computing, etc., to digitally replicate, simulate and enhance physical space, thereby creating a new and interactive virtual environment.

[0003] The initial definition of avatars included flat avatars in online forums, instant messaging software, and social media, and can even be traced back to text user names in earlier text-based multiplayer online games. However, with the advancement of technology, the development of avatars has evolved from simple text user names and flat avatars to three-dimensional models. With the rise of technologies such as the metaverse, the definition of avatars has been further broadened to represent the real projection of users in digital field space.

[0004] Currently in the metaverse, users mostly choose existing virtual avatars, which to a certain extent leads to duplication of virtual avatars. Allowing users to design their own avatars (using provided templates) still poses this problem. How to directly generate virtual avatars based on users so that the avatars have obvious differences requires further research. Summary of the invention

[0005] The present application provides a method and system for generating differentiated virtual avatars in a digital field space, which creates a virtual avatar of a user in a digital field space by constructing a three-dimensional space model based on the user and assigning an image, so that the virtual avatar has obvious differences.

[0006] The above-mentioned purpose of the present application is achieved through the following technical solutions: In a first aspect, the present application provides a method for generating a differentiated virtual avatar in a digital field space, comprising: Obtain three-dimensional point cloud scanning data and image data of the object; Using 3D point cloud scanning data to construct a virtual space model belonging to the object, the virtual space model is composed of multiple surfaces; Cut the image data to obtain sub-image data; Matching the sub-image data with the surface, and adjusting and assigning the sub-image data to the surface after successful matching; The gaps between adjacent surface times are merged to obtain a virtual avatar.

[0007] In a possible implementation manner of the first aspect, when acquiring three-dimensional point cloud scanning data of an object, the object is scanned multiple times, and the angle of each scan is different.

[0008] In a possible implementation manner of the first aspect, cropping the image data includes: The image data is cut once according to the texture, and the image data is divided into multiple parts, which are recorded as partial image data; Part of the image data is identified and the image data is cut according to the identification result to obtain a surface.

[0009] In a possible implementation manner of the first aspect, cropping the image data once according to the texture includes: Performing grayscale processing on the image data to obtain grayscale image data; Select an area on the grayscale image data, the shape of the area is a rectangle; A vector is established inside the region according to the pixels in the region, the length of the vector is the distance between two pixels, and the angle of the vector is the color difference between the two pixels; The similarity of the regions is compared and the image data is cropped once according to the comparison result to obtain partial image data.

[0010] In a possible implementation manner of the first aspect, when one partial image data is completely located inside another partial image data, the two partial image data are merged into one partial image data.

[0011] In a possible implementation manner of the first aspect, identifying part of the image data and cropping the image data according to the recognition result includes: Obtaining the outline of a portion of the image data and cutting the portion of the image data according to the outline; Identify the cropped portion of the image data; Depending on the recognition result, you can choose to keep the recognition result or continue to cut part of the image data according to the outline until the part of the image data is completely recognized.

[0012] In a possible implementation manner of the first aspect, when one contour is located inside another contour, the two contours are merged into one contour.

[0013] In a second aspect, the present application provides a device for generating differentiated virtual avatars in a digital field space, comprising: A data acquisition unit, used to acquire three-dimensional point cloud scanning data and image data of the object; A construction unit, used for constructing a virtual space model belonging to the object using the three-dimensional point cloud scanning data, wherein the virtual space model is composed of a plurality of surfaces; A cutting unit, used for cutting the image data to obtain sub-image data; A matching and assigning unit, used to match the sub-image data with the surface, and after successful matching, adjust the sub-image data and assign it to the surface; The fusion unit is used to fuse the gaps between adjacent surface times to obtain a virtual avatar.

[0014] In a third aspect, the present application provides a system for generating differentiated virtual avatars in a digital field space, the system comprising: one or more memories for storing instructions; and One or more processors, used to call and run the instructions from the memory to execute the method as described in the first aspect and any possible implementation of the first aspect.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium comprising: Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0016] In a fifth aspect, the present application provides a computer program product, comprising program instructions. When the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0017] In a sixth aspect, the present application provides a chip system, which includes a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0018] The chip system may be composed of chips, or may include chips and other discrete devices.

[0019] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic flowchart of the steps of a method for differentiated generation of virtual avatars in a digital field space provided by the present application.

[0021] Figure 2 This is a schematic diagram of three-dimensional point cloud scanning data generated based on an object provided in this application.

[0022] Figure 3 It is a schematic diagram of creating a region on grayscale image data provided by the present application.

[0023] Figure 4 It is a schematic diagram of a vector group provided in this application.

[0024] Figure 5 It is a schematic diagram for comparing two vector groups provided by the present application. DETAILED DESCRIPTION

[0025] The technical solution in this application is further described in detail below in conjunction with the accompanying drawings.

[0026] This application discloses a method for generating differentiated virtual avatars in a digital field space. Figure 1 In some examples, the method for generating differentiated virtual avatars in a digital field space disclosed in the present application includes the following steps: S101, obtaining three-dimensional point cloud scanning data and image data of the object; S102, constructing a virtual space model belonging to the object using the three-dimensional point cloud scanning data, where the virtual space model consists of multiple surfaces; S103, cutting the image data to obtain sub-image data; S104, matching the sub-image data with the surface, and adjusting the sub-image data and assigning it to the surface after the matching is successful; S105, merging the gaps between adjacent surface times to obtain a virtual avatar.

[0027] In general, the method for differentiated generation of virtual avatars in a digital field space provided in this application requires the use of laser radar, image sensors and servers. The laser radar and image sensors are responsible for collecting data, and the server is responsible for processing the data collected by the laser radar and image sensors to generate virtual avatars.

[0028] The specific process is that the user stands on the workbench, and the laser radar and image sensor collect data around the workbench, or there are multiple groups of laser radars and image sensors, and each group of laser radars and image sensors moves up and down at one position to collect data, and the collected data is sent to the server.

[0029] In step S101, the server obtains the three-dimensional point cloud scanning data of the object ( Figure 2 The three-dimensional point cloud scanning data is then used in step S102 to construct a virtual space modeling belonging to the object. The virtual space modeling is composed of multiple surfaces, but the surface at this time has no color, or the surface can be interpreted as the skeleton of the virtual avatar.

[0030] In step S103, the image data is cropped to obtain sub-image data, and then the sub-image data is matched with the surface in S104. After the match is successful, the sub-image data is adjusted and assigned to the surface. The surface at this time has color, and finally the gaps between adjacent surfaces are merged in S105 to obtain a virtual avatar.

[0031] The virtual avatars obtained by the above method are generated based on the user, so that each virtual avatar has obvious differences, and when the user's clothing changes, a new virtual avatar can be generated again. This method not only solves the difficulty problem of users directly using software to generate, but also makes the generation of virtual avatars independent of templates.

[0032] In some examples, when obtaining the 3D point cloud scan data of an object, the object is scanned multiple times, and each scan is performed at a different angle, in order to obtain richer data. It should be understood that when constructing a surface using the 3D point cloud scan data, the surface is generated by points in the 3D space, and the more points there are, the more realistic the shape of the surface is.

[0033] In some examples, the specific way of cropping the image data is: S201, cutting the image data once according to the texture, dividing the image data into multiple parts, which are recorded as partial image data; S202, identifying part of the image data and cutting the image data according to the identification result to obtain a surface.

[0034] The reason for using texture to cut image data is that there are a large number of clothing materials, and the colors and patterns are also extremely rich. If an artificial intelligence recognition model is used for recognition, when new materials, new colors and new patterns appear, it is easy to cause recognition errors, and the differences in clothing shapes will also cause recognition errors.

[0035] In order to solve this problem, the present application uses texture to perform a single cut of the image data. For the same material, the texture will not change, that is, when the texture is used for a single cut, the color, pattern and shape will not be affected.

[0036] After one cutting, the image data is decomposed into multiple partial image data. At this time, the artificial intelligence recognition model is used for recognition, and then the image data is cut according to the recognition result to obtain the surface. The surface obtained at this time is the surface of an object, such as a piece of clothing. After recognition, the entire piece of clothing is regarded as a surface.

[0037] The way to cut the image data once according to the texture is: S301, grayscale processing is performed on the image data to obtain grayscale image data; S302, selecting an area on the grayscale image data, where the shape of the area is a rectangle; S303, establishing a vector inside the region according to the pixels in the region, where the length of the vector is the distance between two pixels, and the angle of the vector is the color difference between the two pixels; S304, comparing the similarities of the regions and cutting the image data once according to the comparison result to obtain partial image data.

[0038] The contents of step S301 to step S304 are to create a region on the grayscale image data. Figure 3 As shown, the region is then used for comparison. The specific method is to establish a vector inside the region according to the pixels in the region. The length of the vector is the distance between the two pixels, and the angle of the vector is the color difference between the two pixels.

[0039] At this point, we will get a vector group. Figure 4 As shown, a vector group includes multiple vectors, and the vectors in the same vector group have the same starting point but different end points.

[0040] The role of the vector group is to visualize the region. This application does not limit the method of establishing vectors within the region, but requires that each region use the same method.

[0041] See also Figure 5 The specific way to compare the similarity of the regions is to overlap the starting points of the two vector groups, and then compare them. The length difference and angle difference of the two corresponding vectors in the two vector groups are weighted and calculated as follows: Difference = length difference*P+angle difference*Q, P+Q=1; When the difference is less than the set value, the corresponding two vectors in the two vector groups are considered to be the same; The two vector groups are similar if the ratio of the number of identical vectors in one vector group (the corresponding vectors in the other vector group) to the number of all vectors in the vector group is greater than a set value.

[0042] In some possible implementations, when one piece of partial image data is completely located inside another piece of partial image data, the two pieces of partial image data are merged into one piece of partial image data.

[0043] In some examples, the method of identifying a portion of the image data and cropping the image data according to the identification result is: S401, obtaining the outline of part of the image data and cutting the part of the image data according to the outline; S402, identifying the cropped portion of image data; S403: Select to retain the recognition result or continue to cut part of the image data according to the outline according to the recognition result until the part of the image data is completely recognized.

[0044] The contents in step S401 to step S403 are corrections to the texture processing process, because there may be a situation where the same texture features belong to two objects. In order to solve this problem, in step S401 to step S403, the outline of the partial image data is first obtained and the partial image data is cut according to the outline, and then the cut partial image data is recognized. The recognition here requires the use of an artificial intelligence recognition model. Finally, according to the recognition result, it is selected to retain the recognition result or continue to cut the partial image data according to the outline until the partial image data is completely recognized.

[0045] In some possible implementations, when one contour is located inside another contour, the two contours are merged into one contour.

[0046] The present application also provides a device for generating a differentiated virtual avatar in a digital field space, comprising: A data acquisition unit, used to acquire three-dimensional point cloud scanning data and image data of the object; A construction unit, used for constructing a virtual space model belonging to the object using the three-dimensional point cloud scanning data, wherein the virtual space model is composed of a plurality of surfaces; A cutting unit, used for cutting the image data to obtain sub-image data; A matching and assigning unit, used to match the sub-image data with the surface, and after successful matching, adjust the sub-image data and assign it to the surface; The fusion unit is used to fuse the gaps between adjacent surface times to obtain a virtual avatar.

[0047] Furthermore, it also includes: A first cutting unit, used for cutting the image data once according to the texture, and dividing the image data into a plurality of parts, which are recorded as partial image data; The second cutting unit is used to identify part of the image data and cut the image data according to the identification result to obtain a surface.

[0048] Furthermore, it also includes: A grayscale processing unit, used for grayscale processing the image data to obtain grayscale image data; The area selection unit is used to select an area on the grayscale image data, and the shape of the area is a rectangle; A vector processing unit, used to establish a vector inside the region according to the pixels in the region, wherein the length of the vector is the distance between two pixels, and the angle of the vector is the color difference between the two pixels; The third cropping unit is used to compare the similarity of the regions and crop the image data once according to the comparison result to obtain partial image data.

[0049] Furthermore, when one partial image data is completely located inside another partial image data, the two partial image data are merged into one partial image data.

[0050] Furthermore, it also includes: A fourth cutting unit, used for obtaining the outline of the partial image data and cutting the partial image data according to the outline; A first recognition unit, used for recognizing the cropped portion of image data; The second recognition unit is used to select to retain the recognition result or continue to cut part of the image data according to the outline according to the recognition result until the part of the image data is completely recognized.

[0051] Further, when one contour is located inside another contour, the two contours are merged into one contour.

[0052] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0053] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0054] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in this application are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0055] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0056] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0057] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0058] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0059] It should also be understood that in various embodiments of the present application, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present application.

[0060] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0061] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a computer-readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0062] The present application also provides a digital field space virtual avatar differentiation generation system, the system comprising: one or more memories for storing instructions; and One or more processors are used to call and run the instructions from the memory to execute the method as described above.

[0063] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device and the network device perform operations of the terminal device and the network device corresponding to the above method.

[0064] The present application also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0065] The chip system may be composed of chips, or may include chips and other discrete devices.

[0066] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0067] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0068] Optionally, the computer instructions are stored in a memory.

[0069] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0070] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0071] The nonvolatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0072] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory.

[0073] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for generating differentiated virtual avatars in a digital field space, characterized in that: include: Obtain three-dimensional point cloud scanning data and image data of the object; Using 3D point cloud scanning data to construct a virtual space model belonging to the object, the virtual space model is composed of multiple surfaces; Cut the image data to obtain sub-image data; Matching the sub-image data with the surface, and adjusting and assigning the sub-image data to the surface after the match is successful; The gaps between adjacent surface times are merged to obtain a virtual avatar.

2. The method for generating differentiated virtual avatars in a digital field space according to claim 1, characterized in that: When acquiring 3D point cloud scanning data of an object, the object is scanned multiple times, and the angle of each scan is different.

3. The method for generating differentiated virtual avatars in a digital field space according to claim 1, characterized in that: Cropping the image data includes: The image data is cut once according to the texture, and the image data is divided into multiple parts, which are recorded as partial image data; Part of the image data is identified and the image data is cut according to the identification result to obtain a surface.

4. The method for generating differentiated virtual avatars in a digital field space according to claim 3, characterized in that: The image data is cut once according to the texture, including: Performing grayscale processing on the image data to obtain grayscale image data; Select an area on the grayscale image data, the shape of the area is a rectangle; A vector is established inside the region according to the pixels in the region. The length of the vector is the distance between two pixels, and the angle of the vector is the color difference between the two pixels. The similarity of the regions is compared and the image data is cropped once according to the comparison result to obtain partial image data.

5. The method for generating differentiated virtual avatars in a digital field space according to claim 4, characterized in that: When one partial image data is completely located inside another partial image data, the two partial image data are merged into one partial image data.

6. The method for generating differentiated virtual avatars in a digital field space according to claim 3, characterized in that: Identifying part of the image data and cropping the image data according to the identification result includes: Obtaining the outline of a portion of the image data and cutting the portion of the image data according to the outline; Identify the cropped portion of the image data; Depending on the recognition result, you can choose to keep the recognition result or continue to cut part of the image data according to the outline until the part of the image data is completely recognized.

7. The method for generating differentiated virtual avatars in a digital field space according to claim 6, characterized in that: When one contour is located inside another contour, the two contours are merged into one contour.

8. A device for generating differentiated virtual avatars in a digital field space, characterized in that: include: A data acquisition unit, used to acquire three-dimensional point cloud scanning data and image data of the object; A construction unit, used for constructing a virtual space model belonging to the object using the three-dimensional point cloud scanning data, wherein the virtual space model is composed of a plurality of surfaces; A cutting unit, used for cutting the image data to obtain sub-image data; A matching and assigning unit, used to match the sub-image data with the surface, and after successful matching, adjust the sub-image data and assign it to the surface; The fusion unit is used to fuse the gaps between adjacent surface times to obtain a virtual avatar.

9. A digital field space virtual avatar differentiation generation system, characterized in that: The system comprises: one or more memories for storing instructions; and One or more processors, configured to call and execute the instructions from the memory to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images