CN117319679A - HEVC (high efficiency video coding) inter-frame rapid coding method based on long-short-time memory network - Google Patents
HEVC (high efficiency video coding) inter-frame rapid coding method based on long-short-time memory network Download PDFInfo
- Publication number
- CN117319679A CN117319679A CN202310894112.5A CN202310894112A CN117319679A CN 117319679 A CN117319679 A CN 117319679A CN 202310894112 A CN202310894112 A CN 202310894112A CN 117319679 A CN117319679 A CN 117319679A
- Authority
- CN
- China
- Prior art keywords
- coding
- inter
- hevc
- long
- memory network
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims description 23
- 230000009467 reduction Effects 0.000 claims description 4
- 230000014509 gene expression Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 230000006835 compression Effects 0.000 description 6
- 238000007906 compression Methods 0.000 description 6
- 238000000638 solvent extraction Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000005192 partition Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- 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
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/119—Adaptive subdivision aspects, e.g. subdivision of a picture into rectangular or non-rectangular coding blocks
-
- 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
- H04N19/149—Data rate or code amount at the encoder output by estimating the code amount by means of a model, e.g. mathematical model or statistical model
-
- 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
- H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
- H04N19/503—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving temporal prediction
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention provides an HEVC (high efficiency video coding) inter-frame rapid coding method based on a long and short time memory network, and belongs to the technical field of HEVC-based video coding. The technical problem of high computational complexity in the inter-frame coding process in HEVC is solved. The technical proposal is as follows: the method comprises the following steps: s1, designing a data preprocessing module to acquire a prediction mode of a current coding unit and inter-frame residual information; s2, introducing a long-short-time memory network, and enhancing the time sequence prediction capability of the inter-frame rapid coding model; s3, the division information of the deep coding units is used for guiding the division of the shallow coding units. The beneficial effects of the invention are as follows: on the premise of ensuring the coding quality, the calculation complexity of the HEVC inter-frame coding process can be effectively reduced.
Description
Technical Field
The invention relates to the technical field of HEVC (high efficiency video coding) based video coding, in particular to an HEVC inter-frame rapid coding method based on a long-short-time memory network.
Background
In recent years, the living standard of people is continuously improved along with the rapid development of economy. In the world of informatization, people have an increasing demand for information, and also have an increasing demand for information visualization and convenience. In the face of the proliferation of video service types, high-definition video and popularization of ultra-high-definition video, the current AVC (Advanced Video Coding, AVC) standard widely applied gradually cannot meet the requirement of high-resolution video service on efficient coding under the condition of limited network resources and storage resources. As such, focusing on the high-efficiency video coding standards HEVC (High Efficiency Video Coding, HEVC) of "lower code rate" and "higher image quality", the compression efficiency is doubled compared with AVC by introducing advanced coding techniques while inheriting the AVC standard hybrid coding framework, i.e., the coding code rate is reduced to 50% of the original coding code rate on the premise of ensuring the same video coding quality, so that it can better serve the coding of high-definition and ultra-high-definition videos.
Wherein, in order to cope with the larger resolution coding requirement, the HEVC standard adopts a more flexible "quadtree" coding unit partition structure (64×64 to 16×16), and discards the coding Macro Block (MB) with the fixed size of 16×16 in the AVC standard; a richer intra prediction angle and a new inter prediction mode are adopted in order to improve compression efficiency. However, with the introduction of these techniques, the coding complexity of HEVC is increased by 253% relative to AVC, where the coding unit recursive partitioning technique based on the "quadtree" structure is a major source of coding complexity increase, and the partitioning process is determined to occupy 80% of the overall coding time.
In conclusion, the HEVC international standard is combined with challenges on the way of large-scale practical application from theoretical research. The HEVC standard introduces a flexible 'quadtree' coding unit division scheme, which is different from other video coding standards and is more suitable for the basis and key points of high-resolution video compression coding. This approach greatly improves the compression performance of the HEVC standard, but inevitably increases coding complexity. The complexity of the method is 2 to 10 times of that of 'macro block' division of the AVC standard, the process accounts for more than 90% of that of an HEVC encoder, and the method becomes a huge gap between popularization and large-scale application of the HEVC standard in the field of practical application. Thus, there is an urgent need for a low complexity coding scheme capable of meeting the needs of practical video applications. How to effectively utilize the prior information of the coding structure to reduce the complexity of the dividing process of the coding units of the quadtree becomes a core problem for promoting the popularization and application of the HEVC standard.
Inter-frame similarity is high as a unique feature of video information, and inter-frame coding naturally becomes a key technology capable of reflecting video coding compression performance. In the process, the block to be encoded uses the encoded reconstructed frame as a reference frame, and inter-frame encoding is realized by a motion estimation and motion compensation method in sequence, so that the time correlation between adjacent image frames in video is used for eliminating time redundancy, and the video compression efficiency is improved. However, as with the intra-frame coding process, the problem of the increasing of coding computation complexity caused by the introduction of the "quadtree" coding unit division scheme still faces.
Therefore, in view of the new situation and the new challenge, aiming at the key problem of HEVC in the practical application field under the new video technology development trend, it is highly needed to propose an HEVC inter-frame fast coding method meeting the video technology development requirement. The inter-frame correlation of the video is effectively utilized to accelerate the division of HEVC coding units, so as to promote the development of HEVC standard coding theory and promote the large-scale popularization of the HEVC standard in the field of practical application.
Disclosure of Invention
The invention aims to provide an HEVC inter-frame rapid coding method based on a long-short-time memory network, which solves the technical problem of high computational complexity in the inter-frame coding process in HEVC and can effectively reduce the computational complexity in the inter-frame coding process of HEVC on the premise of ensuring the coding quality.
The invention is characterized in that: the invention provides an HEVC (high efficiency video coding) inter-frame rapid coding method based on a long and short time memory network.
In order to achieve the aim of the invention, the invention adopts the technical scheme that: an HEVC inter-frame rapid coding method based on a long-short-time memory network comprises the following steps:
1.1, designing a data preprocessing module;
1.2, constructing an inter-frame rapid coding model based on a long-short-time memory network;
and 1.3, guiding the division of the shallow coding units by using the deep coding unit division information.
Further, the step 1.1 specifically includes the following steps:
2.1, setting the minimum partitionable size of the coding unit and the prediction unit;
and 2.2, acquiring the coding mode of the unit to be coded and residual information of inter-frame coding.
Further, the step 1.2 specifically includes the following steps:
3.1, constructing an inter-frame rapid coding model consisting of three modules, namely a forward information extraction module, a time sequence feature integration module of a long-short-time memory network and a feature prediction module based on a feature transfer mechanism;
3.2, performing global dimension reduction on the data by using a generalized characteristic extraction module in the forward information extraction module;
3.3, carrying out division feature extraction on the coding units under different depths by utilizing a multidimensional feature extraction module and a depth difference feature extraction module in the forward information extraction module;
3.4, sending the coding unit division features extracted by the depth difference feature extraction module into different long-short-time memory network structures according to the depth difference to obtain feature expressions at different depths;
and 3.5, guiding the dividing process of the low-depth coding unit by utilizing the coding unit dividing characteristics of the high depth to obtain the characteristic vector predicted value of the coding unit dividing characteristics.
Further, the step 1.3 specifically includes the following steps:
4.1, comparing a predicted value of the inter-frame rapid coding model with a set threshold value;
4.2, if the predicted value is greater than or equal to a set threshold value, judging the coding unit of the next depth as division;
4.3, if the predicted value is smaller than the set threshold value, judging that the coding unit of the next depth is not divided, and further skipping the judgment of whether the sub coding units are divided or not;
4.4, according to the division results of the coding units under different depths, the division prediction of the coding units is completed.
Compared with the prior art, the invention has the beneficial effects that:
1. aiming at the characteristic of strong time correlation of video information, the invention designs and counts the correlation of the current coding unit division depth and the coding unit division depth at the same position of the previous frame, and proves that the time correlation of the video information is still applicable in the coding unit division process.
2. The invention designs a corresponding data preprocessing module according to the pre-coding technology in the reference code rate control technology aiming at the characteristic that the coding information in the inter-frame coding process is inter-frame residual information, and obtains the prediction mode and the inter-frame residual information of the current coding unit without introducing excessive calculation complexity.
3. According to the invention, the LSTM structure is introduced into the network design process, so that the time sequence prediction capability of the network is enhanced.
4. The invention guides the shallow CU division by using the deep CU division information, and realizes the end-to-end prediction of the inter-frame CU division structure by using the convolutional neural network; from the experimental results of the present invention, the coding complexity was reduced by 63.32% on average over the standard test sequence, demonstrating the effectiveness of the present invention. In addition, compared with other methods, the method provided by the invention is a CU partition structure prediction model utilizing video time correlation, and can effectively reduce the calculation complexity of the HEVC inter-frame coding process on the premise of ensuring the coding quality.
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.
Fig. 1 is an overall flowchart of the HEVC inter-frame fast encoding method based on long and short time memory networks of the present invention.
FIG. 2 is a schematic diagram of a data preprocessing process according to the present invention.
Fig. 3 is a schematic diagram of an INTER-frame fast coding model INTER-LSTM architecture based on a long short time memory network (LSTM) in the present invention.
Fig. 4 is a schematic diagram of CU partitioning decisions in the present invention.
Fig. 5 is an algorithm flow chart of a fast coding method between HEVC frames based on long and short time memory network provided by the invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. Of course, the specific embodiments described herein are for purposes of illustration only and are not intended to limit the invention.
Referring to fig. 1 and 5, the present embodiment provides a method for fast encoding between HEVC frames based on long-short-time memory network, comprising the following steps:
1. designing a data preprocessing module;
2. constructing an inter-frame rapid coding model based on a long-short-time memory network;
3. and guiding the division of the shallow coding units by using the deep coding unit division information.
Specifically, referring to fig. 2, in step 1, a data preprocessing module is designed, which specifically includes the following steps:
1) Setting the minimum size into which a Coding Unit (CU) and a Prediction Unit (PU) can be divided to 64×64;
2) And acquiring the coding mode of the coding unit to be coded and residual information of inter-frame coding.
Specifically, referring to fig. 3, in step 2, an inter-frame fast coding model based on a long-short-time memory network is constructed, and the method specifically includes the following steps:
1) Constructing an INTER-LSTM model consisting of three modules, namely a forward information extraction module, an LSTM time sequence feature integration module and a feature prediction module based on a feature transfer mechanism;
2) Performing global dimension reduction on the data by using a generalized feature extraction module in the forward information extraction module;
3) The method comprises the steps that a multidimensional feature extraction module and a depth difference feature extraction module in a forward information extraction module are utilized to further extract partition features of CUs with 3 depths;
4) Sending the CU partition features extracted by the depth difference feature extraction module into different LSTM structures according to the depth difference to obtain feature expressions at different depths;
5) And guiding the dividing process of the low-depth CU by utilizing the high-depth CU dividing characteristics to obtain the characteristic vector predicted value of the coding unit dividing characteristics.
Specifically, referring to fig. 4, in step 3, the partitioning of the shallow coding unit is guided by using the deep coding unit partitioning information, and specifically includes the following steps:
1) Comparing the predicted value of the INTER-LSTM model with a threshold value of 0.5;
2) If the predicted value is greater than or equal to the threshold value of 0.5, the coding unit of the next depth is judged to be divided;
3) If the predicted value is smaller than the threshold value of 0.5, the coding unit of the next depth is judged to be not divided, and then the judgment of whether the sub coding units are divided or not is skipped;
4) And according to the division results of the coding unit under different depths, finishing the division prediction of the coding unit.
To examine the performance of the proposed method of this example, the method of this example was compared with the original method. The experimental platform adopts HM-16.5, the test sequence is 5 types (A, B, C, D, E) given by JCT-VC, 10 standard sequences under different resolutions, and the rate distortion performance of BD-BR and BD-PSNR evaluation algorithms is adopted; wherein, BDBR shows the code rate saving condition of the two methods under the same objective quality, and BD-PSNR shows the difference of the brightness peak signal-to-noise ratio of the two methods under the given equal code rate.
Table 1 shows the performance and the degree of reduction in coding complexity of the proposed method for this example at different QP values on the HEVC standard test sequence. At QP values of 22, 27, 32, 37, the present example suggests that the method reduces the coding complexity by 52.34%,63.55%,66.96% and 70.43%, respectively, on average.
Table 1 presents a comparison of the process and HM-16.5
As shown in table 1, the method of this embodiment can not only save 63.32% of coding time on average on the HEVC standard test sequence, but also maintain good rate-distortion performance, with an average increase in BDBR of 2.132% and an average decrease in BD-PSNR of 0.066dB.
Example 2
To further examine the performance of the proposed method of this example, the method of this example was also compared to reference [1]Mallikarachchi T,Talagala D S,Arachchi H K,et al.Content-Adaptive Feature-Based CU Size Prediction for Fast Low-Delay Video Encoding in HEVC [ J ]. IEEE Transactions on Circuits & Systems for Video Technology,2018,28 (99): 693-705 ].
Table 2 shows the results of the comparison of the proposed method of this example with reference [1 ].
Table 2 presents a comparison of the method and reference [1]
As shown in table 2, the method of the present embodiment maintains better rate-distortion performance with more coding time saved compared to reference [1 ]. BD-PSNR increased by 0.055dB and BDBR decreased by 1.893%.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (4)
1. The HEVC inter-frame rapid coding method based on the long-short-time memory network is characterized by comprising the following steps of:
s1, designing a data preprocessing module;
s2, constructing an inter-frame rapid coding model based on a long-short-time memory network;
s3, the division information of the deep coding units is used for guiding the division of the shallow coding units.
2. The method for fast encoding HEVC interframe based on long and short time memory network according to claim 1, wherein said step S1 specifically comprises the steps of:
s11, setting the minimum partitionable size of the coding unit and the prediction unit;
s12, obtaining the coding mode of the unit to be coded and residual information of inter-frame coding.
3. The method for fast encoding HEVC interframe based on long and short time memory network according to claim 1, wherein said step S2 specifically comprises the steps of:
s21, constructing an inter-frame rapid coding model consisting of three modules, namely a forward information extraction module, a time sequence feature integration module of a long-short-time memory network and a feature prediction module based on a feature transfer mechanism;
s22, performing global dimension reduction on the data by using a generalized characteristic extraction module in the forward information extraction module;
s23, dividing feature extraction is carried out on the coding units under different depths by utilizing a multidimensional feature extraction module and a depth difference feature extraction module in the forward information extraction module;
s24, sending the coding unit division features extracted by the depth difference feature extraction module into different long and short time memory network structures according to the depth difference to obtain feature expressions at different depths;
s25, guiding the dividing process of the low-depth coding unit by using the coding unit dividing characteristics of the high depth to obtain the characteristic vector predicted value of the coding unit dividing characteristics.
4. The method for fast encoding HEVC interframe based on long and short time memory network according to claim 1, wherein said step S3 specifically comprises the steps of:
s31, comparing a predicted value of the inter-frame rapid coding model with a set threshold value;
s32, if the predicted value is greater than or equal to a set threshold value, the coding unit of the next depth is judged to be divided;
s33, if the predicted value is smaller than the set threshold value, the coding unit of the next depth is judged to be not divided, and then judgment of whether the sub coding units are divided or not is skipped;
s34, according to the division results of the coding units under different depths, the division prediction of the coding units is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310894112.5A CN117319679A (en) | 2023-07-20 | 2023-07-20 | HEVC (high efficiency video coding) inter-frame rapid coding method based on long-short-time memory network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310894112.5A CN117319679A (en) | 2023-07-20 | 2023-07-20 | HEVC (high efficiency video coding) inter-frame rapid coding method based on long-short-time memory network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117319679A true CN117319679A (en) | 2023-12-29 |
Family
ID=89280039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310894112.5A Pending CN117319679A (en) | 2023-07-20 | 2023-07-20 | HEVC (high efficiency video coding) inter-frame rapid coding method based on long-short-time memory network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117319679A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108495129A (en) * | 2018-03-22 | 2018-09-04 | 北京航空航天大学 | The complexity optimized method and device of block partition encoding based on deep learning method |
| CN110087087A (en) * | 2019-04-09 | 2019-08-02 | 同济大学 | VVC interframe encode unit prediction mode shifts to an earlier date decision and block divides and shifts to an earlier date terminating method |
| CN115484464A (en) * | 2022-08-03 | 2022-12-16 | 阿里巴巴（中国）有限公司 | Video coding method and device |
-
2023
- 2023-07-20 CN CN202310894112.5A patent/CN117319679A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108495129A (en) * | 2018-03-22 | 2018-09-04 | 北京航空航天大学 | The complexity optimized method and device of block partition encoding based on deep learning method |
| CN110087087A (en) * | 2019-04-09 | 2019-08-02 | 同济大学 | VVC interframe encode unit prediction mode shifts to an earlier date decision and block divides and shifts to an earlier date terminating method |
| CN115484464A (en) * | 2022-08-03 | 2022-12-16 | 阿里巴巴（中国）有限公司 | Video coding method and device |
Non-Patent Citations (3)
| Title |
|---|
| BOUAAFIA S等: "CNN-LSTM Learning Approach-Based Complexity Reduction for High-Efficiency Video Coding Standard", SCIENTIFIC PROGRAMMING 2021(2021):10, 31 March 2021 (2021-03-31), pages 1 - 9 * |
| MAI XU等: "Reducing Complexity of HEVC: A Deep Learning Approach", IEEE TRANSACTIONS ON IMAGE PROCESSING ( VOLUME: 27, ISSUE: 10, OCTOBER 2018), 13 June 2018 (2018-06-13), pages 1 - 14 * |
| 贾克斌等: "基于深层特征学习的高效率视频编码中帧内快速预测算法", 电子与信息学报, 2021, 43(7):9, 5 January 2021 (2021-01-05), pages 2023 - 2030 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110087087B (en) | VVC inter-frame coding unit prediction mode early decision and block division early termination method | |
| Hu et al. | Coarse-to-fine deep video coding with hyperprior-guided mode prediction | |
| CN103248893B (en) | From H.264/AVC standard to code-transferring method and transcoder thereof the fast frame of HEVC standard | |
| CN106961610B (en) | Novel super-high-definition video compression framework combined with super-resolution reconstruction | |
| Shen et al. | Ultra fast H. 264/AVC to HEVC transcoder | |
| CN108347612B (en) | Monitoring video compression and reconstruction method based on visual attention mechanism | |
| CN101600109A (en) | H.264 downsizing transcoding method based on texture and motion feature | |
| CN102595132A (en) | Distributed video encoding and decoding method applied to wireless sensor network | |
| CN1194544C (en) | Video encoding method based on prediction time and space domain conerent movement vectors | |
| CN110351552B (en) | Fast coding method in video coding | |
| CN114885172A (en) | Fast coding unit dividing method for H.266/VVC intra-frame prediction coding | |
| CN114913250A (en) | Video coding and decoding system and method based on semantic segmentation and Hungarian algorithm | |
| Ma et al. | The second generation IEEE 1857 video coding standard | |
| CN110913232B (en) | Selection method and device of TU division mode and readable storage medium | |
| Liu et al. | Research and Optimization of Low-Complexity Motion Estimation Method Based on Visual Perception. | |
| CN102595137B (en) | Fast mode judging device and method based on image pixel block row/column pipelining | |
| CN116489333A (en) | Edge classification model construction method for depth map coding unit division | |
| CN101557519A (en) | Multi-view video coding method | |
| CN114827616B (en) | Compressed video quality enhancement method based on space-time information balance | |
| CN100586185C (en) | Mode selection method for transcoding 264 video to reduce resolving capability | |
| Wang et al. | A low complexity compressed sensing-based codec for consumer depth video sensors | |
| CN117319679A (en) | HEVC (high efficiency video coding) inter-frame rapid coding method based on long-short-time memory network | |
| CN110460842B (en) | Integrated imaging rapid coding method | |
| CN115002482A (en) | End-to-end video compression method and system using structural preservation motion estimation | |
| CN111212292B (en) | H.266-based adaptive CU partitioning and skip mode method |
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 |