WO2022265282A1 - Conversion method and device for high dynamic range format - Google Patents

Conversion method and device for high dynamic range format Download PDF

Info

Publication number
WO2022265282A1
WO2022265282A1 PCT/KR2022/007964 KR2022007964W WO2022265282A1 WO 2022265282 A1 WO2022265282 A1 WO 2022265282A1 KR 2022007964 W KR2022007964 W KR 2022007964W WO 2022265282 A1 WO2022265282 A1 WO 2022265282A1
Authority
WO
WIPO (PCT)
Prior art keywords
hdr10
standard
splitting
arithmetic unit
arithmetic
Prior art date
Application number
PCT/KR2022/007964
Other languages
French (fr)
Inventor
Juolong WANG
Original Assignee
Samsung Electronics Co., Ltd.
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 Samsung Electronics Co., Ltd. filed Critical Samsung Electronics Co., Ltd.
Publication of WO2022265282A1 publication Critical patent/WO2022265282A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
    • H04N21/234309—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements by transcoding between formats or standards, e.g. from MPEG-2 to MPEG-4 or from Quicktime to Realvideo
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/01—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
    • H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
    • H04N19/172—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/40—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video transcoding, i.e. partial or full decoding of a coded input stream followed by re-encoding of the decoded output stream
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/42—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation
    • H04N19/436—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation using parallelised computational arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
    • H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
    • H04N21/440218—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display by transcoding between formats or standards, e.g. from MPEG-2 to MPEG-4
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present disclosure relates to the image processing technology, in particular to a conversion method and device for a high dynamic range (HDR) format.
  • HDR high dynamic range
  • HDR10+ is an upgraded version of HDR 10, supports dynamic metadata processing, and can even provide signals frame by frame for each scene to enable a display apparatus to find the most suitable brightness for HDR display effect with regard to each frame of the picture. Therefore, compared to HDR 10, a video display of HDR10+ is better.
  • the inventor found that the existing methods for generating HDR10+ content based on HDR10 content causes problems such as low efficiency, high power consumption, and high requirements for device performance due to a high complexity of the algorithms.
  • the main purpose of the present disclosure is to provide a conversion method and device for HDR format, which can convert content of HDR10 standard into content of HDR10+, and can improve conversion efficiency, reduce power consumption and apparatus performance requirements.
  • a conversion method for a high dynamic range (HDR) format comprising:
  • the splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard in the hierarchical splitting manner comprises: splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard to obtain a set of basic function modules, according to function types of sub-algorithms; splitting each module in the set of the function modules respectively to obtain a set of functional function modules by taking a functional function as a splitting granularity; splitting each functional function in the set of the functional function modules to obtain the set of the format conversion arithmetic units by taking a basic arithmetic operation as a splitting granularity, wherein single arithmetic process corresponding to repetitive arithmetics is split according to the basic arithmetic operation when the functional function comprises the repetitive arithmetics.
  • the obtaining the arithmetic unit execution order comprises: determining candidate arithmetic unit execution orders that can be adopted when executing the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard by adopting the arithmetic units in the set of the format conversion arithmetic units in a concurrent data processing manner, within a resource overhead range that an apparatus on which the conversion method is to be run can support, based on the resource status information of the apparatus; inputting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard, the resource state information and the candidate arithmetic unit execution orders to a pre-trained arithmetic unit execution order optimization model to be processed, obtaining and outputting an arithmetic unit execution order with the shortest execution duration among the arithmetic unit candidate execution orders.
  • the processing performed by the arithmetic unit execution order optimization model comprises: splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard according to the hierarchical splitting manner by the arithmetic unit execution order optimization model to obtain the set of the format conversion arithmetic units; determining an execution duration of each of the candidate arithmetic unit execution orders within the resource overhead range that the apparatus can support according to the resource status information and according to execution logic of the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard, and outputting the arithmetic unit execution order corresponding to the shortest execution duration.
  • An embodiment of the disclosure also discloses a conversion device for a high dynamic range (HDR) format, comprising:
  • a conversion unit configured to perform, for each frame of data of HDR10 standard content to be converted, a processing of converting each frame of the data to HDR10+ standard based on a preset set of format conversion arithmetic units and in accordance with a preset arithmetic unit execution order, and update HDR10+ standard metadata of a corresponding scene by using HDR10+ standard metadata that is obtained by the processing, wherein the set of the format conversion arithmetic units is obtained by splitting an algorithm for converting content data of HDR10 standard into that of HDR10+ standard in a hierarchical splitting manner, and the arithmetic unit execution order is obtained with a preferred target that an execution duration is the shortest; and
  • a metadata insertion unit configured to insert HDR10+ standard metadata of all the scenes into video stream information of the HDR10 standard content to be converted to obtain corresponding HDR10+ content.
  • the device further comprises a pre-processing unit, configured to split the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard in the hierarchical splitting manner, the splitting comprising:
  • splitting each functional function in the set of the functional function modules to obtain the set of the format conversion arithmetic units by taking a basic arithmetic operation as a splitting granularity, wherein single arithmetic process corresponding to repetitive arithmetics is split according to the basic arithmetic operation when the functional function comprises the repetitive arithmetics.
  • the pre-processing unit is further configured to obtain the arithmetic unit execution order, the obtaining comprising:
  • the pre-processing unit specifically performs the processing adopting the arithmetic unit execution order optimization model, the processing comprises:
  • An embodiment of the disclosure also discloses a conversion apparatus for a high dynamic range format, comprising a processor and a memory, the memory storing an application program for causing the processor to execute the conversion method for the high dynamic range format described above that can be executed by the processor.
  • An embodiment of the disclosure also a computer-readable storage medium storing a computer program for causing the processor to implement the conversion method for a high dynamic range format described above therein.
  • the conversion method and the conversion device for the high dynamic range proposed by the embodiments of the present disclosure split the entire algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard into several arithmetic units in advance, then determine the arithmetic unit execution order with a target that the execution duration is the shortest, after that, based on the arithmetic units obtained by the splitting, according to the execution order, perform a format conversion on the HDR10 standard content to be converted frame by frame to obtain HDR10+ standard metadata of each scene, and finally insert the HDR10+ standard metadata of all scenes into the video stream information of content of the HDR10 standard to be converted, so as to obtain the corresponding HDR10+ content.
  • the arithmetic units after splitting the format conversion algorithm are used to perform the format conversion, and the arithmetic unit execution order is determined with the target that the execution duration is the shortest so as to perform the HDR format conversion.
  • the efficiency of the content of HDR10 standard being converted to that of HDR10+ can be effectively improved within the allowable range of apparatus resources by adopting the parallel processing of the arithmetic units, and arithmetic power consumption can be reduced, thereby the requirements of HDR format conversion on apparatus performance can be effectively reduced.
  • FIG. 1 is a schematic flowchart of a conversion method for a high dynamic range format according to an embodiment of the present disclosure
  • FIG. 2 is a schematic flowchart of a method for splitting an algorithm for converting content data of HDR10 standard into that of HDR10+ standard according to an embodiment of the present disclosure
  • FIG. 3 is a schematic flowchart of a method for determining an execution order of arithmetic units by using an arithmetic unit execution order optimization model according to an embodiment of the present disclosure
  • FIG. 4 is a schematic flowchart of a processing method of arithmetic unit execution order optimization model according to an embodiment of the present disclosure.
  • FIG. 5 is a schematic diagram of structure of a conversion device for a high dynamic range format according to an embodiment of the present disclosure.
  • FIG. 1 is a schematic flowchart of an HDR format conversion method of an embodiment of the present disclosure. As shown in FIG. 1, the high dynamic range format conversion method implemented by this embodiment mainly comprises the following steps:
  • Step 101 for each frame of data of HDR10 standard content to be converted, the each frame of the data is processed to be converted to HDR10+ standard based on a preset set of format conversion arithmetic units and according to a preset arithmetic unit execution order, and a HDR10+ standard metadata of a corresponding scene is updated using a HDR10+ standard metadata obtained by the processing,
  • the set of the format conversion arithmetic units is obtained by splitting an algorithm for converting content data of a HDR10 standard into that of a HDR10+ standard in a hierarchical splitting manner, and the arithmetic unit execution order is obtained with a preferred target that an execution duration is the shortest.
  • the content data of the HDR10 standard are processed by adopting the arithmetic units obtained via splitting the algorithm described above and according to the unit execution order with the shortest execution duration, instead of directly running the entire algorithm for converting the content data of HDR10 standard to that of HDR10+ standard to process the content data of the HDR10 standard.
  • the concurrent processing of the arithmetic units can be used to improve the efficiency of the format conversion by splitting the format conversion algorithm into more fine-grained arithmetic units, and the overall arithmetic efficiency of the algorithm can be improved to the greatest extent and the power consumption can be reduced to the greatest extent, by executing these arithmetic units according to the arithmetic unit execution order with the shortest execution duration.
  • the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard is split based on the hierarchical splitting manner:
  • Step a1 the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard is split to obtain a set of basic function modules according to function types of sub-algorithms.
  • This step is used to split the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard according to the function types of the sub-algorithms included in the algorithm to obtain a basic function module corresponding to a function of each sub-algorithm.
  • Constituent elements of the set of the basic function modules are specifically determined by the function types of the sub-algorithms actually included in the algorithm.
  • a set of basic function modules obtained based on splitting the existing algorithms for converting the content data of HDR10 standard to that of the HDR10+ standard according to the function types of the sub-algorithms includes at least a color space conversion algorithm module, a color conversion algorithm module, a tone mapping algorithm module, and a scene detection algorithm module.
  • Step a2 each module in the set of the function modules is split respectively to obtain a set of functional function modules by using a functional function as a splitting granularity.
  • step a1 the four modules obtained in step a1 are further split according to functional functions to divide each functional function into a functional function module.
  • Step a3 each functional function in the set of the functional function modules is split to obtain the set of format conversion arithmetic units by using a basic arithmetic operation as a splitting granularity, wherein when repetitive arithmetics are included in a functional function, a single arithmetic process corresponding to the repetitive arithmetics is split according to a basic arithmetic operation.
  • each functional function obtained in step a2 is further split to obtain a arithmetic unit corresponding to each basic arithmetic operation(such as addition, subtraction, multiplication, division, etc.), thereby obtaining more fine-grained computing particles, i.e., the arithmetic units, in this way, the possibility of parallel processing of computing particles can be increased to a greater extent, so that the efficiency of format conversion can be effectively improved and the power consumption can be effectively reduced.
  • the repetitive arithmetic processes in the functional functions such as loops, iterative calculations, etc., it is only necessary to split algorithms of one of the repetitive arithmetic processes.
  • a pre-trained arithmetic unit execution order optimization model can be used to determine the arithmetic unit execution order used in step 101, the specific method shown in FIG. 3 comprises the following steps:
  • Step b1 candidate arithmetic unit execution orders that can be adopted when executing the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard by adopting the arithmetic units in the set of format conversion arithmetic units in a concurrent data processing manner are determined within a resource overhead range that a apparatus on which the conversion method is to be run can support, based on resource status information of the apparatus.
  • the resource status information of the apparatus is operating environment information of the apparatus.
  • all arithmetic unit execution orders that the apparatus can support when executing the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard by adopting the arithmetic units in the set of format conversion arithmetic units in the concurrent data processing manner are determined based on the operating environment information of the apparatus, so that in the subsequent steps, the execution order with the shortest execution duration is further selected from all execution orders as an execution order adopted when the format conversion processing is performed for the each frame of the data.
  • the concurrent data processing manner may specifically be a pipeline processing manner.
  • a parallel processing may be utilized to a greater extent and the overall arithmetic efficiency of the format conversion algorithm may be improved by deploying the arithmetic units obtained by splitting the algorithm to different time nodes of a time axis and performing independent parameter configurations.
  • Step b2 the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard, the resource state information and the candidate execution orders of the arithmetic units are input to a pre-trained arithmetic unit execution order optimization model to be processed to obtain and output the arithmetic unit execution order with the shortest execution duration among the candidate arithmetic unit execution orders.
  • the following steps may be specifically adopted by the arithmetic unit execution order optimization model to perform the processing, so as to obtain the arithmetic unit execution order with the shortest execution duration:
  • Step b21 the arithmetic unit execution order optimization model splits the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard in a hierarchical splitting manner to obtain the set of the format conversion arithmetic units.
  • Step b22 an execution duration of the each candidate arithmetic unit execution order is determined within the resource overhead range that the apparatus can support according to the resource status information and according to execution logic of the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard and the arithmetic unit execution order corresponding to the shortest execution duration is output.
  • resource overhead including power consumption and time overhead
  • the model can obtain the execution duration of each candidate arithmetic unit execution order based on the resource overhead of each basic operation.
  • the arithmetic unit execution order optimization model may be implemented by using a decision tree or a nearest neighbor model, and the specific methods are mastered by those skilled in the art, and will not be repeated here.
  • Step 102 HDR10+ standard metadata of all the scenes are inserted into the video stream information of the content of the HDR10 standard that is to be converted to obtain the corresponding HDR10+ content.
  • the algorithm for converting the content of HDR10 standard to that of the HDR10+ standard is performed by using the arithmetic units after splitting the format conversion algorithm and according to the arithmetic unit execution order with the shortest execution duration in the parallel data processing manner.
  • the parallel processing of fine-grained arithmetic units can be used within the allowable range of the apparatus resources to effectively improve the efficiency of converting the content of the HDR10 standard to that of the HDR10+ standard and reduce the arithmetic power consumption, so that the requirements of HDR format conversion on apparatus performance can be effectively reduced.
  • the embodiment of the present disclosure further discloses a conversion device for a high dynamic range format, as shown in FIG. 5, the device comprises:
  • a conversion unit 501 configured to perform, for each frame of data of HDR10 standard content to be converted, a processing of converting each frame of the data to HDR10+ standard based on a preset set of format conversion arithmetic units and in accordance with a preset arithmetic unit execution order, and update HDR10+ standard metadata of a corresponding scene by adipting HDR10+ standard metadata that is obtained by the processing, wherein the set of the format conversion arithmetic units is obtained by splitting an algorithm for converting content data of HDR10 standard into that of HDR10+ standard in a hierarchical splitting manner, and the arithmetic unit execution order is obtained with a preferred target that an execution duration is the shortest.
  • a metadata insertion unit 502 configured to insert HDR10+ standard metadata of all the scenes into video stream information of the HDR10 standard content to be converted to obtain corresponding HDR10+ content.
  • the device further comprises a pre-processing unit 503, configured to split the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard to obtain the set of format conversion arithmetic units in the hierarchical splitting manner, the splitting comprising:
  • splitting each functional function in the set of the functional function modules to obtain the set of the format conversion arithmetic units by taking a basic arithmetic operation as a splitting granularity, wherein single arithmetic process corresponding to repetitive arithmetics is split according to the basic arithmetic operation when the functional function comprises the repetitive arithmetics.
  • the pre-processing unit 503 is further configured to obtain the arithmetic unit execution order, the obtaining comprising:
  • the pre-processing unit 503 specifically performs the processing by adopting the arithmetic unit execution order optimization model, the processing comprises:
  • an embodiment of the present disclosure also discloses a conversion apparatus for the high dynamic range format including a processor and a memory;
  • the memory can be specifically implemented as a plurality of storage media such as electronically erasable programmable read-only memory(EEPROM), flash memory, programmable program read-only memory(PROM), etc.
  • the processor may be implemented to include one or more central processing units or one or more field programmable gate arrays, wherein the field programmable gate arrays integrates one or more central processing unit cores.
  • the central processing units or central processing unit cores may be implemented as a CPU or MCU.
  • a hardware module may include permanent circuits or logic devices (for example, dedicated processors, such as FPGAs or ASICs) specially designed to complete specific operations.
  • the hardware modules may also include programmable logic devices or circuits temporarily configured by software (for example, including general-purpose processors or other programmable processors) for performing specific operations.
  • software for example, including general-purpose processors or other programmable processors
  • the present invention also provides a machine-readable storage medium, in which computer-readable instructions used for executing the above-described conversion method for the high dynamic range format are stored.
  • a system or device equipped with a storage medium on which software program codes for realizing the function of any one of the above-mentioned embodiments and causing the computer (or CPU or MPU) of the system or the device to read and execute the program codes stored in the storage medium is stored on the storage medium may be provided.
  • an operating system or the like operating on the computer can be enabled to complete part or all of the actual operations through instructions based on the program codes.
  • Implementations of storage media used for providing the program codes include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tape, non-volatile memory card and ROM.
  • the program codes can be downloaded from a server computer or a cloud via a communication network.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Television Systems (AREA)

Abstract

The present disclosure discloses a conversion method and device for a high dynamic range format, wherein the method comprising: performing, for each frame of data of HDR10 standard content to be converted, a processing of converting each frame of the data to HDR10+ standard based on a preset set of format conversion arithmetic units and in accordance with a preset arithmetic unit execution order, updating HDR10+ standard metadata of corresponding scenes by using HDR10+ standard metadata that is obtained by the processing, wherein the set of the format conversion arithmetic units is obtained by splitting an algorithm for converting content data of HDR10 standard into that of HDR10+ standard in a hierarchical splitting manner, and the arithmetic unit execution order is obtained with a preferred target that an execution duration is the shortest; and inserting the HDR10+ standard metadata of all the scenes into video stream information of the HDR10 standard content to be converted to obtain corresponding HDR10+ content.

Description

CONVERSION METHOD AND DEVICE FOR HIGH DYNAMIC RANGE FORMAT
The present disclosure relates to the image processing technology, in particular to a conversion method and device for a high dynamic range (HDR) format.
With the development of 5G and display technology, the public's demand for high-quality video viewing experience is increasing. The HDR technology is one of the main technologies of currently improving video viewing experience. With the increasing user demand for HDR technology, the demand for HDR content in the HDR market is also increasing. Current mainstream HDR formats include HDR10, HDR10+, Dolby Vision and so on. Among them, HDR10+ is an upgraded version of HDR 10, supports dynamic metadata processing, and can even provide signals frame by frame for each scene to enable a display apparatus to find the most suitable brightness for HDR display effect with regard to each frame of the picture. Therefore, compared to HDR 10, a video display of HDR10+ is better.
In the process of implementing the present disclosure, the inventor found that the existing methods for generating HDR10+ content based on HDR10 content causes problems such as low efficiency, high power consumption, and high requirements for device performance due to a high complexity of the algorithms.
The main purpose of the present disclosure is to provide a conversion method and device for HDR format, which can convert content of HDR10 standard into content of HDR10+, and can improve conversion efficiency, reduce power consumption and apparatus performance requirements.
In order to achieve the purpose described above, the technical solutions proposed by the present disclosure are as follows:
A conversion method for a high dynamic range (HDR) format, comprising:
performing, for each frame of data of HDR10 standard content to be converted, a processing of converting each frame of the data to HDR10+ standard based on a preset set of format conversion arithmetic units and in accordance with a preset arithmetic unit execution order, updating HDR10+ standard metadata of a corresponding scene by using HDR10+ standard metadata that is obtained by the processing, wherein the set of the format conversion arithmetic units is obtained by splitting an algorithm for converting content data of HDR10 standard into that of HDR10+ standard in a hierarchical splitting manner, and the arithmetic unit execution order is obtained with a preferred target that an execution duration is the shortest; and inserting HDR10+ standard metadata of all the scenes into video stream information of the HDR10 standard content to be converted to obtain corresponding HDR10+ content.
Preferably, wherein the splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard in the hierarchical splitting manner comprises: splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard to obtain a set of basic function modules, according to function types of sub-algorithms; splitting each module in the set of the function modules respectively to obtain a set of functional function modules by taking a functional function as a splitting granularity; splitting each functional function in the set of the functional function modules to obtain the set of the format conversion arithmetic units by taking a basic arithmetic operation as a splitting granularity, wherein single arithmetic process corresponding to repetitive arithmetics is split according to the basic arithmetic operation when the functional function comprises the repetitive arithmetics.
Preferably, the obtaining the arithmetic unit execution order comprises: determining candidate arithmetic unit execution orders that can be adopted when executing the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard by adopting the arithmetic units in the set of the format conversion arithmetic units in a concurrent data processing manner, within a resource overhead range that an apparatus on which the conversion method is to be run can support, based on the resource status information of the apparatus; inputting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard, the resource state information and the candidate arithmetic unit execution orders to a pre-trained arithmetic unit execution order optimization model to be processed, obtaining and outputting an arithmetic unit execution order with the shortest execution duration among the arithmetic unit candidate execution orders.
Preferably, the processing performed by the arithmetic unit execution order optimization model comprises: splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard according to the hierarchical splitting manner by the arithmetic unit execution order optimization model to obtain the set of the format conversion arithmetic units; determining an execution duration of each of the candidate arithmetic unit execution orders within the resource overhead range that the apparatus can support according to the resource status information and according to execution logic of the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard, and outputting the arithmetic unit execution order corresponding to the shortest execution duration.
An embodiment of the disclosure also discloses a conversion device for a high dynamic range (HDR) format, comprising:
a conversion unit, configured to perform, for each frame of data of HDR10 standard content to be converted, a processing of converting each frame of the data to HDR10+ standard based on a preset set of format conversion arithmetic units and in accordance with a preset arithmetic unit execution order, and update HDR10+ standard metadata of a corresponding scene by using HDR10+ standard metadata that is obtained by the processing, wherein the set of the format conversion arithmetic units is obtained by splitting an algorithm for converting content data of HDR10 standard into that of HDR10+ standard in a hierarchical splitting manner, and the arithmetic unit execution order is obtained with a preferred target that an execution duration is the shortest; and
a metadata insertion unit, configured to insert HDR10+ standard metadata of all the scenes into video stream information of the HDR10 standard content to be converted to obtain corresponding HDR10+ content.
Preferably, the device further comprises a pre-processing unit, configured to split the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard in the hierarchical splitting manner, the splitting comprising:
splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard to obtain a set of basic function modules, according to function types of sub-algorithms;
splitting each module in the set of the function modules respectively to obtain a set of functional function modules by taking a functional function as a splitting granularity;
splitting each functional function in the set of the functional function modules to obtain the set of the format conversion arithmetic units by taking a basic arithmetic operation as a splitting granularity, wherein single arithmetic process corresponding to repetitive arithmetics is split according to the basic arithmetic operation when the functional function comprises the repetitive arithmetics.
Preferably, the pre-processing unit is further configured to obtain the arithmetic unit execution order, the obtaining comprising:
determining candidate arithmetic unit execution orders that can be adopted when executing the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard by adopting the arithmetic units in the set of the format conversion arithmetic units in a concurrent data processing manner, within a resource overhead range that the device on which the conversion method is to be run can support, based on the resource status information of the device;
inputting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard, the resource state information and the candidate arithmetic unit execution orders to a pre-trained arithmetic unit execution order optimization model to be processed, obtaining and outputting an arithmetic unit execution order with the shortest execution duration among the candidate arithmetic unit execution orders.
Preferably, the pre-processing unit specifically performs the processing adopting the arithmetic unit execution order optimization model, the processing comprises:
splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard according to the hierarchical splitting manner by the arithmetic unit execution order optimization model to obtain the set of the format conversion arithmetic units;
determining an execution duration of each of the candidate arithmetic unit execution orders within the resource overhead range that the device can support according to the resource status information and according to execution logic of the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard, and outputting the arithmetic unit execution order corresponding to the shortest execution duration.
An embodiment of the disclosure also discloses a conversion apparatus for a high dynamic range format, comprising a processor and a memory, the memory storing an application program for causing the processor to execute the conversion method for the high dynamic range format described above that can be executed by the processor.
An embodiment of the disclosure also a computer-readable storage medium storing a computer program for causing the processor to implement the conversion method for a high dynamic range format described above therein.
The conversion method and the conversion device for the high dynamic range proposed by the embodiments of the present disclosure split the entire algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard into several arithmetic units in advance, then determine the arithmetic unit execution order with a target that the execution duration is the shortest, after that, based on the arithmetic units obtained by the splitting, according to the execution order, perform a format conversion on the HDR10 standard content to be converted frame by frame to obtain HDR10+ standard metadata of each scene, and finally insert the HDR10+ standard metadata of all scenes into the video stream information of content of the HDR10 standard to be converted, so as to obtain the corresponding HDR10+ content. In the solutions described above, the arithmetic units after splitting the format conversion algorithm are used to perform the format conversion, and the arithmetic unit execution order is determined with the target that the execution duration is the shortest so as to perform the HDR format conversion.
Acconrding to an examplary embodiment, the efficiency of the content of HDR10 standard being converted to that of HDR10+ can be effectively improved within the allowable range of apparatus resources by adopting the parallel processing of the arithmetic units, and arithmetic power consumption can be reduced, thereby the requirements of HDR format conversion on apparatus performance can be effectively reduced.
FIG. 1 is a schematic flowchart of a conversion method for a high dynamic range format according to an embodiment of the present disclosure;
FIG. 2 is a schematic flowchart of a method for splitting an algorithm for converting content data of HDR10 standard into that of HDR10+ standard according to an embodiment of the present disclosure;
FIG. 3 is a schematic flowchart of a method for determining an execution order of arithmetic units by using an arithmetic unit execution order optimization model according to an embodiment of the present disclosure;
FIG. 4 is a schematic flowchart of a processing method of arithmetic unit execution order optimization model according to an embodiment of the present disclosure; and
FIG. 5 is a schematic diagram of structure of a conversion device for a high dynamic range format according to an embodiment of the present disclosure.
In order to make the objectives, technical solutions, and advantages of the present disclosure clearer, the present disclosure will be further described in detail below with reference to the accompanying drawings and a specific embodiment.
FIG. 1 is a schematic flowchart of an HDR format conversion method of an embodiment of the present disclosure. As shown in FIG. 1, the high dynamic range format conversion method implemented by this embodiment mainly comprises the following steps:
Step 101, for each frame of data of HDR10 standard content to be converted, the each frame of the data is processed to be converted to HDR10+ standard based on a preset set of format conversion arithmetic units and according to a preset arithmetic unit execution order, and a HDR10+ standard metadata of a corresponding scene is updated using a HDR10+ standard metadata obtained by the processing,
Wherein, the set of the format conversion arithmetic units is obtained by splitting an algorithm for converting content data of a HDR10 standard into that of a HDR10+ standard in a hierarchical splitting manner, and the arithmetic unit execution order is obtained with a preferred target that an execution duration is the shortest.
In this step, in order to improve an efficiency of the format conversion, the content data of the HDR10 standard are processed by adopting the arithmetic units obtained via splitting the algorithm described above and according to the unit execution order with the shortest execution duration, instead of directly running the entire algorithm for converting the content data of HDR10 standard to that of HDR10+ standard to process the content data of the HDR10 standard. In this way, the concurrent processing of the arithmetic units can be used to improve the efficiency of the format conversion by splitting the format conversion algorithm into more fine-grained arithmetic units, and the overall arithmetic efficiency of the algorithm can be improved to the greatest extent and the power consumption can be reduced to the greatest extent, by executing these arithmetic units according to the arithmetic unit execution order with the shortest execution duration.
In one embodiment, in order to refine the granularity of the arithmetic units to the greatest extent, as shown in FIG. 2, the following steps can be specifically adopted, the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard is split based on the hierarchical splitting manner:
Step a1, the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard is split to obtain a set of basic function modules according to function types of sub-algorithms.
This step is used to split the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard according to the function types of the sub-algorithms included in the algorithm to obtain a basic function module corresponding to a function of each sub-algorithm. Constituent elements of the set of the basic function modules are specifically determined by the function types of the sub-algorithms actually included in the algorithm. For example, a set of basic function modules obtained based on splitting the existing algorithms for converting the content data of HDR10 standard to that of the HDR10+ standard according to the function types of the sub-algorithms includes at least a color space conversion algorithm module, a color conversion algorithm module, a tone mapping algorithm module, and a scene detection algorithm module.
Step a2: each module in the set of the function modules is split respectively to obtain a set of functional function modules by using a functional function as a splitting granularity.
In this step, the four modules obtained in step a1 are further split according to functional functions to divide each functional function into a functional function module.
Step a3: each functional function in the set of the functional function modules is split to obtain the set of format conversion arithmetic units by using a basic arithmetic operation as a splitting granularity, wherein when repetitive arithmetics are included in a functional function, a single arithmetic process corresponding to the repetitive arithmetics is split according to a basic arithmetic operation.
In this step, each functional function obtained in step a2 is further split to obtain a arithmetic unit corresponding to each basic arithmetic operation(such as addition, subtraction, multiplication, division, etc.), thereby obtaining more fine-grained computing particles, i.e., the arithmetic units, in this way, the possibility of parallel processing of computing particles can be increased to a greater extent, so that the efficiency of format conversion can be effectively improved and the power consumption can be effectively reduced. Here, for the repetitive arithmetic processes in the functional functions, such as loops, iterative calculations, etc., it is only necessary to split algorithms of one of the repetitive arithmetic processes.
In one embodiment, in order to obtain the arithmetic unit execution order with the best execution efficiency, a pre-trained arithmetic unit execution order optimization model can be used to determine the arithmetic unit execution order used in step 101, the specific method shown in FIG. 3 comprises the following steps:
Step b1, candidate arithmetic unit execution orders that can be adopted when executing the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard by adopting the arithmetic units in the set of format conversion arithmetic units in a concurrent data processing manner are determined within a resource overhead range that a apparatus on which the conversion method is to be run can support, based on resource status information of the apparatus.
The resource status information of the apparatus is operating environment information of the apparatus. In this step, all arithmetic unit execution orders that the apparatus can support when executing the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard by adopting the arithmetic units in the set of format conversion arithmetic units in the concurrent data processing manner are determined based on the operating environment information of the apparatus, so that in the subsequent steps, the execution order with the shortest execution duration is further selected from all execution orders as an execution order adopted when the format conversion processing is performed for the each frame of the data.
The concurrent data processing manner may specifically be a pipeline processing manner. In this way, by using this processing manner, a parallel processing may be utilized to a greater extent and the overall arithmetic efficiency of the format conversion algorithm may be improved by deploying the arithmetic units obtained by splitting the algorithm to different time nodes of a time axis and performing independent parameter configurations.
Step b2: the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard, the resource state information and the candidate execution orders of the arithmetic units are input to a pre-trained arithmetic unit execution order optimization model to be processed to obtain and output the arithmetic unit execution order with the shortest execution duration among the candidate arithmetic unit execution orders.
In one embodiment, as shown in FIG. 4, the following steps may be specifically adopted by the arithmetic unit execution order optimization model to perform the processing, so as to obtain the arithmetic unit execution order with the shortest execution duration:
Step b21: the arithmetic unit execution order optimization model splits the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard in a hierarchical splitting manner to obtain the set of the format conversion arithmetic units.
In this step, the specific method of splitting the algorithm is the same as that of the above steps a1~a3.
Step b22: an execution duration of the each candidate arithmetic unit execution order is determined within the resource overhead range that the apparatus can support according to the resource status information and according to execution logic of the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard and the arithmetic unit execution order corresponding to the shortest execution duration is output.
Here, based on the resource status information of the apparatus, resource overhead (including power consumption and time overhead) for the apparatus to perform each basic operation can be determined. In this way, the model can obtain the execution duration of each candidate arithmetic unit execution order based on the resource overhead of each basic operation.
Specifically, the arithmetic unit execution order optimization model may be implemented by using a decision tree or a nearest neighbor model, and the specific methods are mastered by those skilled in the art, and will not be repeated here.
Step 102: HDR10+ standard metadata of all the scenes are inserted into the video stream information of the content of the HDR10 standard that is to be converted to obtain the corresponding HDR10+ content.
As can be seen from the method embodiment described above, in this embodiment, the algorithm for converting the content of HDR10 standard to that of the HDR10+ standard is performed by using the arithmetic units after splitting the format conversion algorithm and according to the arithmetic unit execution order with the shortest execution duration in the parallel data processing manner. In this way, the parallel processing of fine-grained arithmetic units can be used within the allowable range of the apparatus resources to effectively improve the efficiency of converting the content of the HDR10 standard to that of the HDR10+ standard and reduce the arithmetic power consumption, so that the requirements of HDR format conversion on apparatus performance can be effectively reduced.
The embodiment of the present disclosure further discloses a conversion device for a high dynamic range format, as shown in FIG. 5, the device comprises:
A conversion unit 501, configured to perform, for each frame of data of HDR10 standard content to be converted, a processing of converting each frame of the data to HDR10+ standard based on a preset set of format conversion arithmetic units and in accordance with a preset arithmetic unit execution order, and update HDR10+ standard metadata of a corresponding scene by adipting HDR10+ standard metadata that is obtained by the processing, wherein the set of the format conversion arithmetic units is obtained by splitting an algorithm for converting content data of HDR10 standard into that of HDR10+ standard in a hierarchical splitting manner, and the arithmetic unit execution order is obtained with a preferred target that an execution duration is the shortest.
A metadata insertion unit 502, configured to insert HDR10+ standard metadata of all the scenes into video stream information of the HDR10 standard content to be converted to obtain corresponding HDR10+ content.
In one embodiment, the device further comprises a pre-processing unit 503, configured to split the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard to obtain the set of format conversion arithmetic units in the hierarchical splitting manner, the splitting comprising:
splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard to obtain a set of basic function modules, according to function types of sub-algorithms;
splitting each module in the set of the function modules respectively to obtain a set of functional function modules by taking a functional function as a splitting granularity;
splitting each functional function in the set of the functional function modules to obtain the set of the format conversion arithmetic units by taking a basic arithmetic operation as a splitting granularity, wherein single arithmetic process corresponding to repetitive arithmetics is split according to the basic arithmetic operation when the functional function comprises the repetitive arithmetics.
In one embodiment, the pre-processing unit 503 is further configured to obtain the arithmetic unit execution order, the obtaining comprising:
determining candidate arithmetic unit execution orders that can be adopted when executing the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard by adopting the arithmetic units in the set of the format conversion arithmetic units in a concurrent data processing manner, within a resource overhead range that the device on which the conversion method is to be run can support, based on the resource status information of the device;
inputting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard, the resource state information and the candidate arithmetic unit execution orders to a pre-trained arithmetic unit execution order optimization model to be processed, obtaining and outputting an arithmetic unit execution order with the shortest execution duration among the candidate arithmetic unit execution orders.
In one embodiment, the pre-processing unit 503 specifically performs the processing by adopting the arithmetic unit execution order optimization model, the processing comprises:
splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard according to the hierarchical splitting manner by the arithmetic unit execution order optimization model to obtain the set of the format conversion arithmetic units;
determining an execution duration of each of the candidate arithmetic unit execution orders within the resource overhead range that the device can support according to the resource status information and according to execution logic of the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard, and outputting the arithmetic unit execution order corresponding to the shortest execution duration.
Based on the foregoing embodiment of the conversion method for the high dynamic range format, an embodiment of the present disclosure also discloses a conversion apparatus for the high dynamic range format including a processor and a memory;
an application program executable by the processor to enable the processor to execute the conversion method for the high dynamic range format as described above is stored in the memory;
wherein, the memory can be specifically implemented as a plurality of storage media such as electronically erasable programmable read-only memory(EEPROM), flash memory, programmable program read-only memory(PROM), etc. The processor may be implemented to include one or more central processing units or one or more field programmable gate arrays, wherein the field programmable gate arrays integrates one or more central processing unit cores. Specifically, the central processing units or central processing unit cores may be implemented as a CPU or MCU.
It should be noted that not all steps and modules in the above-mentioned respective processes and structural diagrams are necessary, and some steps or modules can be omitted according to actual requirements. The execution order of respective steps is not fixed and can be adjusted as needed. The division of respective modules is just to facilitate the description of the division of used functions. In actual implementation, one module can be implemented by multiple modules, and the functions of multiple modules can also be implemented by the same module. These modules can be located in the same apparatus and can also be located in different apparatus.
The hardware modules in respective embodiments can be implemented in a mechanical way or an electronic way. For example, a hardware module may include permanent circuits or logic devices (for example, dedicated processors, such as FPGAs or ASICs) specially designed to complete specific operations. The hardware modules may also include programmable logic devices or circuits temporarily configured by software (for example, including general-purpose processors or other programmable processors) for performing specific operations. As for the specific use of the mechanical way, or the use of the dedicated permanent circuits, or the use of temporarily configured circuits (such as being configured by software) to implement hardware modules, it can be determined according to cost and time considerations.
The present invention also provides a machine-readable storage medium, in which computer-readable instructions used for executing the above-described conversion method for the high dynamic range format are stored.
Specifically, a system or device equipped with a storage medium on which software program codes for realizing the function of any one of the above-mentioned embodiments and causing the computer (or CPU or MPU) of the system or the device to read and execute the program codes stored in the storage medium is stored on the storage medium may be provided. In addition, an operating system or the like operating on the computer can be enabled to complete part or all of the actual operations through instructions based on the program codes. It is also possible to write the program codes read from the storage medium to the memory set in the expansion board inserted into the computer or to a memory set in the expansion unit connected to the computer, and then the instructions based on the program codes make the CPU or the like installed on the expansion board or the expansion unit perform part or all of the actual operations, so as to realize the functions of any one of the above-mentioned embodiments.
Implementations of storage media used for providing the program codes include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tape, non-volatile memory card and ROM. Alternatively, the program codes can be downloaded from a server computer or a cloud via a communication network.
In this article, "schematic" means "serving as an example, instance or illustration", and any illustration or embodiment described as "schematic" in this article should not be construed as a more preferred or advantageous technical solution. In order to make the drawings concise, the parts related to the present disclosure are only schematically showed in respective figures, but does not represent the actual structure of a product. In addition, in order to make the drawings concise and easy to understand, in some drawings, only one of the components with the same structure or function is schematically shown, or only one of them is marked. In this article, "a or an" does not mean that the number of relevant parts of the present disclosure is limited to "only a or an", and "a or an" does not mean to exclude the situation where the number of relevant parts of the present disclosure is "more than one". In this article, "upper", "lower", "front", "rear", "left", "right", "inner", "outer", etc. are only used to indicate the relative positional relationship between related parts, rather than limiting the absolute position of these relevant parts.
Any described above are only preferred embodiments of the present disclosure, and are not used to limit the protection scope of the present disclosure. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims (8)

  1. A conversion method for a high dynamic range (HDR) format, the method comprising:
    performing, for each frame of data of HDR10 standard content to be converted, a processing of converting each frame of the data to HDR10+ standard based on a preset set of format conversion arithmetic units and in accordance with a preset arithmetic unit execution order, updating HDR10+ standard metadata of a corresponding scene by using HDR10+ standard metadata that is obtained by the processing,
    wherein the set of the format conversion arithmetic units is obtained by splitting an algorithm for converting content data of HDR10 standard into that of HDR10+ standard in a hierarchical splitting manner, and the arithmetic unit execution order is obtained with a preferred target that an execution duration is the shortest; and
    inserting HDR10+ standard metadata of all the scenes into video stream information of the HDR10 standard content to be converted to obtain corresponding HDR10+ content.
  2. The method of claim 1, wherein the splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard in the hierarchical splitting manner comprises:
    splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard to obtain a set of basic function modules, according to function types of sub-algorithms;
    splitting each module in the set of the function modules respectively to obtain a set of functional function modules by taking a functional function as a splitting granularity;
    splitting each functional function in the set of the functional function modules to obtain the set of the format conversion arithmetic units by taking a basic arithmetic operation as a splitting granularity, wherein single arithmetic process corresponding to repetitive arithmetics is split according to the basic arithmetic operation when the functional function comprises the repetitive arithmetics.
  3. The method of claim 1, wherein the obtaining the arithmetic unit execution order comprises:
    determining candidate arithmetic unit execution orders that can be adopted when executing the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard by adopting the arithmetic units in the set of the format conversion arithmetic units in a concurrent data processing manner, within a resource overhead range that an apparatus on which the conversion method is to be run can support, based on the resource status information of the apparatus;
    inputting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard, the resource state information and the candidate arithmetic unit execution orders to a pre-trained arithmetic unit execution order optimization model to be processed, obtaining and outputting an arithmetic unit execution order with the shortest execution duration among the candidate arithmetic unit execution orders.
  4. The method of claim 3, wherein the processing performed by the arithmetic unit execution order optimization model comprises:
    splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard according to the hierarchical splitting manner by the arithmetic unit execution order optimization model to obtain the set of the format conversion arithmetic units;
    determining an execution duration of each of the candidate arithmetic unit execution orders within the resource overhead range that the apparatus can support according to the resource status information and according to execution logic of the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard, and outputting the arithmetic unit execution order corresponding to the shortest execution duration.
  5. A conversion device for a high dynamic range (HDR) format, comprising:
    a conversion unit, configured to perform, for each frame of data of HDR10 standard content to be converted, a processing of converting each frame of the data to HDR10+ standard based on a preset set of format conversion arithmetic units and in accordance with a preset arithmetic unit execution order, and update HDR10+ standard metadata of a corresponding scene by using HDR10+ standard metadata that is obtained by the processing, wherein the set of the format conversion arithmetic units is obtained by splitting an algorithm for converting content data of HDR10 standard into that of HDR10+ standard in a hierarchical splitting manner, and the arithmetic unit execution order is obtained with a preferred target that an execution duration is the shortest; and
    a metadata insertion unit, configured to insert HDR10+ standard metadata of all the scenes into video stream information of the HDR10 standard content to be converted to obtain corresponding HDR10+ content.
  6. The conversion device of claim 5, wherein the device further comprises a pre-processing unit, configured to split the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard in the hierarchical splitting manner, the splitting comprising:
    splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard to obtain a set of basic function modules, according to function types of sub-algorithms;
    splitting each module in the set of the function modules respectively to obtain a set of functional function modules by taking a functional function as a splitting granularity;
    splitting each functional function in the set of the functional function modules to obtain the set of the format conversion arithmetic units by taking a basic arithmetic operation as a splitting granularity, wherein single arithmetic process corresponding to repetitive arithmetics is split according to the basic arithmetic operation when the functional function comprises the repetitive arithmetics.
  7. The conversion device of claim 5, wherein the pre-processing unit is further configured to obtain the arithmetic unit execution order, the obtaining comprising:
    determining candidate arithmetic unit execution orders that can be adopted when executing the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard by adopting the arithmetic units in the set of the format conversion arithmetic units in a concurrent data processing manner, within a resource overhead range that the device on which the conversion method is to be run can support, based on the resource status information of the device;
    inputting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard, the resource state information and the candidate arithmetic unit execution orders to a pre-trained arithmetic unit execution order optimization model to be processed, obtaining and outputting an arithmetic unit execution order with the shortest execution duration among the candidate arithmetic unit execution orders.
  8. The conversion device of claim 7, wherein the pre-processing unit specifically performs the processing adopting the arithmetic unit execution order optimization model, the processing comprises:
    splitting the algorithm for converting the content data of the HDR10 standard into that of the HDR10+ standard according to the hierarchical splitting manner by the arithmetic unit execution order optimization model to obtain the set of the format conversion arithmetic units;
    determining an execution duration of each of the candidate arithmetic unit execution orders within the resource overhead range that the device can support according to the resource status information and according to execution logic of the algorithm for converting the content data of the HDR10 standard to that of the HDR10+ standard, and outputting the arithmetic unit execution order corresponding to the shortest execution duration.
PCT/KR2022/007964 2021-06-15 2022-06-07 Conversion method and device for high dynamic range format WO2022265282A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110660702.2 2021-06-15
CN202110660702.2A CN113411533B (en) 2021-06-15 2021-06-15 Method and device for converting high dynamic range standard

Publications (1)

Publication Number Publication Date
WO2022265282A1 true WO2022265282A1 (en) 2022-12-22

Family

ID=77683901

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2022/007964 WO2022265282A1 (en) 2021-06-15 2022-06-07 Conversion method and device for high dynamic range format

Country Status (2)

Country Link
CN (1) CN113411533B (en)
WO (1) WO2022265282A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113411533B (en) * 2021-06-15 2023-03-31 三星电子（中国）研发中心 Method and device for converting high dynamic range standard

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180077453A1 (en) * 2015-04-24 2018-03-15 Lg Electronics Inc. Broadcast signal transmitting/receiving method and device
JP2018110403A (en) * 2013-02-21 2018-07-12 コーニンクレッカ フィリップス エヌ ヴェＫｏｎｉｎｋｌｉｊｋｅ Ｐｈｉｌｉｐｓ Ｎ．Ｖ． Method and device for improved hdr image encoding and decoding
WO2020005414A1 (en) * 2018-06-26 2020-01-02 Interdigital Vc Holdings, Inc. Metadata translation in hdr distribution
JP2020533841A (en) * 2017-09-06 2020-11-19 ドルビー ラボラトリーズ ライセンシング コーポレイション Tone curve optimization method and related video encoders and video decoders
KR20210045227A (en) * 2019-10-16 2021-04-26 삼성전자주식회사 Electronic device and operating method for the same
CN113411533A (en) * 2021-06-15 2021-09-17 三星电子（中国）研发中心 Method and device for converting high dynamic range standard

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108769804B (en) * 2018-04-25 2020-12-15 杭州当虹科技股份有限公司 Format conversion method for high dynamic range video
CN109656719B (en) * 2018-12-19 2021-01-01 Oppo广东移动通信有限公司 Algorithm processing method and device, storage medium and terminal equipment
CN112422561B (en) * 2020-11-18 2023-04-07 三星电子（中国）研发中心 Content sharing method and device and method
CN112561081B (en) * 2020-12-18 2022-05-03 北京百度网讯科技有限公司 Conversion method and device of deep learning model, electronic equipment and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018110403A (en) * 2013-02-21 2018-07-12 コーニンクレッカ フィリップス エヌ ヴェＫｏｎｉｎｋｌｉｊｋｅ Ｐｈｉｌｉｐｓ Ｎ．Ｖ． Method and device for improved hdr image encoding and decoding
US20180077453A1 (en) * 2015-04-24 2018-03-15 Lg Electronics Inc. Broadcast signal transmitting/receiving method and device
JP2020533841A (en) * 2017-09-06 2020-11-19 ドルビー ラボラトリーズ ライセンシング コーポレイション Tone curve optimization method and related video encoders and video decoders
WO2020005414A1 (en) * 2018-06-26 2020-01-02 Interdigital Vc Holdings, Inc. Metadata translation in hdr distribution
KR20210045227A (en) * 2019-10-16 2021-04-26 삼성전자주식회사 Electronic device and operating method for the same
CN113411533A (en) * 2021-06-15 2021-09-17 三星电子（中国）研发中心 Method and device for converting high dynamic range standard

Also Published As

Publication number Publication date
CN113411533A (en) 2021-09-17
CN113411533B (en) 2023-03-31

Similar Documents

Publication Publication Date Title
WO2017030252A1 (en) Security check method for container image and device therefor
WO2022265282A1 (en) Conversion method and device for high dynamic range format
WO2014014282A1 (en) Method and apparatus for data processing using graphic processing unit
WO2016099186A1 (en) Display apparatus and controlling method
CN108345555A (en) Interface bridgt circuit based on high-speed serial communication and its method
WO2022146080A1 (en) Algorithm and method for dynamically changing quantization precision of deep-learning network
WO2014010820A1 (en) Method and apparatus for estimating image motion using disparity information of a multi-view image
WO2020166849A1 (en) Display system for sensing defect on large-size display
WO2024019337A1 (en) Video enhancement method and apparatus
WO2019231162A1 (en) Image segmentation method and device
WO2017086522A1 (en) Method for synthesizing chroma key image without requiring background screen
WO2022260392A1 (en) Method and system for generating image processing artificial neural network model operating in terminal
WO2016137035A1 (en) Test case generation device and method, and computer-readable recording medium for recording program for executing same
WO2015023106A1 (en) Apparatus and method for processing image
WO2017007044A1 (en) Signal processing device and method
WO2022265413A1 (en) Method and device for generating intermediate representations of program run in accelerator
WO2020171258A1 (en) Image processing method and device therefor
WO2022181995A1 (en) A method for capturing a high resolution high dynamic range image
WO2015080531A1 (en) Method and apparatus for controlling reconfigurable processor
WO2020184985A1 (en) Method and computer program for processing program for single accelerator using dnn framework in plurality of accelerators
WO2023095945A1 (en) Apparatus and method for generating synthetic data for model training
WO2017052125A1 (en) Method and system for operating sram-based tcam with increased number of bits
WO2023090695A1 (en) System and method for synthesizing low-light images
WO2023120788A1 (en) Data processing system and method capable of snn/cnn simultaneous drive
WO2024117342A1 (en) Virtual machine system and virtual machine provisioning method using same

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22825208

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22825208

Country of ref document: EP

Kind code of ref document: A1