Screen content encoding and decoding method and device based on semantic pixel library
Through the encoding method based on the semantic pixel library, semantic information of screen content is extracted and encoded, and the problems of low encoding efficiency and high complexity in the prior art are solved, and more efficient data processing and transmission are achieved.
Patent Information
- Application Number
- CN202410982469.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing compression framework based on character position perception has low encoding efficiency and high encoding process complexity when encoding screen content.
Using the encoding method based on the semantic pixel library, by establishing a semantic pixel library, semantic information of screen content is extracted and lossless encoding is performed, semantic and non-semantic information is reconstructed using the semantic pixel library, improving encoding efficiency and reducing encoding complexity.
Improve coding efficiency, reduce coding complexity, optimize data storage and transmission efficiency, and reduce bandwidth and storage space requirements.
Smart Images

Figure CN118972640A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data compression, and in particular to a method and device for encoding screen content based on a semantic pixel library, and a method and device for decoding screen content. Background Art
[0002] Screen content coding is a hot research topic in the field of data compression and is also one of the hot spots for international video coding standard competition.
[0003] From the perspective of video coding, the most notable feature of screen video is its diversity and hybridity. Screen images contain not only natural video or image content captured by a video camera or digital camera, but also various graphics, icons, charts, texts, menus and buttons generated by computers. The text content on the screen is changing, and the background is changing or unchanged. However, these changing texts or symbols have certain characteristics, such as the size, position and font of the text and symbols are fixed. Therefore, how to improve the efficiency of coding is currently the most urgent problem to be solved.
[0004] However, the existing compression framework based on character position awareness is divided into a text layer and a background layer, and different encoders are used to encode the text layer and the background layer respectively. When it comes to encoding screen content, the encoding efficiency is low and the complexity of the encoding process is high. Summary of the invention
[0005] In order to solve the technical problems that the existing compression framework based on character position awareness is divided into a text layer and a background layer, and different encoders are used to encode the text layer and the background layer respectively, and the encoding efficiency is low and the complexity of the encoding process is high when encoding the screen content, the present invention provides a method and system for encoding screen content based on a semantic pixel library.
[0006] The technical solution provided by the embodiment of the present invention is as follows:
[0007] First aspect:
[0008] An embodiment of the present invention provides a method for encoding screen content based on a semantic pixel library, comprising:
[0009] S101: Establishing a semantic pixel library according to preset rules;
[0010] S102: Encoding the semantic pixel library using a first lossless encoding scheme;
[0011] S103: Acquire screen content;
[0012] S104: extracting semantic information of each frame of image in the screen content;
[0013] S105: Encode the semantic information using a second lossless coding scheme, and encode the non-semantic information using a screen content coding scheme;
[0014] S106: reconstructing the semantic information through the semantic pixel library, and reconstructing the non-semantic information through a screen content encoding scheme;
[0015] S107: Output the code stream of the current frame image;
[0016] S108: Repeat S104 to S107 until all frame images are encoded.
[0017] Second aspect:
[0018] An embodiment of the present invention provides a device for encoding screen content based on a semantic pixel library, the device comprising:
[0019] Establishing a module for establishing a semantic pixel library according to preset rules;
[0020] A first encoding module, configured to encode the semantic pixel library by adopting a first lossless encoding scheme;
[0021] A first acquisition module, used to acquire screen content;
[0022] An extraction module, used to extract semantic information of each frame of image in the screen content;
[0023] A second encoding module, used to encode the semantic information by a second lossless encoding scheme, and to encode the non-semantic information by a screen content encoding scheme;
[0024] A first reconstruction module, configured to reconstruct the semantic information through the semantic pixel library and reconstruct the non-semantic information through a screen content encoding scheme;
[0025] The first output module is used to output the code stream of the current frame image;
[0026] The first repeating module is used to repeat the extraction module to the first output module until all frame image encoding is completed.
[0027] The third aspect:
[0028] An embodiment of the present invention provides a method for decoding screen content based on a semantic pixel library, comprising:
[0029] S201: Decoding the semantic pixel library using a first lossless decoding scheme to obtain a semantic pixel library;
[0030] S202: Obtain image code stream;
[0031] S203: For each frame of the image, decode the semantic information by using the second lossless decoding scheme to obtain the semantic information, and decode the non-semantic information by using the screen content decoding scheme to obtain the non-semantic information;
[0032] S204: reconstructing the semantic information through the semantic pixel library, and reconstructing the non-semantic information through a screen content decoding solution;
[0033] S205: Outputting reconstructed pixels of the current frame image;
[0034] S206: Repeat S203 to S205 until all frame images are decoded.
[0035] Fourth aspect:
[0036] An embodiment of the present invention provides a decoding device for screen content based on a semantic pixel library, the decoding device comprising:
[0037] A first decoding module, configured to decode the semantic pixel library by adopting a first lossless decoding scheme to obtain the semantic pixel library;
[0038] The second acquisition module is used to acquire the image code stream;
[0039] A second decoding module is used to decode the semantic information of each frame of the image through a second lossless decoding scheme to obtain the semantic information, and to decode the non-semantic information through a screen content decoding scheme to obtain the non-semantic information;
[0040] A second reconstruction module is used to decode the semantic pixel library by adopting the first lossless decoding scheme to obtain the semantic pixel library;
[0041] A second output module, used for outputting the reconstructed pixels of the current frame image;
[0042] The second repeating module is used to repeat the second decoding module to the second output module until all frame images are decoded.
[0043] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:
[0044] In the present invention, a semantic pixel library is established according to preset rules; screen content is obtained, semantic information of each frame image in the screen content is extracted, the semantic information is encoded by a second lossless coding scheme, and non-semantic information is encoded by a screen content coding scheme, thereby improving coding efficiency. The semantic pixel library is encoded by a first lossless coding scheme; the semantic information is reconstructed by the semantic pixel library, and the non-semantic information is reconstructed by a screen content coding scheme. The complexity of coding is effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0046] Figure 1 A schematic diagram of a flow chart of a method for encoding screen content based on a semantic pixel library provided by an embodiment of the present invention;
[0047] Figure 2 A schematic diagram of the structure of a device for encoding screen content based on a semantic pixel library provided by an embodiment of the present invention.
[0048] Figure 3 A schematic diagram of a flow chart of a method for decoding screen content based on a semantic pixel library provided by an embodiment of the present invention;
[0049] Figure 4 A schematic diagram of a screen content decoding device based on a semantic pixel library provided by an embodiment of the present invention DETAILED DESCRIPTION
[0050] The technical solution of the present invention is described below in conjunction with the accompanying drawings.
[0051] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.
[0052] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.
[0053] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.
[0054] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.
[0055] Reference Manual Attached Figure 1 , shows a flow chart of a method for encoding screen content based on a semantic pixel library provided in an embodiment of the present invention.
[0056] The embodiment of the present invention provides a method for encoding screen content based on a semantic pixel library, which can be implemented by an encoding device for screen content based on a semantic pixel library, and the encoding device for screen content based on a semantic pixel library can be a terminal or a server. The processing flow of the method for encoding screen content based on a semantic pixel library can include the following steps:
[0057] S101: Establish a semantic pixel library according to preset rules.
[0058] The semantic pixel library is an advanced data structure for storing and processing image or video data. Different from the traditional pixel value storage method, it associates pixel values with their semantic information, making the image or video data more interpretable and intelligent.
[0059] In a possible implementation, the semantic pixel library includes: a semantic index indexi, a width wi, a height hi, and a pixel value wixhi.
[0060] In a possible implementation manner, establishing a semantic pixel library according to a preset rule in S101 is specifically as follows:
[0061] A semantic pixel library is established through scene modeling.
[0062] In the present invention, the semantic pixel library makes image or video data more intelligent and can support various complex analysis and processing tasks. At the same time, by associating semantic information with pixel values, data storage can be effectively managed and optimized. This optimization can help reduce storage requirements and improve data transmission efficiency, which is particularly important in large-scale data processing.
[0063] S102: Using a first lossless coding scheme to encode a semantic pixel library.
[0064] In a possible implementation, the first encoding scheme and the second encoding scheme are specifically:
[0065] Fixed-length encoding scheme, run-length encoding scheme, dictionary encoding scheme or specific lossless encoding scheme.
[0066] In the present invention, the lossless coding scheme ensures that the data will not lose information during the encoding and decoding process, and can accurately restore the content of the original semantic pixel library to maintain the integrity and accuracy of the data. At the same time, using the first lossless coding scheme to encode the semantic pixel library can make full use of modern coding technology and improve the storage and transmission efficiency of data.
[0067] S103: Acquire screen content.
[0068] Optionally, the screen content is specifically: one-dimensional data, two-dimensional data, fractal graphics, an image, a sequence of images, a video, a remote video, a three-dimensional scene, a sequence of continuously changing three-dimensional scenes, a virtual reality scene, a sequence of continuously changing virtual reality scenes, an image in pixel form, transform domain data of an image, a set of two-dimensional or more bytes, a set of two-dimensional or more bits, a set of pixels and / or a set of three-component pixels.
[0069] S104: Extracting semantic information of each frame of image in the screen content.
[0070] In a possible implementation manner, the semantic information specifically includes: location information and / or a semantic index index.
[0071] In the present invention, semantic information can help the system understand and analyze image content more intelligently. By extracting location information and semantic indexes, the system can accurately locate and identify different objects or areas in the image, thereby achieving more accurate image processing and application. At the same time, extracting and storing semantic information can greatly reduce the amount of data and storage costs compared to the original image data.
[0072] Furthermore, the extraction of semantic information can speed up subsequent processing steps such as target detection, object tracking or scene analysis. By directly accessing key information, the system can perform complex visual tasks more quickly, improving processing efficiency and responsiveness.
[0073] S105: Encode the semantic information using a second lossless coding scheme, and encode the non-semantic information using a screen content coding scheme.
[0074] In a possible implementation, the first encoding scheme and the second encoding scheme are specifically:
[0075] Fixed-length encoding scheme, run-length encoding scheme, dictionary encoding scheme or specific lossless encoding scheme.
[0076] In a possible implementation manner, the non-semantic information specifically includes:
[0077] The original pixel value of the semantic information part is removed and / or the pixel value filled with the semantic information is filled. The pixel value filled is specifically a fixed color value and / or a pixel value interpolated from neighboring pixels.
[0078] In the present invention, the second lossless coding scheme can effectively compress semantic information and reduce the data size as much as possible, thereby saving storage space and transmission bandwidth. At the same time, encoding non-semantic information through the screen content coding scheme can effectively reduce the amount of data during data transmission. In particular, for fill pixel values, using fixed color values or neighboring pixel interpolation pixel values can further optimize data transmission efficiency.
[0079] S106: reconstructing the semantic information through the semantic pixel library, and reconstructing the non-semantic information through the screen content encoding scheme.
[0080] In a possible implementation, the screen content encoding scheme is specifically as follows:
[0081] International screen content coding standards, national screen content coding standards or open source screen content coding schemes.
[0082] In the present invention, the semantic pixel library stores the semantic information of images or videos, and can accurately reconstruct the key semantic content of images or videos through rapid indexing and retrieval. This method is more efficient than directly operating the original pixel data and reduces the complexity of encoding. At the same time, the screen content encoding scheme adopts international standards, domestic standards or open source schemes, which can effectively encode and compress non-semantic information. This can reduce the bandwidth and transmission time required during the transmission process.
[0083] Furthermore, choosing international standards, domestic standards or open source solutions as screen content encoding solutions can ensure the versatility and scalability of the system, enabling it to adapt to the needs of different platforms and systems, and improve the flexibility and operability of the overall system.
[0084] S107: Output the code stream of the current frame image.
[0085] In the present invention, outputting the encoded code stream can reduce the bandwidth and storage space required for data transmission, which is of great significance for the transmission and storage of large-scale data, and can reduce costs and improve the overall efficiency of data processing.
[0086] S108: Repeat S104 to S107 until all frame images are encoded.
[0087] In the present invention, S104 to S107 are repeatedly executed, i.e., extracting semantic information of the image, encoding semantic information, encoding non-semantic information and outputting a code stream, to form a continuous data processing flow. This process-based operation helps to automatically process a large amount of image or video data and can effectively manage the data flow and task execution order.
[0088] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:
[0089] In the present invention, a semantic pixel library is established according to preset rules; screen content is obtained, semantic information of each frame image in the screen content is extracted, the semantic information is encoded by a second lossless coding scheme, and non-semantic information is encoded by a screen content coding scheme, thereby improving coding efficiency. The semantic pixel library is encoded by a first lossless coding scheme; the semantic information is reconstructed by the semantic pixel library, and the non-semantic information is reconstructed by a screen content coding scheme. The complexity of coding is effectively reduced.
[0090] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a screen content encoding device based on a semantic pixel library provided by the present invention.
[0091] The present invention also provides a device 30 for encoding screen content based on a semantic pixel library, comprising:
[0092] Establishing module 301, used to establish a semantic pixel library according to preset rules;
[0093] A first encoding module 302, configured to encode the semantic pixel library using a first lossless encoding scheme;
[0094] A first acquisition module 303, used to acquire screen content;
[0095] An extraction module 304, used to extract semantic information of each frame of image in the screen content;
[0096] A second encoding module 305, configured to encode the semantic information using a second lossless encoding scheme, and to encode the non-semantic information using a screen content encoding scheme;
[0097] A first reconstruction module 306, configured to reconstruct the semantic information through the semantic pixel library and reconstruct the non-semantic information through a screen content coding scheme;
[0098] The first output module 307 is used to output the code stream of the current frame image;
[0099] The first repetition module 308 is used to repeatedly execute the extraction module 304 to the first output module 307 until all frame image encoding is completed.
[0100] The screen content encoding device 30 based on the semantic pixel library provided by the present invention can implement the various screen content decoding methods based on the semantic pixel library in the above method embodiments and can obtain the same technical effects. To avoid repetition, the present invention will not go into details.
[0101] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:
[0102] In the present invention, a semantic pixel library is established according to preset rules; screen content is obtained, semantic information of each frame image in the screen content is extracted, the semantic information is encoded by a second lossless coding scheme, and non-semantic information is encoded by a screen content coding scheme, thereby improving coding efficiency. The semantic pixel library is encoded by a first lossless coding scheme; the semantic information is reconstructed by the semantic pixel library, and the non-semantic information is reconstructed by a screen content coding scheme. The complexity of coding is effectively reduced.
[0103] Reference Manual Attached Figure 3 , showing a flow chart of a method for decoding screen content based on a semantic pixel library provided in an embodiment of the present invention.
[0104] The embodiment of the present invention provides a method for decoding screen content based on a semantic pixel library, which can be implemented by a decoding device for screen content based on a semantic pixel library, and the decoding device for screen content based on a semantic pixel library can be a terminal or a server. The processing flow of the method for decoding screen content based on a semantic pixel library can include the following steps:
[0105] S201: Decoding the semantic pixel library using a first lossless decoding scheme to obtain a semantic pixel library;
[0106] In a possible implementation manner, establishing a semantic pixel library according to a preset rule in S201 is specifically as follows:
[0107] A semantic pixel library is established through scene modeling.
[0108] In a possible implementation, the semantic pixel library includes: a semantic index indexi, a width wi, a height hi, and a pixel value wixhi.
[0109] In a possible implementation manner, the first decoding scheme and the second decoding scheme are specifically:
[0110] Fixed-length decoding scheme, run-length decoding scheme, dictionary decoding scheme or specific lossless decoding scheme.
[0111] In the present invention, by establishing a semantic pixel library and adopting a lossless coding and decoding scheme, image or video data can be effectively compressed. The semantic pixel library records the position, size and value of pixels, so that the image content can be more accurately identified and reconstructed, thereby reducing redundant information during data transmission. At the same time, the semantic index and pixel value information contained in the semantic pixel library can help the system to more accurately reconstruct the important content and structure of the image, thereby improving the visual quality and clarity of the image or video.
[0112] S202: Obtain image code stream;
[0113] S203: For each frame of the image, decode the semantic information by using the second lossless decoding scheme to obtain the semantic information, and decode the non-semantic information by using the screen content decoding scheme to obtain the non-semantic information;
[0114] In the present invention, the second lossless coding scheme can accurately decode semantic information, such as position information or semantic index, which is essential for reconstructing key parts of an image or video. By retaining this semantic information, it can be ensured that the reconstructed image can maintain the original structure and content during subsequent processing and decoding.
[0115] Furthermore, the screen content coding scheme focuses on processing non-semantic information, such as background, details or filler parts, to reduce the amount of data and improve compression efficiency in an optimized way. This layered processing can make the overall encoding and decoding process more efficient and controllable.
[0116] S204: reconstructing the semantic information through the semantic pixel library, and reconstructing the non-semantic information through a screen content decoding solution;
[0117] In a possible implementation manner, the semantic information specifically includes: location information and / or a semantic index index.
[0118] In a possible implementation manner, the non-semantic information specifically includes:
[0119] The original pixel value of the semantic information part is removed and / or the filled pixel value filled with the semantic information; the filled pixel value is specifically a fixed color value and / or an interpolated pixel value of adjacent pixels.
[0120] In a possible implementation manner, the screen content decoding scheme is specifically as follows:
[0121] International screen content decoding standards, domestic screen content decoding standards or open source screen content decoding solutions.
[0122] In the present invention, semantic information is accurately reconstructed through a semantic pixel library, which can ensure that the reconstructed image maintains the original structure and content in key parts, thereby maintaining high-quality visual output. At the same time, the layered image reconstruction method enables the system to process and transmit image data more efficiently. The separate processing of semantic information and non-semantic information enables targeted optimization and acceleration of processing steps during decoding and reconstruction.
[0123] S205: Outputting reconstructed pixels of the current frame image;
[0124] S206: Repeat S203 to S205 until all frame images are decoded.
[0125] In the present invention, by decoding and reconstructing image pixels frame by frame, real-time processing and continuous output of video streams can be achieved. This is crucial for applications such as real-time video transmission and streaming media playback, ensuring that users can instantly obtain updated image content. At the same time, by repeatedly performing decoding and reconstruction steps, the system can continuously optimize and improve the reconstruction quality and efficiency of the image, for example, when processor performance, algorithm optimization or network conditions change, the decoding process can be flexibly adjusted and improved.
[0126] The method for decoding screen content based on a semantic pixel library provided by the present invention is the reverse process of the above encoding method embodiment, and to avoid repetition, the present invention will not go into details.
[0127] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:
[0128] In the present invention, the semantic pixel library is decoded by adopting the first lossless coding scheme to obtain the semantic pixel library, obtain the image code stream, and for each frame of the image, the semantic information is decoded by the second lossless coding scheme to obtain the semantic information, and the non-semantic information is decoded by the screen content coding scheme to obtain the non-semantic information, thereby improving the decoding efficiency. The semantic information is reconstructed by the semantic pixel library, and the non-semantic information is reconstructed by the screen content coding scheme, thereby effectively reducing the complexity of the coding.
[0129] Reference Manual Attached Figure 4 , showing a structural schematic diagram of a screen content decoding device based on a semantic pixel library provided by the present invention.
[0130] The present invention also provides a decoding device 40 for screen content based on a semantic pixel library, comprising:
[0131] A first decoding module 401 is used to decode the semantic pixel library using a first lossless decoding scheme to obtain the semantic pixel library;
[0132] The second acquisition module 402 is used to acquire an image code stream;
[0133] The second decoding module 403 is used to decode the semantic information of each frame of the image through the second lossless decoding scheme to obtain the semantic information, and decode the non-semantic information through the screen content decoding scheme to obtain the non-semantic information;
[0134] The second reconstruction module 404 is used to decode the semantic pixel library by adopting the first lossless decoding scheme to obtain the semantic pixel library;
[0135] The second output module 405 is used to output the reconstructed pixels of the current frame image;
[0136] The second repeating module 406 is used to repeatedly execute the second decoding module 403 to the second output module 405 until all frame images are decoded.
[0137] A decoding device 40 for screen content based on a semantic pixel library provided by the present invention can implement the various decoding methods for screen content based on a semantic pixel library in the above method embodiments and can obtain the same technical effects. To avoid repetition, the present invention will not go into details.
[0138] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:
[0139] In the present invention, the semantic pixel library is decoded by adopting the first lossless coding scheme to obtain the semantic pixel library, obtain the image code stream, and for each frame of the image, the semantic information is decoded by the second lossless coding scheme to obtain the semantic information, and the non-semantic information is decoded by the screen content coding scheme to obtain the non-semantic information, thereby improving the decoding efficiency. The semantic information is reconstructed by the semantic pixel library, and the non-semantic information is reconstructed by the screen content coding scheme, thereby effectively reducing the complexity of the coding.
[0140] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
[0141] There are a few points to note:
[0142] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.
[0143] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.
[0144] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.
[0145] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.
Claims
1. A method for encoding screen content based on a semantic pixel library, characterized in that: include: S101: Establishing a semantic pixel library according to preset rules; S102: Encoding the semantic pixel library using a first lossless encoding scheme; S103: Acquire screen content; S104: extracting semantic information of each frame of image in the screen content; S105: Encode the semantic information using a second lossless coding scheme, and encode the non-semantic information using a screen content coding scheme; S106: reconstructing the semantic information through the semantic pixel library, and reconstructing the non-semantic information through a screen content encoding scheme; S107: Output the code stream of the current frame image; S108: Repeat S104 to S107 until all frame images are encoded.
2. A device for encoding screen content based on a semantic pixel library, characterized in that: The encoding device comprises: Establishing a module for establishing a semantic pixel library according to preset rules; A first encoding module, configured to encode the semantic pixel library by adopting a first lossless encoding scheme; A first acquisition module, used to acquire screen content; An extraction module, used to extract semantic information of each frame of image in the screen content; A second encoding module, used to encode the semantic information by a second lossless encoding scheme, and to encode the non-semantic information by a screen content encoding scheme; A first reconstruction module, configured to reconstruct the semantic information through the semantic pixel library and reconstruct the non-semantic information through a screen content encoding scheme; The first output module is used to output the code stream of the current frame image; The first repeating module is used to repeat the extraction module to the first output module until all frame image encoding is completed.
3. A method for decoding screen content based on a semantic pixel library, characterized in that: include: S201: Decoding the semantic pixel library using a first lossless decoding scheme to obtain a semantic pixel library; S202: Obtain image code stream; S203: For each frame of the image, decode the semantic information by using the second lossless decoding scheme to obtain the semantic information, and decode the non-semantic information by using the screen content decoding scheme to obtain the non-semantic information; S204: reconstructing the semantic information through the semantic pixel library, and reconstructing the non-semantic information through a screen content decoding solution; S205: Outputting reconstructed pixels of the current frame image; S206: Repeat S203 to S205 until all frame images are decoded.
4. The method for decoding screen content based on a semantic pixel library according to claim 3, characterized in that: The specific steps of establishing a semantic pixel library according to preset rules in S201 are as follows: A semantic pixel library is established through scene modeling.
5. The method for decoding screen content based on a semantic pixel library according to claim 3, characterized in that: The semantic pixel library includes: semantic index indexi, width wi, height hi and pixel value wixhi.
6. The method for decoding screen content based on a semantic pixel library according to claim 3, characterized in that: The first decoding scheme and the second decoding scheme are specifically: Fixed-length decoding scheme, run-length decoding scheme, dictionary decoding scheme or specific lossless decoding scheme.
7. The method for decoding screen content based on a semantic pixel library according to claim 3, characterized in that: The semantic information specifically includes: location information and / or semantic index index.
8. The method for decoding screen content based on a semantic pixel library according to claim 3, characterized in that: The non-semantic information is specifically: The original pixel value of the semantic information part is removed and / or the filled pixel value filled with the semantic information; the filled pixel value is specifically a fixed color value and / or an interpolated pixel value of adjacent pixels.
9. The method for decoding screen content based on a semantic pixel library according to claim 3, characterized in that: The screen content decoding scheme is specifically as follows: International screen content decoding standards, domestic screen content decoding standards or open source screen content decoding solutions.
10. A device for decoding screen content based on a semantic pixel library, characterized in that: The decoding device comprises: A first decoding module, configured to decode the semantic pixel library by adopting a first lossless decoding scheme to obtain the semantic pixel library; The second acquisition module is used to acquire the image code stream; A second decoding module is used to decode the semantic information of each frame of the image through a second lossless decoding scheme to obtain the semantic information, and to decode the non-semantic information through a screen content decoding scheme to obtain the non-semantic information; A second reconstruction module is used to decode the semantic pixel library by adopting the first lossless decoding scheme to obtain the semantic pixel library; A second output module, used for outputting the reconstructed pixels of the current frame image; The second repeating module is used to repeat the second decoding module to the second output module until all frame images are decoded.
