Projects per year
This work addresses the problem of predicting the compression efficiency of a video codec solely from features extracted from uncompressed content. Towards this goal, we have used a database of videos of homogeneous texture and extracted both spatial and frequency domain features. The videos are encoded using High Efficiency Video Coding (HEVC) reference codec at different quantization scales and their Rate-Distortion (RD) curves are modelled using linear regression. Using the extracted features and the fitted parameters of the RD model, a Support Vector Regression Model (SVRM) is trained to learn the relationship of the textural features with the RD curves. The SVRM is tested using iterative five-fold cross-validation. The presented experimental results demonstrate that RD curve characteristics can be predicted based on the textural features of the uncompressed videos, which offers potential benefits for encoder optimization.
|Title of host publication||Picture Coding Symposium (PCS), 2016|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Number of pages||5|
|Publication status||Published - 24 Apr 2017|
- Feature extraction
- Bit rate
- Video sequences
FingerprintDive into the research topics of 'Predicting video rate-distortion curves using textural features'. Together they form a unique fingerprint.
25 Jun 2019
Student thesis: Doctoral Thesis › Doctor of Philosophy (PhD)File