RU2800627C2 - Method of data processing, server and computer storage medium - Google Patents

Abstract

FIELD: computer technologies; data processing.

SUBSTANCE: invention relates to a mobile edge computing (MEC) server and a data processing method. The method includes establishing common models in a given set of models; receiving three-dimensional (3D) video data from the terminal and establishing an initial model based on the 3D video data; matching the source model with models from the given set of models, and the given set of models contains common models of the plurality of target objects; and sending pointing information to the terminal based on the matching result, wherein establishing common models in a given set of models includes obtaining a plurality of sample data items, wherein the plurality of sample data items contains at least one of global data corresponding to each target object or local data, corresponding to different parts of each target object; and establishing a common target object model based on the plurality of sample data items in case the plurality of sample data items contains global data corresponding to each target object; establishing local models of different parts of the target object based on the plurality of sample data items in case the plurality of sample data items contains local data corresponding to different parts of each target object, and generating a common target object model based on the local models of different parts of the target object, while sending to the indication information terminal based on the matching result, includes sending to the terminal the first indication information and correcting the characteristic parameters of the fitted model that do not correspond to the characteristic parameters of the original model, in accordance with the characteristic parameters of the original model, if the matching result is that the original model corresponds to one of the models from the predetermined set of models, wherein the first indication information indicates that the terminal continuously transmits the following 3D video data; sending second indication information to the terminal if the result of matching is that the original model does not match each of the models in the predetermined set of models, wherein the second indication information indicates that the terminal is re-acquiring 3D video data.

EFFECT: increasing the efficiency of generating the object model by the server based on the 3D video received from the terminal.

7 cl, 7 dwg

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

The application claims priority and rights under Chinese Patent Application No. 201811161566.7 filed on September 30, 2018.

FIELD OF TECHNOLOGY TO WHICH THE INVENTION RELATES

The present invention relates to data processing technologies, and in particular to a data processing method, a server, and a computer storage medium.

BACKGROUND OF THE INVENTION

With the continuous development of the mobile communication network, the transmission speed in the mobile communication network is rapidly increasing, which provides strong technical support for the emergence and development of three-dimensional (3D) video services. The 3D video data contains two-dimensional (2D) image data (eg, RGB data) and depth data, and 2D video data and depth data are transmitted separately in a 3D video data transmission process. However, since a large amount of 3D video data is obtained, the amount of data to be transmitted is also very large and much technical support is required in the process of data transmission. Thus, the mobile communication network must have a high data rate and a stable data transmission environment. In addition, due to the large amount of data, the time spent on simulating the Mobile Edge Computing (MEC) server is very long.

SUMMARY OF THE INVENTION

In order to solve the above technical problems, the embodiments of the present invention provide a data processing method, a server, and a computer storage medium.

In a first aspect, embodiments of the present invention provide a data processing method. This method is applied to the MEC server and includes the following operations.

Three-dimensional (3D) video data is received from the terminal, and an initial model is established based on the 3D video data.

The source model is mapped to models from a given set of models, where the given set of models contains common models of the set of target objects.

Based on the matching result, indication information is sent to the terminal.

In a second aspect, embodiments of the present invention provide an MEC server. The MEC server contains a processor and a communication interface.

The communication interface is adapted to receive three-dimensional (3D) video data from the terminal.

The processor is adapted to set the initial model based on the 3D video data; and match the source model with models from the given set of models, where the given set of models contains common models of the set of target objects.

The communication interface is adapted to send indication information to the terminal based on the matching result.

In a third aspect, embodiments of the present invention provide an MEC server. The MEC server contains a communication block, a modeling block and a mapping block.

The communication unit is adapted to receive 3D video data from the terminal.

The simulation unit is adapted to establish an initial model based on the 3D video data received by the communication unit.

The matching block is adapted to match the source model with models from a given set of models, where the given set of models contains common models of a set of target objects.

The communication unit is further adapted to send indication information to the terminal based on the matching result obtained by the matching unit.

In a fourth aspect, in embodiments of the present invention, a computer storage medium is further provided. The computer storage medium contains a computer instruction stored thereon which, when executed by the processor, causes the processor to execute a data processing method. According to the method: three-dimensional (3D) video data is received from the terminal, and based on the 3D video data, an initial model is set; the source model is compared with models from a given set of models, and the given set of models contains common models of the set of target objects; and based on the matching result, indication information is sent to the terminal.

In embodiments of the present invention, a data processing method, a server, and a computer storage medium are provided. The method includes the following steps: 3D video data is received from the terminal, and based on the 3D video data, an initial model is set; the source model is compared with models from a given set of models, and the given set of models contains common models of the set of target objects; and based on the matching result, indication information is sent to the terminal. According to the technical solutions provided in the embodiments of the present invention, the general models of a plurality of targets are set on the server, on the one hand, the server can perform matching with the given models based on the received 3D video data frame, and can quickly set the model of the target based on the fitted model, thus significantly reducing the time required for simulation; on the other hand, since the models are set on the server, the requirement for technical support required in the communication process is reduced, a high transmission rate and a stable transmission medium may not be required, and this is suitable for various communication scenarios. In addition, since the models are set on the server, it is also possible to perform simulation without transmitting all of the 3D video data received by the terminal, and therefore the amount of data to be transmitted is also reduced to a certain extent.

BRIEF DESCRIPTION OF GRAPHICS

In FIG. 1 is a block diagram of a system in which a data processing method according to an embodiment of the present invention is applied.

In FIG. 2 is a first flowchart of a data processing method according to an embodiment of the present invention.

In FIG. 3 is a second flow diagram of a data processing method according to an embodiment of the present invention.

In FIG. 4 is a third flowchart of a data processing method according to an embodiment of the present invention.

In FIG. 5 is a diagram of a component structure of a server according to an embodiment of the present invention.

In FIG. 6 is a diagram of another component structure of a server according to an embodiment of the present invention.

In FIG. 7 is a diagram of a component structure of a server hardware according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE INVENTION

Before a detailed description of the technical solutions in the embodiments of the present invention, the system architecture in which the data processing method is applied in the embodiment of the present invention will be briefly described. The data processing method in the embodiment of the present invention is applied to the corresponding 3D video data service. This service may be, for example, a service for sharing 3D video data or a live broadcast service based on 3D video data, etc. However, due to the large amount of 3D video data, for depth data and 2D video data transmitted, Accordingly, in the process of data transmission, significant technical support is required, and therefore, the mobile communication network must have a high data rate and a stable data transmission environment.

In FIG. 1 is a block diagram of a system in which a data processing method according to an embodiment of the present invention is applied. As shown in FIG. 1, the system may include a terminal, a base station, a MEC server, a service processing server, a core network, the Internet, etc. To realize data synchronization between the MEC server and the service processing server via the core network, a high-speed channel is established.

For example, in an application scenario where two terminals communicate with each other in FIG. 1, MEC server A is a MEC server deployed near terminal A (sending side), and core network A is the core network in the area where terminal A is located. Accordingly, MEC server B is a MEC server deployed near terminal B ( receiving party), and the core network B is the core network in the area where the terminal B is located. B MEC and the service processing server through the core network B to implement data synchronization.

After transmitting the 3D video data sent by the terminal A to the MEC server A, the MEC server A synchronizes the data with the service processing server via the core network A; and the MEC server B receives the 3D video data sent by the terminal A from the service processing server, and sends the 3D video data to the terminal B for display.

Here, if the terminal B and the terminal A realize the transmission through the same MEC server, the terminal B and the terminal A realize the transmission of 3D video data directly through the same MEC server, and the participation of the service processing server is not required, and this method is called the local backhaul method. . In particular, it is assumed that the terminal B and the terminal A realize the transmission of 3D video data through the server A MEC, after the transmission of the 3D video data sent by the terminal A to the server A MEC, the server A MEC sends this 3D video data to the terminal B for display.

Here, the terminal can selectively access, based on the network state or the configuration state of the terminal, or the algorithm set by the terminal, a 4G evolved next generation base station (eNB) or access a 5G gNB, so that the eNB connects to the MEC server via the access network. Long Term Evolution (LTE) and the gNB connects to the MEC server via the Next Generation Radio Access Network (NG-RAN).

Here, the MEC server is deployed at the network edge near the terminal or data source, and the so-called "terminal proximity" or "data source proximity" includes "terminal proximity" or "data source proximity" not only in logical positions, but also in geographic locations. Unlike the case in the corresponding mobile communication network, where the main service processing servers are deployed in several large cities, multiple MEC servers can be deployed in one city. For example, if there are many users in an office building, it may be appropriate to deploy one MEC server near the office building.

As an edge computing gateway having basic network, computing, storage, and application convergence capabilities, the MEC server provides platform support including device area, network area, data area, and edge computing application area. The MEC server is connected with various types of intelligent devices and sensors, and provides intelligent connection and data processing services in place, so that applications and data of various types are processed in the MEC server, and thus key intelligent services such as real-time services, service intelligence are realized. , data aggregation and interactive operation, security and privacy protection, and effectively improve the efficiency of intelligent decision making of each service.

Embodiments of the present invention also provide a data processing method that is applied to a server. The server is the MEC server shown in FIG. 1. In FIG. 2 is a first flowchart of a data processing method according to an embodiment of the present invention. As shown in FIG. 2, the method includes the following steps.

In block 201: 3D video data is received from the terminal, and based on this 3D video data, an initial model is set.

In block 202: the source model is mapped to models from the specified model set, where the specified model set contains common models of the target set.

In block 203: based on the matching result, indication information is sent to the terminal.

In an embodiment, the 3D video data is obtained by the terminal from an acquisition component that is at least capable of receiving depth data. The receiving component may establish a communication channel with at least one terminal so that the corresponding terminal receives the 3D video data.

More specifically, in one implementation method, since the acquisition component capable of obtaining depth data is relatively expensive, the terminal does not have a function to acquire 3D video data. The 3D video receiving component receives data independently of the terminal; and the acquisition component establishes a communication channel with the communication component in the terminal so that the 3D video data received by the acquisition component is input to the terminal. The acquisition component may in particular be implemented by at least one of the following: a depth perception camera, a dual camera, a 3D structured lighting camera module, and a time-of-flight (TOF) camera module.

Here, the receiving component may establish a communication channel with at least one terminal to transmit the received 3D video data to the at least one terminal, so that the 3D video data is supplied to the corresponding terminal. Thus, the 3D video data obtained by the acquisition component can be shared with at least one terminal to realize sharing of the acquisition component.

In another implementation, the terminal itself has a function to receive 3D video data. The terminal is provided with an acquiring component configured to at least acquire depth data, and for example, is provided with at least one of the following components for acquiring 3D video data: a depth perception camera, a dual camera, a 3D structured lighting camera module, and a camera module TOF.

The acquired 3D video data includes 2D video data and depth data, and the 2D video data is used to describe flat image characteristics, for example, may be RGB data; and the depth data is used to describe the distance characteristics between the surface of an object captured by the acquisition component and the acquisition component.

This embodiment is applied to an application scenario in which the quality of the communication channel between the terminal and the MEC server is good, i.e., the scenario in which the transmission rate and transmission stability of the communication channel meet a predetermined condition, for example, the communication channel transmission rate is higher than the first a predetermined threshold, and the data packet loss ratio is lower than the second predetermined threshold. In such a high-speed, low latency scenario, the transmission of the terminal corresponds to 3D video data, and the terminal does not store the 3D video data locally, but directly sends the 3D video data.

In this embodiment, the so-called terminal does not store the 3D video data locally, but directly sends the 3D video data, which means that the data that has been sent is not stored locally by the terminal, and the data that has not been sent still needs to be stored by the terminal. locally.

In this embodiment, as one implementation, the received 3D video data includes 2D video data and depth data. As another implementation, the received 3D video data may also include only depth data. The server performs simulation based on the depth data in the received 3D video data to obtain the original model.

In this embodiment, the server predefines a set of models, and this set of models contains the common models of a plurality of targets. Each of the targets may be a real person, a virtual person, a real animal, a virtual animal, and the like, and the type of each of the targets is not defined for it by the embodiment. In a real application, a set of models may include multiple sets of submodels, and each set of submodels may target one type of target. For example, for real people, an appropriate set of submodules is pre-installed; and the corresponding set of sub-modules can be pre-installed for some types of real animals like dogs etc.

In an embodiment, as shown in FIG. 3, the method further includes the following steps.

In block 204: a plurality of sample data items are obtained, and here the plurality of sample data items include at least one of global data corresponding to each target or local data corresponding to different parts of each target.

At block 205: establishing a general target object model based on a plurality of sample data items; or establishing local models of different parts of the target object based on a plurality of sample data items and, based on the local models of different parts of the target object, generating a general model of the target object.

In this embodiment, the server establishes the general models in accordance with the plurality of received sample data items. As a first implementation, the sample data obtained includes global data corresponding to each target. For example, if the target is a real person, the sample data is the global real person data. As another implementation, the resulting sample data includes local data corresponding to different parts of each target. For example, the target object is a real person, and the real person may have a head region, a torso region (the torso region may further be specifically divided into a shoulder region, a chest region, and a waist region, etc.), and a limb region (the limb region may be further divided into arm area, hand area, leg area and foot area, etc.), etc., the sample data can be directed to local areas of the above different parts of a real person.

In this embodiment, the plurality of sample data items correspond to different targets, or even correspond to different parts of different targets. General models are set for different targets.

As an implementation method, when the sample data includes global data corresponding to each target object, the general model of the target object is set based on the global data.

As another implementation method, when the sample data includes local data corresponding to different parts of each target object, local models of the target object are established based on the local data. In addition, local models of different parts of different targets can be assembled and combined, for example, to obtain a local model a1 and a local model a2 of target A; and obtaining the local model b1 and the local model b2 of the target B. On the one hand, the general model of the target A can be set based on the local model a1 and the local model a2, and the general model of the target B can be set based on the local model b1 and local model b2. On the other hand, a general model may be established based on the local model a1 and local model b2, and another general model may be established based on the local model b1 and local model a2. In this embodiment, a large number of generic target object models can be derived from local models, thereby facilitating model matching.

In this embodiment, the sample data may include only depth data, or may also include depth data and 2D video data. Any data that allows a 3D model to be established falls within the protection scope of an embodiment of the present invention.

It may be appreciated that operations 204 and 205 are performed prior to operation 202, that is, before the source model is matched with models from a given set of models, common models are established in the set of models.

In this embodiment, the server matches the source model with models from a given set of models.

As one implementation, the server maps the source model to shared models from a given set of models. This embodiment is applied to a scenario in which the received 3D video data is global data corresponding to the target. As an example, if the terminal sends the received 3D video data corresponding to the entire target to the server completely, the 3D video data received by the server is 3D video data corresponding to the entire target, and the initial model set by the server based on the 3D video data is is the source model corresponding to the entire target object.

As another implementation, the server maps the source model to the local models that form the shared model from a given set of models. This embodiment is applied to a scenario in which the received 3D video data is local data corresponding to portions of the target. As an example, if the terminal transmits the received 3D video data corresponding to each part of the target object to the server, accordingly, the server needs to perform appropriate modeling of the received 3D video data corresponding to each part, that is, the received original model here is the original model corresponding to each part. target object.

In this embodiment, the performance of the original model is matched against models in a given set of models, where the signatures of the original model are extracted and the signatures of the original model are compared to the signatures of each model in the set of models to obtain a degree of fit.

In particular, regardless of whether the source model matches the entire target object, or the source model matches each part of the target object, in the process of matching the source model with models from a given set of models, as an implementation method, the characteristic parameters of the original model and the extracted characteristic parameters are extracted compared with the characteristic parameters of each model of the set of models; if the degree of match between the extracted features and the features of one of the models in the set of models exceeds a predetermined threshold, it can be indicated that the matching is successful; and accordingly, if the degree of match between the extracted features and the features of any of the models in the set of models does not exceed a predetermined threshold, it can be indicated that the match has failed. In particular, the characteristic parameters may be parameters for describing characteristics of at least one of a contour characteristic point or a bone characteristic point.

In an embodiment, as shown in FIG. 4, the method further includes the following operation.

In block 203a: When the matching result is that the original model matches one of the models in the predetermined set of models, the first indication information is sent to the terminal, here the first indication information indicates that the terminal continuously transmits other 3D video data.

In this embodiment, if the MEC server determines that the original model corresponds to one of the models in the predetermined set of models, i.e., the model corresponding to the 3D video data is successfully set, the first indication information is sent to the terminal, and here the first indication information indicates, that the previously transmitted 3D video data can be simulated successfully, and the next 3D video data can be continuously transmitted.

In the method of implementing the present invention, when the result of the matching is that the original model matches one of the models from the given set of models, the first model is generated based on the 3D video data and the fitted model.

In an embodiment, when the result of the matching is that the source model matches one of the models from the given set of models, it is indicated that the general model of the corresponding target has been stored on the server. However, the overall model is often not fully consistent with the target corresponding to the 3D video data. In this embodiment, the fitted model is corrected and optimized based on 3D video data (including 2D video data and depth data). It may be understood that in order to obtain a first model corresponding to the target, only appropriate adjustments need to be made based on the fitted model. Compared with the model generation method based on 3D video data, the time taken to establish the model can be significantly reduced in this embodiment of the present invention.

In the method of implementing the present invention, when the result of the matching is that the original model matches one of the models from the predetermined set of models, the method further includes updating the fitted model based on the 3D video data. In this implementation, the fitted model (i.e., the overall model corresponding to the target) can be optimized. In particular, the model is optimized based on the depth data and 2D video data in the 3D video data. The optimization method may be to adjust the characteristic parameters of the model, which do not correspond to the characteristic parameters of the original model, in accordance with the characteristic parameters of the original model, so that the model is more accurate and closer to the target object.

In an embodiment, as shown in FIG. 4, the method further includes the following operation.

In block 203b: when the matching result is that the original model does not match any of the models in the predetermined model set, the second indication information is sent to the terminal, and here the second indication information indicates that the terminal is reacquiring 3D video data.

In this embodiment, if the MEC server determines that the original model does not match any of the models in the given set of models, indicate that the model corresponding to the 3D video data has not been successfully set by the server, the second indication information is sent to the terminal, and here the second the indication information indicates that the previously transmitted 3D video data cannot be successfully simulated and the corresponding 3D video data needs to be retransmitted.

According to the technical solutions provided in the embodiments of the present invention, by setting the general models of a plurality of targets on the server, on the one hand, the server can perform matching with the given models based on the received 3D video data frame, and can quickly set the target object model based on the fitted model. , thus significantly reducing the time required for simulation; on the other hand, since the models are set on the server, the requirement for technical support required in the communication process is reduced, high transmission speed and stable transmission may not be required, and this method is applicable to various communication scenarios. And furthermore, since the models are set on the server, it is not necessary to transmit all the 3D video data received by the terminal for simulation, and therefore the amount of data to be transmitted is also reduced to a certain extent.

To implement the server-side method in the embodiments of the present invention, an MEC server is further provided in the embodiments of the present invention. In FIG. 5 shows a view of the component structure of a server in one embodiment of the present invention. As shown in FIG. 5, the server comprises a communication unit 31, a modeling unit 32 and a matching unit 33.

The communication unit 31 is adapted to receive 3D video data from the terminal.

The simulation unit 32 is adapted to establish an initial model based on the 3D video data received by the communication unit 31 .

The matching block 33 is adapted to match the source model with models from a given set of models, where the given set of models contains common models of a plurality of target objects.

The communication unit 31 is further adapted to send indication information to the terminal based on the matching result obtained by the matching unit 33 .

In an embodiment, as shown in FIG. 6, the server further comprises a receiving unit 34 adapted to receive a plurality of sample data items, here the plurality of sample data items includes at least one of global data corresponding to each target or local data corresponding to different parts of each target.

Modeling unit 32 is further adapted to establish a general target object model based on a plurality of sample data items; or establishing local models of different parts of the target object based on a plurality of sample data items and generating a general model of the target object based on local models of different parts of the target object.

As one implementation, the communication unit 31 is adapted to send the first indication information to the terminal when the matching result is that the original model matches one of the models from the given set of models, and here the first indication information indicates that the terminal continuously transmits other 3D data. video.

In one embodiment, the modeling unit 32 is further adapted to update the fitted model based on the 3D video data when the result of the matching is that the original model matches one of the models from the predetermined set of models.

As one implementation, the communication unit 31 is adapted to send the second indication information to the terminal when the matching result is that the original model does not match each of the models in the predetermined set of models, and here the second indication information indicates that the terminal is reacquiring 3D data video.

In this embodiment of the present invention, the simulation unit 32, the mapping unit 33, and the acquisition unit 34 in the server may be implemented by a processor in the terminal in an actual application, such as a central processing unit (CPU), a digital signal processor (DSP), a microcontroller unit (MCU) ) or field programmable gate array (FPGA). The communication unit 31 in the server may be implemented by a communication module (including a main communication subsystem, an operating system, a communication module, a standard interface and protocol, etc.) and a transceiver antenna.

In the embodiment, when the server performs data processing, the division of the above software modules is for example only. In an actual application, the above processing may be performed by different software modules as needed. That is, the internal structure of the server is divided into different program modules to complete all or part of the above processing. In addition, the server provided by the above embodiment and the embodiments of the data processing method belong to the same concept, and the specific implementation process is described in detail in the method embodiment and will not be repeated.

Based on the hardware implementation of the device, a server is further provided in the embodiments of the present invention. In FIG. 7 shows a representation of the server hardware component structure in one embodiment of the present invention. As shown in FIG. 7, the server includes a storage device, a processor, and a computer program stored in the storage device and configured to run on the processor. The processor executes a computer program to: receive 3D video data from the terminal and set an initial model based on the 3D video data; match the source model with models from the given set of models, where the given set of models includes common models of the plurality of target objects; and send indication information to the terminal based on the matching result.

In one embodiment, the processor executes a computer program to: obtain a plurality of sample data items, wherein the plurality of sample data items includes at least one of global data corresponding to each target or local data corresponding to different parts of each target; set a general target object model based on the plurality of sample data items, or establish local models of different parts of the target object based on the plurality of sample data items, and generate a common target object model based on local models of different parts of the target object.

In one embodiment, the processor executes a program to: send the first indication information to the terminal when the matching result is that the original model matches one of the models from the given set of models, and here the first indication information indicates that the terminal is continuously transmitting other 3D data video.

In one embodiment, the processor executes a program to: update the fitted model based on the 3D video data when the matching result is that the original model matches one of the models from a given set of models.

In one embodiment, the processor executes a program to: send second indication information to the terminal when the matching result is that the original model does not match each of the models in the given set of models, and here the second indication information indicates that the terminal is reacquiring 3D data video.

The server further comprises a communication interface. The various components on the server are connected to each other via a bus system. The bus system is adapted for connection and data transfer between various components. In addition to the data bus, the bus system further comprises a power bus, a control bus, and a status signal bus.

The storage device in an embodiment may be a volatile storage device or a non-volatile storage device, and may also include both a volatile storage device and a non-volatile storage device. The non-volatile memory may be Read Only Memory (ROM), Programmable Read Only Memory (PROM), Erasable Programmable Read Only Memory (EPROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Ferromagnetic Random Access Memory (FRAM), Flash memory, magnetic surface storage, optical disc or compact disc read only memory (CD-ROM); and the magnetic surface storage device may be a magnetic disk storage device or a magnetic tape storage device. The volatile storage device may be a random access memory (RAM) that is used as an external high speed cache. As illustrative, but not limiting, various forms of RAM may be used, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), channel synchronous dynamic random access memory (SLDRAM), and direct resident access bus random access memory (DRRAM). The storage device described in this embodiment of the present invention is intended to include, but is not limited to, these storage devices and any other suitable types of storage devices.

The method described in the embodiments of the present invention may be applied to or implemented by a processor. The processor may be an integrated circuit chip and has signal processing capability. During implementation, each operation of the method may be implemented by a hardware integrated logic circuit in a processor or by an instruction in the form of software. The processor may be a general purpose processor, a DSP or other programmable logic device, a discrete or transistorized logic device, a discrete hardware component, etc. The processor may implement or perform each method, operation, and logic flow diagram disclosed in the embodiments. of the present invention. A general purpose processor may be a microprocessor or any conventional processor, etc. The method steps in the embodiments of the present invention may be directly implemented as implemented by a hardware decode processor or implemented by a combination of hardware and software modules in a decode processor. The program modules may be located on a storage medium. The storage medium is located in the storage device. The processor reads the information in the storage device and implements the operations of the method in combination with the hardware modules.

Embodiments of the present invention further provide a chip that includes a processor. The processor may call the computer program from the storage device and run the computer program to implement the method in the embodiments of the present invention.

In some embodiments, the chip may further comprise a storage device. The processor may call the computer program from the storage device and run the computer program to implement the method in the embodiments of the present invention.

The memory device is a separate device, independent of the processor, and may also be integrated into the processor.

In some embodiments, the chip may further comprise an input interface. The processor may control the input interface to communicate with other devices or chips, and in particular may receive information or data sent by other devices or chips.

In some embodiments, the chip may further comprise an output interface. The processor may control the output interface to communicate with other devices or chips, and in particular may output information or data to other devices or chips.

In some embodiments, a chip may be applied to an MEC server according to embodiments of the present invention. In addition, the chip can implement the corresponding sequences of operations implemented by the MEC server in each method in the embodiments of the present invention, which will not be repeated here for brevity.

The chip in embodiments of the present invention may also be referred to as a system level chip, a system chip, a system of a chip, or a system on a chip, etc.

In embodiments of the present invention, a computer storage medium is further provided, which in particular is a computer-readable storage medium. The computer storage medium stores a computer instruction that, when executed by the processor, implements the data processing method that is applied to the MEC server in the embodiments of the present invention.

In embodiments of the present invention, a computer program product is further provided that contains a computer program instruction.

In some embodiments, a computer program product may be applied to an MEC server according to embodiments of the present invention. In addition, the instruction of the computer program causes the computer to perform the corresponding sequences of operations implemented by the MEC server in each method in the embodiments of the present invention, which will not be repeated here for brevity.

In embodiments of the present invention, a computer program is also provided.

In some embodiments, a computer program may be applied to an MEC server according to embodiments of the present invention. When the computer program is running on the computer, the computer executes the corresponding sequences of operations implemented by the MEC server in each method in the embodiments of the present invention, which will not be repeated here for brevity.

Additional Embodiments

At least some embodiments of the present invention provide a method for processing data. The method for processing the data is applicable to a Mobile Edge Computing (MEC) server and includes:

receiving three-dimensional (3D) video data from the terminal and establishing an initial model based on the 3D video data;

matching the source model with models from the given set of models, and the given set of models contains common models of the plurality of target objects; And

sending indication information to the terminal based on the matching result.

According to at least some embodiments, the method further includes establishing common models in a given set of models.

According to at least some embodiments, establishing common models in a given set of models includes:

obtaining a plurality of sample data items, the plurality of sample data items comprising at least one of global data corresponding to each target or local data corresponding to different parts of each target; And

establishing a general target object model based on the plurality of sample data items in case the plurality of sample data items contains global data corresponding to each target object; establishing local models of different parts of the target object based on the plurality of sample data items in case the plurality of sample data items contains local data corresponding to different parts of each target object, and generating a general model of the target object based on local models of different parts of the target object.

According to at least some embodiments, the 3D video data comprises 2D video data and depth data, or comprises depth data and

Establishing an initial model based on 3D video data includes:

performing a simulation based on the depth data from the 3D video data to obtain the original model.

According to at least some embodiments, matching the source model to models from a given set of models includes:

extraction of characteristic parameters of the original model;

comparing the characteristic parameters of the original model with the characteristic parameters of each of the models from a given set of models to obtain a degree of conformity;

indicating that the matching is successful if the degree of correspondence between the characteristic parameters of the original model and the characteristic parameters of one of the models from the given set of models exceeds a predetermined threshold; And

an indication that the match has failed if the degree of correspondence between the characteristic parameters of the original model and the characteristic parameters of each of the models from the given set of models does not exceed a predetermined threshold.

According to at least some embodiments, sending indication information to the terminal based on the matching result includes:

sending, to the terminal, first indication information if the matching result is that the original model matches one of the models from the predetermined set of models, wherein the first indication information indicates that the terminal continuously transmits the next 3D video data.

According to at least some embodiments, sending indication information to the terminal based on the matching result includes:

sending second indication information to the terminal if the result of matching is that the original model does not match each of the models in the predetermined set of models, wherein the second indication information indicates that the terminal is re-acquiring 3D video data.

According to at least some embodiments, the method further comprises:

updating the fitted model based on the 3D video data if the matching result is that the original model matches one of the models from the given set of models.

In at least some embodiments of the present invention, a Mobile Edge Computing (MEC) server is provided, comprising a transceiver and a processor, wherein

the transceiver is adapted to receive 3D video data from the terminal; And

the processor is adapted to set the initial model based on the 3D video data; and to match the source model with models from the given set of models, and the given set of models contains common models of the plurality of target objects; And

the transceiver is adapted to send indication information to the terminal based on the matching result.

According to at least some embodiments, the processor is adapted to install common models in a given set of models.

In at least some embodiments, the processor is adapted to:

obtain a plurality of sample data items, the plurality of sample data items comprising at least one of global data corresponding to each target object or local data corresponding to different parts of each target object; And

establish a general target object model based on the plurality of sample data items in case the plurality of sample data items contains global data corresponding to each target object; establish local models of different parts of the target object based on the plurality of sample data items in case the plurality of sample data items contains local data corresponding to different parts of each target object, and generate a general model of the target object based on local models of different parts of the target object.

According to at least some embodiments, the 3D video data comprises 2D video data and depth data or contains depth data.

In at least some embodiments, the processor is adapted to perform simulation based on the depth data from the 3D video data to obtain an initial model.

In at least some embodiments, the processor is adapted to:

extract the characteristic parameters of the original model;

compare the characteristic parameters of the original model with the characteristic parameters of each of the models from the given set of models to obtain a degree of correspondence;

indicate that the match is successful if the degree of correspondence between the characteristic parameters of the original model and the characteristic parameters of one of the models from the given set of models exceeds a predetermined threshold; And

indicate that the match has failed if the degree of correspondence between the characteristic parameters of the original model and the characteristic parameters of each of the models from the given set of models does not exceed a given threshold.

According to at least some embodiments, the transceiver is adapted to send first indication information to the terminal in case the matching result is that the original model matches one of the models from a given set of models, wherein the first indication information indicates that the terminal continuously transmits the following data 3D video.

In at least some embodiments, the transceiver is adapted to send second indication information to the terminal in case the matching result is that the original model does not match each of the models in a given set of models, wherein the second indication information indicates that the terminal is reacquiring data 3D video.

In at least some embodiments, the processor is further adapted to update the fitted model based on the 3D video data if the result of the matching is that the original model matches one of the models from the given set of models.

In at least some embodiments of the present invention, a Mobile Edge Computing (MEC) server is provided, comprising a communication unit, a modeling unit, and a mapping unit, where the communication unit is adapted to receive 3D video data from a terminal; the simulation unit is adapted to set the initial model based on the 3D video data received by the communication unit; the matching unit is adapted to match the source model with models from a given set of models, and the given set of models contains common models of a plurality of target objects; and the communication unit is further adapted to send indication information to the terminal based on the matching result obtained by the matching unit.

According to at least some embodiments, the simulator is adapted to establish common models in a given set of models.

According to at least some embodiments, there is further an acquisition unit, where the acquisition unit is adapted to receive a plurality of sample data items, wherein the plurality of sample data items comprises at least one of global data corresponding to each target or local data corresponding to different parts of each target. object; And

the modeling unit is further adapted to establish a general target object model based on the plurality of sample data items in case the plurality of sample data items contains global data corresponding to each target object; establish local models of different parts of the target object based on the plurality of sample data items in case the plurality of sample data items contains local data corresponding to different parts of each target object, and generate a general model of the target object based on local models of different parts of the target object.

According to at least some embodiments, the 3D video data comprises 2D video data and depth data or contains depth data.

According to at least some embodiments, the modeling unit is adapted to perform simulation based on the depth data from the 3D video data to obtain the original model.

According to at least some embodiments, the mapper is adapted to: extract characteristic parameters of the original model; compare the characteristic parameters of the original model with the characteristic parameters of each of the models from the given set of models to obtain a degree of correspondence; indicate that the match is successful if the degree of correspondence between the characteristic parameters of the original model and the characteristic parameters of one of the models from the given set of models exceeds a predetermined threshold; indicate that the match has failed if the degree of correspondence between the characteristic parameters of the original model and the characteristic parameters of each of the models from the given set of models does not exceed a given threshold.

According to at least some embodiments, the communication unit is adapted to send to the terminal first indication information in case the matching result is that the original model matches one of the models from the given set of models, wherein the first indication information indicates that the terminal continuously transmits the following 3D video data.

According to at least some embodiments, the communication unit is adapted to send second indication information to the terminal in case the matching result is that the original model does not match each of the models from the given set of models, wherein the second indication information indicates that the terminal is reacquiring 3D video data.

According to at least some embodiments, the modeling unit is further adapted to update the fitted model based on the 3D video data if the result of the matching is that the original model matches one of the models from the given set of models.

In at least some embodiments of the present invention, a non-volatile computer-readable storage medium is provided that stores a computer instruction that, when executed by a Mobile Edge Computing (MEC) server processor, causes the processor to perform the data processing method of the above additional embodiments.

In embodiments of the present invention, a data processing method, a server, and a computer storage medium are provided. The method includes the following steps: 3D video data is received from the terminal, and based on the 3D video data, an initial model is set; the source model is mapped to models from a predetermined set of models, where the predetermined set of models contains common models of a plurality of target objects; and based on the matching result, indication information is sent to the terminal. According to the technical solutions provided in the embodiments of the present invention, the general models of a plurality of targets are set on the server, on the one hand, the server can perform matching with the given models based on the received 3D video data frame, and can quickly set the model of the target based on the fitted model, thus significantly reducing the time required for simulation; on the other hand, since the models are set on the server, the requirement for technical support required in the communication process is reduced, a high transmission rate and a stable transmission medium may not be required, and this is suitable for various communication scenarios. In addition, since the models are set on the server, it is also possible to perform simulation without transmitting all of the 3D video data received by the terminal, and therefore the amount of data to be transmitted is also reduced to a certain extent.

In several embodiments provided in the present invention, the disclosed methods and servers may be implemented differently. The devices described in the above embodiments are merely illustrative. For example, the division into blocks is only a division of logical functions, and in actual implementation there may be another division. For example, many blocks or components may be combined or integrated into another system, or some features may be ignored or not performed. In addition, the interconnections, direct connections, or communication connections of components shown or described may be indirect connections or communication connections through some device or block interfaces, and may be electrical, mechanical, or otherwise.

Blocks described as separate parts may or may not be physically separated, and parts shown as blocks may or may not be physical blocks, may be located in the same location, or may be distributed among multiple network blocks. Some or all of the blocks may be selected according to actual needs in order to achieve the goals of the solutions of the embodiments.

In addition, each functional block in the embodiments of the present invention may be integrated into the second processing unit, and each block may also be independently used as one unit, or two or more than two units may also be integrated into one unit. The built-in block may be realized by using the form of hardware, and may also be implemented by using the form of hardware and software function blocks.

Those skilled in the art can understand that all or part of the operations for implementing the above described method embodiments can be performed by hardware corresponding to the software command. The program may be stored on a computer-readable storage medium. The program, when executed, performs the operations of the embodiments of the method. The storage medium includes various media capable of storing program code such as a mobile storage device, ROM, RAM, magnetic disk, or optical disk.

When implemented as a software functional block and sold or used as a stand-alone product, the integrated block may be stored on a computer-readable storage medium. Based on such an understanding, the technical solutions of the present invention per se, or a part contributing to the prior art, or some technical solutions can be implemented as a software product. The computer program product is stored on a storage medium and includes several instructions that cause a computing device (which may be a personal computer, a server, or a network device) to perform all or some of the operations of the methods described in the embodiments of the present invention. The above storage medium includes any medium that can store program code, such as a mobile storage device, ROM, RAM, magnetic disk or optical disk.

The technical solutions in the embodiments of the present invention can be combined arbitrarily without conflict.

The foregoing descriptions are only specific ways of implementing the present invention, but are not intended to limit the scope of the legal protection of the present invention. Any variation or substitution that can easily be understood by a person skilled in the art within the technical scope disclosed in the present invention should fall under the protection scope of the invention.

Claims (40)

1. A data processing method, characterized in that the method is applied to a mobile peripheral computing (MEC) server, the method comprising: establishing common models in a given set of models; receiving (201) three-dimensional (3D) video data from the terminal and establishing (201) an initial model based on the 3D video data; matching (202) the source model with models from a given set of models, wherein the given set of models contains common models of the plurality of target objects; And sending (203) to the terminal pointing information based on the matching result, while the establishment of common models in a given set of models includes: obtaining (204) a plurality of sample data items, the plurality of sample data items comprising at least one of global data corresponding to each target or local data corresponding to different parts of each target; And establishing (205) a general target object model based on the plurality of sample data items if the plurality of sample data items contains global data corresponding to each target object; establishing (205) local models of different parts of the target object based on the plurality of sample data items in case the plurality of sample data items contains local data corresponding to different parts of each target object, and generating (205) a general model of the target object based on the local models of the different parts target object wherein sending to the terminal of indication information based on the matching result includes: sending (203a) to the terminal the first indication information and correcting the characteristic parameters of the fitted model that do not correspond to the characteristic parameters of the original model, in accordance with the characteristic parameters of the original model in case the result of the matching is that the original model corresponds to one of the models from the given a model set, the first indication information indicating that the terminal continuously transmits the next 3D video data; sending (203b) to the terminal second indication information in case the matching result is that the original model does not match each of the models from the given set of models, wherein the second indication information indicates that the terminal is reacquiring 3D video data. 2. The method according to claim. 1, characterized in that the 3D video data contains 2D video data and depth data, or contains depth data and establishment (201) of the original model based on the 3D video data includes: performing a simulation based on the depth data from the 3D video data to obtain the original model. 3. The method according to claim 1 or 2, characterized in that the comparison (202) of the original model with models from a given set of models includes: extraction of characteristic parameters of the original model; comparing the characteristic parameters of the original model with the characteristic parameters of each of the models from a given set of models to obtain a degree of conformity; indicating that the matching is successful if the degree of correspondence between the characteristic parameters of the original model and the characteristic parameters of one of the models from the given set of models exceeds a predetermined threshold; And an indication that the match has failed if the degree of correspondence between the characteristic parameters of the original model and the characteristic parameters of each of the models from the given set of models does not exceed a predetermined threshold. 4. Server of mobile peripheral computing (MEC), characterized in that it contains: a communication unit (31) adapted to receive three-dimensional (3D) video data from the terminal; a modeling unit (32) adapted to establish an initial model based on the 3D video data received by the communication unit (31); a matching unit (33) adapted to match the source model with models from the predetermined set of models, the predetermined set of models containing common models of the set of target objects; And wherein the communication unit (31) is additionally adapted to send indication information to the terminal based on the matching result obtained by the matching unit, at the same time, the simulation block (32) is additionally adapted to install common models in a given set of models, while the MEC server additionally contains a receiving block (34), and at the same time the receiving unit (34) is adapted to receive a plurality of sample data items, the plurality of sample data items containing at least one of global data corresponding to each target object or local data corresponding to different parts of each target object; And the modeling unit (32) is adapted to establish a general model of the target object based on the plurality of sample data items in case the plurality of sample data items contains global data corresponding to each target object; establish local models of different parts of the target object based on a plurality of sample data elements in case the plurality of sample data elements contains local data corresponding to different parts of each target object, and generate a general model of the target object based on local models of different parts of the target object, wherein the communication unit (31) is adapted to send the first indication information to the terminal and correct the characteristic parameters of the fitted model, which do not correspond to the characteristic parameters of the original model, in accordance with the characteristic parameters of the original model, if the matching result is that the original model corresponds one of the models from the predetermined set of models, the first indication information indicating that the terminal continuously transmits the next 3D video data; and send the second indication information to the terminal if the matching result is that the original model does not match each of the models in the predetermined set of models, the second indication information indicating that the terminal is reacquiring the 3D video data. 5. The server according to claim. 4, characterized in that the 3D video data contains 2D video data and depth data, or contains depth data and the simulation unit (32) is adapted to perform simulation based on the depth data in the 3D video data to obtain the original model. 6. The server according to claim 4 or 5, characterized in that the mapping unit (33) is adapted: extract the characteristic parameters of the original model; compare the characteristic parameters of the original model with the characteristic parameters of each of the models from the given set of models to obtain a degree of correspondence; indicate that the match is successful if the degree of correspondence between the characteristic parameters of the original model and the characteristic parameters of one of the models from the given set of models exceeds a predetermined threshold; And indicate that the match has failed if the degree of correspondence between the characteristic parameters of the original model and the characteristic parameters of each of the models from the given set of models does not exceed a given threshold. 7. A mobile peripheral computing (MEC) server containing a processor, a storage device and a communication interface, characterized in that the storage device is adapted to store the computer program; the communication interface is adapted to communicate with an external device controlled by the processor; And the processor is adapted to execute a computer program stored in the storage device to perform the data processing method of any one of claims. 1-3.