File travel digital human modeling method and system

Abstract

The invention relates to the technical field of digital human generation, and particularly discloses a text travel digital human modeling method and system, and the method comprises the steps: obtaining the scene information of a text travel scene, and creating a digital twinborn model; acquiring a video of a public area, performing feature recognition on the video, constructing a virtual digital human, and inserting a digital twinborn model; receiving an access request containing access parameters sent by a remote user, intercepting a digital twinborn model containing the virtual digital human according to the access parameters, and sending the digital twinborn model to the remote user; feedback information of a remote user is obtained in real time, and the intercepted digital twinborn model containing the virtual digital human is adjusted according to the feedback information. According to the remote travel service provided by the invention, a console game is converted into an online game, so that the authenticity is greatly improved, the utilization rate is favorably improved, and good travel service is provided for people who are inconvenient to go out.

Description

Technical Field

[0001] The present invention relates to the field of digital human generation technology, and in particular to a cultural tourism digital human modeling method and system. Background Art

[0002] "Cultural Tourism Digital Human," short for "Cultural Tourism Digital Human," is an innovative application of cutting-edge technologies, including digital technology, artificial intelligence, and virtual reality, that has been adopted in recent years within the cultural tourism industry. It primarily refers to virtual characters created through digital modeling, AI-driven development, speech synthesis, and motion capture, enhancing the interactivity, immersion, and communication effectiveness of cultural tourism scenarios.

[0003] Existing cultural and tourism digital humans are only used to provide explanation services, to assist and guide people in work and travel, etc., and the interaction positions of most cultural and tourism digital humans are fixed, resulting in problems such as insufficient interactivity and low utilization rate. Therefore, how to improve the interactivity and utilization rate of cultural and tourism digital humans is the technical problem that the technical solution of the present invention aims to solve. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for modeling a digital human in cultural tourism to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A cultural tourism digital human modeling method and system, the method comprising:

[0007] Obtain scene information of cultural and tourism scenes and create digital twin models;

[0008] Obtain videos from public areas, perform feature recognition on the videos, build virtual digital humans, and insert them into the digital twin model;

[0009] Receiving an access request containing access parameters sent by a remote user, intercepting a digital twin model containing a virtual digital human according to the access parameters, and sending it to the remote user;

[0010] In the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, feedback information from the remote user is obtained in real time, and the intercepted digital twin model containing the virtual digital human is adjusted according to the feedback information.

[0011] As a further solution of the present invention: the step of obtaining scene information of the cultural tourism scene and creating a digital twin model includes:

[0012] Obtain a map of the cultural tourism scene and locate the passable area based on the plot features of the map;

[0013] Get the center line of the traffic area and select the middle point on the center line based on the preset step size;

[0014] Obtaining the subject level of each intermediate point in the direction perpendicular to the center line, and determining the offset of the intermediate point according to the subject level;

[0015] Determine the offset point of each intermediate point based on the offset;

[0016] A motion path is generated based on the offset points, and the motion path is sent to the visual acquisition robot to acquire visual information. The process of acquiring visual information is to rotationally acquire an image at each offset point, with the acquisition direction rotating 360 degrees in the horizontal plane.

[0017] Creating a digital twin model based on the visual information and a map of the cultural tourism scene;

[0018] The calculation process of the offset is:

[0019] Where P is the offset, α is the preset correction coefficient, N is the number of all subjects in the vertical centerline direction, and L is the maximum value of the target. i represents the subject level of the i-th subject, d i Represents the distance between the i-th subject and the middle point. The distance has a sign, which is determined by the direction relationship between the subject and the middle point. The direction corresponding to the positive sign is the preset value.

[0020] As a further solution of the present invention: the steps of obtaining a video of a public area, performing feature recognition on the video, constructing a virtual digital human, and inserting the virtual digital human into the digital twin model include:

[0021] Access videos of public areas;

[0022] Tracking people in the video, determining the person frame at each moment, and simultaneously determining the person's position;

[0023] When a person frame is detected, the contour of the area within the person frame is recognized and the person frame is divided into area blocks; wherein the variance of the pixel values ​​within each area block is less than a preset variance threshold;

[0024] Build virtual digital humans based on regional blocks;

[0025] Insert the virtual digital human into the digital twin model according to the personnel position to obtain the digital twin model containing the virtual digital human at each moment.

[0026] As a further solution of the present invention: the step of constructing a virtual digital human based on the regional blocks includes:

[0027] Count the segmentation results and their corresponding virtual digital humans to construct a mapping table; the mapping table includes segmentation result items and virtual digital human items. The segmentation result is a matrix generated by regional blocks. When the personnel position corresponding to the regional block does not belong to the cultural and tourism scene, the data item corresponding to the regional block is deleted from the mapping table;

[0028] When a new segmentation result is obtained, the virtual digital person is matched in the mapping table;

[0029] When the matching fails, the segmented area blocks are read in sequence, the model library is located at the position in the person frame, and the model is searched in the model library based on the area blocks;

[0030] The model found is statistically analyzed based on the position sequence of the area blocks in the personnel frame, a virtual digital human is constructed, and the mapping table is updated synchronously;

[0031] The generation process of the segmentation results is as follows:

[0032] The average color value of each area block is obtained, and then the average color value is calculated according to the position relationship of the area blocks to obtain a matrix as the segmentation result.

[0033] As a further solution of the present invention, the steps of receiving an access request containing access parameters from a remote user, intercepting a digital twin model containing a virtual digital human according to the access parameters, and sending the model to the remote user include:

[0034] Receive access requests from remote users and open parameter acquisition ports to users;

[0035] The access time, access coordinates and access direction input by the remote user are received by the port based on the parameter acquisition;

[0036] Locating the digital twin model according to the access time, and obtaining a captured image according to the access coordinates and access direction;

[0037] The digital twin model containing the virtual digital human is captured based on the captured image and sent to the remote user.

[0038] As a further solution of the present invention: in the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, the steps of obtaining feedback information from the remote user in real time and adjusting the intercepted digital twin model containing the virtual digital human according to the feedback information include:

[0039] In the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, the facial data of the remote user is obtained in real time based on the pre-granted interaction permissions;

[0040] Input facial data into the trained emotion assessment model and output the favorability;

[0041] Query the virtual human in the intercepted digital twin model as the remote user's favorability towards the virtual human;

[0042] Adjustments are made to all virtual digital humans in the digital twin model based on favorability.

[0043] The technical solution of the present invention also provides a cultural tourism digital human modeling system, the system comprising:

[0044] Twin model creation module, used to obtain scene information of cultural and tourism scenes and create digital twin models;

[0045] The digital human construction module is used to obtain videos of public areas, perform feature recognition on the videos, build virtual digital humans, and insert them into the digital twin model;

[0046] The model interception and display module is used to receive an access request containing access parameters sent by a remote user, intercept the digital twin model containing the virtual digital human according to the access parameters, and send it to the remote user;

[0047] The display content adjustment module is used to obtain feedback information from remote users in real time during the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, and adjust the intercepted digital twin model containing the virtual digital human according to the feedback information.

[0048] As a further solution of the present invention: the twin model creation module includes:

[0049] A traffic area positioning unit, used to obtain a map of the cultural tourism scene and locate the traffic area based on the land features of the map;

[0050] A middle point selection unit is used to obtain the middle line of the passage area and select middle points on the middle line based on a preset step size;

[0051] an offset determination unit, configured to obtain a subject level of each intermediate point in a direction perpendicular to the center line, and determine an offset of the intermediate point according to the subject level;

[0052] An offset point determination unit, configured to determine the offset point of each intermediate point based on the offset amount;

[0053] A visual information acquisition unit is configured to generate a motion path based on the offset points and transmit the motion path to a visual acquisition robot to acquire visual information. The process of acquiring visual information comprises rotating an image at each offset point, with the acquisition direction rotating 360 degrees in the horizontal plane.

[0054] Creating an execution unit for creating a digital twin model based on the visual information and the map of the cultural and tourism scene;

[0055] The calculation process of the offset is:

[0056] Where P is the offset, α is the preset correction coefficient, N is the number of all subjects in the vertical centerline direction, and L is the maximum value of the target. i represents the subject level of the i-th subject, d i Represents the distance between the i-th subject and the middle point. The distance has a sign, which is determined by the direction relationship between the subject and the middle point. The direction corresponding to the positive sign is the preset value.

[0057] As a further solution of the present invention: the digital human construction module includes:

[0058] A video acquisition unit, used for acquiring videos of public areas;

[0059] A personnel positioning unit, used to track personnel in the video, determine the personnel frame at each moment, and simultaneously determine the personnel position;

[0060] A frame segmentation unit is configured to, when a person frame is detected, perform contour recognition on the area within the person frame and segment the person frame into area blocks; wherein the variance of the pixel values ​​within each area block is less than a preset variance threshold;

[0061] A regional block application unit, used to construct a virtual digital human based on regional blocks;

[0062] The insertion execution unit is used to insert the virtual digital human into the digital twin model according to the personnel position, and obtain the digital twin model containing the virtual digital human at each moment.

[0063] As a further solution of the present invention: the model interception display module includes:

[0064] A port opening unit is used to receive access requests from remote users and open parameter acquisition ports to users;

[0065] a parameter receiving unit, configured to receive access time, access coordinates, and access direction input by a remote user based on the parameter acquisition port;

[0066] A map acquisition unit is used to locate the digital twin model according to the access time and obtain the intercepted map according to the access coordinates and access direction;

[0067] The interception execution unit is used to intercept the digital twin model containing the virtual digital human based on the intercepted image and send it to the remote user.

[0068] Compared with the prior art, the present invention has the following beneficial effects:

[0069] The present invention constructs a digital twin model based on cultural and tourism scenarios, obtains tourists based on public videos, constructs virtual digital humans corresponding to the tourists in real time, inserts the digital twin model, and provides remote tourism services based on the digital twin model containing the real-time changing virtual digital humans. It has strong interactivity and high degree of restoration, which is equivalent to converting a stand-alone game into an online game, greatly improving the authenticity, helping to improve the interactivity and usage rate of existing cultural and tourism digital humans, and providing good cultural and tourism services for people who have difficulty traveling. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention.

[0071] Figure 1 The overall flow chart of the cultural tourism digital human modeling method is shown.

[0072] Figure 2 The structural diagram of the cultural and tourism digital human modeling system is shown. DETAILED DESCRIPTION

[0073] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0074] Figure 1 This is a general flow chart of a digital human modeling method and system for cultural tourism. In an embodiment of the present invention, a digital human modeling method for cultural tourism includes:

[0075] Step S100: Acquire scene information of the cultural tourism scene and create a digital twin model;

[0076] The technical solution of the present invention is applied to areas available for sightseeing, such as scenic spots, which are called cultural and tourism scenes. Maps and visual information of the cultural and tourism scenes are obtained, and a three-dimensional model is constructed based on a preset scale. The construction process requires regular data updates. Therefore, the constructed three-dimensional model is called a digital twin model.

[0077] Step S200: Obtain a video of a public area, perform feature recognition on the video, build a virtual digital human, and insert it into the digital twin model;

[0078] Cultural and tourism scenes generally belong to public areas. Cameras will be installed in public areas. The cameras will obtain real-time videos of public areas and perform feature recognition on the videos to obtain virtual digital people corresponding to tourists. Since the positions of tourists at different times are different, the virtual digital people at different times are also different. After inserting the digital twin model, the digital twin models at different times are obtained.

[0079] It should be noted that although access to videos in public areas is permitted by default, the process of processing the videos and generating virtual digital people needs to be informed to tourists. Only after obtaining explicit authorization from tourists can the videos be accessed and "secondary creation" be performed on them.

[0080] Step S300: receiving an access request containing access parameters sent by a remote user, intercepting a digital twin model containing a virtual digital human according to the access parameters, and sending it to the remote user;

[0081] The reason why the technical solution of the present invention constructs a digital twin model containing a virtual digital human is to provide remote tour services, receive access requests containing access parameters sent by remote users, and the access parameters indicate when the remote users access what content, and intercept the digital twin model containing the virtual digital human according to the access parameters and send it to the remote users.

[0082] Specifically, regarding the remote access process, the moment when the remote user sends the access request is regarded as the access moment. After sending the access request, the execution entity of the technical solution of the present invention establishes a connection channel with the remote user, receives the perspective (a type of access parameter) selected by the remote user on the personal device, intercepts the digital twin model containing the virtual digital human in the perspective, and sends it to the remote user.

[0083] Step S400: in the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, obtaining feedback information from the remote user in real time, and adjusting the intercepted digital twin model containing the virtual digital human according to the feedback information;

[0084] After sending the intercepted digital twin model containing the virtual digital human to the remote user, feedback information sent by the remote user is received in real time. The simplest feedback information is the preference for each virtual digital human entered by the remote user. By replacing the virtual digital human with a lower preference with a virtual digital human with a higher preference, a digital twin model that is more popular with the remote user can be obtained, thereby optimizing his remote tour experience.

[0085] Regarding step S100, the steps of obtaining scene information of the cultural tourism scene and creating a digital twin model include:

[0086] Obtain a map of the cultural tourism scene and locate the passable area based on the plot features of the map;

[0087] Get the center line of the traffic area and select the middle point on the center line based on the preset step size;

[0088] Obtaining the subject level of each intermediate point in the direction perpendicular to the center line, and determining the offset of the intermediate point according to the subject level;

[0089] Determine the offset point of each intermediate point based on the offset;

[0090] A motion path is generated based on the offset points, and the motion path is sent to the visual acquisition robot to acquire visual information. The process of acquiring visual information is to rotationally acquire an image at each offset point, with the acquisition direction rotating 360 degrees in the horizontal plane.

[0091] A digital twin model is created based on the visual information and the map of the cultural and tourism scene.

[0092] Obtain a map of the cultural and tourism scene, and locate the passage area based on the land features of the map. Existing map services are extremely developed, and the process of locating the passage area is very easy. In the map provided by the manager of the cultural and tourism scene, the passage area is very obvious and accurate; obtain the center line of the passage area, select intermediate points on the center line based on a preset step size, and the step size refers to the distance at which a point is selected on the center line, which is called an intermediate point. Obtain the main level of each intermediate point in the vertical center line direction, determine the offset of the intermediate point based on the main level, determine the offset point of each intermediate point based on the offset, use the offset points corresponding to all intermediate points as waypoints, generate a motion path, and send the motion path to the visual acquisition robot to obtain visual information; wherein, each time the visual acquisition robot reaches an offset point, it rotates 360 degrees to continuously collect images to obtain visual information, and the collection directions during the rotation process are all in the same horizontal plane (or in a horizontal plane interlayer with an extremely low height, and the vertical deviation is less than a preset threshold); create a digital twin model based on the visual information and the map of the cultural and tourism scene.

[0093] Among them, for the process of determining the offset, there are actually two directions perpendicular to the center line for each intermediate point, which are located on both sides of the center line. The subjects on both sides of the center line in the cultural and tourism scene are obtained, and the subject level of the subject is queried. The subject level is the existing data, and the rating of the scenic spot is used. The offset can be determined according to the subject level.

[0094] The offset calculation process includes:

[0095] Where P is the offset, α is the preset correction coefficient, N is the number of all subjects in the vertical centerline direction, and L is the maximum value of the target. irepresents the subject level of the i-th subject, d i Represents the distance between the i-th subject and the middle point. The distance has a sign, which is determined by the direction relationship between the subject and the middle point. The direction corresponding to the positive sign is the preset value.

[0096] Regarding the direction corresponding to the positive sign, you can set any direction on both sides to be positive. The above calculation process takes into account the influence of all subjects. If the calculated value is positive, it will shift in the positive direction. If the calculated value is negative, it will shift in the negative direction.

[0097] Regarding step S200, the steps of obtaining a video of a public area, performing feature recognition on the video, constructing a virtual digital human, and inserting the virtual digital human into the digital twin model include:

[0098] Access videos of public areas;

[0099] Tracking people in the video, determining the person frame at each moment, and simultaneously determining the person's position;

[0100] When a person frame is detected, the contour of the area within the person frame is recognized and the person frame is divided into area blocks; wherein the variance of the pixel values ​​within each area block is less than a preset variance threshold;

[0101] Build virtual digital humans based on regional blocks;

[0102] Insert the virtual digital human into the digital twin model according to the personnel position to obtain the digital twin model containing the virtual digital human at each moment.

[0103] By acquiring videos of public areas, the existing personnel tracking algorithm can be used to determine the personnel frame at each moment. After locating the personnel frame, the personnel position is also determined. The personnel position is generally the center position of the bottom edge of the personnel frame, which is a coordinate. When the personnel frame is detected, the contour of the area within the personnel frame is recognized and the personnel frame is divided into area blocks. The pixel values ​​of each pixel in the same area block are almost the same. After the area block is determined, a virtual digital human is constructed based on the area block. The virtual digital human is inserted into the digital twin model according to the personnel position to obtain a digital twin model containing the virtual digital human at each moment.

[0104] Specifically, the steps of constructing a virtual digital human based on the regional blocks include:

[0105] Count the segmentation results and their corresponding virtual digital humans to construct a mapping table; the mapping table includes segmentation result items and virtual digital human items. The segmentation result is a matrix generated by regional blocks. When the personnel position corresponding to the regional block does not belong to the cultural and tourism scene, the data item corresponding to the regional block is deleted from the mapping table;

[0106] When a new segmentation result is obtained, the virtual digital person is matched in the mapping table;

[0107] When the matching fails, the segmented area blocks are read in sequence, the model library is located at the position in the person frame, and the model is searched in the model library based on the area blocks;

[0108] The model queried is statistically analyzed based on the position sequence of the area blocks in the personnel frame, a virtual digital human is constructed, and the mapping table is updated synchronously.

[0109] In an example of the technical solution of the present invention, the conversion relationship between area blocks and virtual digital people is explained. For a person frame, after contour recognition, multiple area blocks can be obtained, and the average color value of each area block is obtained. Then, the average color value is statistically calculated based on the positional relationship of the area blocks to obtain a matrix (there may be missing data in the matrix). At this time, the matrix is ​​used as the segmentation result to represent the characteristics of a tourist; after each tourist constructs a virtual digital person, it will be stored in a mapping table, which includes segmentation result items and virtual digital person items. The segmentation result is the above-mentioned matrix; for new tourists, after obtaining the area block, a matrix is ​​constructed based on the area block, and the matrix is ​​traversed through the mapping table to query whether there is a constructed virtual digital person. If so, it can be read directly. If not, a new virtual digital person needs to be constructed.

[0110] Specifically, the methods for building new virtual digital humans include:

[0111] The segmented area blocks are read in sequence, the model library is located at the position in the personnel frame, and the model is queried in the model library based on the area blocks; the queried models are counted according to the position sequence of the area blocks in the personnel frame to obtain the virtual digital human. At the same time, the segmentation result (matrix) of the area block is obtained, the obtained virtual digital human is obtained, a new data item is created, and inserted into the mapping table.

[0112] In addition, the data storage time in the mapping table can be very long, such as one month, which means that all tourists who have visited the cultural and tourism scene within one month will be recorded, but the mapping table in this way will be very large. Therefore, the technical solution of the present invention also provides a self-deletion function: when the personnel position corresponding to the area block does not belong to the cultural and tourism scene, the data item corresponding to the area block is deleted in the mapping table.

[0113] Regarding step S300, the steps of receiving an access request containing access parameters from a remote user, intercepting a digital twin model containing a virtual digital human according to the access parameters, and sending the model to the remote user include:

[0114] Receive access requests from remote users and open parameter acquisition ports to users;

[0115] The access time, access coordinates and access direction input by the remote user are received by the port based on the parameter acquisition;

[0116] Locating the digital twin model according to the access time, and obtaining a captured image according to the access coordinates and access direction;

[0117] The digital twin model containing the virtual digital human is captured based on the captured image and sent to the remote user.

[0118] Receive an access request from a remote user, open a parameter acquisition port to the user, and receive the access time, access coordinates and access direction input by the remote user based on the parameter acquisition port. The parameter acquisition port is a conventional data acquisition port. On personal devices, you can refer to the first-person perspective construction process; locate the digital twin model according to the access time, obtain a screenshot based on the access coordinates and access direction, and capture the digital twin model containing the virtual digital human based on the screenshot, and send it to the remote user; this process is very simple, which is equivalent to building a virtual three-dimensional scene. Remote users can view models from different angles in the virtual three-dimensional scene. Many existing applications based on the first-person perspective have such functions.

[0119] Regarding step S400, in the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, the step of obtaining feedback information from the remote user in real time and adjusting the intercepted digital twin model containing the virtual digital human according to the feedback information includes:

[0120] In the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, the facial data of the remote user is obtained in real time based on the pre-granted interaction permissions;

[0121] Input facial data into the trained emotion assessment model and output the favorability;

[0122] Query the virtual human in the intercepted digital twin model as the remote user's favorability towards the virtual human;

[0123] Adjustments are made to all virtual digital humans in the digital twin model based on favorability.

[0124] In an example of the technical solution of the present invention, the data structure of the feedback information is specifically defined. In the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, the facial data of the remote user is obtained in real time based on the pre-granted interaction permission, the facial data is input into the trained emotion evaluation model, and the favorability is output. At this time, the obtained favorability is considered to be the favorability of the currently observed virtual digital human. Therefore, the virtual digital human in the intercepted digital twin model is queried as the remote user's favorability towards the virtual digital human.

[0125] Adjust all virtual digital humans in the digital twin model based on the favorability. The specific operation process includes:

[0126] Read a virtual digital human whose favorability is greater than a preset first favorability threshold, read the average color value of each corresponding area block, calculate the average color value based on the position of the area block, construct an adjustment image filter based on the preset transparency, and superimpose the image filter on a virtual digital human whose favorability is less than a preset second favorability threshold.

[0127] The principle of this process is to believe that the focus of virtual digital people lies in their color, and to superimpose the color value characteristics of virtual digital people with high favorability on virtual digital people with low favorability, thereby optimizing the color.

[0128] Figure 2 The structure diagram of the cultural tourism digital human modeling system is shown. In a preferred embodiment of the technical solution of the present invention, a cultural tourism digital human modeling system is also provided. The system 10 includes:

[0129] The twin model creation module 11 is used to obtain scene information of the cultural tourism scene and create a digital twin model;

[0130] The digital human construction module 12 is used to obtain videos of public areas, perform feature recognition on the videos, construct a virtual digital human, and insert it into the digital twin model;

[0131] The model interception and display module 13 is used to receive an access request containing access parameters sent by a remote user, intercept the digital twin model containing the virtual digital human according to the access parameters, and send it to the remote user;

[0132] The display content adjustment module 14 is used to obtain feedback information from the remote user in real time during the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, and adjust the intercepted digital twin model containing the virtual digital human according to the feedback information.

[0133] Furthermore, the twin model creation module 11 includes:

[0134] A traffic area positioning unit, used to obtain a map of the cultural tourism scene and locate the traffic area based on the land features of the map;

[0135] A middle point selection unit is used to obtain the middle line of the passage area and select middle points on the middle line based on a preset step size;

[0136] an offset determination unit, configured to obtain a subject level of each intermediate point in a direction perpendicular to the center line, and determine an offset of the intermediate point according to the subject level;

[0137] An offset point determination unit, configured to determine the offset point of each intermediate point based on the offset amount;

[0138] A visual information acquisition unit is configured to generate a motion path based on the offset points and transmit the motion path to a visual acquisition robot to acquire visual information. The process of acquiring visual information comprises rotating an image at each offset point, with the acquisition direction rotating 360 degrees in the horizontal plane.

[0139] An execution unit is created to create a digital twin model based on the visual information and the map of the cultural and tourism scene.

[0140] Specifically, the digital human construction module 12 includes:

[0141] A video acquisition unit, used for acquiring videos of public areas;

[0142] A personnel positioning unit, used to track personnel in the video, determine the personnel frame at each moment, and simultaneously determine the personnel position;

[0143] A frame segmentation unit is configured to, when a person frame is detected, perform contour recognition on the area within the person frame and segment the person frame into area blocks; wherein the variance of the pixel values ​​within each area block is less than a preset variance threshold;

[0144] A regional block application unit, used to construct a virtual digital human based on regional blocks;

[0145] The insertion execution unit is used to insert the virtual digital human into the digital twin model according to the personnel position, and obtain the digital twin model containing the virtual digital human at each moment.

[0146] Furthermore, the model interception display module 13 includes:

[0147] A port opening unit is used to receive access requests from remote users and open parameter acquisition ports to users;

[0148] a parameter receiving unit, configured to receive access time, access coordinates, and access direction input by a remote user based on the parameter acquisition port;

[0149] A map acquisition unit is used to locate the digital twin model according to the access time and obtain the intercepted map according to the access coordinates and access direction;

[0150] The interception execution unit is used to intercept the digital twin model containing the virtual digital human based on the intercepted image and send it to the remote user.

[0151] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A cultural tourism digital human modeling method, characterized in that: The method comprises: Obtain scene information of cultural and tourism scenes and create digital twin models; Obtain videos from public areas, perform feature recognition on the videos, build virtual digital humans, and insert them into the digital twin model; Receiving an access request containing access parameters sent by a remote user, intercepting a digital twin model containing a virtual digital human according to the access parameters, and sending it to the remote user; In the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, feedback information from the remote user is obtained in real time, and the intercepted digital twin model containing the virtual digital human is adjusted according to the feedback information.

2. The cultural tourism digital human modeling method according to claim 1, characterized in that: The steps of obtaining scene information of the cultural tourism scene and creating a digital twin model include: Obtain a map of the cultural tourism scene and locate the passable area based on the plot features of the map; Get the center line of the traffic area and select the middle point on the center line based on the preset step size; Obtaining the subject level of each intermediate point in the direction perpendicular to the center line, and determining the offset of the intermediate point according to the subject level; Determine the offset point of each intermediate point based on the offset; A motion path is generated based on the offset points, and the motion path is sent to the visual acquisition robot to acquire visual information. The process of acquiring visual information is to rotationally acquire an image at each offset point, with the acquisition direction rotating 360 degrees in the horizontal plane. Creating a digital twin model based on the visual information and a map of the cultural tourism scene; The calculation process of the offset is: Where P is the offset, α is the preset correction coefficient, N is the number of all subjects in the vertical centerline direction, and L is the maximum value of the target. i represents the subject level of the i-th subject, d i Represents the distance between the i-th subject and the middle point. The distance has a sign, which is determined by the direction relationship between the subject and the middle point. The direction corresponding to the positive sign is a preset value.

3. The cultural tourism digital human modeling method according to claim 1, characterized in that: The steps of obtaining a video of a public area, performing feature recognition on the video, constructing a virtual digital human, and inserting the virtual human into the digital twin model include: Access videos of public areas; Tracking people in the video, determining the person frame at each moment, and simultaneously determining the person's position; When a person frame is detected, the contour of the area within the person frame is recognized and the person frame is divided into area blocks; wherein the variance of the pixel values ​​within each area block is less than a preset variance threshold; Build virtual digital humans based on regional blocks; Insert the virtual digital human into the digital twin model according to the personnel position to obtain the digital twin model containing the virtual digital human at each moment.

4. The cultural tourism digital human modeling method according to claim 3 is characterized in that: The steps of constructing a virtual digital human based on the regional blocks include: Count the segmentation results and their corresponding virtual digital humans to construct a mapping table; the mapping table includes segmentation result items and virtual digital human items. The segmentation result is a matrix generated by regional blocks. When the personnel position corresponding to the regional block does not belong to the cultural and tourism scene, the data item corresponding to the regional block is deleted from the mapping table; When a new segmentation result is obtained, the virtual digital person is matched in the mapping table; When the matching fails, the segmented area blocks are read in sequence, the model library is located at the position in the person frame, and the model is searched in the model library based on the area blocks; The model found is statistically analyzed based on the position sequence of the area blocks in the personnel frame, a virtual digital human is constructed, and the mapping table is updated synchronously; The generation process of the segmentation results is as follows: The average color value of each area block is obtained, and then the average color value is calculated according to the position relationship of the area blocks to obtain a matrix as the segmentation result.

5. The cultural tourism digital human modeling method according to claim 1, characterized in that: The step of receiving an access request containing access parameters sent by a remote user, intercepting a digital twin model containing a virtual digital human according to the access parameters, and sending the model to the remote user comprises: Receive access requests from remote users and open parameter acquisition ports to users; The access time, access coordinates and access direction input by the remote user are received by the port based on the parameter acquisition; Locating the digital twin model according to the access time, and obtaining a captured image according to the access coordinates and access direction; The digital twin model containing the virtual digital human is captured based on the captured image and sent to the remote user.

6. The cultural tourism digital human modeling method according to claim 1, characterized in that: The step of obtaining feedback information from the remote user in real time during the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, and adjusting the intercepted digital twin model containing the virtual digital human according to the feedback information includes: In the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, the facial data of the remote user is obtained in real time based on the pre-granted interaction permissions; Input facial data into the trained emotion assessment model and output the favorability; Query the virtual digital human in the intercepted digital twin model as the remote user's favorability towards the virtual digital human; Adjust all virtual digital humans in the digital twin model based on favorability.

7. A cultural tourism digital human modeling system, characterized by: The system comprises: Twin model creation module, used to obtain scene information of cultural and tourism scenes and create digital twin models; The digital human construction module is used to obtain videos of public areas, perform feature recognition on the videos, build virtual digital humans, and insert them into the digital twin model; The model interception and display module is used to receive an access request containing access parameters sent by a remote user, intercept the digital twin model containing the virtual digital human according to the access parameters, and send it to the remote user; The display content adjustment module is used to obtain feedback information from remote users in real time during the process of sending the intercepted digital twin model containing the virtual digital human to the remote user, and adjust the intercepted digital twin model containing the virtual digital human according to the feedback information.

8. The cultural tourism digital human modeling system according to claim 7, characterized in that: The twin model creation module includes: A traffic area positioning unit, used to obtain a map of the cultural tourism scene and locate the traffic area based on the land features of the map; A middle point selection unit is used to obtain the middle line of the passage area and select middle points on the middle line based on a preset step size; an offset determination unit, configured to obtain a subject level of each intermediate point in a direction perpendicular to the center line, and determine an offset of the intermediate point according to the subject level; An offset point determination unit, configured to determine the offset point of each intermediate point based on the offset amount; A visual information acquisition unit is configured to generate a motion path based on the offset points and transmit the motion path to a visual acquisition robot to acquire visual information. The process of acquiring visual information comprises rotating an image at each offset point, with the acquisition direction rotating 360 degrees in the horizontal plane. Creating an execution unit for creating a digital twin model based on the visual information and the map of the cultural and tourism scene; The calculation process of the offset is: Where P is the offset, α is the preset correction coefficient, N is the number of all subjects in the vertical centerline direction, and L is the maximum value of the target. i represents the subject level of the i-th subject, d i Represents the distance between the i-th subject and the middle point. The distance has a sign, which is determined by the direction relationship between the subject and the middle point. The direction corresponding to the positive sign is a preset value.

9. The cultural tourism digital human modeling system according to claim 8, characterized in that: The digital human building module includes: A video acquisition unit, used to acquire videos of public areas; A personnel positioning unit, configured to track personnel in the video, determine the personnel frame at each moment, and simultaneously determine the personnel position; A frame segmentation unit is configured to, when a person frame is detected, perform contour recognition on the area within the person frame and segment the person frame into area blocks; wherein the variance of the pixel values ​​within each area block is less than a preset variance threshold; A regional block application unit, used to construct a virtual digital human based on regional blocks; The insertion execution unit is used to insert the virtual digital human into the digital twin model according to the personnel position, and obtain the digital twin model containing the virtual digital human at each moment.

10. The cultural tourism digital human modeling system according to claim 9, characterized in that: The model interception display module includes: A port opening unit is used to receive access requests from remote users and open parameter acquisition ports to users; a parameter receiving unit, configured to receive access time, access coordinates, and access direction input by a remote user based on the parameter acquisition port; A map acquisition unit is used to locate the digital twin model according to the access time and obtain the intercepted map according to the access coordinates and access direction; The interception execution unit is used to intercept the digital twin model containing the virtual digital human based on the intercepted image and send it to the remote user.

Images