Fast CU Split Decisions for HEVC Inter Coding Using Support Vector Machines

Heindel A, Haubner T, Kaup A (2016)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2016

Event location: Nuremberg DE

ISBN: 978-1-5090-5966-9

DOI: 10.1109/PCS.2016.7906358

Abstract

High Efficiency Video Coding (HEVC) is known to be the state of the art in video compression. However, aiming at real-time applications, its very high number of possible coding options makes it necessary to approximate the selection of coding modes by fast algorithms. For this purpose Coding Unit (CU) split decisions are made by Support Vector Machine (SVM) classifiers in this paper. We use one SVM model per depth and the traditional Rate-Distortion Optimization (RDO) is used as fallback method in the case of uncertain SVM decisions. Regarding the sequence classes ClassB to ClassE, the proposed algorithm achieves encoding time reductions of more than 60%, accompanied by only 1.8% additional bitrate (lowdelay main configuration). Considering all sequence classes from ClassA to ClassF, the additional bitrate increases to 4% for the lowdelay main and about 3% for the randomaccess main configuration, with a similar encoding time reduction of more than 60%.

Authors with CRIS profile

How to cite

APA:

Heindel, A., Haubner, T., & Kaup, A. (2016). Fast CU Split Decisions for HEVC Inter Coding Using Support Vector Machines. In Proceedings of the Picture Coding Symposium (PCS). Nuremberg, DE.

MLA:

Heindel, Andreas, Thomas Haubner, and André Kaup. "Fast CU Split Decisions for HEVC Inter Coding Using Support Vector Machines." Proceedings of the Picture Coding Symposium (PCS), Nuremberg 2016.

BibTeX: Download