CN111935484A - Video frame compression coding method and device - Google Patents
Video frame compression coding method and device Download PDFInfo
- Publication number
- CN111935484A CN111935484A CN202011040419.1A CN202011040419A CN111935484A CN 111935484 A CN111935484 A CN 111935484A CN 202011040419 A CN202011040419 A CN 202011040419A CN 111935484 A CN111935484 A CN 111935484A
- Authority
- CN
- China
- Prior art keywords
- pixel
- coding
- information
- values
- compression
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/146—Data rate or code amount at the encoder output
- H04N19/147—Data rate or code amount at the encoder output according to rate distortion criteria
-
- 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
- H04N19/176—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 block, e.g. a macroblock
-
- 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
- H04N19/182—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 a pixel
-
- 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
- H04N19/70—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention discloses a video frame compression coding method and a device, which firstly determine pixel coding values from each group of video frames in sequence, secondly determine pixel overlapping information corresponding to the pixel coding values based on the obtained pre-established coding block division strategy and the coding distortion information of each group of video frames and update the coding block division strategy, secondly classify the pixel coding values based on the updated coding block division strategy to obtain characteristic pixel coding values and overlapping pixel coding values, thirdly determine pixel transmission information of the overlapping pixel coding values in parallel when carrying out compression coding on each group of video frames according to the characteristic pixel coding values, and identify the pixel transmission information to obtain transmission path parameters, and finally store the transmission path parameters and delete the overlapping pixel coding values. According to the method, each group of video frames are compressed and encoded according to the characteristic pixel encoding values, the effect on the ultra-high definition video frames is more obvious, and the compression ratio is larger; and under the same compression ratio, the image quality is better.
Description
Technical Field
The present application relates to the field of video coding technologies, and in particular, to a method and an apparatus for video frame compression coding.
Background
With the rapid development of communication technology, video communication has become one of the mainstream technologies for people to communicate between people. Compared with text communication and voice communication, video communication can efficiently realize the transmission of data information, thereby improving the communication efficiency.
With the increasing maturity of imaging technology and display technology, the quality of video images is higher and higher, and the corresponding video data is larger and larger. In order to realize real-time video communication, compression encoding of video data is required when video data is transmitted between devices. However, it is difficult to increase the compression ratio while ensuring the quality of video images by using the conventional compression encoding technique.
Disclosure of Invention
The present specification provides a video frame compression coding method and apparatus, so as to solve or partially solve the technical problems in the prior art.
The present specification discloses a video frame compression encoding method, the method comprising:
sequentially determining pixel coding values from each group of video frames according to pixel distribution information based on each group of video frames and a coding sequence pre-generated by an affine transformation matrix corresponding to each group of video frames;
determining pixel overlapping information corresponding to the pixel coding value based on the acquired pre-established coding block division strategy and the coding distortion information of each group of video frames, and updating the coding block division strategy based on the pixel overlapping information;
marking the pixel coding values based on the updated coding block division strategy to obtain characteristic pixel coding values and overlapping pixel coding values;
then, according to the characteristic pixel coding values, determining pixel transmission information of the overlapped pixel coding values in parallel when each group of video frames are subjected to compression coding, and identifying the pixel transmission information to obtain transmission path parameters;
and storing the transmission path parameters and deleting the overlapped pixel coding values.
Preferably, the method further comprises:
and when the pixel coding values of other video frames are marked, updating the coding block division strategy by adopting the stored transmission path parameters.
Preferably, the updating the coding block partitioning policy by using the stored delivery path parameters includes:
extracting dividing logic path information and coding block distribution information of the coding block dividing strategy according to a quality loss coefficient of video frame quality data corresponding to the transmission path parameter in the coding block dividing strategy; respectively constructing a path list corresponding to the dividing logic path information and a distribution list corresponding to the coding block distribution information;
determining first video frame description information of the path list and second video frame description information corresponding to the distribution list, determining a pixel distribution correlation degree between the first video frame description information and the second video frame description information, and determining a ratio of the number of target correlation degrees in the pixel distribution correlation degree, wherein the number of the target correlation degrees is used for representing that pixel gray values of the first video frame description information and the second video frame description information in the same video frame area are the same;
determining a division distortion rate distribution curve corresponding to the coding block division strategy based on the occupation ratio, extracting a plurality of curve segments with compression labels from the division distortion rate distribution curve, and calculating the continuity between every two curve segments; marking the curve segment with the continuity larger than the set distance, and determining the curve segment with the maximum marking frequency as a target curve segment;
listing the coding block compression queues corresponding to the target curve segments, and generating pixel compression paths corresponding to the coding block compression queues; calculating a matching coefficient of the pixel compression path and the coding block distribution information, and determining a pixel area in each group of video frames corresponding to the non-compressive distortion distribution between the pixel compression path and the coding block distribution information according to the matching coefficient; and adding the transmission path parameters to the pixel regions in each group of video frames in a target format in the execution parameters corresponding to the coding block division strategy so as to update the coding block division strategy.
Preferably, marking the pixel code value based on the updated coding block division strategy to obtain a characteristic pixel code value and an overlapping pixel code value, includes:
determining a plurality of first compression weight values of the pixel coding value based on the updated coding block partitioning strategy;
marking the pixel coding values according to the plurality of first compression weight values to obtain a first mark set and a second mark set; wherein the first set of labels is used to characterize the characteristic pixel encoding values and the second set of labels is used to characterize the overlapping pixel encoding values;
calculating a correlation coefficient of the first set of labels and the second set of labels; when the correlation coefficient is larger than a set coefficient, weighting a first compression weight value of the pixel code value based on the determined first pixel code queue of the first mark set and the determined second pixel code queue of the second mark set to obtain a plurality of second compression weight values; executing a similar step of marking the pixel coding values according to the first compression weight values to obtain a first mark set and a second mark set based on the second compression weight values until the calculated correlation coefficient is less than or equal to the set coefficient; and determining a first target mark set corresponding to the correlation coefficient smaller than or equal to the set coefficient as a characteristic pixel coding value, and determining a second target mark set corresponding to the correlation coefficient smaller than or equal to the set coefficient as an overlapped pixel coding value.
Preferably, the sequentially determining pixel coding values from each group of video frames according to a coding order pre-generated based on the pixel distribution information of each group of video frames and the affine transformation matrix corresponding to each group of video frames includes:
determining video frame transcoding parameters corresponding to affine transformation matrixes corresponding to each group of video frames from the pixel distribution information of each group of video frames;
generating a pixel transcoding path corresponding to the video frame transcoding parameters based on the order priority of the encoding order;
calculating a compression distortion ratio between the video frame transcoding parameters and the pixel transcoding path; when the compression distortion ratio is larger than a preset threshold value, determining pixel coding values from each group of video frames according to the sequence from high to low of sequence priority; and when the compression distortion ratio is less than or equal to a preset threshold value, determining pixel coding values from each group of video frames according to the sequence from low to high of the sequence priority.
Preferably, determining pixel overlap information corresponding to the pixel coding value based on the obtained pre-established coding block division strategy and coding distortion information of each group of video frames, and updating the coding block division strategy based on the pixel overlap information includes:
acquiring a plurality of distorted pixel pairs in the coding distortion information and extracting a target pixel of which the gray level of each distorted pixel pair is changed in a corresponding video frame; wherein each target pixel has a different pixel partition boundary value;
after arranging each target pixel according to the magnitude sequence of the distortion proportion corresponding to each distortion pixel pair, calculating the difference value of pixel division boundary values between every two adjacent target pixels; judging whether the difference value of the pixel division boundary values between every two adjacent target pixels reaches a preset difference value or not; if the preset difference value is reached, determining that the associated compression parameters exist between the two adjacent target pixels, and if the preset difference value is not reached, determining that the associated compression parameters do not exist between the two adjacent target pixels;
drawing a coding distortion record table of the coding distortion information according to the target pixel with the associated compression parameter, extracting a plurality of distortion record data from the coding distortion record table and integrating the distortion record data into the pixel overlapping information;
and updating the coding block division strategy based on the priority of distortion record data corresponding to the pixel overlapping information in time sequence.
Preferably, when each group of video frames is compressed and encoded according to the characteristic pixel encoding value, pixel transmission information of the overlapping pixel encoding value is determined in parallel, and the pixel transmission information is identified to obtain a transmission path parameter, including:
when each group of video frames is compressed and coded according to the characteristic pixel coding values, determining overlapping position information of the overlapping pixel coding values and overlapping gray values of the overlapping pixel coding values in parallel;
according to the overlapping position information and the overlapping gray value, performing feature extraction on the overlapping pixel coding value to obtain pixel transmission information of the overlapping pixel coding value;
and inputting the pixel transmission information into a preset convolutional neural network in a set coding format and acquiring transmission path parameters output by the preset convolutional neural network.
This specification discloses a video frame compression encoding apparatus, the apparatus comprising:
the encoding value determining module is used for sequentially determining pixel encoding values from each group of video frames according to pixel distribution information based on each group of video frames and an encoding sequence pre-generated by an affine transformation matrix corresponding to each group of video frames;
the strategy updating module is used for determining pixel overlapping information corresponding to the pixel coding value based on the acquired pre-established coding block division strategy and the coding distortion information of each group of video frames, and updating the coding block division strategy based on the pixel overlapping information;
the coding block division strategy is used for dividing the pixel coding values into a plurality of pixel coding values according to the pixel coding values;
the video frame compression module is used for determining pixel transmission information of the overlapped pixel coding values in parallel when each group of video frames are compressed and coded according to the characteristic pixel coding values and identifying the pixel transmission information to obtain transmission path parameters;
and the code value deleting module is used for storing the transmission path parameters and deleting the overlapped pixel code values.
Preferably, the policy updating module is further configured to:
and when the pixel coding values of other video frames are marked, updating the coding block division strategy by adopting the stored transmission path parameters.
Preferably, the policy updating module is further configured to:
extracting dividing logic path information and coding block distribution information of the coding block dividing strategy according to a quality loss coefficient of video frame quality data corresponding to the transmission path parameter in the coding block dividing strategy; respectively constructing a path list corresponding to the dividing logic path information and a distribution list corresponding to the coding block distribution information;
determining first video frame description information of the path list and second video frame description information corresponding to the distribution list, determining a pixel distribution correlation degree between the first video frame description information and the second video frame description information, and determining a ratio of the number of target correlation degrees in the pixel distribution correlation degree, wherein the number of the target correlation degrees is used for representing that pixel gray values of the first video frame description information and the second video frame description information in the same video frame area are the same;
determining a division distortion rate distribution curve corresponding to the coding block division strategy based on the occupation ratio, extracting a plurality of curve segments with compression labels from the division distortion rate distribution curve, and calculating the continuity between every two curve segments; marking the curve segment with the continuity larger than the set distance, and determining the curve segment with the maximum marking frequency as a target curve segment;
listing the coding block compression queues corresponding to the target curve segments, and generating pixel compression paths corresponding to the coding block compression queues; calculating a matching coefficient of the pixel compression path and the coding block distribution information, and determining a pixel area in each group of video frames corresponding to the non-compressive distortion distribution between the pixel compression path and the coding block distribution information according to the matching coefficient; and adding the transmission path parameters to the pixel regions in each group of video frames in a target format in the execution parameters corresponding to the coding block division strategy so as to update the coding block division strategy.
Through one or more technical schemes of this description, this description has following beneficial effect or advantage:
firstly, pixel coding values are determined from each group of video frames in sequence, then pixel overlapping information corresponding to the pixel coding values is determined based on an obtained pre-established coding block division strategy and coding distortion information of each group of video frames, the coding block division strategy is updated, then the pixel coding values are classified based on the updated coding block division strategy to obtain characteristic pixel coding values and overlapping pixel coding values, then pixel transmission information of the overlapping pixel coding values is determined in parallel when each group of video frames are subjected to compression coding according to the characteristic pixel coding values, the pixel transmission information is identified to obtain transmission path parameters, and finally the transmission path parameters are stored and the overlapping pixel coding values are deleted. Therefore, each group of video frames can be compressed and coded according to the characteristic pixel coding values, and the compression ratio is improved on the premise of ensuring the quality of video images.
The above description is only an outline of the technical solution of the present specification, and the embodiments of the present specification are described below in order to make the technical means of the present specification more clearly understood, and the present specification and other objects, features, and advantages of the present specification can be more clearly understood.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the specification. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flow diagram illustrating a method for compression encoding video frames according to an embodiment of the present disclosure.
Fig. 2 is a block diagram of a video frame compression encoding apparatus according to an embodiment of the present specification.
Fig. 3 shows a schematic diagram of a video communication device according to one embodiment of the present description.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In order to solve the technical problem that the compression ratio is difficult to improve on the premise of ensuring the quality of video images in the existing compression coding technology, the embodiment of the invention provides a video frame compression coding method and a video frame compression coding device, which can mark pixel coding values based on an updated coding block division strategy to obtain characteristic pixel coding values and overlapping pixel coding values, and perform compression coding on each group of video frames based on the characteristic pixel coding values, thereby improving the compression ratio on the premise of ensuring the quality of the video images.
To achieve the above object, please first refer to fig. 1, which provides a flowchart of a video frame compression encoding method, which can be applied to a video communication device, for example, before the video communication device sends video frame data. Further, the method may include the following steps S110 to S150.
And step S110, sequentially determining pixel coding values from each group of video frames according to the pixel distribution information based on each group of video frames and the coding sequence pre-generated by the affine transformation matrix corresponding to each group of video frames.
Step S120, determining pixel overlapping information corresponding to the pixel coding value based on the acquired pre-established coding block division strategy and the coding distortion information of each group of video frames, and updating the coding block division strategy based on the pixel overlapping information.
And step S130, marking the pixel coding value based on the updated coding block division strategy to obtain a characteristic pixel coding value and an overlapped pixel coding value.
Step S140, determining pixel transmission information of the overlapped pixel coding values in parallel when each group of video frames are compressed and coded according to the characteristic pixel coding values, and identifying the pixel transmission information to obtain transmission path parameters.
Step S150, storing the transmission path parameter and deleting the overlapped pixel coding value.
In specific implementation, through the steps S110 to S150, firstly, pixel encoding values are sequentially determined from each group of video frames, secondly, pixel overlapping information corresponding to the pixel encoding values is determined based on the obtained pre-established encoding block division strategy and the encoding distortion information of each group of video frames, and the encoding block division strategy is updated, secondly, the pixel encoding values are classified based on the updated encoding block division strategy to obtain a characteristic pixel encoding value and an overlapping pixel encoding value, thirdly, pixel transmission information of the overlapping pixel encoding values is determined in parallel when each group of video frames is compression-encoded according to the characteristic pixel encoding value, and the pixel transmission information is identified to obtain transmission path parameters, and finally, the transmission path parameters are stored and the overlapping pixel encoding values are deleted. Therefore, each group of video frames can be compressed and coded according to the characteristic pixel coding values, and the compression ratio is improved on the premise of ensuring the quality of video images.
Optionally, in order to improve the real-time performance and accuracy of updating the coding block partitioning policy, on the basis of the above steps S110 to S150, the following step S160 is further included: and when the pixel coding values of other video frames are marked, updating the coding block division strategy by adopting the stored transmission path parameters. Therefore, the coding block division strategy can be accurately updated in real time by adopting the stored transmission path parameters.
Further, in order to ensure that the encoding block division strategy after updating can realize the distinction of the correlation degree and the feature degree of the encoding value, the step S160 may further include what is described in the following steps S161 to S164 when implemented.
Step S161, extracting dividing logic path information and coding block distribution information of the coding block dividing policy according to a quality loss coefficient of the video frame quality data corresponding to the transmission path parameter in the coding block dividing policy; and respectively constructing a path list corresponding to the dividing logic path information and a distribution list corresponding to the coding block distribution information.
Step S162, determining first video frame description information of the path list and second video frame description information corresponding to the distribution list, determining a pixel distribution correlation between the first video frame description information and the second video frame description information, and determining a ratio of a number of target correlations in the pixel distribution correlation, which is used for representing that a pixel gray value of the first video frame description information and a pixel gray value of the second video frame description information in a same video frame region are the same, in the pixel distribution correlation.
Step S163, determining a division distortion rate distribution curve corresponding to the coding block division strategy based on the percentage, extracting a plurality of curve segments with compression labels from the division distortion rate distribution curve, and calculating continuity between every two curve segments; and marking the curve segment with the continuity larger than the set distance, and determining the curve segment with the maximum marking times as the target curve segment.
Step S164, listing the coding block compression queues corresponding to the target curve segments, and generating pixel compression paths corresponding to the coding block compression queues; calculating a matching coefficient of the pixel compression path and the coding block distribution information, and determining a pixel area in each group of video frames corresponding to the non-compressive distortion distribution between the pixel compression path and the coding block distribution information according to the matching coefficient; and adding the transmission path parameters to the pixel regions in each group of video frames in a target format in the execution parameters corresponding to the coding block division strategy so as to update the coding block division strategy.
It can be understood that when the contents described in the above steps S161 to S164 are applied, it can be ensured that the encoding block division policy after updating can achieve the discrimination of the correlation and the feature degree of the encoding value.
In one possible embodiment, in order to accurately determine the pixel coding values and avoid missing pixel coding values, the step S110 describes that the pixel coding values are sequentially determined from each group of video frames according to the coding order pre-generated based on the pixel distribution information of each group of video frames and the affine transformation matrix corresponding to each group of video frames, and further includes the following steps S111 to S113.
And step S111, determining video frame transcoding parameters corresponding to the affine transformation matrix corresponding to each group of video frames from the pixel distribution information of each group of video frames.
And step S112, generating a pixel transcoding path corresponding to the video frame transcoding parameter based on the order priority of the coding order.
Step S113, calculating a compression distortion ratio between the video frame transcoding parameters and the pixel transcoding path; when the compression distortion ratio is larger than a preset threshold value, determining pixel coding values from each group of video frames according to the sequence from high to low of sequence priority; and when the compression distortion ratio is less than or equal to a preset threshold value, determining pixel coding values from each group of video frames according to the sequence from low to high of the sequence priority.
By implementing the above steps S111 to S113, the pixel code value can be accurately determined, and the pixel code value is prevented from missing.
In an alternative embodiment, in order to ensure that the coding block division strategy does not have the problem of increased division error when the coding block division strategy is updated, in step S120, pixel overlap information corresponding to the pixel coding value is determined based on the obtained pre-established coding block division strategy and the coding distortion information of each group of video frames, and the coding block division strategy is updated based on the pixel overlap information, which may exemplarily include the contents described in the following steps S121 to S124.
Step S121, obtaining a plurality of distorted pixel pairs in the coding distortion information and extracting a target pixel of each distorted pixel pair with gray level change in a corresponding video frame; wherein each target pixel has a different pixel partition boundary value.
Step S122, after arranging each target pixel according to the magnitude sequence of the distortion proportion corresponding to each distortion pixel, calculating the difference value of the pixel division boundary value between every two adjacent target pixels; judging whether the difference value of the pixel division boundary values between every two adjacent target pixels reaches a preset difference value or not; and if the preset difference is not reached, determining that no related compression parameter exists between the two adjacent target pixels.
Step S123, drawing a coding distortion record table of the coding distortion information according to the target pixel with the associated compression parameter, extracting a plurality of distortion record data from the coding distortion record table and integrating the distortion record data into the pixel overlapping information.
Step S124, updating the coding block division strategy based on the priority of the distortion recording data corresponding to the pixel overlapping information in time sequence.
Based on the contents described in the above steps S121 to S124, it can be ensured that the coding block division strategy does not have the problem of increased division error when the coding block division strategy is updated.
In an implementation manner, the step S140 may further be implemented by determining pixel transfer information of the overlapped pixel coding values in parallel when performing compression coding on each group of video frames according to the characteristic pixel coding value, and identifying the pixel transfer information to obtain a transfer path parameter, which is further implemented by the following steps S141 to S143.
Step S141, when each group of video frames is compressed and encoded according to the characteristic pixel encoded values, determining overlapping position information of the overlapping pixel encoded values and overlapping gray-scale values of the overlapping pixel encoded values in parallel.
Step S142, performing feature extraction on the overlapping pixel code value according to the overlapping position information and the overlapping gray value to obtain pixel transmission information of the overlapping pixel code value.
Step S143, inputting the pixel transmission information into a preset convolutional neural network in a set encoding format and obtaining a transmission path parameter output by the preset convolutional neural network.
In this way, the transmission path parameters can be accurately determined according to the steps S141 to S143 to ensure the synchronization of the transmission path parameters in terms of time sequence.
Based on the same inventive concept as the above embodiment, please refer to fig. 2, which is a block diagram of a video frame compression encoding apparatus 200, wherein the video frame compression encoding apparatus 200 includes:
an encoding value determining module 210, configured to sequentially determine pixel encoding values from each group of video frames according to a pre-generated encoding sequence based on pixel distribution information of each group of video frames and an affine transformation matrix corresponding to each group of video frames;
a policy updating module 220, configured to determine pixel overlap information corresponding to the pixel coding value based on the obtained pre-established coding block division policy and coding distortion information of each group of video frames, and update the coding block division policy based on the pixel overlap information;
an encoding value marking module 230, configured to mark the pixel encoding value based on the updated encoding block partitioning policy to obtain a feature pixel encoding value and an overlapping pixel encoding value;
the video frame compression module 240 is configured to determine pixel transmission information of the overlapping pixel coding values in parallel when each group of video frames is compressed and coded according to the characteristic pixel coding values, and identify the pixel transmission information to obtain a transmission path parameter;
and an encoding value deleting module 250, configured to store the transmission path parameter and delete the overlapping pixel encoding value.
Optionally, the policy updating module 220 is further configured to:
and when the pixel coding values of other video frames are marked, updating the coding block division strategy by adopting the stored transmission path parameters.
Optionally, the policy updating module 220 is further configured to:
extracting dividing logic path information and coding block distribution information of the coding block dividing strategy according to a quality loss coefficient of video frame quality data corresponding to the transmission path parameter in the coding block dividing strategy; respectively constructing a path list corresponding to the dividing logic path information and a distribution list corresponding to the coding block distribution information;
determining first video frame description information of the path list and second video frame description information corresponding to the distribution list, determining a pixel distribution correlation degree between the first video frame description information and the second video frame description information, and determining a ratio of the number of target correlation degrees in the pixel distribution correlation degree, wherein the number of the target correlation degrees is used for representing that pixel gray values of the first video frame description information and the second video frame description information in the same video frame area are the same;
determining a division distortion rate distribution curve corresponding to the coding block division strategy based on the occupation ratio, extracting a plurality of curve segments with compression labels from the division distortion rate distribution curve, and calculating the continuity between every two curve segments; marking the curve segment with the continuity larger than the set distance, and determining the curve segment with the maximum marking frequency as a target curve segment;
listing the coding block compression queues corresponding to the target curve segments, and generating pixel compression paths corresponding to the coding block compression queues; calculating a matching coefficient of the pixel compression path and the coding block distribution information, and determining a pixel area in each group of video frames corresponding to the non-compressive distortion distribution between the pixel compression path and the coding block distribution information according to the matching coefficient; and adding the transmission path parameters to the pixel regions in each group of video frames in a target format in the execution parameters corresponding to the coding block division strategy so as to update the coding block division strategy.
Optionally, the encoded value marking module 230 is specifically configured to:
determining a plurality of first compression weight values of the pixel coding value based on the updated coding block partitioning strategy;
marking the pixel coding values according to the plurality of first compression weight values to obtain a first mark set and a second mark set; wherein the first set of labels is used to characterize the characteristic pixel encoding values and the second set of labels is used to characterize the overlapping pixel encoding values;
calculating a correlation coefficient of the first set of labels and the second set of labels; when the correlation coefficient is larger than a set coefficient, weighting a first compression weight value of the pixel code value based on the determined first pixel code queue of the first mark set and the determined second pixel code queue of the second mark set to obtain a plurality of second compression weight values; executing a similar step of marking the pixel coding values according to the first compression weight values to obtain a first mark set and a second mark set based on the second compression weight values until the calculated correlation coefficient is less than or equal to the set coefficient; and determining a first target mark set corresponding to the correlation coefficient smaller than or equal to the set coefficient as a characteristic pixel coding value, and determining a second target mark set corresponding to the correlation coefficient smaller than or equal to the set coefficient as an overlapped pixel coding value.
Optionally, the encoding value determining module 210 is further configured to:
determining video frame transcoding parameters corresponding to affine transformation matrixes corresponding to each group of video frames from the pixel distribution information of each group of video frames;
generating a pixel transcoding path corresponding to the video frame transcoding parameters based on the order priority of the encoding order;
calculating a compression distortion ratio between the video frame transcoding parameters and the pixel transcoding path; when the compression distortion ratio is larger than a preset threshold value, determining pixel coding values from each group of video frames according to the sequence from high to low of sequence priority; and when the compression distortion ratio is less than or equal to a preset threshold value, determining pixel coding values from each group of video frames according to the sequence from low to high of the sequence priority.
Optionally, the policy updating module 220 is specifically configured to:
acquiring a plurality of distorted pixel pairs in the coding distortion information and extracting a target pixel of which the gray level of each distorted pixel pair is changed in a corresponding video frame; wherein each target pixel has a different pixel partition boundary value;
after arranging each target pixel according to the magnitude sequence of the distortion proportion corresponding to each distortion pixel pair, calculating the difference value of pixel division boundary values between every two adjacent target pixels; judging whether the difference value of the pixel division boundary values between every two adjacent target pixels reaches a preset difference value or not; if the preset difference value is reached, determining that the associated compression parameters exist between the two adjacent target pixels, and if the preset difference value is not reached, determining that the associated compression parameters do not exist between the two adjacent target pixels;
drawing a coding distortion record table of the coding distortion information according to the target pixel with the associated compression parameter, extracting a plurality of distortion record data from the coding distortion record table and integrating the distortion record data into the pixel overlapping information;
and updating the coding block division strategy based on the priority of distortion record data corresponding to the pixel overlapping information in time sequence.
Optionally, the video frame compression module 240 is specifically configured to:
when each group of video frames is compressed and coded according to the characteristic pixel coding values, determining overlapping position information of the overlapping pixel coding values and overlapping gray values of the overlapping pixel coding values in parallel;
according to the overlapping position information and the overlapping gray value, performing feature extraction on the overlapping pixel coding value to obtain pixel transmission information of the overlapping pixel coding value;
and inputting the pixel transmission information into a preset convolutional neural network in a set coding format and acquiring transmission path parameters output by the preset convolutional neural network.
Based on the same inventive concept as in the previous embodiments, the present specification further provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of any of the methods described above.
Based on the same inventive concept as in the previous embodiment, as shown in fig. 3, an embodiment of the present specification further provides a video communication device 300, which includes a memory 310, a processor 320, and a computer program stored in the memory 310 and executable on the processor 320, wherein the processor 320 implements the steps of any one of the methods described above when executing the program.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, this description is not intended for any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present specification and that specific languages are described above to disclose the best modes of the specification.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present description may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the specification, various features of the specification are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that is, the present specification as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this specification.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the description and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of this description may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components of a gateway, proxy server, system in accordance with embodiments of the present description. The present description may also be embodied as an apparatus or device program (e.g., computer program and computer program product) for performing a portion or all of the methods described herein. Such programs implementing the description may be stored on a computer-readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the specification, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The description may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (10)
1. A method for video frame compression encoding, the method comprising:
sequentially determining pixel coding values from each group of video frames according to pixel distribution information based on each group of video frames and a coding sequence pre-generated by an affine transformation matrix corresponding to each group of video frames;
determining pixel overlapping information corresponding to the pixel coding value based on the acquired pre-established coding block division strategy and the coding distortion information of each group of video frames, and updating the coding block division strategy based on the pixel overlapping information;
marking the pixel coding values based on the updated coding block division strategy to obtain characteristic pixel coding values and overlapping pixel coding values;
then, according to the characteristic pixel coding values, determining pixel transmission information of the overlapped pixel coding values in parallel when each group of video frames are subjected to compression coding, and identifying the pixel transmission information to obtain transmission path parameters;
and storing the transmission path parameters and deleting the overlapped pixel coding values.
2. The method of claim 1, wherein the method further comprises:
and when the pixel coding values of other video frames are marked, updating the coding block division strategy by adopting the stored transmission path parameters.
3. The method of claim 2, wherein updating a coding block partitioning policy with stored delivery path parameters comprises:
extracting dividing logic path information and coding block distribution information of the coding block dividing strategy according to a quality loss coefficient of video frame quality data corresponding to the transmission path parameter in the coding block dividing strategy; respectively constructing a path list corresponding to the dividing logic path information and a distribution list corresponding to the coding block distribution information;
determining first video frame description information of the path list and second video frame description information corresponding to the distribution list, determining a pixel distribution correlation degree between the first video frame description information and the second video frame description information, and determining a ratio of the number of target correlation degrees in the pixel distribution correlation degree, wherein the number of the target correlation degrees is used for representing that pixel gray values of the first video frame description information and the second video frame description information in the same video frame area are the same;
determining a division distortion rate distribution curve corresponding to the coding block division strategy based on the occupation ratio, extracting a plurality of curve segments with compression labels from the division distortion rate distribution curve, and calculating the continuity between every two curve segments; marking the curve segment with the continuity larger than the set distance, and determining the curve segment with the maximum marking frequency as a target curve segment;
listing the coding block compression queues corresponding to the target curve segments, and generating pixel compression paths corresponding to the coding block compression queues; calculating a matching coefficient of the pixel compression path and the coding block distribution information, and determining a pixel area in each group of video frames corresponding to the non-compressive distortion distribution between the pixel compression path and the coding block distribution information according to the matching coefficient; and adding the transmission path parameters to the pixel regions in each group of video frames in a target format in the execution parameters corresponding to the coding block division strategy so as to update the coding block division strategy.
4. The method of any of claims 1-3, wherein marking the pixel code values based on the updated coded block partitioning policy yields a eigen pixel code value and an overlapping pixel code value, comprising:
determining a plurality of first compression weight values of the pixel coding value based on the updated coding block partitioning strategy;
marking the pixel coding values according to the plurality of first compression weight values to obtain a first mark set and a second mark set; wherein the first set of labels is used to characterize the characteristic pixel encoding values and the second set of labels is used to characterize the overlapping pixel encoding values;
calculating a correlation coefficient of the first set of labels and the second set of labels; when the correlation coefficient is larger than a set coefficient, weighting a first compression weight value of the pixel code value based on the determined first pixel code queue of the first mark set and the determined second pixel code queue of the second mark set to obtain a plurality of second compression weight values; executing a similar step of marking the pixel coding values according to the first compression weight values to obtain a first mark set and a second mark set based on the second compression weight values until the calculated correlation coefficient is less than or equal to the set coefficient; and determining a first target mark set corresponding to the correlation coefficient smaller than or equal to the set coefficient as a characteristic pixel coding value, and determining a second target mark set corresponding to the correlation coefficient smaller than or equal to the set coefficient as an overlapped pixel coding value.
5. The method of claim 1, wherein determining pixel code values from each set of video frames in turn according to a pre-generated coding order based on pixel distribution information for each set of video frames and an affine transformation matrix corresponding to each set of video frames comprises:
determining video frame transcoding parameters corresponding to affine transformation matrixes corresponding to each group of video frames from the pixel distribution information of each group of video frames;
generating a pixel transcoding path corresponding to the video frame transcoding parameters based on the order priority of the encoding order;
calculating a compression distortion ratio between the video frame transcoding parameters and the pixel transcoding path; when the compression distortion ratio is larger than a preset threshold value, determining pixel coding values from each group of video frames according to the sequence from high to low of sequence priority; and when the compression distortion ratio is less than or equal to a preset threshold value, determining pixel coding values from each group of video frames according to the sequence from low to high of the sequence priority.
6. The method of claim 1, wherein determining pixel overlap information corresponding to the pixel coding value based on the obtained pre-established coding block partitioning strategy and coding distortion information for each set of video frames, and updating the coding block partitioning strategy based on the pixel overlap information comprises:
acquiring a plurality of distorted pixel pairs in the coding distortion information and extracting a target pixel of which the gray level of each distorted pixel pair is changed in a corresponding video frame; wherein each target pixel has a different pixel partition boundary value;
after arranging each target pixel according to the magnitude sequence of the distortion proportion corresponding to each distortion pixel pair, calculating the difference value of pixel division boundary values between every two adjacent target pixels; judging whether the difference value of the pixel division boundary values between every two adjacent target pixels reaches a preset difference value or not; if the preset difference value is reached, determining that the associated compression parameters exist between the two adjacent target pixels, and if the preset difference value is not reached, determining that the associated compression parameters do not exist between the two adjacent target pixels;
drawing a coding distortion record table of the coding distortion information according to the target pixel with the associated compression parameter, extracting a plurality of distortion record data from the coding distortion record table and integrating the distortion record data into the pixel overlapping information;
and updating the coding block division strategy based on the priority of distortion record data corresponding to the pixel overlapping information in time sequence.
7. The method of claim 1, wherein determining pixel transfer information for the overlapping pixel code values in parallel when compression coding each set of video frames based on the characteristic pixel code values and identifying the pixel transfer information to obtain transfer path parameters comprises:
when each group of video frames is compressed and coded according to the characteristic pixel coding values, determining overlapping position information of the overlapping pixel coding values and overlapping gray values of the overlapping pixel coding values in parallel;
according to the overlapping position information and the overlapping gray value, performing feature extraction on the overlapping pixel coding value to obtain pixel transmission information of the overlapping pixel coding value;
and inputting the pixel transmission information into a preset convolutional neural network in a set coding format and acquiring transmission path parameters output by the preset convolutional neural network.
8. An apparatus for video frame compression encoding, the apparatus comprising:
the encoding value determining module is used for sequentially determining pixel encoding values from each group of video frames according to pixel distribution information based on each group of video frames and an encoding sequence pre-generated by an affine transformation matrix corresponding to each group of video frames;
the strategy updating module is used for determining pixel overlapping information corresponding to the pixel coding value based on the acquired pre-established coding block division strategy and the coding distortion information of each group of video frames, and updating the coding block division strategy based on the pixel overlapping information;
the coding block division strategy is used for dividing the pixel coding values into a plurality of pixel coding values according to the pixel coding values;
the video frame compression module is used for determining pixel transmission information of the overlapped pixel coding values in parallel when each group of video frames are compressed and coded according to the characteristic pixel coding values and identifying the pixel transmission information to obtain transmission path parameters;
and the code value deleting module is used for storing the transmission path parameters and deleting the overlapped pixel code values.
9. The apparatus of claim 8, wherein the policy update module is further configured to:
and when the pixel coding values of other video frames are marked, updating the coding block division strategy by adopting the stored transmission path parameters.
10. The apparatus of claim 9, wherein the policy update module is further to:
extracting dividing logic path information and coding block distribution information of the coding block dividing strategy according to a quality loss coefficient of video frame quality data corresponding to the transmission path parameter in the coding block dividing strategy; respectively constructing a path list corresponding to the dividing logic path information and a distribution list corresponding to the coding block distribution information;
determining first video frame description information of the path list and second video frame description information corresponding to the distribution list, determining a pixel distribution correlation degree between the first video frame description information and the second video frame description information, and determining a ratio of the number of target correlation degrees in the pixel distribution correlation degree, wherein the number of the target correlation degrees is used for representing that pixel gray values of the first video frame description information and the second video frame description information in the same video frame area are the same;
determining a division distortion rate distribution curve corresponding to the coding block division strategy based on the occupation ratio, extracting a plurality of curve segments with compression labels from the division distortion rate distribution curve, and calculating the continuity between every two curve segments; marking the curve segment with the continuity larger than the set distance, and determining the curve segment with the maximum marking frequency as a target curve segment;
listing the coding block compression queues corresponding to the target curve segments, and generating pixel compression paths corresponding to the coding block compression queues; calculating a matching coefficient of the pixel compression path and the coding block distribution information, and determining a pixel area in each group of video frames corresponding to the non-compressive distortion distribution between the pixel compression path and the coding block distribution information according to the matching coefficient; and adding the transmission path parameters to the pixel regions in each group of video frames in a target format in the execution parameters corresponding to the coding block division strategy so as to update the coding block division strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011040419.1A CN111935484B (en) | 2020-09-28 | 2020-09-28 | Video frame compression coding method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011040419.1A CN111935484B (en) | 2020-09-28 | 2020-09-28 | Video frame compression coding method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111935484A true CN111935484A (en) | 2020-11-13 |
| CN111935484B CN111935484B (en) | 2021-01-19 |
Family
ID=73334607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011040419.1A Active CN111935484B (en) | 2020-09-28 | 2020-09-28 | Video frame compression coding method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111935484B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115460382A (en) * | 2022-11-09 | 2022-12-09 | 苏州迈创信息技术有限公司 | Security and protection engineering monitoring data safety transmission method |
| CN116828211A (en) * | 2023-08-30 | 2023-09-29 | 华洋通信科技股份有限公司 | Wireless transmission self-adaptive coding method for video under mine |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102196265A (en) * | 2010-03-16 | 2011-09-21 | 索尼公司 | Image encoding apparatus and method, image decoding apparatus and method, and program |
| CN102484710A (en) * | 2009-07-29 | 2012-05-30 | 高通股份有限公司 | Method and device for pixel interpolation |
| CN102970529A (en) * | 2012-10-22 | 2013-03-13 | 北京航空航天大学 | Multi-viewpoint video fractal coding compressing and uncompressing method based on objects |
| US20150281720A1 (en) * | 2002-01-05 | 2015-10-01 | Samsung Electronics Co., Ltd. | Image coding and decoding method and apparatus considering human visual characteristics |
| US20150341658A1 (en) * | 2012-02-27 | 2015-11-26 | Via Telecom Co., Ltd. | Motion estimation and in-loop filtering method and device thereof |
| US20150382025A1 (en) * | 2014-06-26 | 2015-12-31 | Futurewei Technologies, Inc. | Method and device for providing depth based block partitioning in high efficiency video coding |
| CN105469353A (en) * | 2015-12-25 | 2016-04-06 | 上海携程商务有限公司 | Embedding method and device of watermark image, and extraction method and device of watermark image |
| US20180309991A1 (en) * | 2016-03-02 | 2018-10-25 | MatrixView, Inc. | Video encoding with adaptive rate distortion control by skipping blocks of a lower quality video into a higher quality video |
| CN109417633A (en) * | 2016-04-29 | 2019-03-01 | 英迪股份有限公司 | Method and apparatus for encoding/decoding video signal |
| CN109769119A (en) * | 2018-12-18 | 2019-05-17 | 中国科学院深圳先进技术研究院 | A kind of low complex degree vision signal code processing method |
-
2020
- 2020-09-28 CN CN202011040419.1A patent/CN111935484B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150281720A1 (en) * | 2002-01-05 | 2015-10-01 | Samsung Electronics Co., Ltd. | Image coding and decoding method and apparatus considering human visual characteristics |
| CN102484710A (en) * | 2009-07-29 | 2012-05-30 | 高通股份有限公司 | Method and device for pixel interpolation |
| CN102196265A (en) * | 2010-03-16 | 2011-09-21 | 索尼公司 | Image encoding apparatus and method, image decoding apparatus and method, and program |
| US20150341658A1 (en) * | 2012-02-27 | 2015-11-26 | Via Telecom Co., Ltd. | Motion estimation and in-loop filtering method and device thereof |
| CN102970529A (en) * | 2012-10-22 | 2013-03-13 | 北京航空航天大学 | Multi-viewpoint video fractal coding compressing and uncompressing method based on objects |
| US20150382025A1 (en) * | 2014-06-26 | 2015-12-31 | Futurewei Technologies, Inc. | Method and device for providing depth based block partitioning in high efficiency video coding |
| CN105469353A (en) * | 2015-12-25 | 2016-04-06 | 上海携程商务有限公司 | Embedding method and device of watermark image, and extraction method and device of watermark image |
| US20180309991A1 (en) * | 2016-03-02 | 2018-10-25 | MatrixView, Inc. | Video encoding with adaptive rate distortion control by skipping blocks of a lower quality video into a higher quality video |
| CN109417633A (en) * | 2016-04-29 | 2019-03-01 | 英迪股份有限公司 | Method and apparatus for encoding/decoding video signal |
| CN109769119A (en) * | 2018-12-18 | 2019-05-17 | 中国科学院深圳先进技术研究院 | A kind of low complex degree vision signal code processing method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115460382A (en) * | 2022-11-09 | 2022-12-09 | 苏州迈创信息技术有限公司 | Security and protection engineering monitoring data safety transmission method |
| CN116828211A (en) * | 2023-08-30 | 2023-09-29 | 华洋通信科技股份有限公司 | Wireless transmission self-adaptive coding method for video under mine |
| CN116828211B (en) * | 2023-08-30 | 2023-11-14 | 华洋通信科技股份有限公司 | Wireless transmission self-adaptive coding method for video under mine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111935484B (en) | 2021-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020098422A1 (en) | Encoded pattern processing method and device , storage medium and electronic device | |
| CN108229290B (en) | Video object segmentation method and device, electronic equipment and storage medium | |
| CN111797976B (en) | Training method, image recognition method, device, equipment and medium for neural network | |
| CN111935484B (en) | Video frame compression coding method and device | |
| CN110490203B (en) | Image segmentation method and device, electronic equipment and computer readable storage medium | |
| CN112966754B (en) | Sample screening method, sample screening device and terminal equipment | |
| US11709915B2 (en) | Classifying images utilizing generative-discriminative feature representations | |
| CN111723841A (en) | Text detection method and device, electronic equipment and storage medium | |
| US20190108627A1 (en) | Automated system and method of retaining images based on a user's feedback on image quality | |
| CN111767750A (en) | Image processing method and device | |
| CN112966755A (en) | Inductance defect detection method and device and readable storage medium | |
| CN111327946A (en) | Video quality evaluation and feature dictionary training method, device and medium | |
| CN113628116B (en) | Training method and device for image processing network, computer equipment and storage medium | |
| US11887277B2 (en) | Removing compression artifacts from digital images and videos utilizing generative machine-learning models | |
| CN112102200A (en) | Image completion model initialization method, training method and image completion method | |
| CN112183224A (en) | Model training method for image recognition, image recognition method and device | |
| CN115439367A (en) | Image enhancement method and device, electronic equipment and storage medium | |
| CN112669240B (en) | High-definition image restoration method and device, electronic equipment and storage medium | |
| KR102305981B1 (en) | Method for Training to Compress Neural Network and Method for Using Compressed Neural Network | |
| CN110414845B (en) | Risk assessment method and device for target transaction | |
| CN113744158A (en) | Image generation method and device, electronic equipment and storage medium | |
| CN115546239B (en) | Target segmentation method and device based on boundary attention and distance transformation | |
| CN116958954B (en) | License plate recognition method, device and storage medium based on key points and bypass correction | |
| CN113592766B (en) | Coronary angiography image segmentation method based on depth sequence information fusion | |
| CN110276720B (en) | Image generation method and 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 |