CN102148996A - Method for deciding prediction mode of intra-frame macro block - Google Patents
Method for deciding prediction mode of intra-frame macro block Download PDFInfo
- Publication number
- CN102148996A CN102148996A CN 201010106522 CN201010106522A CN102148996A CN 102148996 A CN102148996 A CN 102148996A CN 201010106522 CN201010106522 CN 201010106522 CN 201010106522 A CN201010106522 A CN 201010106522A CN 102148996 A CN102148996 A CN 102148996A
- Authority
- CN
- China
- Prior art keywords
- frame
- macro block
- intra
- predictive mode
- pixel distribution
- 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
Images
Landscapes
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention relates to an algorithm for deciding a prediction mode of an intra-frame macro block. In the algorithm, the decision of the prediction mode is simplified by using a machine learning technique. Because an optimal mode is decided from all calculated modes when H.264/AVC is used for macro block prediction, the defect of high calculation complexity is caused, and the H.264/AVC is not in favor of equipment which has resource stress, such as mobile equipment and the like. The machine learning technique is used in the algorithm, and modes which are not used in decision are not calculated, thereby shortening calculation range and reducing calculation overhead.
Description
Technical field
The present invention relates to field of video encoding, particularly a kind of intra-frame macro block predictive mode decision algorithm.
Background technology
H.264/AVC as the up-to-date video standard of ITU and MPEG joint development, obtained very big raising than traditional video standard.H.264 the lifting of compression efficiency is depended on to a great extent and is had the numerous coding modes that can select for use.In order to make full use of the advantage of various patterns, select optimal mode, utilization rate distortion optimization technology RDO H.264 judges optimal mode after calculating all patterns.The great like this computation complexity that increased.For the equipment of resource anxiety, only select a feasible coding mode subclass usually, thereby abandoned a lot of complexity pattern efficiently, sacrificed video quality.
And the focus of current artificial intelligence is machine learning, also cries data mining.That data mining extracts from lot of data is potential, do not show well known useful information, pattern and trend, and then reorganizes the technology that the existing structure of knowledge makes it constantly to improve the performance of self.It is the core of artificial intelligence.The wherein famous C4.5 algorithm (Quinlan J.R., " C4.5:Programs for Machine Learning ", MorganKaufman Publishers Inc., San Francisco, CA, 1993) that has commonly used.The C4.5 algorithm has the classifying rules easy to understand of generation, accuracy rate advantage of higher.
Summary of the invention
This is to realize by following steps from intra-frame macro block predictive mode decision algorithm purpose:
1. set up decision tree according to table 1:
| Node ID | The macro block | Model selection | |
| 1 | In the frame | 4x4 in the 16x16 VS frame in the frame | |
| 2 | 16x16 in the frame | The non-DC of |
|
| 3 | 16x16 in the frame | Plane pattern VS hor, the |
|
| 4 | 16x16 in the frame | Ver pattern |
|
| 5 | 4x4 in the frame | The non-DC of |
|
| 6 | 4x4 in the frame | ?0，3，5，7?VS?1，4，6，8 | |
| 7 | 4x4 in the frame | ?0，5?VS?3，7 | |
| 8 | 4x4 in the frame | ?1，6?VS?4，8 | |
| 9 | 4x4 in the frame | ?0?VS?5 |
| 10 | 4x4 in the frame | ?3?VS?7 |
| 11 | 4x4 in the frame | ?1?VS?6 |
| 12 | 4x4 in the frame | ?4?VS?8 |
Table 1
2. determine input attributes: the pixel distribution of current macro, the pixel distribution of current sub-macro block, current macro is left and right, the pixel distribution of upper and lower macro block, and current sub-macro block is left and right, the pixel distribution of upper and lower sub-macro block.
3. carry out the training process of machine learning.
With input attributes and H.264 encoder macro block mode and predictive mode be input to together in the J48 calculation body of C4.5 and train, as shown in Figure 2.
4. training process finishes just can use normally machine learning to carry out the predictive mode selection, as shown in Figure 3.
Description of drawings
Do some explanations below in conjunction with accompanying drawing.
Fig. 1. intra-frame macro block coding decision tree.
Fig. 2. decision tree is set up figure.
Fig. 3. training process finishes back model selection flow chart.
Specific implementation process
To intra-frame macro block predictive mode decision algorithm, concrete implementation step is described below:
1. set up decision tree according to table 1.
2. determine input attributes: the pixel distribution of current macro, the pixel distribution of current sub-macro block, current macro is left and right, the pixel distribution of upper and lower macro block, and current sub-macro block is left and right, the pixel distribution of upper and lower sub-macro block.
3. carry out the training process of machine learning.
With input attributes with H.264 encoder macro block mode and predictive mode are input to together in the J48 calculation body of C4.5 and train.
4. training process finishes just can use normally machine learning to carry out the predictive mode selection.
Claims (3)
1. an intra-frame macro block predictive mode decision algorithm is characterized in that, comprises the steps:
1) sets up decision tree.
2) determine input attributes.
3) carry out the training process of machine learning.
4) training process finishes to use machine learning to carry out the predictive mode selection.
2. intra-frame macro block predictive mode decision algorithm as claimed in claim 1 is characterized in that intra-frame macro block coding decision tree in the described step 1):
3. intra-frame macro block predictive mode decision algorithm as claimed in claim 1 is characterized in that determining in the described step 3) input attributes:
The pixel distribution of current macro, the pixel distribution of current sub-macro block, current macro is left and right, the pixel distribution of upper and lower macro block, and current sub-macro block is left and right, the pixel distribution of upper and lower sub-macro block.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010106522 CN102148996A (en) | 2010-02-04 | 2010-02-04 | Method for deciding prediction mode of intra-frame macro block |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010106522 CN102148996A (en) | 2010-02-04 | 2010-02-04 | Method for deciding prediction mode of intra-frame macro block |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102148996A true CN102148996A (en) | 2011-08-10 |
Family
ID=44422956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010106522 Pending CN102148996A (en) | 2010-02-04 | 2010-02-04 | Method for deciding prediction mode of intra-frame macro block |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102148996A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015070775A1 (en) * | 2013-11-15 | 2015-05-21 | Mediatek Inc. | Method and apparatus for performing block prediction search based on restored sample values derived from stored sample values in data buffer |
| US10499069B2 (en) | 2015-02-19 | 2019-12-03 | Magic Pony Technology Limited | Enhancing visual data using and augmenting model libraries |
| US10602163B2 (en) | 2016-05-06 | 2020-03-24 | Magic Pony Technology Limited | Encoder pre-analyser |
| US10666962B2 (en) | 2015-03-31 | 2020-05-26 | Magic Pony Technology Limited | Training end-to-end video processes |
| US10685264B2 (en) | 2016-04-12 | 2020-06-16 | Magic Pony Technology Limited | Visual data processing using energy networks |
| US10692185B2 (en) | 2016-03-18 | 2020-06-23 | Magic Pony Technology Limited | Generative methods of super resolution |
-
2010
- 2010-02-04 CN CN 201010106522 patent/CN102148996A/en active Pending
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015070775A1 (en) * | 2013-11-15 | 2015-05-21 | Mediatek Inc. | Method and apparatus for performing block prediction search based on restored sample values derived from stored sample values in data buffer |
| CN105745927A (en) * | 2013-11-15 | 2016-07-06 | 联发科技股份有限公司 | Method and apparatus for performing block prediction search based on restored sample values derived from stored sample values in data buffer |
| CN105745927B (en) * | 2013-11-15 | 2019-03-26 | 联发科技股份有限公司 | The method and apparatus searched based on the recovery sample value perfoming block prediction that stored samples value derives from from data buffer |
| US10715813B2 (en) | 2013-11-15 | 2020-07-14 | Mediatek Inc. | Method and apparatus for performing block prediction search based on restored sample values derived from stored sample values in data buffer |
| US10516890B2 (en) | 2015-02-19 | 2019-12-24 | Magic Pony Technology Limited | Accelerating machine optimisation processes |
| US10523955B2 (en) | 2015-02-19 | 2019-12-31 | Magic Pony Technology Limited | Enhancement of visual data |
| US10547858B2 (en) | 2015-02-19 | 2020-01-28 | Magic Pony Technology Limited | Visual processing using temporal and spatial interpolation |
| US10582205B2 (en) | 2015-02-19 | 2020-03-03 | Magic Pony Technology Limited | Enhancing visual data using strided convolutions |
| US11528492B2 (en) | 2015-02-19 | 2022-12-13 | Twitter, Inc. | Machine learning for visual processing |
| US10623756B2 (en) | 2015-02-19 | 2020-04-14 | Magic Pony Technology Limited | Interpolating visual data |
| US10630996B2 (en) | 2015-02-19 | 2020-04-21 | Magic Pony Technology Limited | Visual processing using temporal and spatial interpolation |
| US10904541B2 (en) | 2015-02-19 | 2021-01-26 | Magic Pony Technology Limited | Offline training of hierarchical algorithms |
| US10499069B2 (en) | 2015-02-19 | 2019-12-03 | Magic Pony Technology Limited | Enhancing visual data using and augmenting model libraries |
| US10887613B2 (en) | 2015-02-19 | 2021-01-05 | Magic Pony Technology Limited | Visual processing using sub-pixel convolutions |
| US10666962B2 (en) | 2015-03-31 | 2020-05-26 | Magic Pony Technology Limited | Training end-to-end video processes |
| US10692185B2 (en) | 2016-03-18 | 2020-06-23 | Magic Pony Technology Limited | Generative methods of super resolution |
| US10685264B2 (en) | 2016-04-12 | 2020-06-16 | Magic Pony Technology Limited | Visual data processing using energy networks |
| US10602163B2 (en) | 2016-05-06 | 2020-03-24 | Magic Pony Technology Limited | Encoder pre-analyser |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102148996A (en) | Method for deciding prediction mode of intra-frame macro block | |
| CN103763570B (en) | Rapid HEVC intra-frame prediction method based on SATD | |
| CN104038764B (en) | A kind of H.264 arrive video transcoding method H.265 and transcoder | |
| CN104333756B (en) | HEVC predictive mode fast selecting methods based on relativity of time domain | |
| CN100574447C (en) | Fast intraframe predicting mode selecting method based on the AVS video coding | |
| CN104394409B (en) | HEVC predictive mode fast selecting methods based on spatial correlation | |
| CN107566846A (en) | Video coding skip mode decision-making technique, device, equipment and storage medium | |
| CN100553335C (en) | Macro-block level bit rate control method in a kind of video code conversion | |
| CN101022555B (en) | Interframe predictive coding mode quick selecting method | |
| CN101170688A (en) | A quick selection method for macro block mode | |
| CN106604035B (en) | A method of the estimation for Video coding and compression | |
| CN103533359A (en) | H.264 code rate control method | |
| CN103796023A (en) | H.265/HEVC transcoding method and transcoder based on H.264/AVC macro block structure and texture | |
| WO2018120797A1 (en) | Intra-frame prediction method for inter-frame prediction frame | |
| CN101304529A (en) | Method and device for selecting macro block pattern | |
| CN108174204A (en) | A kind of interframe fast schema selection method based on decision tree | |
| CN103888770B (en) | A kind of video code conversion system efficiently and adaptively based on data mining | |
| CN103596003B (en) | Interframe predication quick mode selecting method for high-performance video coding | |
| CN104581152A (en) | HEVC intra-frame prediction mode decision accelerating method | |
| CN103702122A (en) | Coding mode selection method, device and coder | |
| CN101867818B (en) | Selection method and device of macroblock mode | |
| CN101895761B (en) | Quick intraframe prediction algorithm | |
| WO2018076827A1 (en) | Code rate estimation method for intra-frame coding in video coding | |
| CN101883275B (en) | Video coding method | |
| CN100558169C (en) | The fast selecting method of inter-frame mode in the video code conversion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| ASS | Succession or assignment of patent right |
Owner name: CHENGDU BOSHENG INFORMATION TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: CHENGDU SHIJIA ELECTRONIC INDUSTRIAL CO., LTD. Effective date: 20120620 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 610041 CHENGDU, SICHUAN PROVINCE TO: 610000 CHENGDU, SICHUAN PROVINCE |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20120620 Address after: 610000 Chengdu Province, high tech Zone, North Road, No. 19 Applicant after: Chengdu Bosheng Information Technology Co., Ltd. Address before: 610041, nine Avenue, Wuhou District, Sichuan, Chengdu Applicant before: Chengdu Shijia Electronics industrial Co., Ltd. |
|
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110810 |