CN111427456B - Real-time interaction method, device and equipment based on holographic imaging and storage medium - Google Patents

Abstract

The invention relates to the technical field of holographic interaction, and discloses a real-time interaction method, a real-time interaction device, a real-time interaction equipment and a storage medium based on holographic imaging, wherein the method comprises the following steps: the method comprises the steps of obtaining environment information and life body information of a target scene, establishing a target scene model according to the environment information and the life body information, carrying out holographic projection on the target scene model, obtaining preset interaction points in the target scene model, establishing an interaction mode based on the preset interaction points, and carrying out interaction on a corresponding scene adjusting device in the target scene or the target scene model so as to improve modeling speed and the precision, the visual degree and the visual degree of the target scene model, further realizing real-time man-machine interaction of the target scene model and the scene adjusting device, meeting the requirements of diversity, innovation and interactivity of users, and improving the practicability and user experience of the holographic interaction.

Description

Holographic imaging-based real-time interactive method, device, device and storage medium

technical field

The present invention relates to the technical field of holographic interaction, and in particular, to a real-time interaction method, device, device and storage medium based on holographic imaging.

Background technique

With the advent of holographic projection technology, holographic projection technology has been widely used in film and television, science and technology exhibitions and other fields, but it is rarely involved in the field of vehicle and remote monitoring. Most of the existing vehicle products and remote monitoring systems are only one-way planes Display, lack of interactive design, users can only passively receive information, can not use voice, motion commands, remote terminals, etc. for human-computer interaction, poor control experience, can not meet people's needs for diversity, innovation and interactivity. Therefore, how to realize real-time human-computer interaction based on holographic imaging technology to improve the practicability and user experience of holographic interaction has become an urgent problem to be solved.

The above content is only used to assist the understanding of the technical solutions of the present invention, and does not mean that the above content is the prior art.

SUMMARY OF THE INVENTION

The main purpose of the present invention is to provide a real-time interaction method, device, device and storage medium based on holographic imaging, aiming to solve the technology of how to realize real-time human-computer interaction based on holographic imaging technology to improve the practicability and user experience of holographic interaction question.

In order to achieve the above object, the present invention provides a real-time interaction method based on holographic imaging, the method includes the following steps:

Acquire the environmental information and life information of the target scene, and establish a target scene model according to the environmental information and the life information;

Perform holographic projection on the target scene model, and obtain preset interaction points in the target scene model;

An interaction mode is established based on the preset interaction point, and the corresponding scene adjustment device in the target scene or the target scene model is interacted according to the interaction mode.

Preferably, the step of acquiring the environmental information and the living body information of the target scene, and establishing the target scene model according to the environmental information and the living body information, specifically includes:

Obtain the environmental information and life information of the target scene from the preset position respectively;

performing three-dimensional modeling based on the environmental information, generating a first model, and inputting the first model into the first splicing layer;

perform three-dimensional modeling based on the living body information, generate a second model, and input the second model into the second splicing layer;

adaptively splicing the first model in the first splicing layer and the second model in the second splicing layer to generate a preliminary scene model;

Effect processing is performed on the preliminary scene model to generate a target scene model.

Preferably, the step of performing effect processing on the preliminary scene model to generate a target scene model specifically includes:

Obtain the user's location parameters and preset effect enhancement parameters;

Effect processing is performed on the preliminary scene model according to the position parameter and the preset effect enhancement parameter to obtain a target scene model.

Preferably, before the step of performing holographic projection on the target scene model and acquiring preset interaction points in the target scene model, the method further includes:

Performing life action recognition and device drive identification on the target scene model, to obtain life body action information and device drive information in the target scene model;

Matching the life body motion information with the motion samples in the preset motion database, and when the matching is successful, obtain the identification information of the successfully matched motion samples;

obtaining a preset adjustment point of the target scene model;

The preset interaction point is determined according to the device driving information, the identification information and the preset adjustment point.

Preferably, the step of establishing an interaction mode based on the preset interaction point, and interacting with the corresponding scene adjustment device or the target scene model in the target scene according to the interaction mode, specifically includes:

receiving instruction information from a preset path, and identifying an instruction object corresponding to the instruction information;

The interaction type of the interaction mode is determined according to the instruction object, the interaction type includes a first interaction mode and a second interaction mode, and the first interaction mode is established based on the preset adjustment points in the preset interaction points, The second interaction mode is established based on the device driving information and the identification information in the preset interaction point;

When the interaction type is the first interaction mode, interact with the target scene model according to the first interaction mode;

When the interaction type is the second interaction mode, interact with the corresponding scene adjustment apparatus in the target scene according to the second interaction mode.

Preferably, before the step of receiving the instruction information from the preset path and identifying the instruction object corresponding to the instruction information, the method further includes:

Establish a preset vocabulary recognition model based on the preset vocabulary database;

performing preset precision training on the preset vocabulary recognition model to obtain a preset object recognition model;

Correspondingly, the step of receiving the instruction information from the preset path and identifying the instruction object corresponding to the instruction information specifically includes:

Receive voice command information from a user, perform feature extraction on the voice command information, and obtain key voice information;

The voice key information is input into the preset object recognition model for identification, and an instruction object corresponding to the voice instruction information is obtained.

Preferably, the step of receiving the instruction information from the preset path and identifying the instruction object corresponding to the instruction information specifically includes:

Determine a target alert level according to the vital information and the identification information;

When the target alert level is greater than a preset alert level, obtain an alert action corresponding to the target alert level;

Generate alert instruction information according to the alert action, and identify an instruction object corresponding to the alert instruction information.

In addition, in order to achieve the above object, the present invention also proposes a real-time interactive device based on holographic imaging, the device comprising:

a model building module, used for acquiring the environmental information and the living body information of the target scene, and establishing the target scene model according to the environmental information and the living body information;

an interaction establishment module, configured to perform holographic projection on the target scene model, and obtain preset interaction points in the target scene model;

The real-time interaction module is configured to establish an interaction mode based on the preset interaction point, and interact with the corresponding scene adjustment device or the target scene model in the target scene according to the interaction mode.

In addition, in order to achieve the above object, the present invention also proposes a real-time interactive device based on holographic imaging, the device includes: a memory, a processor, and a holographic imaging-based image stored on the memory and run on the processor The real-time interactive program based on holographic imaging is configured to implement the steps of the real-time interactive method based on holographic imaging as described above.

In addition, in order to achieve the above object, the present invention also provides a storage medium, on which a real-time interactive program based on holographic imaging is stored, and when the real-time interactive program based on holographic imaging is executed by a processor, the implementation is as described above. The steps of a real-time interactive method based on holography.

The present invention obtains the environment information and life body information of the target scene, establishes a target scene model according to the environment information and the life body information, performs holographic projection on the target scene model, and obtains the predictions in the target scene model. Set an interaction point, establish an interaction mode based on the preset interaction point, interact with the corresponding scene adjustment device or the target scene model in the target scene according to the interaction mode, Classification and acquisition of living body information and environmental information corresponding to non-living bodies, and then establishing a target scene model based on the environmental information and the living body information to improve the modeling speed and the accuracy of the target scene model; The target scene model is subjected to holographic projection to realize the all-round display of the target scene model, and to improve the degree of intuition and image of the display of the target scene model; by obtaining the preset interaction points in the target scene model, based on the The preset interaction point establishes an interaction mode, and then interacts with the corresponding scene adjustment device or the target scene model in the target scene according to the interaction mode to realize real-time real-time monitoring of the target scene model and the scene adjustment device. Human-computer interaction meets the needs of users for diversity, innovation and interactivity, and improves the practicality and user experience of holographic interaction.

Description of drawings

1 is a schematic structural diagram of a real-time interactive device based on holographic imaging of a hardware operating environment involved in an embodiment of the present invention;

2 is a schematic flowchart of the first embodiment of the real-time interaction method based on holographic imaging of the present invention;

3 is a schematic flowchart of a second embodiment of a real-time interaction method based on holographic imaging according to the present invention;

FIG. 4 is a structural block diagram of the first embodiment of the real-time interaction device based on holographic imaging according to the present invention.

The realization, functional characteristics and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments.

Detailed ways

It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

Referring to FIG. 1 , FIG. 1 is a schematic structural diagram of a real-time interactive device based on holographic imaging of a hardware operating environment involved in an embodiment of the present invention.

As shown in FIG. 1 , the real-time interactive device based on holographic imaging may include: a processor 1001 , such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002 , a user interface 1003 , a network interface 1004 , and a memory 1005 . Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. Optionally, the network interface 1004 may include a standard wired interface and a wireless interface (eg, a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or may be a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .

Those skilled in the art can understand that the structure shown in FIG. 1 does not constitute a limitation on the real-time interactive device based on holographic imaging, and may include more or less components than the one shown, or combine some components, or different Component placement.

As shown in FIG. 1 , the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module and a real-time interactive program based on holographic imaging.

In the real-time interactive device based on holographic imaging shown in FIG. 1, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; in the real-time interactive device based on holographic imaging of the present invention The processor 1001 and the memory 1005 can be set in the real-time interactive device based on holographic imaging, and the real-time interactive device based on holographic imaging calls the real-time interactive program based on holographic imaging stored in the memory 1005 through the processor 1001, and executes the present invention The real-time interaction method based on holographic imaging provided by the embodiment.

An embodiment of the present invention provides a real-time interaction method based on holographic imaging. Referring to FIG. 2 , FIG. 2 is a schematic flowchart of the first embodiment of the real-time interaction method based on holographic imaging of the present invention.

In this embodiment, the real-time interaction method based on holographic imaging includes the following steps:

Step S10: acquiring the environmental information and the living body information of the target scene, and establishing a target scene model according to the environmental information and the living body information;

It is easy to understand that in this embodiment, before performing holographic projection on the target scene, it is necessary to perform 3D modeling on the target scene to generate a target scene model, and when performing 3D modeling on the target scene, it is also necessary to When performing 3D modeling, in order to improve the accuracy of modeling, the living body and the non-living body can be modeled separately, and the living body can be classified into species first to obtain the species category of the living body, and then according to the species The category performs state monitoring and motion capture corresponding to the category, obtains the information of the living body, scans the three-dimensional information of the non-living body, obtains the environmental information, and then establishes a target scene model based on the environmental information and the living body information.

It should be noted that when scanning the three-dimensional information of the non-living body, the category of the non-living body can also be obtained. In a specific implementation, the non-living body can be divided into adjustable devices and non-adjustable devices. , and then further classify the adjustable device to obtain the category of the adjustable device, and further obtain device drive information of the adjustable device according to the category of the adjustable device, the device drive information includes the adjustment hub, Adjust switches, control valves, etc.

Step S20: Perform holographic projection on the target scene model, and acquire preset interaction points in the target scene model;

It should be noted that, before performing holographic projection on the target scene model, a preset interaction point needs to be established. The preset interaction point is an adjustable virtual interaction point, which can be established based on the target scene model. Realize operations such as rotating, zooming in, and reducing the target scene model, and can also be established based on the adjustable device in the target scene to start, close, and correspond to the adjustable device in the target scene. The amplitude adjustment of the adjustment data (such as the brightness level adjustment of electric lamps, the wind adjustment of air conditioners, the volume adjustment of audio equipment, the brightness adjustment of display equipment), etc.

In a specific implementation, the target scene model may be subjected to life body motion recognition and device drive identification, to obtain life body motion information and device drive information in the target scene model, and to compare the life body motion information with preset actions The action samples in the database are matched, and when the matching is successful, the identification information of the successfully matched action samples is obtained, and the identification information can be the action category of the action sample, and the action category can be based on the established action sample The preset category mapping table is used to determine, and the user can also enter the target action into the preset action database as an action sample, and then obtain the preset adjustment point of the target scene model, and then according to the device drive information, the identifier The information and the preset adjustment point determine a preset interaction point, the preset interaction point can be divided into a first preset interaction point and a second preset interaction point, and the first preset interaction point can be the preset interaction point. An adjustment point is set to adjust the target scene model; the second preset interaction point may be an interaction point established based on the device drive information and the identification information, specifically, the preset interaction simulation model can be used to calculate the The identification information of the action sample and the interaction item of the device driving information, obtain the target interaction item that meets the needs of the user, and correspond the target interaction item to the preset device model of the device model corresponding to each scene adjustment device in the target scene model The interaction point is denoted as the second preset interaction point, and the preset device interaction point is established based on each drive unit (such as a switch unit, a windshield unit, etc.) of the scene adjustment device in the target scene, and the drive unit is in the preset hologram. The interactive control center has an integrated control unit, and the control unit is used to control the startup and shutdown of the scene adjustment device (mainly the adjustable device in the scene adjustment device), and the amplitude adjustment of the corresponding adjustment data. It is assumed that the interaction simulation model is obtained by further training the initial interaction simulation model established based on the preset interaction behavior data and historical interaction behavior data through the convolutional neural network algorithm.

Step S30 : establishing an interaction mode based on the preset interaction point, and interacting with the corresponding scene adjustment device or the target scene model in the target scene according to the interaction mode.

It is easy to understand that after the preset interaction point is established, the target scene model can be holographically projected, and the preset interaction point in the target scene model can be acquired, based on the preset interaction point. Establish an interaction mode, and interact with the corresponding scene adjustment device in the target scene or the target scene model according to the interaction mode, and can establish different types of the target scene model and the scene adjustment device in the target scene. The corresponding scene adjustment device in the target scene and the target scene model can be interacted respectively in the interactive mode, and an interactive mode can also be established, and then the two can be selectively interacted according to the received instruction information, that is, if the received instruction information is received. If the received instruction information only involves the adjustment of the target scene model, then only the target scene model is adjusted; if the received instruction information only involves the adjustment of the adjustable device in the target scene , then only the adjustable device is adjusted; if the received instruction information involves both the target scene model and the adjustable device, then the adjustable device and the target scene model are adjusted. Comprehensive adjustment, for example, it is recognized that in the received instruction information, the corresponding control instruction is to enlarge the area where the electric light is located in the target scene model, and turn on the electric light, then the area where the electric light is located is amplified by a preset range. , and turn on the electric light to the preset gear. As for whether to enlarge the area where the electric light is located or turn on the electric light first, those skilled in the art can set as needed, which is not limited in this embodiment.

In a specific implementation, the instruction information from the preset path can be received first, the instruction object corresponding to the instruction information can be identified, and the interaction type of the interaction mode can be determined according to the instruction object, and the interaction type includes a first interaction mode and a second interaction type. An interaction mode, the first interaction mode is established based on the preset adjustment points in the preset interaction points, and is used to realize operations such as rotating, zooming in, and zooming out of the target scene model, and the second interaction mode is based on the preset adjustment points. The device driving information and the identification information in the preset interaction point are established to realize the startup, shutdown, amplitude adjustment, etc. of the scene adjustment device in the target scene; when the interaction type is the first In an interaction mode, interact with the target scene model according to the first interaction mode; when the interaction type is the second interaction mode, perform interaction with the target scene model corresponding to the target scene according to the second interaction mode The scene adjustment device interacts.

It should be noted that the instruction information from the preset path may be the user's voice instruction information, or may be the warning instruction information generated by the preset holographic interactive control center, and the instruction information in the preset path is the user's voice. When the instruction information is used, a preset vocabulary recognition model can be established based on the preset vocabulary database, and then preset accuracy training is performed on the preset vocabulary recognition model to obtain a preset object recognition model with a preset recognition accuracy. Accuracy training is to perform sentiment analysis training and recognition accuracy optimization on the preset vocabulary recognition model, obtain the preset object recognition model, and then receive voice command information from the user, perform feature extraction on the voice command information, and obtain voice key information, input the voice key information into the preset object recognition model for recognition, and obtain the command object corresponding to the voice command information. For example, when the user says "zoom in", it can be recognized by the preset object recognition model In order to enlarge the target scene model, the target scene model is enlarged to a preset multiple. For another example, when the user says "turn on the light", the preset object recognition model can be identified as turning on the target scene. the light switch, then turn on the light in the target scene model to the preset brightness level;

When the instruction information of the preset path is the warning instruction information, the target warning level may be determined according to the vital body information and the identification information, and when the target warning level is greater than the preset warning level, the The alert action corresponding to the target alert level, generate alert instruction information according to the alert action, identify the instruction object corresponding to the alert instruction information, and the vital information includes not only the body shape data of the living body, but also the breathing frequency of the living body , body temperature and other vital state data, for example, during the holographic interaction of the scene where the pet is located, if the pet's body temperature is detected to be higher than the preset body temperature value, and the pet's current motion matches the lounging sample in the motion sample and exceeds the preset value time, the determined target warning level is greater than the preset warning level, then obtain the warning action corresponding to the target warning level (the warning action can be set by yourself according to the target scene, here it can be set to start or adjust the corresponding drive unit, and continuously record the temperature of the pet through the body temperature detector), generate warning command information according to the warning action, and identify the command object corresponding to the warning command information (in this scenario, the objects identified are air conditioners and body temperature detectors), according to The instruction object determines the interaction type of the interaction mode, which corresponds to the scene adjustment device in the target scene, then determines that the interaction type is the second interaction mode, and then adjusts the corresponding scene in the target scene according to the second interaction mode. The adjustment device interacts (this scenario is to activate or adjust the air conditioner to the preset temperature, and continuously record the pet's body temperature. When the pet's body temperature is still higher than the preset body temperature value and exceeds the preset body temperature warning time, the communication function can be activated to make an emergency call. At the same time, the area where the pet is located is enlarged in the corresponding area in the target scene model).

It should be understood that the above are only examples, and do not constitute any limitation to the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as required, which is not limited by the present invention.

This embodiment acquires the environmental information and the living body information of the target scene, establishes a target scene model according to the environmental information and the living body information, performs holographic projection on the target scene model, and obtains the information in the target scene model. Preset interaction points, establish an interaction mode based on the preset interaction points, interact with the corresponding scene adjustment device in the target scene or the target scene model according to the interaction mode, The living body information and environmental information corresponding to the living body and the non-living body are classified and obtained, and then a target scene model is established based on the environmental information and the living body information to improve the modeling speed and the accuracy of the target scene model; The target scene model is holographically projected to achieve an all-round display of the target scene model, and to improve the degree of intuition and imagery of the target scene model display; by acquiring preset interaction points in the target scene model, based on The preset interaction point establishes an interaction mode, and then interacts with the corresponding scene adjustment device or the target scene model in the target scene according to the interaction mode to realize the interaction between the target scene model and the scene adjustment device. Real-time human-computer interaction meets the needs of users for diversity, innovation and interactivity, and improves the practicality and user experience of holographic interaction.

Referring to FIG. 3 , FIG. 3 is a schematic flowchart of a second embodiment of a real-time interaction method based on holographic imaging of the present invention.

Based on the above-mentioned first embodiment, in this embodiment, the step S10 includes:

Step S101 : respectively acquiring the environmental information and the living body information of the target scene from a preset position;

It is easy to understand that, when acquiring the environmental information and the living body information, the environmental information and living body information of the target scene can be obtained from different preset positions, and can also be obtained from different angles of the preset positions. The environmental information and life information of the target scene are acquired, and the different positions can be the four ends of two line segments that are established with the pivot point of the target scene and are perpendicular to each other and take the pivot point as the intersection point, such as The target scene is approximately a circle, the pivot point is the center of the circle, and the two line segments are the intersections of two perpendicular and intersecting diameters and the circle; in the environmental information of the target scene from the different angles When acquiring the information of the living body, the different angles of the preset position can be set to four angles directly in front of the pivot point, directly behind, directly left, and directly right, or can be set according to the preset It is convenient for the holographic projection angle to project, and the target area of the target scene can also collect environmental information and life information according to user needs. The preset position and different angles of the preset position can be set according to actual needs. , which is not limited in this embodiment.

In this embodiment, it should be understood that the terms of orientation or positional relationship indicated by "front", "rear", "left", "right", etc. are only for the convenience of describing the embodiment of the present invention and simplifying the description, rather than An indication or implication that the referred device or element must have a particular orientation, be constructed and operate in a particular orientation, is not to be construed as a limitation of the invention.

Step S102: perform three-dimensional modeling based on the environmental information, generate a first model, and input the first model into the first splicing layer;

Step S103: performing three-dimensional modeling based on the living body information, generating a second model, and inputting the second model into the second splicing layer;

Step S104: adaptively splicing the first model in the first splicing layer and the second model in the second splicing layer to generate a preliminary scene model;

It should be noted that when 3D modeling is performed based on the environmental information and the living body information, the 3D modeling can be performed based on the environmental information first, a first model is generated, and the first model is input into the first model. In a splicing layer, three-dimensional modeling is performed based on the information of the living body, a second model is generated, and the second model is input into the second splicing layer, and then the second model in the first splicing layer is analyzed. A model is adaptively spliced with the second model in the second splicing layer to generate a primary scene model. The first model is a model established based on environmental information corresponding to non-living bodies, and the second model It is a model established based on the living body information corresponding to the living body, the first splicing layer is a splicing layer that stores the first model for subsequent adaptive splicing, and the second splicing layer is a splicing layer for storing the second model. In the splicing layer of subsequent adaptive splicing, in the specific implementation, further detailed modeling can be carried out according to user needs, such as the environmental information of non-living bodies is further divided into environmental information corresponding to adjustable devices and environmental information corresponding to non-adjustable devices. environment information, and then model the environment information corresponding to the adjustable device and the environment information corresponding to the non-adjustable device respectively. It can be seen that this embodiment is not limited to the first model and the second model. When the environmental information corresponding to the adjustable device and the environmental information corresponding to the non-adjustable device are separately modeled, the first model can be established based on the environmental information corresponding to the adjustable device, the second model can be established based on the environmental information corresponding to the non-adjustable device, and the life-based Correspondingly, this embodiment is not limited to the first splicing layer and the second splicing layer, that is, the first model established based on the environmental information corresponding to the adjustable device is imported into the In the first splicing layer, the second model established based on the environmental information corresponding to the non-adjustable device is imported into the second splicing layer, and the third model established based on the living body information corresponding to the living body is imported into the third splicing layer, Then perform adaptive splicing on the first model in the first splicing layer, the second model in the second splicing layer and the third model in the third splicing layer , to generate the primary scene model.

In another implementation manner, the first model and the second model can also be divided according to user needs. For example, when the user focuses on real-time holographic interaction with a certain target area (for example, when realizing real-time holographic interaction with supermarkets, the The target area can be set as a shelf area with a high theft rate; when realizing real-time holographic interaction with the scene where the pet is located, the target area can be set as the regular activity area of the pet), then 3D modeling is performed on the target area to generate the first First modeling, import the first modeling into the first splicing layer, then perform 3D modeling on the area that is not the target area, generate a second modeling, and import the second modeling into the second modeling In the splicing layer, adaptive splicing is performed on the first model in the first splicing layer and the second model in the second splicing layer to generate a primary scene model. In a specific implementation, in order to further improve the modeling speed, a first-precision three-dimensional modeling can also be performed on the target area, a first modeling can be generated, and the first modeling can be imported into the first splicing layer. performing a second-precision three-dimensional modeling on an area that is not the target area, generating a second modeling, and importing the second modeling into a second splicing layer, wherein the first accuracy is greater than the second accuracy, and then adaptively splicing the first model in the first splicing layer and the second model in the second splicing layer.

Step S105: Perform effect processing on the preliminary scene model to generate a target scene model.

It should be noted that, when effect processing is performed on the preliminary scene model, the user's position parameters and preset effect enhancement parameters may be obtained, and then the preliminary The scene model performs effect processing to obtain the target scene model. In the specific implementation, the category of the model constituting the individual of the preliminary scene model can be obtained first, and then the model of the preliminary scene model can be rendered according to the category of the model constituting the individual. The light source effect and material constituting the individual surface can also be subjected to three-dimensional environment light source direction, shadow processing, etc. on the primary scene model. Further, scale adjustment and difference processing can also be performed on the preliminary scene model after the above-mentioned processing. Specifically, the holographic projection screen of the preliminary scene model can be scaled through a matrix transformation operation to meet the preset imaging scale rules. The preset imaging scale rule may be in accordance with the scale parameters corresponding to the model constituent individuals in the historical rendering database, may also be in accordance with the scale coefficient corresponding to the model constituent individuals in the preset scale relationship mapping table, or may be based on user requirements. The target area that the user wants to pay attention to is enlarged and displayed differently from the surrounding environment, and the specific enlargement ratio may be determined according to actual needs, which is not limited in this embodiment. Then, according to the imaging difference between the left and right eyes of the user, the corresponding difference processing can be performed on the projected image of the preliminary scene model to further improve the stereoscopic degree of the preliminary scene model, and the projection angle of the projected image can also be determined according to the position parameter. When there are multiple users, the projection angles corresponding to the multiple users can be combined for compromise processing, and the projection images of the primary scene model can be angularly shifted and converted, so that the projection images conforming to the anti-perspective principle are located where the users are. Within the angle range of the preset effect enhancement parameters, effect enhancement and screen rendering can also be performed on the adaptively processed preliminary scene model according to the preset effect enhancement parameters. Specifically, the screen boundary setting and screen shadow setting can be performed according to the preset effect enhancement parameters. , dynamic effect rendering and other processing, and then use the anti-perspective principle to reversely project the projected image of the initial scene model at the preset position or preset angle to the preset display device according to the visual imaging law to generate the target scene model.

It should be understood that the above are only examples, and do not constitute any limitation to the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as required, which is not limited by the present invention.

In this embodiment, three-dimensional modeling is performed on the environmental information and the living body information, respectively, and input into the corresponding splicing layers, and then different models in different splicing layers are adaptively spliced to generate a preliminary scene. The model realizes differentiated modeling, improves the modeling accuracy, and further improves the projection accuracy of the holographic projection. By obtaining the user's position parameters and preset effect enhancement parameters, according to the position parameters and the preset effect enhancement parameters The preliminary scene model performs effect processing to obtain a target scene model so as to improve the three-dimensionality of the target scene model and the interactive experience of the user.

In addition, an embodiment of the present invention also provides a storage medium, where a real-time interactive program based on holographic imaging is stored on the storage medium, and when the real-time interactive program based on holographic imaging is executed by a processor, the above-mentioned holographic-based interactive program is implemented Steps of a real-time interactive method of imaging.

Referring to FIG. 4 , FIG. 4 is a structural block diagram of a first embodiment of a real-time interaction device based on holographic imaging of the present invention.

As shown in FIG. 4 , the real-time interaction device based on holographic imaging proposed by the embodiment of the present invention includes:

The model building module 10 is used for acquiring the environmental information and the living body information of the target scene, and establishing the target scene model according to the environmental information and the living body information;

It is easy to understand that in this embodiment, before performing holographic projection on the target scene, it is necessary to perform 3D modeling on the target scene to generate a target scene model, and when performing 3D modeling on the target scene, it is also necessary to When performing 3D modeling, in order to improve the accuracy of modeling, the living body and the non-living body can be modeled separately, and the living body can be classified into species first to obtain the species category of the living body, and then according to the species The category performs state monitoring and motion capture corresponding to the category, obtains the information of the living body, scans the three-dimensional information of the non-living body, obtains the environmental information, and then establishes a target scene model based on the environmental information and the living body information.

It should be noted that when scanning the three-dimensional information of the non-living body, the category of the non-living body can also be obtained. In a specific implementation, the non-living body can be divided into adjustable devices and non-adjustable devices. , and then further classify the adjustable device to obtain the category of the adjustable device, and further obtain device drive information of the adjustable device according to the category of the adjustable device, the device drive information includes the adjustment hub, Adjust switches, control valves, etc.

An interaction establishment module 20, configured to perform holographic projection on the target scene model, and obtain preset interaction points in the target scene model;

It should be noted that, before performing holographic projection on the target scene model, a preset interaction point needs to be established. The preset interaction point is an adjustable virtual interaction point, which can be established based on the target scene model. Realize operations such as rotating, zooming in, and reducing the target scene model, and can also be established based on the adjustable device in the target scene to start, close, and correspond to the adjustable device in the target scene. The amplitude adjustment of the adjustment data (such as the brightness level adjustment of electric lamps, the wind adjustment of air conditioners, the volume adjustment of audio equipment, the brightness adjustment of display equipment), etc.

In a specific implementation, the target scene model may be subjected to life body motion recognition and device drive identification, to obtain life body motion information and device drive information in the target scene model, and to compare the life body motion information with preset actions The action samples in the database are matched, and when the matching is successful, the identification information of the successfully matched action samples is obtained, and the identification information can be the action category of the action sample, and the action category can be based on the established action sample The preset category mapping table is used to determine, and the user can also enter the target action into the preset action database as an action sample, and then obtain the preset adjustment point of the target scene model, and then according to the device drive information, the identifier The information and the preset adjustment point determine a preset interaction point, the preset interaction point can be divided into a first preset interaction point and a second preset interaction point, and the first preset interaction point can be the preset interaction point. An adjustment point is set to adjust the target scene model; the second preset interaction point may be an interaction point established based on the device drive information and the identification information, specifically, the preset interaction simulation model can be used to calculate the The identification information of the action sample and the interaction item of the device driving information, obtain the target interaction item that meets the needs of the user, and correspond the target interaction item to the preset device model of the device model corresponding to each scene adjustment device in the target scene model The interaction point is denoted as the second preset interaction point, and the preset device interaction point is established based on each drive unit (such as a switch unit, a windshield unit, etc.) of the scene adjustment device in the target scene, and the drive unit is in the preset hologram. The interactive control center has an integrated control unit, and the control unit is used to control the startup and shutdown of the scene adjustment device (mainly the adjustable device in the scene adjustment device), and the amplitude adjustment of the corresponding adjustment data. It is assumed that the interaction simulation model is obtained by further training the initial interaction simulation model established based on the preset interaction behavior data and historical interaction behavior data through the convolutional neural network algorithm.

The real-time interaction module 30 is configured to establish an interaction mode based on the preset interaction point, and interact with the corresponding scene adjustment device or the target scene model in the target scene according to the interaction mode.

It is easy to understand that after the preset interaction point is established, the target scene model can be holographically projected, and the preset interaction point in the target scene model can be acquired, based on the preset interaction point. Establish an interaction mode, and interact with the corresponding scene adjustment device in the target scene or the target scene model according to the interaction mode, and can establish different types of the target scene model and the scene adjustment device in the target scene. The corresponding scene adjustment device in the target scene and the target scene model can be interacted respectively in the interactive mode, and an interactive mode can also be established, and then the two can be selectively interacted according to the received instruction information, that is, if the received instruction information is received. If the received instruction information only involves the adjustment of the target scene model, then only the target scene model is adjusted; if the received instruction information only involves the adjustment of the adjustable device in the target scene , then only the adjustable device is adjusted; if the received instruction information involves both the target scene model and the adjustable device, then the adjustable device and the target scene model are adjusted. Comprehensive adjustment, for example, it is recognized that in the received instruction information, the corresponding control instruction is to enlarge the area where the electric light is located in the target scene model, and turn on the electric light, then the area where the electric light is located is amplified by a preset range. , and turn on the electric light to the preset gear. As for whether to enlarge the area where the electric light is located or turn on the electric light first, those skilled in the art can set as needed, which is not limited in this embodiment.

In a specific implementation, the instruction information from the preset path can be received first, the instruction object corresponding to the instruction information can be identified, and the interaction type of the interaction mode can be determined according to the instruction object, and the interaction type includes a first interaction mode and a second interaction type. An interaction mode, the first interaction mode is established based on the preset adjustment points in the preset interaction points, and is used to realize operations such as rotating, zooming in, and zooming out of the target scene model, and the second interaction mode is based on the preset adjustment points. The device driving information and the identification information in the preset interaction point are established to realize the startup, shutdown, amplitude adjustment, etc. of the scene adjustment device in the target scene; when the interaction type is the first In an interaction mode, interact with the target scene model according to the first interaction mode; when the interaction type is the second interaction mode, perform interaction with the target scene model corresponding to the target scene according to the second interaction mode The scene adjustment device interacts.

It should be noted that the instruction information from the preset path may be the user's voice instruction information, or may be the warning instruction information generated by the preset holographic interactive control center, and the instruction information in the preset path is the user's voice. When the instruction information is used, a preset vocabulary recognition model can be established based on the preset vocabulary database, and then preset accuracy training is performed on the preset vocabulary recognition model to obtain a preset object recognition model with a preset recognition accuracy. Accuracy training is to perform sentiment analysis training and recognition accuracy optimization on the preset vocabulary recognition model, obtain the preset object recognition model, and then receive voice command information from the user, perform feature extraction on the voice command information, and obtain voice key information, input the voice key information into the preset object recognition model for recognition, and obtain the command object corresponding to the voice command information. For example, when the user says "zoom in", it can be recognized by the preset object recognition model In order to enlarge the target scene model, the target scene model is enlarged to a preset multiple. For another example, when the user says "turn on the light", the preset object recognition model can be identified as turning on the target scene. the light switch, then turn on the light in the target scene model to the preset brightness level.

When the instruction information of the preset path is the warning instruction information, the target warning level may be determined according to the vital body information and the identification information, and when the target warning level is greater than the preset warning level, the The alert action corresponding to the target alert level, generate alert instruction information according to the alert action, identify the instruction object corresponding to the alert instruction information, and the vital information includes not only the body shape data of the living body, but also the breathing frequency of the living body , body temperature and other vital state data, for example, when performing holographic interaction on the scene where the pet is located, if the pet's body temperature is detected to be higher than the preset body temperature value, and the pet's current movement conforms to the action sample, the lying down sample has exceeded the preset value time, the determined target warning level is greater than the preset warning level, then obtain the warning action corresponding to the target warning level (the warning action can be set by yourself according to the target scene, here it can be set to start or adjust the corresponding drive unit, and continuously record the temperature of the pet through the body temperature detector), generate warning command information according to the warning action, and identify the command object corresponding to the warning command information (in this scenario, the objects identified are air conditioners and body temperature detectors), according to The instruction object determines the interaction type of the interaction mode, which corresponds to the scene adjustment device in the target scene, then determines that the interaction type is the second interaction mode, and then adjusts the corresponding scene in the target scene according to the second interaction mode. The adjustment device interacts (this scenario is to activate or adjust the air conditioner to the preset temperature, and continuously record the pet's body temperature. When the pet's body temperature is still higher than the preset body temperature value and exceeds the preset body temperature warning time, the communication function can be activated to make an emergency call. At the same time, the area where the pet is located is enlarged in the corresponding area in the target scene model).

It should be understood that the above are only examples, and do not constitute any limitation to the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as required, which is not limited by the present invention.

This embodiment acquires the environmental information and the living body information of the target scene, establishes a target scene model according to the environmental information and the living body information, performs holographic projection on the target scene model, and obtains the information in the target scene model. Preset interaction points, establish an interaction mode based on the preset interaction points, interact with the corresponding scene adjustment device in the target scene or the target scene model according to the interaction mode, The living body information and environmental information corresponding to the living body and the non-living body are classified and obtained, and then a target scene model is established based on the environmental information and the living body information to improve the modeling speed and the accuracy of the target scene model; The target scene model is holographically projected to achieve an all-round display of the target scene model, and to improve the degree of intuition and imagery of the target scene model display; by acquiring preset interaction points in the target scene model, based on The preset interaction point establishes an interaction mode, and then interacts with the corresponding scene adjustment device or the target scene model in the target scene according to the interaction mode to realize the interaction between the target scene model and the scene adjustment device. Real-time human-computer interaction meets the needs of users for diversity, innovation and interactivity, and improves the practicability and user experience of holographic interaction.

Based on the above-mentioned first embodiment of the real-time interaction device based on holographic imaging of the present invention, a second embodiment of the real-time interaction device based on holographic imaging of the present invention is proposed.

In this embodiment, the model building module 10 is further configured to obtain the environmental information and the living body information of the target scene from the preset positions respectively;

It is easy to understand that, when acquiring the environmental information and the living body information, the environmental information and living body information of the target scene can be obtained from different preset positions, and can also be obtained from different angles of the preset positions. The environmental information and life information of the target scene are acquired, and the different positions can be the four ends of two line segments that are established with the pivot point of the target scene and are perpendicular to each other and take the pivot point as the intersection point, such as The target scene is approximately a circle, the pivot point is the center of the circle, and the two line segments are the intersections of two perpendicular and intersecting diameters and the circle; in the environmental information of the target scene from the different angles When acquiring the information of the living body, the different angles of the preset position can be set to four angles directly in front of the pivot point, directly behind, directly left, and directly right, or can be set according to the preset It is convenient for the holographic projection angle to project, and the target area of the target scene can also collect environmental information and life information according to user needs. The preset position and different angles of the preset position can be set according to actual needs. , which is not limited in this embodiment.

In this embodiment, it should be understood that the terms of orientation or positional relationship indicated by "front", "rear", "left", "right", etc. are only for the convenience of describing the embodiment of the present invention and simplifying the description, rather than An indication or implication that the referred device or element must have a particular orientation, be constructed and operate in a particular orientation, is not to be construed as a limitation of the invention.

The model building module 10 is further configured to perform three-dimensional modeling based on the environmental information, generate a first model, and input the first model into the first splicing layer;

The model building module 10 is further configured to perform three-dimensional modeling based on the living body information, generate a second model, and input the second model into the second splicing layer;

The model building module 10 is further configured to perform adaptive splicing on the first model in the first splicing layer and the second model in the second splicing layer to generate a preliminary scene model ;

It should be noted that when 3D modeling is performed based on the environmental information and the living body information, the 3D modeling can be performed based on the environmental information first, a first model is generated, and the first model is input into the first model. In a splicing layer, three-dimensional modeling is performed based on the information of the living body, a second model is generated, and the second model is input into the second splicing layer, and then the second model in the first splicing layer is analyzed. A model is adaptively spliced with the second model in the second splicing layer to generate a primary scene model. The first model is a model established based on environmental information corresponding to non-living bodies, and the second model It is a model established based on the living body information corresponding to the living body, the first splicing layer is a splicing layer that stores the first model for subsequent adaptive splicing, and the second splicing layer is a splicing layer for storing the second model. In the splicing layer of subsequent adaptive splicing, in the specific implementation, further detailed modeling can be carried out according to user needs, such as the environmental information of non-living bodies is further divided into environmental information corresponding to adjustable devices and environmental information corresponding to non-adjustable devices. environment information, and then model the environment information corresponding to the adjustable device and the environment information corresponding to the non-adjustable device respectively. It can be seen that this embodiment is not limited to the first model and the second model. When the environmental information corresponding to the adjustable device and the environmental information corresponding to the non-adjustable device are separately modeled, the first model can be established based on the environmental information corresponding to the adjustable device, the second model can be established based on the environmental information corresponding to the non-adjustable device, and the life-based Correspondingly, this embodiment is not limited to the first splicing layer and the second splicing layer, that is, the first model established based on the environmental information corresponding to the adjustable device is imported into the In the first splicing layer, the second model established based on the environmental information corresponding to the non-adjustable device is imported into the second splicing layer, and the third model established based on the living body information corresponding to the living body is imported into the third splicing layer, Then perform adaptive splicing on the first model in the first splicing layer, the second model in the second splicing layer and the third model in the third splicing layer , to generate the primary scene model.

In another implementation manner, the first model and the second model can also be divided according to user needs. For example, when the user focuses on real-time holographic interaction with a certain target area (for example, when realizing real-time holographic interaction with supermarkets, the The target area can be set as a shelf area with a high theft rate; when realizing real-time holographic interaction with the scene where the pet is located, the target area can be set as the regular activity area of the pet), then 3D modeling is performed on the target area to generate the first First modeling, import the first modeling into the first splicing layer, then perform 3D modeling on the area that is not the target area, generate a second modeling, and import the second modeling into the second modeling In the splicing layer, adaptive splicing is performed on the first model in the first splicing layer and the second model in the second splicing layer to generate a primary scene model. In a specific implementation, in order to further improve the modeling speed, a first-precision three-dimensional modeling can also be performed on the target area, a first modeling can be generated, and the first modeling can be imported into the first splicing layer. performing a second-precision three-dimensional modeling on an area that is not the target area, generating a second modeling, and importing the second modeling into a second splicing layer, wherein the first accuracy is greater than the second accuracy, and then adaptively splicing the first model in the first splicing layer and the second model in the second splicing layer.

The model building module 10 is further configured to perform effect processing on the preliminary scene model to generate a target scene model.

It should be noted that, when effect processing is performed on the preliminary scene model, the user's position parameters and preset effect enhancement parameters may be obtained, and then the preliminary The scene model performs effect processing to obtain the target scene model. In the specific implementation, the category of the model constituting the individual of the preliminary scene model can be obtained first, and then the model of the preliminary scene model can be rendered according to the category of the model constituting the individual. The light source effect and material constituting the individual surface can also be subjected to three-dimensional environment light source direction, shadow processing, etc. on the primary scene model. Further, scale adjustment and difference processing can also be performed on the preliminary scene model after the above-mentioned processing. Specifically, the holographic projection screen of the preliminary scene model can be scaled through a matrix transformation operation to meet the preset imaging scale rules. The preset imaging scale rule may be in accordance with the scale parameters corresponding to the model constituent individuals in the historical rendering database, may also be in accordance with the scale coefficient corresponding to the model constituent individuals in the preset scale relationship mapping table, or may be based on user requirements. The target area that the user wants to pay attention to is enlarged and displayed differently from the surrounding environment, and the specific enlargement ratio may be determined according to actual needs, which is not limited in this embodiment. Then, according to the imaging difference between the left and right eyes of the user, the corresponding difference processing can be performed on the projected image of the preliminary scene model to further improve the stereoscopic degree of the preliminary scene model, and the projection angle of the projected image can also be determined according to the position parameter. When there are multiple users, the projection angles corresponding to the multiple users can be combined for compromise processing, and the projection images of the primary scene model can be angularly shifted and converted, so that the projection images conforming to the anti-perspective principle are located where the users are. Within the angle range of the preset effect enhancement parameters, effect enhancement and screen rendering can also be performed on the adaptively processed preliminary scene model according to the preset effect enhancement parameters. Specifically, the screen boundary setting and screen shadow setting can be performed according to the preset effect enhancement parameters. , dynamic effect rendering and other processing, and then use the anti-perspective principle to reversely project the projected image of the initial scene model at the preset position or preset angle to the preset display device according to the visual imaging law to generate the target scene model.

It should be understood that the above are only examples, and do not constitute any limitation to the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as required, which is not limited by the present invention.

The model building module 10 is also used to obtain the user's position parameters and preset effect enhancement parameters;

The model building module 10 is further configured to perform effect processing on the preliminary scene model according to the position parameter and the preset effect enhancement parameter to obtain a target scene model.

The interaction establishment module 20 is further configured to perform life body motion recognition and device drive identification on the target scene model, and obtain life body motion information and device drive information in the target scene model;

The interaction establishment module 20 is further configured to match the motion information of the living body with the motion samples in the preset motion database, and when the matching is successful, obtain the identification information of the successfully matched motion samples;

The interaction establishment module 20 is further configured to obtain a preset adjustment point of the target scene model;

The interaction establishing module 20 is further configured to determine a preset interaction point according to the device driving information, the identification information and the preset adjustment point.

The real-time interaction module 30 is further configured to receive instruction information from a preset path, and identify an instruction object corresponding to the instruction information;

The real-time interaction module 30 is further configured to determine the interaction type of the interaction mode according to the instruction object, the interaction type includes a first interaction mode and a second interaction mode, and the first interaction mode is based on the preset interaction point The preset adjustment point in the preset adjustment point is established, and the second interaction mode is established based on the device drive information and the identification information in the preset interaction point;

The real-time interaction module 30 is further configured to interact with the target scene model according to the first interaction mode when the interaction type is the first interaction mode;

The real-time interaction module 30 is further configured to interact with the corresponding scene adjustment device in the target scene according to the second interaction mode when the interaction type is the second interaction mode.

The real-time interaction module 30 is further configured to establish a preset vocabulary recognition model based on a preset vocabulary database;

The real-time interaction module 30 is further configured to perform preset precision training on the preset vocabulary recognition model to obtain a preset object recognition model;

The real-time interaction module 30 is further configured to receive voice command information from a user, perform feature extraction on the voice command information, and obtain key voice information;

The real-time interaction module 30 is further configured to input the voice key information into the preset object recognition model for identification, and obtain an instruction object corresponding to the voice instruction information.

The real-time interaction module 30 is further configured to determine a target warning level according to the vital information and the identification information;

The real-time interaction module 30 is further configured to obtain an alert action corresponding to the target alert level when the target alert level is greater than a preset alert level;

The real-time interaction module 30 is further configured to generate warning instruction information according to the warning action, and identify an instruction object corresponding to the warning instruction information.

For other embodiments or specific implementations of the real-time interaction device based on holographic imaging of the present invention, reference may be made to the foregoing method embodiments, and details are not described herein again.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or system comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or system. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article or system that includes the element.

The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages or disadvantages of the embodiments.

From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art. The computer software products are stored in a storage medium (such as read-only memory/random access). memory, magnetic disk, optical disc), including several instructions to make a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present invention.

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

Claims (9)

1. A real-time interaction method based on holographic imaging is characterized by comprising the following steps:

acquiring environmental information and life information of a target scene, and establishing a target scene model according to the environmental information and the life information;

performing holographic projection on the target scene model, and acquiring preset interaction points in the target scene model;

establishing an interaction mode based on the preset interaction points, and interacting the corresponding scene adjusting device or the target scene model in the target scene according to the interaction mode;

before the step of performing holographic projection on the target scene model and acquiring the preset interaction point in the target scene model, the method further includes:

carrying out life body action recognition and device driving recognition on the target scene model to obtain life body action information and device driving information in the target scene model;

matching the living body action information with action samples in a preset action database, and acquiring identification information of the action samples which are successfully matched when the matching is successful;

acquiring a preset adjusting point of the target scene model;

and determining a preset interaction point according to the device driving information, the identification information and the preset adjusting point.

2. The method according to claim 1, wherein the step of obtaining environmental information and animate body information of the target scene and establishing a model of the target scene according to the environmental information and the animate body information specifically comprises:

respectively acquiring environmental information and life information of a target scene from a preset position;

performing three-dimensional modeling based on the environment information, generating a first model, and inputting the first model into a first splicing layer;

performing three-dimensional modeling based on the life body information, generating a second model, and inputting the second model into a second splicing layer;

performing adaptive splicing on the first model in the first splicing layer and the second model in the second splicing layer to generate a first-order scene model;

and performing effect processing on the initial-stage scene model to generate a target scene model.

3. The method according to claim 2, wherein the step of performing effect processing on the initial-stage scene model to generate the target scene model specifically comprises:

acquiring a position parameter and a preset effect enhancement parameter of a user;

and performing effect processing on the initial-stage scene model according to the position parameter and the preset effect enhancement parameter to obtain a target scene model.

4. The method according to claim 1, wherein the step of establishing an interaction pattern based on the preset interaction points and interacting the corresponding scene adjusting device or the target scene model in the target scene according to the interaction pattern specifically comprises:

receiving instruction information from a preset path, and identifying an instruction object corresponding to the instruction information;

determining an interaction type of an interaction mode according to the instruction object, wherein the interaction type comprises a first interaction mode and a second interaction mode, the first interaction mode is established based on the preset adjusting point in the preset interaction point, and the second interaction mode is established based on the device driving information and the identification information in the preset interaction point;

when the interaction type is the first interaction mode, interacting the target scene model according to the first interaction mode;

and when the interaction type is the second interaction mode, interacting the corresponding scene adjusting device in the target scene according to the second interaction mode.

5. The method of claim 4, wherein before the step of receiving the instruction information from the predetermined path and identifying the instruction object corresponding to the instruction information, the method further comprises:

establishing a preset vocabulary recognition model based on a preset vocabulary database;

performing preset precision training on the preset vocabulary recognition model to obtain a preset object recognition model;

correspondingly, the step of receiving the instruction information from the preset path and identifying the instruction object corresponding to the instruction information specifically includes:

receiving voice instruction information from a user, and performing feature extraction on the voice instruction information to obtain voice key information;

and inputting the voice key information into the preset object recognition model for recognition to obtain an instruction object corresponding to the voice instruction information.

6. The method according to claim 4, wherein the step of receiving the instruction information from the preset path and identifying the instruction object corresponding to the instruction information specifically comprises:

determining a target warning grade according to the life information and the identification information;

when the target warning grade is larger than a preset warning grade, acquiring a warning action corresponding to the target warning grade;

and generating warning instruction information according to the warning action, and identifying a command object corresponding to the warning instruction information.

7. A real-time interactive device based on holographic imaging, the device comprising:

the model establishing module is used for acquiring environmental information and life information of a target scene and establishing a target scene model according to the environmental information and the life information;

the interaction establishing module is used for carrying out holographic projection on the target scene model and acquiring preset interaction points in the target scene model;

the real-time interaction module is used for establishing an interaction mode based on the preset interaction point and interacting the corresponding scene adjusting device or the target scene model in the target scene according to the interaction mode;

the interaction establishing module is further used for carrying out life body action identification and device driving identification on the target scene model to obtain life body action information and device driving information in the target scene model;

the interaction establishing module is also used for matching the living body action information with action samples in a preset action database, and acquiring identification information of the action samples successfully matched when the matching is successful;

the interaction establishing module is also used for acquiring a preset adjusting point of the target scene model;

the interaction establishing module is further configured to determine a preset interaction point according to the device driving information, the identification information, and the preset adjustment point.

8. Real-time interactive device based on holographic imaging, characterized in that it comprises: a memory, a processor and a holographic imaging based real-time interaction program stored on the memory and executable on the processor, the holographic imaging based real-time interaction program being configured to implement the steps of the holographic imaging based real-time interaction method as claimed in any one of claims 1 to 6.

9. A storage medium, wherein the storage medium stores thereon a real-time interactive holographic imaging based program, and the real-time holographic imaging based program is executed by a processor to implement the steps of the real-time holographic imaging based interactive method according to any one of claims 1 to 6.

Images