CN117097808A - XR streaming data sending and receiving method and device based on semantic communication - Google Patents

XR streaming data sending and receiving method and device based on semantic communication Download PDF

Info

Publication number
CN117097808A
CN117097808A CN202310962233.9A CN202310962233A CN117097808A CN 117097808 A CN117097808 A CN 117097808A CN 202310962233 A CN202310962233 A CN 202310962233A CN 117097808 A CN117097808 A CN 117097808A
Authority
CN
China
Prior art keywords
data
semantic
training
neural network
decoding
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
CN202310962233.9A
Other languages
Chinese (zh)
Inventor
牛冠冲
尹泽芃
杨清海
毛亮
黄振江
颜斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Tongze Kangwei Intelligent Technology Co ltd
Guangzhou Institute of Technology of Xidian University
Original Assignee
Guangzhou Tongze Kangwei Intelligent Technology Co ltd
Guangzhou Institute of Technology of Xidian University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Tongze Kangwei Intelligent Technology Co ltd, Guangzhou Institute of Technology of Xidian University filed Critical Guangzhou Tongze Kangwei Intelligent Technology Co ltd
Priority to CN202310962233.9A priority Critical patent/CN117097808A/en
Publication of CN117097808A publication Critical patent/CN117097808A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/131—Protocols for games, networked simulations or virtual reality
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/04—Protocols for data compression, e.g. ROHC
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/06—Notations for structuring of protocol data, e.g. abstract syntax notation one [ASN.1]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Security & Cryptography (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)

Abstract

The invention discloses an XR series flow data sending and receiving method and device based on semantic communication, which are characterized in that initial XR data are acquired, the initial XR data are input into a semantic extraction model for generating semantic coding data, the semantic extraction model is obtained by inputting a plurality of XR training data with semantic coding into a neural network for training, the initial XR data can be well identified, so that semantic coding is generated, the semantic coding data are transmitted to XR data receiving equipment, so that the XR data receiving equipment decodes and plays based on the semantic coding data, and therefore the transmission and playing of the XR data are completed. According to the invention, XR data is analyzed, semantic coding data is used as a transmission carrier of the XR data, and the transmitted data volume can be reduced, so that network transmission delay and bandwidth requirements of XR application are reduced.

Description

XR streaming data sending and receiving method and device based on semantic communication
Technical Field
The invention relates to the field of virtual reality, in particular to an XR streaming data sending and receiving method and device based on semantic communication.
Background
XR (Extended Reality) streaming technology is a technology combining XR technologies such as virtual reality, augmented reality, mixed reality and the like with technologies such as cloud computing, network transmission and the like. The XR streaming technology may transmit XR content to the user device over the network, enabling a remote XR experience. This technique allows users to enjoy a high quality XR experience without having high performance devices. Implementation of XR streaming technology requires solving a number of technical challenges, such as latency, bandwidth, etc.
Because XR streaming content generally requires a large amount of data, transmitting complete XR data over a network requires more time, requires users to use more bandwidth for data transmission, and is prone to high latency. And because XR applications are very delay sensitive, high delay XR streaming schemes can significantly reduce the user's XR streaming experience, thus requiring some optimization technique to reduce the delay.
Therefore, a need exists for an XR streaming data processing strategy that addresses the problem of high latency in XR streaming technology.
Disclosure of Invention
The embodiment of the invention provides an XR streaming data sending and receiving method and device based on semantic communication, which are used for improving the data transmission efficiency of an XR streaming technology.
In order to solve the above problems, an embodiment of the present invention provides an XR streaming data sending method based on semantic communication, including:
acquiring initial XR data;
inputting the initial XR data into a preset semantic extraction model to obtain semantic coding data; the semantic extraction model is obtained by inputting a plurality of XR training data marked with semantic codes into a neural network for training;
and transmitting the semantic coding data to an XR data receiving device.
As an improvement of the above solution, the training method of the semantic extraction model includes:
acquiring a plurality of XR data to be trained;
performing semantic coding on each XR to-be-trained data to obtain a plurality of XR training data marked with semantic coding;
and inputting the XR training data marked with the semantic codes into a neural network for training to obtain a semantic extraction model.
As an improvement of the above-described aspect, the neural network includes: a recurrent neural network, a convolutional neural network, and a graph convolution neural network; inputting the plurality of XR training data marked with semantic codes into a neural network for training, wherein the XR training data comprises the following steps:
judging the type of XR training data marked with semantic codes;
when the XR training data are time sequence and text information source types, the XR training data corresponding to the time sequence and the text information source types are input into a cyclic neural network for training;
when the XR training data is the image information source type, inputting the XR training data corresponding to the image information source type into a convolutional neural network for training;
when the XR training data is of the graph data source type, the XR training data corresponding to the graph data source type is input into the graph convolution neural network for training.
Correspondingly, an embodiment of the present invention further provides an XR data transmission device, including: the device comprises a data acquisition module, a data encoding module and a data sending module;
the data acquisition module is used for acquiring initial XR data;
the data encoding module is used for inputting the initial XR data into a preset semantic extraction model to obtain semantic encoded data; the semantic extraction model is obtained by inputting a plurality of XR training data marked with semantic codes into a neural network for training;
the data transmitting module is used for transmitting the semantic coding data to an XR data receiving end
Correspondingly, an embodiment of the invention also provides an XR streaming data receiving method based on semantic communication, which comprises the following steps:
receiving semantically encoded data transmitted by an XR data transmission device;
inputting the semantic coding data into a preset semantic decoding model to obtain XR decoding data; the semantic decoding model is obtained by inputting a plurality of marks into a neural network from XR semantic coding training data of decoding data for training;
rendering and playing are performed based on the XR decoded data.
As an improvement of the above solution, the training method of the semantic decoding model includes:
acquiring a plurality of XR semantic coding data to be trained;
marking decoding data of each XR semantic coding data to be trained to obtain XR semantic coding training data;
and inputting the XR semantic coding training data into a neural network for training to obtain a semantic decoding model.
Correspondingly, an embodiment of the present invention further provides an XR data receiving apparatus, including: the device comprises a data receiving module, a data decoding module and a data playing module;
the data receiving module is used for receiving the semantic coding data transmitted by the XR data transmitting end;
the data decoding module is used for inputting the semantic coding data into a preset semantic decoding model to obtain XR decoding data; the semantic decoding model is obtained by inputting a plurality of marks into a neural network from XR semantic coding training data of decoding data for training;
and the data playing module is used for rendering and playing based on the XR decoding data.
Correspondingly, an embodiment of the present invention further provides an XR streaming data sending and receiving system based on semantic communication, including: an XR data transmitting device, an XR data receiving device and a network device; the XR data transmitting equipment is connected with the XR data receiving equipment through network equipment; the XR data transmission device is applied with the XR data transmission device disclosed by the invention; the XR data receiving device uses an XR data receiving device according to the invention.
From the above, the invention has the following beneficial effects:
the invention provides an XR series flow data transmitting method based on semantic communication, which is characterized in that initial XR data are acquired, the initial XR data are input into a semantic extraction model for generating semantic coding data, the semantic extraction model is obtained by inputting a plurality of XR training data with semantic coding into a neural network for training, the initial XR data can be well identified, so that semantic coding is generated, the semantic coding data are transmitted to an XR data receiving device, so that the XR data receiving device decodes and plays based on the semantic coding data, and therefore, the transmission and the playing of the XR data are completed. According to the invention, XR data is analyzed, semantic coding data is used as a transmission carrier of the XR data, and the transmitted data volume can be reduced, so that network transmission delay and bandwidth requirements of XR application are reduced.
Furthermore, the XR data is converted into the semantic coded data for transmission, and if the XR data receiving equipment does not have relevant decoding data, the obtained semantic coded data cannot be decoded, recovered and reconstructed, so that the information security of XR data transmission is protected.
Drawings
Fig. 1 is a flow chart of an XR streaming data transmission method based on semantic communication according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an XR data transmission device according to an embodiment of the present invention;
FIG. 3 is a flow chart of an XR streaming data transmission method based on semantic communication according to an embodiment of the invention;
FIG. 4 is a schematic diagram of an XR data receiving apparatus according to an embodiment of the invention;
fig. 5 is a schematic structural diagram of an XR streaming data transmission and reception system based on semantic communication according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of an XR streaming data sending method based on semantic communication according to an embodiment of the present invention, as shown in fig. 1, the embodiment includes steps 101 to 103, where each step is specifically as follows:
step 101: initial XR data is acquired.
In this embodiment, the initial XR data is data participating in the computing process of the XR application, such as: at the user equipment end, the initial XR data transmitted can be audio and video data, illumination information data, motion information data and the like; at the remote device side, the initial XR data to be sent may be rendered audio/video data.
Step 102: inputting the initial XR data into a preset semantic extraction model to obtain semantic coding data; the semantic extraction model is obtained by inputting a plurality of XR training data marked with semantic codes into a neural network for training.
In this embodiment, the training method of the semantic extraction model includes:
acquiring a plurality of XR data to be trained;
performing semantic coding on each XR to-be-trained data to obtain a plurality of XR training data marked with semantic coding;
and inputting the XR training data marked with the semantic codes into a neural network for training to obtain a semantic extraction model.
As an improvement of the above-described aspect, the neural network includes: a recurrent neural network, a convolutional neural network, and a graph convolution neural network; inputting the plurality of XR training data marked with semantic codes into a neural network for training, wherein the XR training data comprises the following steps:
judging the type of XR training data marked with semantic codes;
when the XR training data are time sequence and text information source types, the XR training data corresponding to the time sequence and the text information source types are input into a cyclic neural network for training;
when the XR training data is the image information source type, inputting the XR training data corresponding to the image information source type into a convolutional neural network for training;
when the XR training data is of the graph data source type, the XR training data corresponding to the graph data source type is input into the graph convolution neural network for training.
In a specific embodiment, the XR to be trained data used for semantic coding is extracted and reconstructed through a deep learning network, and the process provides strong priori knowledge for transmission of transmission signals, so that the transmission effectiveness and reliability are effectively improved.
Step 103: and transmitting the semantic coding data to an XR data receiving device.
Referring to fig. 2, fig. 2 is a schematic structural diagram of an XR data transmission device according to an embodiment of the present invention, including: a data acquisition module 201, a data encoding module 202 and a data transmitting module 203;
the data acquisition module is used for acquiring initial XR data;
the data encoding module is used for inputting the initial XR data into a preset semantic extraction model to obtain semantic encoded data; the semantic extraction model is obtained by inputting a plurality of XR training data marked with semantic codes into a neural network for training;
the data sending module is used for transmitting the semantic coding data to an XR data receiving end.
Referring to fig. 3, fig. 3 is a flow chart of an XR streaming data receiving method based on semantic communication according to an embodiment of the present invention, as shown in fig. 3, the embodiment includes steps 301 to 303, where each step is specifically as follows:
step 301: the semantically encoded data transmitted by the XR data transmission device is received.
In this embodiment, the semantically encoded data is transmitted through a communication channel established by the network device.
Step 302: inputting the semantic coding data into a preset semantic decoding model to obtain XR decoding data; the semantic decoding model is obtained by inputting a plurality of marks into a neural network from XR semantic coding training data of decoding data for training.
In this embodiment, the training method of the semantic decoding model includes:
acquiring a plurality of XR semantic coding data to be trained;
marking decoding data of each XR semantic coding data to be trained to obtain XR semantic coding training data;
and inputting the XR semantic coding training data into a neural network for training to obtain a semantic decoding model.
In a specific embodiment, the semantically encoded data is input into a pre-trained semantic decoding model for decoding. If the information source has multi-mode or heterogeneous property, semantic processing is needed to be carried out on multi-source data during semantic extraction and decoding.
In a specific embodiment, the XR data sending device and the XR data receiving device share a set of local semantic knowledge base, namely the coded data of the related XR data sending device and the decoded data of the related XR data receiving device are in one-to-one correspondence, and priori knowledge under a specific scene of the neural network is given through a data driving method.
Step 303: rendering and playing are performed based on the XR decoded data.
In this embodiment, the obtained recovered XR data is processed, such as playing, rendering, and calculating, so as to implement a complete XR data semantic communication flow.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an XR data receiving apparatus according to an embodiment of the present invention, including: a data receiving module 401, a data decoding module 402 and a data playing module 403;
the data receiving module is used for receiving the semantic coding data transmitted by the XR data transmitting end;
the data decoding module is used for inputting the semantic coding data into a preset semantic decoding model to obtain XR decoding data; the semantic decoding model is obtained by inputting a plurality of marks into a neural network from XR semantic coding training data of decoding data for training;
and the data playing module is used for rendering and playing based on the XR decoding data.
It can be understood that the above system item embodiment corresponds to the method item embodiment of the present invention, and may implement the semantic communication based XR streaming data sending and receiving method of the submarine cable provided by any one of the method item embodiments of the present invention.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an XR streaming data sending and receiving system based on semantic communication according to an embodiment of the present invention, including: an XR data transmission device 501, an XR data reception device 502 and a network device 503; the XR data transmitting equipment is connected with the XR data receiving equipment through network equipment; the XR data transmission device is applied with the XR data transmission device disclosed by the invention; the XR data receiving device uses an XR data receiving device as described.
In a specific embodiment, the XR data transmission device may be a user device or a remote device, and the XR data receiving device may be a user device or a remote device;
if the XR data transmitting equipment is user equipment, the XR data receiving equipment is remote equipment;
if the XR data transmission device is a remote device, the XR data receiving device is a user device.
The user equipment is terminal equipment of a user and is responsible for realizing acquisition and uploading of XR application local sensor data, receiving streaming information sent from remote equipment and performing corresponding processing; the remote equipment is usually high-power equipment such as a server, performs rendering calculation of XR application according to XR interaction data sent by the user equipment, and sends the rendered data such as audio and video to the user equipment; network devices are typically network infrastructure that delivers data in a network, responsible for implementing the data interaction functions of user devices with remote devices.
It can be understood that the semantic communication can understand the service requirement and environment in advance, understand, extract and transmit the semantic features of the information source, and ensure that the information sink can understand the received semantic features of the information source, so that the information source information based on the semantic is successfully recovered. By accurately extracting and efficiently transmitting semantic features, the semantic communication can greatly reduce the transmission bandwidth requirements of large-bandwidth services such as video, pictures and the like in XR application scenes, thereby greatly improving the communication efficiency and user experience. Typically, the type and state of XR application data is fixed and known on both the user device and the remote device, which can be efficiently compressed and recovered based on the local semantic knowledge base and the deep learning network without significant information loss.
According to the embodiment, the initial XR data are acquired and input into the semantic extraction model for generating semantic coding data, the semantic extraction model is obtained by inputting a plurality of XR training data with semantic coding into the neural network for training, the initial XR data can be well identified, so that semantic coding is generated, the semantic coding data are transmitted to the XR data receiving device, the XR data receiving device decodes and plays based on the semantic coding data, and therefore transmission and playing of the XR data are completed. According to the invention, XR data is analyzed, semantic coding data is used as a transmission carrier of the XR data, and the transmitted data volume can be reduced, so that network transmission delay and bandwidth requirements of XR application are reduced. In this embodiment, XR data is converted into semantic encoded data for transmission, and if the XR data receiving device does not have associated decoding data, the obtained semantic encoded data cannot be decoded, recovered and reconstructed, which protects the information security of XR data transmission.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.

Claims (8)

1. An XR streaming data sending method based on semantic communication is characterized by comprising the following steps:
acquiring initial XR data;
inputting the initial XR data into a preset semantic extraction model to obtain semantic coding data; the semantic extraction model is obtained by inputting a plurality of XR training data marked with semantic codes into a neural network for training;
and transmitting the semantic coding data to an XR data receiving device.
2. The XR stream data transmission method based on semantic communication according to claim 1, wherein the training method of the semantic extraction model comprises:
acquiring a plurality of XR data to be trained;
performing semantic coding on each XR to-be-trained data to obtain a plurality of XR training data marked with semantic coding;
and inputting the XR training data marked with the semantic codes into a neural network for training to obtain a semantic extraction model.
3. The XR stream data transmission method based on semantic communication according to claim 2, wherein the neural network comprises: a recurrent neural network, a convolutional neural network, and a graph convolution neural network; inputting the plurality of XR training data marked with semantic codes into a neural network for training, wherein the XR training data comprises the following steps:
judging the type of XR training data marked with semantic codes;
when the XR training data are time sequence and text information source types, the XR training data corresponding to the time sequence and the text information source types are input into a cyclic neural network for training;
when the XR training data is the image information source type, inputting the XR training data corresponding to the image information source type into a convolutional neural network for training;
when the XR training data is of the graph data source type, the XR training data corresponding to the graph data source type is input into the graph convolution neural network for training.
4. An XR data transmission device comprising: the device comprises a data acquisition module, a data encoding module and a data sending module;
the data acquisition module is used for acquiring initial XR data;
the data encoding module is used for inputting the initial XR data into a preset semantic extraction model to obtain semantic encoded data; the semantic extraction model is obtained by inputting a plurality of XR training data marked with semantic codes into a neural network for training;
the data sending module is used for transmitting the semantic coding data to an XR data receiving end.
5. An XR streaming data receiving method based on semantic communication, comprising:
receiving semantically encoded data transmitted by an XR data transmission device;
inputting the semantic coding data into a preset semantic decoding model to obtain XR decoding data; the semantic decoding model is obtained by inputting a plurality of marks into a neural network from XR semantic coding training data of decoding data for training;
rendering and playing are performed based on the XR decoded data.
6. The XR stream data receiving method based on semantic communication according to claim 5, wherein the training method of the semantic decoding model comprises:
acquiring a plurality of XR semantic coding data to be trained;
marking decoding data of each XR semantic coding data to be trained to obtain XR semantic coding training data;
and inputting the XR semantic coding training data into a neural network for training to obtain a semantic decoding model.
7. An XR data receiving device comprising: the device comprises a data receiving module, a data decoding module and a data playing module;
the data receiving module is used for receiving the semantic coding data transmitted by the XR data transmitting end;
the data decoding module is used for inputting the semantic coding data into a preset semantic decoding model to obtain XR decoding data; the semantic decoding model is obtained by inputting a plurality of marks into a neural network from XR semantic coding training data of decoding data for training;
and the data playing module is used for rendering and playing based on the XR decoding data.
8. An XR streaming data transmission and reception system based on semantic communication, comprising: an XR data transmitting device, an XR data receiving device and a network device; the XR data transmitting equipment is connected with the XR data receiving equipment through network equipment; the XR data transmission device for use with the XR data transmission device described in claim 4; the XR data receiving device employing the XR data receiving device of claim 7.
CN202310962233.9A 2023-08-01 2023-08-01 XR streaming data sending and receiving method and device based on semantic communication Withdrawn CN117097808A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310962233.9A CN117097808A (en) 2023-08-01 2023-08-01 XR streaming data sending and receiving method and device based on semantic communication

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310962233.9A CN117097808A (en) 2023-08-01 2023-08-01 XR streaming data sending and receiving method and device based on semantic communication

Publications (1)

Publication Number Publication Date
CN117097808A true CN117097808A (en) 2023-11-21

Family

ID=88770779

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310962233.9A Withdrawn CN117097808A (en) 2023-08-01 2023-08-01 XR streaming data sending and receiving method and device based on semantic communication

Country Status (1)

Country Link
CN (1) CN117097808A (en)

Similar Documents

Publication Publication Date Title
CN109104243B (en) Pixel communication method, information sending terminal and information receiving terminal
NZ585907A (en) System and method for protecting certain types of multimedia data transmitted over a communication channel
CN102238390B (en) Image-library-based video and image coding and decoding method and system
CN103179431A (en) Method for redirecting, transcoding and separating audio/video under VDI (Virtual Desktop Infrastructure) condition
EP2712660A3 (en) Video compression system and method for compensating for bandwidth limitations for a communication channel
KR101773156B1 (en) Communication method, system and device for optical network system
CN110225416A (en) A kind of transmission method of video, the network terminal, intelligent terminal and storage device
CN115146125A (en) Receiving end data filtering method and device under semantic communication multi-address access scene
CN113315972A (en) Video semantic communication method and system based on hierarchical knowledge expression
CN117097808A (en) XR streaming data sending and receiving method and device based on semantic communication
CN106937127B (en) Display method and system for intelligent search preparation
WO2002057877A3 (en) Uncompressed multimedia data transmission and switching
CN114095055B (en) Low-code rate biorthogonal code coding spreading method and device
KR100785012B1 (en) Methods and apparatuses for generating and recovering 3D compression data
CN102098581A (en) Method and device for realizing video games
CN111787417B (en) Audio and video transmission control method based on artificial intelligence AI and related equipment
CN101521786A (en) High definition transcoding method based on digital television HDTV platform
CN116962742A (en) Live video image data transmission method, device and live video system
CN101459833B (en) Transcoding method used for similar video code stream and transcoding device thereof
KR20040075938A (en) Robust signal coding
EP3637734B1 (en) Video data display method and device
CN113674387B (en) Video processing method and device for unnatural scene video
CN103875241B (en) For the method and apparatus of the treatment interference when digital picture time series is transmitted
CN217902443U (en) Cross-network information transmission device based on image recognition
CN210867973U (en) Video acquisition terminal and video transmission and interaction system applying same

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20231121