Classification-based early termination for coding tree structure decision in HEVC

Correa, Guilherme; Assunção, Pedro; Cruz, Luis A. da Silva; Agostini, Luciano

http://hdl.handle.net/10400.8/13559

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Classification-based early termination for coding tree structure decision in HEVC.pdf	The High Efficiency Video Coding (HEVC) standard provides improved compression rates in comparison to its predecessors at the cost of large increases in computational complexity. An important share of such increases is due to the introduction of flexible Coding Tree structures, which best configuration is decided through exhaustive tests in a Rate-Distortion Optimization (RDO) scheme. In this work, an early termination method for the decision of such structures was designed using classification trees obtained through Data Mining techniques. The classification trees were trained using intermediate encoding results from a training set of video sequences and implemented in the encoder to skip the full RDO-based decision. An average reduction of 37% in the HEVC encoder computational complexity was achieved when using the designed classification trees, with a negligible cost of only 0.28% in terms of Bjontegaard Delta-rate increase.	548.88 KB	Adobe PDF	Download

Send Feedback

Authors

Correa, Guilherme

Assunção, Pedro

Cruz, Luis A. da Silva

Agostini, Luciano

Abstract(s)

The High Efficiency Video Coding (HEVC) standard provides improved compression rates in comparison to its predecessors at the cost of large increases in computational complexity. An important share of such increases is due to the introduction of flexible Coding Tree structures, which best configuration is decided through exhaustive tests in a Rate-Distortion Optimization (RDO) scheme. In this work, an early termination method for the decision of such structures was designed using classification trees obtained through Data Mining techniques. The classification trees were trained using intermediate encoding results from a training set of video sequences and implemented in the encoder to skip the full RDO-based decision. An average reduction of 37% in the HEVC encoder computational complexity was achieved when using the designed classification trees, with a negligible cost of only 0.28% in terms of Bjontegaard Delta-rate increase.

Description

EISBN - 978-147994242-8

Keywords

early termination classification trees data mining computational complexity high efficiency video coding (HEVC)

URI

http://hdl.handle.net/10400.8/13559

Citation

Correa, G., Assuncao, P., da Silva Cruz, L. A., & Agostini, L. (2014, December). Classification-based early termination for coding tree structure decision in HEVC. In 2014 21st IEEE International Conference on Electronics, Circuits and Systems (ICECS) (pp. 239-242). IEEE. DOI: https://doi.org/10.1109/icecs.2014.7049966.