CN115953432A

CN115953432A - Image-based motion prediction method and apparatus, electronic device, and storage medium

Info

Publication number: CN115953432A
Application number: CN202310035548.9A
Authority: CN
Inventors: 李蕾; 崔新宇
Original assignee: Beijing Zitiao Network Technology Co Ltd
Current assignee: Beijing Zitiao Network Technology Co Ltd
Priority date: 2023-01-10
Filing date: 2023-01-10
Publication date: 2023-04-11

Abstract

The disclosure provides an image-based motion prediction method, an apparatus, an electronic device, and a storage medium. The method comprises the following steps: acquiring touch information of the augmented reality equipment; generating a depth image of a rendered scene according to the touch information; acquiring point cloud coordinate information corresponding to the depth images of two adjacent frames; determining a depth vector of the depth image according to the point cloud coordinate information; carrying out vector calculation on the depth vector to obtain a three-dimensional affine vector; and sending the three-dimensional affine vector to the augmented reality equipment so that the augmented reality equipment performs motion prediction according to the three-dimensional affine vector. The method disclosed by the invention solves the problem that the motion prediction of the moving object in the front and back directions in the two-dimensional image is inaccurate.

Description

Image-based motion prediction method and apparatus, electronic device, and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for motion prediction based on an image, an electronic device, and a storage medium.

Background

The motion prediction of the moving object is realized by calculating the translation vector of the two-dimensional plane image in the related technology, and the motion prediction is effective for the plane motion prediction of the moving object, but when the moving object moves in the direction vertical to the image picture, the motion prediction result calculated in the related technology is often greatly deviated from the actual motion result, and if an inaccurate prediction frame is applied to a prediction interpolation frame of a video image, negative optimization phenomena such as image display abnormity, picture jitter and the like can be generated.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

The present disclosure provides an image-based motion prediction method, apparatus, electronic device, and storage medium.

The present disclosure adopts the following technical solutions.

In some embodiments, the present disclosure provides an image-based motion prediction method applied to a system accessing an augmented reality device, including:

acquiring touch information of the augmented reality equipment;

generating a depth image of a rendered scene according to the touch information;

acquiring point cloud coordinate information corresponding to the depth images of two adjacent frames;

determining a depth vector of the depth image according to the point cloud coordinate information;

carrying out vector calculation on the depth vector to obtain a three-dimensional affine vector;

and sending the three-dimensional stereo affine vector to the augmented reality equipment so that the augmented reality equipment performs motion prediction according to the three-dimensional stereo affine vector.

In some embodiments, the present disclosure provides an image-based motion prediction method applied to an augmented reality device, including:

receiving the three-dimensional affine vector and the three-color image sent by the system;

generating a motion prediction image frame from the three-dimensional stereo affine vector and the tristimulus image;

displaying the motion prediction image frame in a frame interpolation and/or frame interpolation manner.

In some embodiments, the present disclosure provides an image-based motion prediction apparatus for a system accessing an augmented reality device, including:

the first processing module is used for acquiring touch information of the augmented reality device;

the second processing module is used for generating a depth image of a rendered scene according to the touch information;

the third processing module is used for acquiring point cloud coordinate information corresponding to the depth images of two adjacent frames;

the fourth processing module is used for determining a depth vector of the depth image according to the point cloud coordinate information;

the fifth processing module is used for carrying out vector calculation on the depth vector to obtain a three-dimensional affine vector;

and the sixth processing module is configured to send the three-dimensional affine vector to the augmented reality device, so that the augmented reality device performs motion prediction according to the three-dimensional affine vector.

In some embodiments, the present disclosure provides an image-based motion prediction apparatus applied to an augmented reality device, including:

the seventh processing module is used for receiving the three-dimensional affine vector and the three-color image sent by the system;

an eighth processing module, configured to generate a motion prediction image frame according to the three-dimensional stereo affine vector and the three-color image;

and the ninth processing module is used for displaying the motion prediction image frame in a frame inserting and/or frame complementing mode.

In some embodiments, the present disclosure provides an electronic device comprising: at least one memory and at least one processor;

the memory is used for storing program codes, and the processor is used for calling the program codes stored in the memory to execute the method.

In some embodiments, the present disclosure provides a computer-readable storage medium for storing program code which, when executed by a processor, causes the processor to perform the above-described method.

The image-based motion prediction method provided by the embodiment of the disclosure is applied to a system accessing an augmented reality device, and comprises the steps of obtaining touch information of the augmented reality device, generating a depth image of a rendered scene according to the touch information, obtaining point cloud coordinate information corresponding to two adjacent frames of the depth image, determining a depth vector of the depth image according to the point cloud coordinate information, carrying out vector calculation on the depth vector to obtain a three-dimensional affine vector, and sending the three-dimensional affine vector to the augmented reality device, so that the augmented reality device carries out motion prediction according to the three-dimensional affine vector. Therefore, the disclosed embodiment provides an object motion prediction method applied to a three-dimensional scene, affine motion prediction based on three-dimensional is realized by calculating the depth vector of an image, and the problem of inaccurate prediction of motion of a moving object in a two-dimensional image in the front and back directions is solved.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.

Fig. 1 is one of flowcharts of an image-based motion prediction method according to an embodiment of the present disclosure.

Fig. 2 is a schematic diagram of an image-based motion prediction method according to an embodiment of the present disclosure.

Fig. 3 is a second schematic diagram of an image-based motion prediction method according to an embodiment of the disclosure.

Fig. 4 is a second flowchart of an image-based motion prediction method according to an embodiment of the disclosure.

Fig. 5 is a third schematic diagram of a method for image-based motion prediction according to an embodiment of the disclosure.

Fig. 6 is a third flowchart of an image-based motion prediction method according to an embodiment of the present disclosure.

Fig. 7 is a schematic structural diagram of an image-based motion prediction apparatus according to an embodiment of the present disclosure.

Fig. 8 is a second schematic structural diagram of an image-based motion prediction apparatus according to an embodiment of the present disclosure.

Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that various steps recited in method embodiments of the present disclosure may be performed in parallel and/or in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description. The term "responsive to" and related terms mean that one signal or event is affected to some extent, but not necessarily completely or directly, by another signal or event. If an event x occurs "in response" to an event y, x may respond directly or indirectly to y. For example, the occurrence of y may ultimately result in the occurrence of x, but other intermediate events and/or conditions may exist. In other cases, y may not necessarily result in the occurrence of x, and x may occur even though y has not already occurred. Furthermore, the term "responsive to" may also mean "at least partially responsive to".

The term "determining" broadly encompasses a wide variety of actions that can include obtaining, calculating, computing, processing, deriving, investigating, looking up (e.g., looking up in a table, a database or another data structure), ascertaining and the like, and can also include receiving (e.g., receiving information), accessing (e.g., accessing data in a memory) and the like, as well as resolving, selecting, choosing, establishing and the like, and the like. Relevant definitions for other terms will be given in the following description. Relevant definitions for other terms will be given in the following description.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a" or "an" in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that reference to "one or more" unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

As shown in fig. 1, fig. 1 is a flowchart of an image-based motion prediction method according to an embodiment of the present disclosure, and is applied to a system accessing an augmented reality device, including the following steps.

Step S01: acquiring touch information of the augmented reality equipment;

in some embodiments, the image motion prediction method provided by the related art adopts a two-dimensional image-based motion Vector (motion Vector) prediction method or an optical flow (optical flow) prediction method, which are effective for plane motion prediction of an object but are not suitable for motion prediction when the object moves in a vertical picture direction.

Among them, the motion vector prediction method is to find the best corresponding block of a currently coded block in a coded picture (referred to as a reference frame) and calculate an offset (i.e., a motion vector) of the corresponding block. As shown in fig. 2, assuming that the current frame is P, the reference frame is Pr, and the current coding block is B, a best matching block Br with the smallest subtraction residual error with the block B is found in Pr, and Br is called B. In HEVC coding, motion vectors are included in the coded data stream. HEVC (High Efficiency Video Coding) is a new Video compression standard, and is used to extend the h.264/AVC Coding standard.

The optical flow method is a method for calculating motion information of an object between adjacent frames by finding a correspondence between a previous frame and a current frame using a change of a pixel in an image sequence in a time domain and a correlation between adjacent frames.

In addition, whether motion estimation and motion compensation are performed by using a motion vector prediction method or an optical flow method, plane motion is predicted in the category of two-dimensional images, and prediction accuracy of a motion trajectory of an object during plane translation can only be ensured.

Therefore, to solve the problem that the prediction of the motion of an object in a two-dimensional image in the front and back directions is inaccurate, the embodiments of the present disclosure provide a method for motion estimation and motion compensation of an object in a three-dimensional stereo scene, which can be applied to the fields of video transmission and display.

In some embodiments, the transmitting end is illustrated as applied to a system for accessing an augmented reality device, such as a game engine. First, control information of the augmented reality device is acquired, and specifically, touch information of a user is acquired through a controller of the augmented reality device. It can be understood that the game engine determines the current world coordinates, motion conditions, control information, and the like of the user through the touch information of the user, so as to directly influence the game scene rendered by the game engine.

Step S02: generating a depth image of a rendered scene according to the touch information;

in some embodiments, the game engine may output a three-color image (RGB image) and a depth image rendered corresponding to the game model coordinates according to the input touch information.

Step S03: acquiring point cloud coordinate information corresponding to the depth images of two adjacent frames;

in some embodiments, after a depth image is acquired, first point clouds and second point clouds corresponding to two adjacent frames of the depth image are constructed, each encoding minimum unit is divided according to the minimum unit of encoding of the depth image, one point in the point clouds is generated correspondingly, and the minimum unit of encoding of the depth image corresponds to two-dimensional coordinates in an RGB image in a one-to-one mode. And then, for each coding unit, respectively acquiring first point cloud coordinate information corresponding to the first point cloud and second point cloud coordinate information corresponding to the second point cloud. The point cloud is a data set of points in a coordinate system, and the points contain rich information including three-dimensional coordinates X, Y, Z, color, classification value, intensity value, time, and the like. It should be noted that, the manner of generating the point cloud from the depth map and the manner of acquiring the point cloud to acquire the specific three-dimensional coordinate of a certain point in the point cloud may refer to related technologies, and details are not repeated here.

Step S04: determining a depth vector of the depth image according to the point cloud coordinate information;

in some embodiments, as shown in fig. 2, during the time from the first frame to the second frame, a point on the first frame image is shifted, and the point is also changed in the front-back direction, i.e., in the depth direction. Therefore, according to the depth Vector calculating method and device, after the one-to-one correspondence relationship between the positions of the points on the first frame and the positions of the points on the second frame is confirmed through the Motion Vector, the depth information of the points in the first frame and the depth information of the points in the second frame are calculated, and then the depth vectors of the points are obtained. Specifically, the difference of the depth information of the coding unit in the two adjacent frames of the depth image is calculated to obtain the depth vector of the coding unit.

Step S05: carrying out vector calculation on the depth vector to obtain a three-dimensional affine vector;

in some embodiments, after the depth Vector is obtained, the motion Vector Montion Vector and the depth Vector may be subjected to Vector calculation to obtain a three-dimensional affine Vector. Specifically, vector superposition calculation is performed on the planar motion vector and the depth vector to obtain a three-dimensional affine vector of the coding unit.

Step S06: and sending the three-dimensional stereo affine vector to the augmented reality equipment so that the augmented reality equipment performs motion prediction according to the three-dimensional stereo affine vector.

In some embodiments, after obtaining the three-dimensional stereo affine vector, the three-dimensional stereo affine vector is sent to a receiving end, for example, an augmented reality device, so that the augmented reality device predicts a subsequent video frame sequence according to the three-dimensional stereo affine vector.

In some embodiments, the obtaining touch information of the augmented reality device includes:

acquiring touch information of a user through a controller of the augmented reality device;

wherein the touch information includes at least one of six-degree-of-freedom sensor data, motion information for the controller, user gesture information, and user head motion information.

In some embodiments, in response to a trigger operation on the augmented reality device controller, touch information is acquired, and the touch information includes six-degree-of-freedom sensor data (6 Dof), motion information of the operation controller, touch information of a handle button, gesture information, head motion information, and the like. Wherein, the controller includes handle controller and wear controller.

In some embodiments, the generating a depth image of a rendered scene according to the touch information includes:

and generating a rendered three-color image and a rendered depth image according to the touch information.

In some embodiments, a game engine accessing the augmented reality device may output rendered images, including RGB images and depth images, corresponding to game model coordinates according to the input touch information.

In some embodiments, the obtaining point cloud coordinate information corresponding to two adjacent frames of the depth image includes:

constructing a first point cloud and a second point cloud corresponding to the depth images of two adjacent frames;

and acquiring first point cloud coordinate information and second point cloud coordinate information corresponding to each coding unit in the depth image.

In some embodiments, the depth images of adjacent frames respectively generate respective corresponding point clouds, and then according to the coordinate positions of points in the point clouds in the three-dimensional stereo coordinate system of the point clouds, first point cloud coordinate information and second point cloud coordinate information corresponding to each coding unit in the depth images are sequentially extracted.

In some embodiments, the determining a depth vector for the depth image from the point cloud coordinate information comprises:

determining depth information of the coding unit in two adjacent frames of the depth images according to the first point cloud coordinate information and the second point cloud coordinate information;

and calculating the difference value of the depth information of the coding unit in the two adjacent frames of the depth images to obtain the depth vector of the coding unit.

In some embodiments, first depth information corresponding to the coding unit is determined according to the first point cloud coordinate information, and second depth information corresponding to the coding unit is determined according to the second point cloud coordinate information. Then, the depth vector can be determined by calculating the change of the depth information of the coding unit, for example, calculating the difference value of the depth information of the coding unit in the two adjacent frames of the depth image, so as to obtain the depth vector of the coding unit.

In some embodiments, the vector calculation on the depth vector to obtain a three-dimensional stereo affine vector includes:

acquiring a plane motion vector of the coding unit;

and carrying out vector superposition calculation on the plane motion vector and the depth vector to obtain a three-dimensional affine vector of the coding unit.

In some embodiments, after the depth Vector is obtained, two space vectors, namely, the motion Vector and the depth Vector, may be subjected to superposition calculation to obtain a three-dimensional affine Vector, and the result is shown in fig. 5.

In some embodiments, further comprising:

after the connection with the augmented reality device is established, only one frame of three-color image is sent to the augmented reality device, or three-color images are sent to the augmented reality device at preset time intervals.

In some embodiments, ideally only one frame of RGB encoded image would be sent initially, after which the subsequent sequence of video frames would be predicted only by sending the three-dimensional stereo affine vector. Or, the encoded RGB image data may be sent at certain intervals, following the principle of maximizing data transmission efficiency, and the rest of the data packets only send three-dimensional stereo affine vectors.

In some embodiments, as shown in fig. 3, taking 3D-HEVC coding as an example (other coding schemes may be used as input together with their corresponding depth maps), the specific process flow is as follows: respectively generating point clouds corresponding to depth images of adjacent frames, wherein each coding minimum unit in the depth images corresponds to a point in the point clouds one by one, then extracting distance depth information from an observation point according to the coordinate position of the point in the point clouds in a three-dimensional coordinate system of the point, further determining a depth vector according to the depth information change of each coding unit in the depth images of the two adjacent frames, generating an affine vector, and finally predicting the motion of a planar object according to the affine vector of each coding unit. The 3D-HEVC coding structure is an extension of HEVC, and each view texture and depth map coding mainly adopts an HEVC coding framework, but a plurality of new coding technologies are added on the basis of the HEVC coding structure, so that the HEVC coding structure is more beneficial to coding of a depth map and multiple views. 3D-HEVC is compatible with the coding and decoding of 2D video, while depth maps employ a modified HEVC coding structure.

In some embodiments, as shown in fig. 4, an embodiment of the present disclosure provides an image-based motion prediction method, applied to a transmitting end, including:

step a: acquiring touch information of a head-wearing and handle controller end;

step b: a virtual reality equipment game engine (a sending end) outputs a rendering image corresponding to the game model coordinates according to the input 6Dof data;

step c: the game engine outputs the rendered RGB image and the depth image;

step d: acquiring depth vectors of two adjacent frames;

step e: carrying out Vector calculation on the plane Motion Vector and the depth Vector to obtain a three-dimensional (3D) affine Vector;

step f: and sending the RGB image and the three-dimensional affine vector to a receiving end, such as a virtual reality head-mounted end.

The embodiment of the present disclosure further provides an image-based motion prediction method, which is applied to a receiving end, and includes:

step g: generating a prediction frame according to the received RGB image and the three-dimensional affine vector;

step h: predicted frames are displayed on the virtual reality head-mounted end in a frame inserting or frame supplementing mode

It can be seen that the difference between the image-based motion prediction method provided by the embodiment of the present disclosure and the related art is: 1. the present disclosure needs to generate depth vectors in addition to the Motion Vector of the plane; 2. calculating to obtain a three-dimensional affine Vector according to the depth Vector and the Motion Vector; and 3, performing motion prediction on the video frame through the three-dimensional affine vector. The method improves the method for realizing motion prediction only by a translation vector or plane optical flow method in the related art, supplements the prediction in the front and back direction by a depth vector, and predicts the motion of a moving object in an image by an affine vector. The method can not only ensure the accuracy of motion trail prediction during plane translation, but also provide the guarantee of motion prediction in the front and back directions of the picture.

As shown in fig. 6, an embodiment of the present disclosure further provides an image-based motion prediction method applied to an augmented reality device, including:

step S11: receiving a three-dimensional affine vector and a three-color image sent by a system;

step S12: generating a motion prediction image frame according to the three-dimensional stereo affine vector and the three-color image;

step S13: displaying the motion prediction image frame in a frame interpolation and/or frame complementation manner.

In some embodiments, the receiving end takes an augmented reality device as an example, and the scene includes, but is not limited to, an augmented reality streaming scene. And the augmented reality equipment generates a prediction frame according to the received RGB image data and the three-dimensional stereo affine vector, and the prediction frame is displayed at the augmented reality head-mounted end in a frame inserting and/or frame supplementing mode. Because the data volume of the three-dimensional stereo affine vector is far smaller than that of RGB coded data, the data volume and bandwidth pressure of network transmission can be reduced to the greatest extent. In addition, the motion prediction method based on the image provided by the embodiment of the disclosure realizes the prediction of the frame interpolation based on the depth vector, and better meets the requirements of the virtual reality scene.

As shown in fig. 7, an embodiment of the present disclosure further provides an image-based motion prediction apparatus, which is applied to a system accessing an augmented reality device, and includes:

the system comprises a first processing module 1, a second processing module and a display module, wherein the first processing module is used for acquiring touch information of the augmented reality device;

the second processing module 2 is configured to generate a depth image of a rendered scene according to the touch information;

the third processing module 3 is used for acquiring point cloud coordinate information of the depth images of two adjacent frames;

the fourth processing module 4 is configured to determine a depth vector of the depth image according to the point cloud coordinate information;

the fifth processing module 5 is configured to perform vector calculation on the depth vector to obtain a three-dimensional affine vector;

a sixth processing module 6, configured to send the three-dimensional affine vector to the augmented reality device, so that the augmented reality device performs motion prediction according to the three-dimensional affine vector.

As shown in fig. 8, an embodiment of the present disclosure further provides an image-based motion prediction apparatus applied to an augmented reality device, including:

the seventh processing module 7 is configured to receive the three-dimensional affine vector and the three-color image sent by the system;

an eighth processing module 8, configured to generate a motion prediction image frame according to the three-dimensional stereo affine vector and the three-color image;

a ninth processing module 9, configured to display the motion prediction image frame in a frame interpolation and/or frame compensation manner.

For the embodiments of the apparatus, reference is made to the partial description of the method embodiments for relevant points, since they substantially correspond to the method embodiments. The above-described apparatus embodiments are merely illustrative, wherein the modules described as separate modules may or may not be separate. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement without inventive effort.

The method and apparatus of the present disclosure have been described above based on embodiments and application examples. In addition, the present disclosure also provides an electronic device and a computer-readable storage medium, which are described below.

Referring now to fig. 9, shown is a schematic block diagram of an electronic device (e.g., a terminal device or server) 800 suitable for use in implementing embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in the drawings is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

The electronic device 800 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 801 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage means 808 into a Random Access Memory (RAM) 803. In the RAM803, various programs and data necessary for the operation of the electronic apparatus 800 are also stored. The processing apparatus 801, the ROM 802, and the RAM803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.

Generally, the following devices may be connected to the I/O interface 805: input devices 806 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 807 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage 808 including, for example, magnetic tape, hard disk, etc.; and a communication device 809. The communication means 809 may allow the electronic device 800 to communicate wirelessly or by wire with other devices to exchange data. While shown with various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication means 809, or installed from the storage means 808, or installed from the ROM 802. The computer program, when executed by the processing apparatus 801, performs the above-described functions defined in the methods of the embodiments of the present disclosure.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to perform the methods of the present disclosure as described above.

Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems on a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

According to one or more embodiments of the present disclosure, there is provided an image-based motion prediction method applied to a system accessing an augmented reality device, including:

acquiring touch information of the augmented reality equipment;

and sending the three-dimensional affine vector to the augmented reality equipment so that the augmented reality equipment performs motion prediction according to the three-dimensional affine vector.

According to one or more embodiments of the present disclosure, there is provided a method for acquiring touch information of an augmented reality device, including:

According to one or more embodiments of the present disclosure, there is provided a method for generating a depth image of a rendered scene according to the touch information, including:

According to one or more embodiments of the present disclosure, a method for acquiring point cloud coordinate information corresponding to two adjacent frames of the depth image is provided, including:

In accordance with one or more embodiments of the present disclosure, there is provided a method of determining a depth vector of the depth image from the point cloud coordinate information, comprising:

According to one or more embodiments of the present disclosure, there is provided a method, where performing vector calculation on the depth vector to obtain a three-dimensional stereo affine vector, includes:

acquiring a planar motion vector of the coding unit;

In accordance with one or more embodiments of the present disclosure, there is provided a method, further comprising:

According to one or more embodiments of the present disclosure, there is provided an image-based motion prediction method applied to an augmented reality device, including:

receiving a three-dimensional affine vector and a three-color image sent by a system;

displaying the motion prediction image frame in a frame interpolation and/or frame complementation manner.

According to one or more embodiments of the present disclosure, there is provided an image-based motion prediction apparatus applied to a system for accessing an augmented reality device, including:

the third processing module is used for acquiring point cloud coordinate information of two adjacent frames of the depth images;

According to one or more embodiments of the present disclosure, there is provided an image-based motion prediction apparatus applied to an augmented reality device, including:

a ninth processing module for displaying the motion prediction image frame in an interpolated frame and/or a frame-compensated frame manner.

According to one or more embodiments of the present disclosure, there is provided an electronic device including: at least one memory and at least one processor;

wherein the at least one memory is configured to store program code and the at least one processor is configured to call the program code stored in the at least one memory to perform the method of any one of the above.

According to one or more embodiments of the present disclosure, a computer-readable storage medium for storing program code, which, when executed by a processor, causes the processor to perform the above-described method, is provided.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other combinations of features described above or equivalents thereof without departing from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. An image-based motion prediction method applied to a system accessing an augmented reality device is characterized by comprising the following steps:

acquiring touch information of the augmented reality device;

2. The method according to claim 1, wherein the obtaining touch information of the augmented reality device comprises:

3. The method of claim 1, wherein generating the depth image of the rendered scene according to the touch information comprises:

4. The method of claim 1, wherein the obtaining point cloud coordinate information corresponding to two adjacent frames of the depth image comprises:

5. The method of claim 4, wherein determining a depth vector for the depth image from the point cloud coordinate information comprises:

6. The method of claim 5, wherein said vector computing said depth vector to obtain a three-dimensional stereo affine vector comprises:

acquiring a plane motion vector of the coding unit;

7. The method of claim 3, further comprising:

8. An image-based motion prediction method applied to an augmented reality device, comprising:

generating a motion prediction image frame according to the three-dimensional stereo affine vector and the three-color image;

9. An image-based motion prediction apparatus applied to a system for accessing an augmented reality device, comprising:

10. An image-based motion prediction apparatus applied to an augmented reality device, comprising:

11. An electronic device, comprising:

at least one memory and at least one processor;

wherein the at least one memory is configured to store program code and the at least one processor is configured to invoke the program code stored in the at least one memory to perform the method of any of claims 1 to 8.

12. A computer readable storage medium for storing program code which, when executed by a computer device, causes the computer device to perform the method of any of claims 1 to 8.