CN117097946B - Video all-in-one machine and control method for same - Google Patents
Video all-in-one machine and control method for same Download PDFInfo
- Publication number
- CN117097946B CN117097946B CN202311351970.1A CN202311351970A CN117097946B CN 117097946 B CN117097946 B CN 117097946B CN 202311351970 A CN202311351970 A CN 202311351970A CN 117097946 B CN117097946 B CN 117097946B
- Authority
- CN
- China
- Prior art keywords
- displayed
- video data
- sub
- audio
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000002776 aggregation Effects 0.000 claims abstract description 139
- 238000004220 aggregation Methods 0.000 claims abstract description 139
- 230000001360 synchronised effect Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000010606 normalization Methods 0.000 claims abstract description 17
- 239000013598 vector Substances 0.000 claims description 41
- 230000008569 process Effects 0.000 claims description 23
- 238000012216 screening Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 6
- 238000000605 extraction Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012674 dispersion polymerization Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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]
- H04N21/40—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
- H04N21/44008—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 operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- 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
- H04N21/439—Processing of audio elementary streams
- H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
-
- 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
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/462—Content or additional data management, e.g. creating a master electronic program guide from data received from the Internet and a Head-end, controlling the complexity of a video stream by scaling the resolution or bit-rate based on the client capabilities
- H04N21/4622—Retrieving content or additional data from different sources, e.g. from a broadcast channel and the Internet
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Studio Circuits (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention provides a video all-in-one machine and a control method for the video all-in-one machine, which relate to the technical field of image communication, wherein the video all-in-one machine comprises: the normalization processing module performs respective normalization processing on the image display parameters and the sound attribute parameters of the original video frame sequences of all the audio data sources to be displayed; the synchronous dividing module synchronously divides each normalized video data frame sequence and each normalized sound data frame sequence; the aggregation analysis module carries out heterogeneous aggregation analysis on all the sub-audio data sources to be displayed to obtain heterogeneous aggregation analysis results; the time sequence adjustment module and the coordination display module are used for adjusting the time sequence of all sub-audio data sources to be displayed of all audio data sources to be displayed based on the heterogeneous aggregation analysis result and integrating and displaying the sub-audio data sources to be displayed to obtain a multi-source time sequence coordination display result of the video all-in-one machine; the method is used for realizing time sequence coordination of video data of the video all-in-one machine capable of multi-source display, and further ensuring content coordination of the multi-source display video.
Description
Technical Field
The invention relates to the technical field of image communication, in particular to a video all-in-one machine and a control method for the video all-in-one machine.
Background
At present, the video all-in-one machine on the market can be externally connected with various video signal sources such as a computer, an advertising machine, a projector, an electronic whiteboard and a sound box, has the advantages of large-screen display and multi-input, can realize the function of simultaneously displaying video data of a plurality of video signal sources in a plurality of areas, and is highly integrated electronic circuit integrated display equipment.
When the content of the video data displayed by the video all-in-one machine has certain relevance, if the content with relevance is displayed simultaneously, the video display effect is better. However, the existing video all-in-one machine can only directly display video data of various audio data sources to the video all-in-one machine according to preset display areas and display parameters, so that the video content of the video all-in-one machine simultaneously displaying a plurality of video data is poor in time sequence synchronism and time sequence coordination, and further the video display effect is required to be improved.
Therefore, the invention provides a video all-in-one machine and a control method for the video all-in-one machine.
Disclosure of Invention
The invention provides a video all-in-one machine and a control method for the video all-in-one machine, which are used for realizing time sequence coordination of video data of the video all-in-one machine capable of being displayed in multiple sources, further ensuring time sequence synchronism and content coordination of the video displayed in multiple sources and further improving video display effect.
The invention provides a video all-in-one machine, which comprises:
the normalization processing module is used for respectively normalizing the image display parameters and the sound attribute parameters of the original video frame sequences of all the audio data sources to be displayed to obtain normalized video data frame sequences and normalized sound data frame sequences of all the audio data sources to be displayed;
the synchronous dividing module is used for synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of each audio data source to be displayed to obtain sub-normalized video data frame sequences and sub-normalized sound data frame sequences of a plurality of sub-audio data sources to be displayed of each audio data source to be displayed;
the aggregation analysis module is used for carrying out heterogeneous aggregation analysis on all the sub-audio data sources to be displayed based on the sub-normalized video data frame sequences and the sub-normalized sound data frame sequences of the plurality of sub-audio data sources to be displayed of each audio data source to be displayed to obtain a heterogeneous aggregation analysis result;
the time sequence adjustment module is used for performing time sequence adjustment on all sub-audio data sources to be displayed of all audio data sources to be displayed based on the heterogeneous aggregation analysis result to obtain a plurality of new audio data sources to be displayed;
And the coordination display module is used for carrying out integrated display on a plurality of new audio data sources to be displayed to obtain a multi-source time sequence coordination display result of the video all-in-one machine.
Preferably, the normalization processing module includes:
the category dividing sub-module is used for dividing the image display parameters and the sound attribute parameters in all original video frames contained in all original video data frame sequences of all audio data sources to be displayed respectively to obtain a display parameter set of each image display parameter category and a sound attribute parameter set of each sound attribute parameter category;
the first processing submodule is used for determining the difference value between the maximum value and the minimum value in each display parameter set to be used as a first difference value, taking the difference value between the specific value of each image display parameter and the minimum value in the display parameter set corresponding to the image display parameter class as a second difference value, and taking the ratio of the first difference value to the second difference value as a normalized image display parameter of the image display parameter;
the second processing sub-module is used for determining the difference value between the maximum value and the minimum value in each sound attribute parameter set as a third difference value, taking the difference value between the specific value of each sound attribute parameter and the minimum value in the sound attribute parameter set of the corresponding sound attribute parameter category as a fourth difference value, and taking the ratio of the third difference value and the fourth difference value as a normalized sound attribute parameter of the sound attribute parameter;
And the parameter setting sub-module is used for setting the display picture parameters and the sound attribute parameters of the original video data frame sequences of all the audio data sources to be displayed as corresponding normalized image display parameters and normalized sound attribute parameters to obtain normalized video data frame sequences and normalized sound data frame sequences of all the audio data sources to be displayed.
Preferably, the synchronous dividing module includes:
the length determining submodule is used for determining the dividing length based on the data length of the audio data source to be displayed;
the multi-dividing sub-module is used for dividing the audio data source to be displayed for a plurality of times based on the dividing length to obtain a plurality of primary sub-audio data sources to be displayed in each dividing process;
the feature determination submodule is used for determining a first feature vector of a primary sub-normalized video data frame sequence corresponding to each primary sub-audio data source to be displayed and a second feature vector of the primary sub-normalized sound data frame sequence;
the similarity determining sub-module is used for determining cosine similarity between first feature vectors of the adjacent primary normalized video data frame sequences obtained in the single dividing process, and taking the cosine similarity as first cosine similarity, and determining cosine similarity between second feature vectors of the adjacent primary normalized sound data frame sequences obtained in the single dividing process, and taking the cosine similarity as second cosine similarity;
And the synchronous dividing sub-module is used for synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of the audio data source to be displayed based on the first cosine similarity and the second cosine similarity of the adjacent primary sub-audio data sources to be displayed, which are obtained in all the dividing processes, so as to obtain sub-normalized video data frame sequences and sub-normalized sound data frame sequences of a plurality of sub-audio data sources to be displayed of each audio data source to be displayed.
Preferably, the feature determination submodule includes:
the first determining unit is used for determining the sliding window size of the time sequence model based on the dividing length, sliding in the normalized video data frame sequence based on the sliding window size to obtain first characteristic information of each primary sub-normalized video data frame sequence, and sequentially inputting the determined plurality of first characteristic information into the time sequence model to obtain a first characteristic vector of each primary sub-normalized video data frame sequence;
the second determining unit is used for sliding in the sound data frame sequence based on the sliding window of the sliding window size to obtain second characteristic information of each primary sub-normalized sound data frame sequence, and sequentially inputting the determined second characteristic information into the time sequence model to obtain second characteristic vectors of each primary sub-normalized sound data frame sequence.
Preferably, the synchronous dividing sub-module comprises:
the first time determining unit is used for taking the dividing time between adjacent primary sub-audio data sources to be displayed, which are corresponding to the first cosine similarity which is not more than the cosine similarity threshold value and obtained in all dividing processes, as a first dividing time;
the second time determining unit is used for regarding the division time between the adjacent primary sub-audio data sources to be displayed, which are corresponding to the second cosine similarity which is not more than the cosine similarity threshold value and obtained in all the division processes, as a second division time;
the synchronous dividing unit is used for synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of the audio data source to be displayed by taking the first dividing moment and the second dividing moment as dividing limits to obtain the sub-normalized video data frame sequence and the sub-normalized sound data frame sequence of the audio data source to be displayed of a plurality of sub-audio data sources to be displayed of each audio data source to be displayed.
Preferably, the aggregation analysis module comprises:
the first aggregation sub-module is used for screening video heterogeneous aggregation sets of a plurality of sub-audio data source sets to be displayed from sub-normalized video data frame sequences of all sub-audio data sources to be displayed of all audio data sources to be displayed, wherein one sub-audio data source to be displayed of each audio data source to be displayed is contained in the sub-audio data source set to be displayed, the screened sub-audio data source sets to be displayed do not contain the same sub-audio data source to be displayed, and one sub-normalized video data frame sequence of each audio data source to be displayed is contained in the video heterogeneous aggregation set;
The second aggregation sub-module is used for screening out sound heterogeneous aggregation sets of a plurality of sub-audio data source sets to be displayed from sub-normalized sound data frame sequences of all sub-audio data sources to be displayed of all audio data sources to be displayed, wherein the sound heterogeneous aggregation sets comprise one sub-normalized sound data frame sequence of each audio data source to be displayed;
the heterogeneous aggregation sub-module is used for carrying out heterogeneous aggregation analysis on all sub-audio data sources to be displayed based on cosine similarity of first feature vectors of different normalized video data frame sequences in the video heterogeneous aggregation set and cosine similarity of second feature vectors of different normalized sound data frame sequences in the sound heterogeneous aggregation set to obtain heterogeneous aggregation analysis results.
Preferably, the heterogeneous polymerization submodule includes:
the first computing unit is used for taking the average value of cosine similarity among the first feature vectors of all different normalized video data frame sequences in the video heterogeneous aggregation set as the aggregation degree of the video heterogeneous aggregation set;
the second calculation unit is used for taking the average value of the content similarity of different normalized voice data frame sequences in the voice heterogeneous aggregation set as the aggregation degree of the voice heterogeneous aggregation set;
And the final analysis unit is used for taking the sub-to-be-displayed audio data source set of which the aggregation degree of the corresponding video heterogeneous aggregation set is greater than the aggregation degree threshold value and the aggregation degree of the corresponding sound heterogeneous aggregation set is greater than the aggregation degree threshold value as a final heterogeneous aggregation data source set and taking all the final heterogeneous aggregation data source sets as heterogeneous aggregation analysis results.
Preferably, the timing adjustment module includes:
the comprehensive ordinal number determining submodule is used for taking the average value of the sequencing ordinals of all the sub-audio data sources to be displayed in the audio data sources to be displayed in each final heterogeneous aggregation data source set in the heterogeneous aggregation analysis result as the comprehensive ordinals of the corresponding final heterogeneous aggregation data source sets;
the set ordering determining submodule is used for ordering all final heterogeneous aggregation data source sets based on the sequence from small to large of the comprehensive ordinal numbers to obtain the final ordinal numbers of all final heterogeneous aggregation data source sets;
the sequence adjustment sub-module is used for setting the final ordinal number of the sub-audio data sources to be displayed as the final ordinal number corresponding to the final heterogeneous aggregate data source set, and adjusting the sequence of all the sub-audio data sources to be displayed in the audio data sources to be displayed based on the final ordinal number to obtain a plurality of new audio data sources to be displayed.
Preferably, the coordination display module includes:
the multi-source integration module is used for integrating a plurality of new audio data sources to be displayed based on the display requirement of each audio data source to be displayed to obtain audio data to be displayed;
the video display module is used for displaying the audio display data to be displayed and obtaining a multi-source time sequence coordination display result of the video all-in-one machine.
The invention provides a control method for a video all-in-one machine, which is used for controlling the video all-in-one machine in any one of embodiments 1 to 9, and comprises the following steps:
s1: respectively normalizing the image display parameters and the sound attribute parameters of the original video frame sequences of all the audio data sources to be displayed to obtain normalized video data frame sequences and normalized sound data frame sequences of all the audio data sources to be displayed;
s2: synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of each audio data source to be displayed to obtain sub-normalized video data frame sequences and sub-normalized sound data frame sequences of a plurality of sub-audio data sources to be displayed of each audio data source to be displayed;
s3: based on the sub-normalized video data frame sequences and the sub-normalized sound data frame sequences of the plurality of sub-audio data sources to be displayed of each audio data source to be displayed, carrying out heterogeneous aggregation analysis on all the sub-audio data sources to be displayed to obtain a heterogeneous aggregation analysis result;
S4: based on the heterogeneous aggregation analysis result, performing time sequence adjustment on all sub-audio data sources to be displayed of all audio data sources to be displayed to obtain a plurality of new audio data sources to be displayed;
s5: and integrating and displaying a plurality of new audio data sources to be displayed to obtain a multi-source time sequence coordination display result of the video all-in-one machine.
Compared with the prior art, the invention has the following beneficial effects: the method comprises the steps of carrying out normalization and synchronous division on image display parameters and sound attribute parameters of a plurality of audio data sources to be displayed, carrying out heterogeneous aggregation analysis on sub-normalization video data frame sequences and sub-normalization sound data frame sequences of a plurality of sub-audio data sources to be displayed of the audio data sources to be displayed, which are obtained after the synchronous division, and further carrying out time sequence adjustment on all sub-audio data sources to be displayed in the audio data sources to be displayed based on a heterogeneous analysis result, so that the video data of a plurality of audio data sources with certain relevance to the content to be displayed simultaneously of the video all-in-one machine have higher content synchronism in time sequence, and realizing time sequence coordination on the video data of the video all-in-one machine capable of being displayed in a multi-source mode, thereby ensuring the time sequence synchronism and the content coordination of the video to be displayed in a multi-source mode, and further improving the video display effect.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a video all-in-one machine according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a normalization processing module according to an embodiment of the present invention;
fig. 3 is a flowchart of a control method for a video all-in-one machine according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1:
The present invention provides a video all-in-one machine, referring to fig. 1, comprising:
the normalization processing module is used for respectively normalizing all audio data sources to be displayed (namely, a plurality of audio data sources which need to be displayed in the video all-in-one machine, wherein the audio data sources comprise sound data and dynamic image data), the image display parameters of the original video frame sequence of all the audio data sources to be displayed (namely, the display parameters of the video frames which are contained in the video corresponding to the original video frame sequence, such as pixel values, chroma values, brightness values and the like of pixel points in the video frames) and the sound attribute parameters (namely, the parameters of the sound data which are contained in the video corresponding to the original video frame sequence, such as loudness, tone, frequency and the like) are respectively normalized (the process comprises normalization processing of the image display parameters of the original video frame sequence of all the audio data sources to be displayed, and normalization processing of the sound attribute parameters of the original video frame sequence of all the audio data sources to be displayed) to obtain the normalized video frame sequence of all the audio data sources to be displayed (namely, the frame sequence obtained after normalization processing of the image display parameters contained in the original video frame sequence are normalized);
Normalizing the image display parameters and the sound attribute parameters of the audio data source to be displayed, realizing unified parameters, and facilitating the subsequent accurate self-division of the video data frame sequence and the sound data frame sequence;
the synchronous dividing module is used for synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of each audio data source to be displayed (synchronous dividing refers to time sequence synchronization) to obtain sub-normalized video data frame sequences and sub-normalized sound data frame sequences of a plurality of sub-audio data sources to be displayed of each audio data source to be displayed;
the aggregation analysis module is used for carrying out heterogeneous aggregation analysis on all the sub-audio data sources to be displayed based on the sub-normalized video data frame sequences and the sub-normalized sound data frame sequences of the plurality of sub-audio data sources to be displayed of each audio data source to be displayed (the heterogeneous aggregation analysis is to carry out aggregation analysis on part of the audio data sources of different audio data sources to be displayed, wherein the aggregation analysis is to analyze the aggregation degree between the part of the audio data sources of different audio data sources to be displayed, and the aggregation degree can be considered as the content similarity degree), so as to obtain heterogeneous aggregation analysis results (namely the result finally obtained in the heterogeneous aggregation analysis step);
Based on the heterogeneous aggregation analysis process, partial audio data sources with certain relevance in the content of different audio data sources to be displayed, which need to be displayed simultaneously, of the video all-in-one machine can be analyzed;
the time sequence adjustment module is used for performing time sequence adjustment on all sub-audio data sources to be displayed of all audio data sources to be displayed based on the heterogeneous aggregation analysis result to obtain a plurality of new audio data sources to be displayed;
the coordination display module is used for carrying out integrated display on a plurality of new audio data sources to be displayed to obtain a multi-source time sequence coordination display result of the video all-in-one machine (namely, a time sequence adjustment is carried out on all sub-audio data sources to be displayed in the audio data sources to be displayed, so that the video all-in-one machine needs to display the video data of a plurality of audio data sources with certain relevance in the content simultaneously, and the video display result has higher time sequence synchronism and content coordination);
and further, based on the heterogeneous analysis result, time sequence adjustment is carried out on all sub-audio data sources to be displayed in the audio data sources to be displayed, so that the video data of a plurality of audio data sources with certain relevance to the content to be displayed simultaneously of the video all-in-one machine are higher in time sequence content synchronism, the time sequence coordination of the video data of the video all-in-one machine capable of being displayed in multiple sources is realized, the time sequence synchronism and the content coordination of the video displayed in multiple sources are further ensured, and the video display effect is further improved.
Example 2:
on the basis of embodiment 1, the normalization processing module, referring to fig. 2, includes:
a category dividing sub-module, configured to respectively divide the image display parameters and the sound attribute parameters in all the original video frames included in all the original video frame sequences of all the audio data sources to be displayed (for example, pixel value class, brightness value class, gray value class), and obtain a display parameter set of each image display parameter class (i.e., a set of identical image display parameters of all the pixels of all the video frames including all the audio data sources to be displayed, for example, a set of pixel values of all the pixels), and a sound attribute parameter set of each sound attribute parameter class (i.e., a set of identical sound attribute parameters of all the sound data including all the audio data sources to be displayed, for example, a set of sound loudness values of all the sound data);
the first processing submodule is used for determining the difference value between the maximum value and the minimum value in each display parameter set to be used as a first difference value, taking the difference value between the specific value of each image display parameter and the minimum value in the display parameter set corresponding to the image display parameter class as a second difference value, and taking the ratio of the first difference value to the second difference value as a normalized image display parameter (namely, the normalized image display parameter);
The second processing sub-module is configured to determine a difference between a maximum value and a minimum value in each sound attribute parameter set, as a third difference, and use a difference between a specific value of each sound attribute parameter and a minimum value in a sound attribute parameter set of a corresponding sound attribute parameter category as a fourth difference, and use a ratio of the third difference to the fourth difference as a normalized sound attribute parameter of the sound attribute parameter (i.e., the sound attribute parameter after normalization processing);
and the parameter setting sub-module is used for setting the display picture parameters and the sound attribute parameters of the original video data frame sequences of all the audio data sources to be displayed as corresponding normalized image display parameters and normalized sound attribute parameters to obtain normalized video data frame sequences and normalized sound data frame sequences of all the audio data sources to be displayed.
The normalization of the image display parameters and the sound attribute parameters of the audio data source to be displayed realizes the unification of the parameters of all the audio data sources to be displayed, and is convenient for the subsequent accurate self-division of the video data frame sequence and the sound data frame sequence.
Example 3:
on the basis of embodiment 1, the synchronous dividing module includes:
The length determining submodule is used for determining a division length based on the data length of the audio data source to be displayed (namely, searching a preset data length-division length corresponding table based on the data length to determine a corresponding division length, wherein the division length is represented by a divided time interval);
the effect of reasonably determining the corresponding division length based on the data length to ensure the subsequent time sequence coordination is realized;
the multi-dividing sub-module is used for dividing the audio data source to be displayed for a plurality of times based on the dividing length to obtain a plurality of primary sub-audio data sources to be displayed in each dividing process;
the feature determining sub-module is used for determining a first feature vector (namely a feature vector representing time sequence features of the normalized video data frame sequence obtained based on LSTM time sequence feature extraction) of a primary sub-normalized video data frame sequence corresponding to each primary sub-audio data source to be displayed (namely a feature vector representing time sequence features of the normalized video data frame sequence obtained based on LSTM time sequence feature extraction) and a second feature vector (namely a feature vector representing time sequence features of the normalized sound data frame sequence obtained based on LSTM time sequence feature extraction) of the primary sub-normalized sound data frame sequence (namely a feature vector representing time sequence features of the normalized sound data frame sequence obtained based on LSTM time sequence feature extraction);
Characterizing the normalized and divided partial normalized video data frame sequence and normalized sound data frame sequence by utilizing the feature vector characterizing the time sequence feature, so as to realize the datamation representation of the content of the audio data source to be displayed on the time sequence change feature;
the similarity determining sub-module is used for determining cosine similarity between first feature vectors of the adjacent primary normalized video data frame sequences obtained in the single dividing process, and taking the cosine similarity as first cosine similarity, and determining cosine similarity between second feature vectors of the adjacent primary normalized sound data frame sequences obtained in the single dividing process, and taking the cosine similarity as second cosine similarity;
the cosine similarity is used for representing the content correlation of the adjacent primary sub-normalized video frame sequences and the adjacent primary sub-normalized sound data frame sequences on each, so that the sub-normalized video data frame sequences and the sub-normalized sound data frame sequences of a plurality of sub-audio data sources to be displayed, which are obtained through synchronous division, are partial data frame sequences containing different video contents, namely the accurate division of the audio data sources to be displayed is ensured on the basis of the correlation of the video contents on time sequence;
And the synchronous dividing sub-module is used for synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of the audio data source to be displayed based on the first cosine similarity and the second cosine similarity of the adjacent primary sub-audio data sources to be displayed, which are obtained in all the dividing processes, so as to obtain sub-normalized video data frame sequences and sub-normalized sound data frame sequences of a plurality of sub-audio data sources to be displayed of each audio data source to be displayed.
Example 4:
on the basis of embodiment 3, the feature determination submodule includes:
the first determining unit is configured to determine a timing model (i.e., an LSTM model, which is a pre-trained and capable of identifying difference information in adjacent video frames in a sliding manner), and when the timing model is pre-trained, use a large number of videos marked with the difference information (i.e., corresponding feature vectors) of the adjacent video frames as training samples) (the sliding window size is a square with the dividing length as a side length), slide in the normalized video data frame sequence based on the sliding window size to obtain first feature information of each preliminary sub-normalized video data frame sequence (i.e., the difference information between the adjacent video frames in the preliminary sub-normalized video data frame sequence), sequentially input the determined plurality of first feature information into the timing model to obtain first feature vectors of each preliminary sub-normalized video data frame sequence (i.e., feature vectors determined by the timing model and representing the corresponding first feature information, for example, the feature vectors may be represented by displacement vectors of physical centers of difference regions in the adjacent video frames);
The second determining unit is configured to slide in the sound data frame sequence based on a sliding window of the sliding window size, obtain second feature information of each preliminary sub-normalized sound data frame sequence (that is, difference information between adjacent sound data frames in the preliminary sub-normalized sound data frame sequence), sequentially input the determined plurality of second feature information into the time sequence model, and obtain second feature vectors of each preliminary sub-normalized sound data frame sequence (that is, determine feature vectors representing the corresponding first feature information for the time sequence model, for example, the feature vectors may use a change vector of loudness values of adjacent sound signal frames in a loudness value curve corresponding to the preliminary sub-normalized sound data frame sequence, that is, a vector in which a previous loudness value points to a subsequent loudness value in the loudness value curve).
The method can respectively extract the change characteristics of the video data and the sound data of the audio data source to be displayed on the time sequence based on the time sequence model, and vectorize the characteristics, so that the subsequent analysis of the video content relevance and the time sequence characteristics is facilitated.
Example 5:
on the basis of embodiment 3, the synchronous dividing sub-module includes:
the first time determining unit is configured to take, as a first division time, a division time between adjacent primary sub-audio data sources to be displayed corresponding to a first cosine similarity obtained in all the division processes, where the division time does not exceed a cosine similarity threshold (i.e., is a maximum value allowed when the division time is determined between the preset adjacent primary sub-audio data sources to be displayed);
The second time determining unit is used for regarding the division time between the adjacent primary sub-audio data sources to be displayed, which are corresponding to the second cosine similarity which is not more than the cosine similarity threshold value and obtained in all the division processes, as a second division time;
the synchronous dividing unit is used for synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of the audio data source to be displayed by taking the first dividing moment and the second dividing moment as dividing limits to obtain the sub-normalized video data frame sequence and the sub-normalized sound data frame sequence of the audio data source to be displayed of a plurality of sub-audio data sources to be displayed of each audio data source to be displayed.
The cosine similarity is introduced in the process to calculate the content relevance between the video data of the adjacent primary audio data sources to be displayed and the content relevance of the sound data, so that the accurate division of the audio data sources to be displayed is realized.
Example 6:
on the basis of embodiment 4, the aggregation analysis module includes:
the first aggregation sub-module is used for screening video heterogeneous aggregation sets of a plurality of sub-audio data source sets to be displayed from sub-normalized video data frame sequences of all sub-audio data sources to be displayed of all audio data sources to be displayed, wherein one sub-audio data source to be displayed of each audio data source to be displayed is contained in the sub-audio data source set to be displayed, the screened sub-audio data source sets to be displayed do not contain the same sub-audio data source to be displayed, and one sub-normalized video data frame sequence of each audio data source to be displayed is contained in the video heterogeneous aggregation set;
The second aggregation sub-module is used for screening out sound heterogeneous aggregation sets of a plurality of sub-audio data source sets to be displayed from sub-normalized sound data frame sequences of all sub-audio data sources to be displayed of all audio data sources to be displayed, wherein the sound heterogeneous aggregation sets comprise one sub-normalized sound data frame sequence of each audio data source to be displayed;
the heterogeneous aggregation sub-module is used for carrying out heterogeneous aggregation analysis on all sub-audio data sources to be displayed based on cosine similarity of first feature vectors of different normalized video data frame sequences in the video heterogeneous aggregation set and cosine similarity of second feature vectors of different normalized sound data frame sequences in the sound heterogeneous aggregation set to obtain heterogeneous aggregation analysis results.
The method is used for calculating cosine similarity of different normalized video data frame sequences and cosine similarity of different normalized sound data frame sequences contained in the heterogeneous aggregation set, and can realize heterogeneous aggregation analysis of all sub-audio data sources to be displayed.
Example 7:
on the basis of example 6, the heterogeneous polymerization submodule includes:
a first calculating unit, configured to treat a mean value of cosine similarities between first feature vectors of all different normalized video data frame sequences in the video heterogeneous aggregation set as an aggregation degree of the video heterogeneous aggregation set (i.e. characterize content similarities between all normalized video data frame sequences included in the video heterogeneous aggregation set);
A second calculation unit, configured to treat the average value of the content similarities of different normalized voice data frame sequences in the voice heterogeneous aggregation set as the aggregation degree of the voice heterogeneous aggregation set (i.e. characterize the content similarities between all normalized voice data frame sequences included in the voice heterogeneous aggregation set);
and the final analysis unit is used for taking the sub-to-be-displayed audio data source set of which the aggregation degree of the corresponding video heterogeneous aggregation set is greater than the aggregation degree threshold value and the aggregation degree of the corresponding sound heterogeneous aggregation set is greater than the aggregation degree threshold value as a final heterogeneous aggregation data source set and taking all the final heterogeneous aggregation data source sets as heterogeneous aggregation analysis results.
And calculating the aggregation degree of the video heterogeneous aggregation set and the aggregation degree of the sound heterogeneous aggregation set by utilizing cosine similarity among the first feature vectors of all different normalized video data frame sequences in the video heterogeneous aggregation set and content similarity of different normalized sound data frame sequences in the sound heterogeneous aggregation set, and based on comparison of the aggregation degree and an aggregation degree threshold value, realizing heterogeneous aggregation analysis of all sub-audio data sources to be displayed, namely enabling the sub-audio data sources to be displayed contained in the final heterogeneous aggregation data source set in the finally obtained heterogeneous aggregation analysis result to have certain content correlation.
Example 8:
on the basis of embodiment 7, the timing adjustment module includes:
the comprehensive ordinal number determining submodule is used for taking the average value of the ranking ordinals of all the sub-audio data sources to be displayed in each final heterogeneous aggregate data source set in the heterogeneous aggregate analysis result in the affiliated audio data source to be displayed (namely the audio data source to be displayed of the sub-audio data source to be displayed) as the comprehensive ordinals of the corresponding final heterogeneous aggregate data source set (the ordinals representing the comprehensive ranking condition of all the sub-audio data sources to be displayed contained in the final heterogeneous aggregate data source set in the respective affiliated audio data source to be displayed);
the aggregate sequencing determination submodule is used for sequencing all final heterogeneous aggregate data source aggregates based on the sequence from small to large of the comprehensive ordinal numbers to obtain the final ordinal numbers of all final heterogeneous aggregate data source aggregates (namely, the sequencing ordinal numbers of the final heterogeneous aggregate data source aggregates in all final heterogeneous aggregate data source aggregates);
the sequence adjustment sub-module is used for setting the final ordinal number of the sub-audio data sources to be displayed as the final ordinal number corresponding to the final heterogeneous aggregate data source set, and adjusting the sequence of all the sub-audio data sources to be displayed in the audio data sources to be displayed based on the final ordinal number to obtain a plurality of new audio data sources to be displayed.
Based on the above process, the video display result of the video all-in-one machine after time sequence adjustment has better correlation on the content displayed at the same time, and original ordering characteristics are reserved as much as possible.
Example 9:
on the basis of embodiment 1, the coordination display module includes:
the multi-source integration module is used for integrating a plurality of new audio data sources to be displayed (namely, adjusting the plurality of audio data sources to be displayed according to the display requirements) based on the display requirements (such as a display area, display brightness and the like) of each audio data source to be displayed to obtain audio data to be displayed;
the video display module is used for displaying the audio display data to be displayed and obtaining a multi-source time sequence coordination display result of the video all-in-one machine.
The process time is the integrated display of the new audio data sources to be displayed of all the video all-in-one machines generated after coordination.
Example 10:
the present invention provides a control method for a video all-in-one machine, for controlling the video all-in-one machine described in any one of embodiments 1 to 9, referring to fig. 3, including:
s1: respectively normalizing the image display parameters and the sound attribute parameters of the original video frame sequences of all the audio data sources to be displayed to obtain normalized video data frame sequences and normalized sound data frame sequences of all the audio data sources to be displayed;
S2: synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of each audio data source to be displayed to obtain sub-normalized video data frame sequences and sub-normalized sound data frame sequences of a plurality of sub-audio data sources to be displayed of each audio data source to be displayed;
s3: based on the sub-normalized video data frame sequences and the sub-normalized sound data frame sequences of the plurality of sub-audio data sources to be displayed of each audio data source to be displayed, carrying out heterogeneous aggregation analysis on all the sub-audio data sources to be displayed to obtain a heterogeneous aggregation analysis result;
s4: based on the heterogeneous aggregation analysis result, performing time sequence adjustment on all sub-audio data sources to be displayed of all audio data sources to be displayed to obtain a plurality of new audio data sources to be displayed;
s5: and integrating and displaying a plurality of new audio data sources to be displayed to obtain a multi-source time sequence coordination display result of the video all-in-one machine.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A video all-in-one machine, comprising:
the normalization processing module is used for respectively normalizing the image display parameters and the sound attribute parameters of the original video frame sequences of all the audio/video data sources to be displayed to obtain normalized video data frame sequences and normalized sound data frame sequences of all the audio/video data sources to be displayed;
the synchronous dividing module is used for synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of each audio/video data source to be displayed to obtain sub-normalized video data frame sequences and sub-normalized sound data frame sequences of a plurality of sub-audio/video data sources to be displayed of each audio/video data source to be displayed;
the aggregation analysis module is used for carrying out heterogeneous aggregation analysis on all the sub-audio and video data sources to be displayed based on the sub-normalized video data frame sequences and the sub-normalized sound data frame sequences of the plurality of sub-audio and video data sources to be displayed of each audio and video data source to be displayed, so as to obtain a heterogeneous aggregation analysis result;
the time sequence adjustment module is used for performing time sequence adjustment on all sub-audio and video data sources to be displayed of all audio and video data sources to be displayed based on the heterogeneous aggregation analysis result to obtain a plurality of new audio and video data sources to be displayed;
And the coordination display module is used for carrying out integrated display on a plurality of new audio and video data sources to be displayed to obtain a multi-source time sequence coordination display result of the video all-in-one machine.
2. The video all-in-one machine of claim 1, wherein the normalization processing module comprises:
the category dividing sub-module is used for dividing the image display parameters and the sound attribute parameters in all original video frames contained in all original video data frame sequences of all audio and video data sources to be displayed respectively to obtain a display parameter set of each image display parameter category and a sound attribute parameter set of each sound attribute parameter category;
the first processing submodule is used for determining the difference value between the maximum value and the minimum value in each display parameter set to be used as a first difference value, taking the difference value between the specific value of each image display parameter and the minimum value in the display parameter set corresponding to the image display parameter class as a second difference value, and taking the ratio of the first difference value to the second difference value as a normalized image display parameter of the image display parameter;
the second processing sub-module is used for determining the difference value between the maximum value and the minimum value in each sound attribute parameter set as a third difference value, taking the difference value between the specific value of each sound attribute parameter and the minimum value in the sound attribute parameter set of the corresponding sound attribute parameter category as a fourth difference value, and taking the ratio of the third difference value and the fourth difference value as a normalized sound attribute parameter of the sound attribute parameter;
And the parameter setting sub-module is used for setting the display picture parameters and the sound attribute parameters of the original video data frame sequences of all the audio and video data sources to be displayed as corresponding normalized image display parameters and normalized sound attribute parameters to obtain normalized video data frame sequences and normalized sound data frame sequences of all the audio and video data sources to be displayed.
3. The video all-in-one machine of claim 1, wherein the synchronous dividing module comprises:
the length determining submodule is used for determining the dividing length based on the data length of the audio and video data source to be displayed;
the multi-dividing sub-module is used for dividing the audio and video data source to be displayed for a plurality of times based on the dividing length to obtain a plurality of primary sub-audio and video data sources to be displayed in each dividing process;
the characteristic determining submodule is used for determining a first characteristic vector of a primary sub-normalized video data frame sequence corresponding to each primary sub-audio/video data source to be displayed and a second characteristic vector of the primary sub-normalized sound data frame sequence;
the similarity determining sub-module is used for determining cosine similarity between first feature vectors of the adjacent primary normalized video data frame sequences obtained in the single dividing process, and taking the cosine similarity as first cosine similarity, and determining cosine similarity between second feature vectors of the adjacent primary normalized sound data frame sequences obtained in the single dividing process, and taking the cosine similarity as second cosine similarity;
And the synchronous dividing sub-module is used for synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of the audio/video data source to be displayed based on the first cosine similarity and the second cosine similarity of the adjacent primary sub-audio/video data sources to be displayed, which are obtained in all the dividing processes, so as to obtain sub-normalized video data frame sequences and sub-normalized sound data frame sequences of a plurality of sub-audio/video data sources to be displayed of each audio/video data source to be displayed.
4. A video all-in-one machine as claimed in claim 3 wherein the feature determination sub-module comprises:
the first determining unit is used for determining the sliding window size of the time sequence model based on the dividing length, sliding in the normalized video data frame sequence based on the sliding window size to obtain first characteristic information of each primary sub-normalized video data frame sequence, and sequentially inputting the determined plurality of first characteristic information into the time sequence model to obtain a first characteristic vector of each primary sub-normalized video data frame sequence;
the second determining unit is used for sliding in the sound data frame sequence based on the sliding window of the sliding window size to obtain second characteristic information of each primary sub-normalized sound data frame sequence, and sequentially inputting the determined second characteristic information into the time sequence model to obtain second characteristic vectors of each primary sub-normalized sound data frame sequence.
5. A video all-in-one machine as claimed in claim 3, wherein the synchronous dividing sub-module comprises:
the first time determining unit is used for taking the dividing time between adjacent primary sub-audio and video data sources to be displayed, which are corresponding to the first cosine similarity which is not more than the cosine similarity threshold value and obtained in all dividing processes, as a first dividing time;
the second time determining unit is used for regarding the division time between the adjacent primary sub-audio and video data sources to be displayed, which are corresponding to the second cosine similarity which is not more than the cosine similarity threshold value and obtained in all the division processes, as a second division time;
the synchronous dividing unit is used for synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of the audio/video data source to be displayed by taking the first dividing moment and the second dividing moment as dividing limits to obtain sub-normalized video data frame sequences and sub-normalized sound data frame sequences of a plurality of sub-audio/video data sources to be displayed of each audio/video data source to be displayed.
6. The video all-in-one machine of claim 4, wherein the aggregate analysis module comprises:
the first aggregation sub-module is used for screening video heterogeneous aggregation sets of a plurality of sub-audio/video data source sets to be displayed from sub-normalized video data frame sequences of all sub-audio/video data sources to be displayed of all the audio/video data sources to be displayed, wherein one sub-audio/video data source to be displayed of each audio/video data source to be displayed is contained in the sub-audio/video data source set to be displayed, the same sub-audio/video data source to be displayed is not contained among the screened sub-audio/video data source sets to be displayed, and one sub-normalized video data frame sequence of each audio/video data source to be displayed is contained in the video heterogeneous aggregation set;
The second aggregation sub-module is used for screening out sound heterogeneous aggregation sets of a plurality of sub-audio and video data source sets to be displayed from sub-normalized sound data frame sequences of all sub-audio and video data sources to be displayed of all the audio and video data sources to be displayed, wherein the sound heterogeneous aggregation sets comprise one sub-normalized sound data frame sequence of each audio and video data source to be displayed;
the heterogeneous aggregation sub-module is used for carrying out heterogeneous aggregation analysis on all sub-audio and video data sources to be displayed based on cosine similarity of first feature vectors of different normalized video data frame sequences in the video heterogeneous aggregation set and cosine similarity of second feature vectors of different normalized sound data frame sequences in the sound heterogeneous aggregation set to obtain heterogeneous aggregation analysis results.
7. The video all-in-one of claim 6, wherein the heterogeneous aggregation sub-module comprises:
the first computing unit is used for taking the average value of cosine similarity among the first feature vectors of all different normalized video data frame sequences in the video heterogeneous aggregation set as the aggregation degree of the video heterogeneous aggregation set;
the second calculation unit is used for taking the average value of the content similarity of different normalized voice data frame sequences in the voice heterogeneous aggregation set as the aggregation degree of the voice heterogeneous aggregation set;
And the final analysis unit is used for taking the sub-to-be-displayed audio and video data source set of which the aggregation degree of the corresponding video heterogeneous aggregation set is larger than the aggregation degree threshold value and the aggregation degree of the corresponding sound heterogeneous aggregation set is larger than the aggregation degree threshold value as a final heterogeneous aggregation data source set and taking all the final heterogeneous aggregation data source sets as heterogeneous aggregation analysis results.
8. The video all-in-one machine of claim 7, wherein the timing adjustment module comprises:
the comprehensive ordinal number determining submodule is used for taking the average value of the sequencing ordinals of all the sub-audio and video data sources to be displayed in the audio and video data sources to be displayed in each final heterogeneous aggregation data source set in the heterogeneous aggregation analysis result as the comprehensive ordinals of the corresponding final heterogeneous aggregation data source sets;
the set ordering determining submodule is used for ordering all final heterogeneous aggregation data source sets based on the sequence from small to large of the comprehensive ordinal numbers to obtain the final ordinal numbers of all final heterogeneous aggregation data source sets;
the sequence adjustment sub-module is used for setting the final ordinal number of the sub-audio/video data source to be displayed as the final ordinal number corresponding to the final heterogeneous aggregate data source set, and adjusting the sequence of all sub-audio/video data sources to be displayed in the audio/video data source to be displayed based on the final ordinal number to obtain a plurality of new audio/video data sources to be displayed.
9. The video all-in-one machine of claim 1, wherein the coordinated display module comprises:
the multi-source integration module is used for integrating a plurality of new audio/video data sources to be displayed based on the display requirement of each audio/video data source to be displayed to obtain audio/video data to be displayed;
the video display module is used for displaying the audio and video data to be displayed and obtaining a multi-source time sequence coordination display result of the video all-in-one machine.
10. A control method for a video all-in-one machine, characterized by being used for controlling the video all-in-one machine according to any one of claims 1 to 9, comprising:
s1: respectively normalizing the image display parameters and the sound attribute parameters of the original video frame sequences of all the audio and video data sources to be displayed to obtain normalized video data frame sequences and normalized sound data frame sequences of all the audio and video data sources to be displayed;
s2: synchronously dividing the normalized video data frame sequence and the normalized sound data frame sequence of each audio/video data source to be displayed to obtain sub-normalized video data frame sequences and sub-normalized sound data frame sequences of a plurality of sub-audio/video data sources to be displayed of each audio/video data source to be displayed;
S3: based on the sub-normalized video data frame sequences and the sub-normalized sound data frame sequences of the plurality of sub-audio-video data sources to be displayed of each audio-video data source, carrying out heterogeneous aggregation analysis on all the sub-audio-video data sources to be displayed to obtain a heterogeneous aggregation analysis result;
s4: based on the heterogeneous aggregation analysis result, performing time sequence adjustment on all sub-audio and video data sources to be displayed of all audio and video data sources to be displayed to obtain a plurality of new audio and video data sources to be displayed;
s5: and integrating and displaying a plurality of new audio and video data sources to be displayed to obtain a multi-source time sequence coordination display result of the video all-in-one machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311351970.1A CN117097946B (en) | 2023-10-19 | 2023-10-19 | Video all-in-one machine and control method for same |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311351970.1A CN117097946B (en) | 2023-10-19 | 2023-10-19 | Video all-in-one machine and control method for same |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117097946A CN117097946A (en) | 2023-11-21 |
| CN117097946B true CN117097946B (en) | 2024-02-02 |
Family
ID=88775432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311351970.1A Active CN117097946B (en) | 2023-10-19 | 2023-10-19 | Video all-in-one machine and control method for same |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117097946B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108259783A (en) * | 2016-12-29 | 2018-07-06 | 杭州海康威视数字技术股份有限公司 | A kind of character matrix synchronism output control method, device and electronic equipment |
| CN111601133A (en) * | 2019-02-21 | 2020-08-28 | 杭州海康威视数字技术股份有限公司 | Multimedia data synchronous output system and method |
| WO2022152320A1 (en) * | 2021-01-14 | 2022-07-21 | 海信视像科技股份有限公司 | Display device and sound and picture parameter adjusting method |
| WO2023040506A1 (en) * | 2021-09-16 | 2023-03-23 | 腾讯科技（深圳）有限公司 | Model-based data processing method and apparatus, electronic device, computer-readable storage medium, and computer program product |
-
2023
- 2023-10-19 CN CN202311351970.1A patent/CN117097946B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108259783A (en) * | 2016-12-29 | 2018-07-06 | 杭州海康威视数字技术股份有限公司 | A kind of character matrix synchronism output control method, device and electronic equipment |
| CN111601133A (en) * | 2019-02-21 | 2020-08-28 | 杭州海康威视数字技术股份有限公司 | Multimedia data synchronous output system and method |
| WO2022152320A1 (en) * | 2021-01-14 | 2022-07-21 | 海信视像科技股份有限公司 | Display device and sound and picture parameter adjusting method |
| WO2023040506A1 (en) * | 2021-09-16 | 2023-03-23 | 腾讯科技（深圳）有限公司 | Model-based data processing method and apparatus, electronic device, computer-readable storage medium, and computer program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117097946A (en) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102020123304A1 (en) | DEEP LEARNING FOR CLOSED SEMANTIC SEGMENTATION IN VIDEO WITH AUTOMATED INTERACTIVITY AND IMPROVED TIME COHERENCE | |
| US9679380B2 (en) | Emotion modification for image and video content | |
| CN112215171B (en) | Target detection method, device, equipment and computer readable storage medium | |
| Huang et al. | A new hardware-efficient algorithm and reconfigurable architecture for image contrast enhancement | |
| WO2023138590A1 (en) | Reference-free video quality determination method and apparatus, and device and storage medium | |
| CN110072047A (en) | Control method, device and the hardware device of image deformation | |
| WO2019090580A1 (en) | System and method for image dynamic range adjusting | |
| CN107113464B (en) | Content providing apparatus, display apparatus, and control method thereof | |
| CN108549859B (en) | Multi-screen interactive network teaching method and device | |
| WO2023035939A1 (en) | Backlight adjustment method and apparatus, device, and storage medium | |
| CN111859893A (en) | Image-text typesetting method, device, equipment and medium | |
| CN117097946B (en) | Video all-in-one machine and control method for same | |
| CN116259281A (en) | Display equipment and backlight control method | |
| CN116578225A (en) | Image processing method, apparatus, device, computer readable storage medium, and product | |
| WO2023040431A1 (en) | Tone mapping method, device and system | |
| CN110599394A (en) | Method and device for processing pictures in online presentation, storage medium and equipment | |
| CN112598074B (en) | Image processing method and device, computer readable storage medium and electronic equipment | |
| CN111554224B (en) | Display panel mura compensation method and device and display device | |
| CN110196919B (en) | Movie recommendation method and device based on key frames, terminal equipment and storage medium | |
| CN110941728A (en) | Electronic file processing method and device | |
| CN100539706C (en) | The dynamic display device of intermediate data and display packing | |
| CN111489769B (en) | Image processing method, device and hardware device | |
| CN115720279B (en) | Method and device for showing arbitrary special effects in live broadcast scene | |
| US20230230555A1 (en) | Image Processing Method, Apparatus, Electronic Device, And Computer-Readable Storage Medium | |
| US20240153157A1 (en) | Image processing method and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |