View : 25 Download: 0
Machine Learning-Based Fast Angular Prediction Mode Decision Technique in Video Coding
- Machine Learning-Based Fast Angular Prediction Mode Decision Technique in Video Coding
- Ryu S.; Kang J.
- Ewha Authors
- SCOPUS Author ID
- Issue Date
- Journal Title
- IEEE Transactions on Image Processing
- vol. 27, no. 11, pp. 5525 - 5538
- Fast intra prediction; fast mode decision; HEVC test model (HM); HEVC/H265; joint exploration model (JEM); machine learning; random forest
- Institute of Electrical and Electronics Engineers Inc.
- SCI; SCIE; SCOPUS
- In this paper, we propose a machine learning-based fast intra-prediction mode decision algorithm, using random forest that is an ensemble model of randomized decision trees. The random forest is used to estimate an intra-prediction mode from a prediction unit and to reduce encoding time significantly by avoiding the intensive Rate-Distortion (R-D) optimization of a number of intra-prediction modes. To this aim, we develop a randomized tree model including parameterized split functions at nodes to learn directional block-based features. The feature uses only four pixels reflecting a directional property of a block, and, thus the evaluation is fast and efficient. To integrate the proposed technique into the conventional video coding standard frameworks, the intra-prediction mode derived from the proposed technique, called an inferred mode, is used to shrink the pool of the candidate modes before carrying out the R-D optimization. The proposed technique is implemented into the high efficiency video coding test model reference software of the state-of-the-art video coding standard and joint exploration model reference software, by integrating the random forest trained off-line into the codecs. Experimental results demonstrate that the proposed technique achieves significant encoding time reduction with only slight coding loss as compared with the reference software models. © 1992-2012 IEEE.
- Appears in Collections:
- 엘텍공과대학 > 전자공학과 > Journal papers
- Files in This Item:
There are no files associated with this item.
- RIS (EndNote)
- XLS (Excel)
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.