Complexity scalability for real-time HEVC encoders

Corrêa, Guilherme; Assunção, Pedro; Agostini, Luciano; Cruz, Luís A. da Silva

doi:10.1007/s11554-013-0392-8

Cited by 29 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rationale for considering using this attribute in the decision process is that there exists a correlation among maximum depths of spatially neighboring CTUs, as we have shown in [37]. The value of Neigh_Depth is calculated as follows.…”

Section: B Early Termination For Determining Coding Treesmentioning

confidence: 99%

Fast HEVC Encoding Decisions Using Data Mining

Corrêa

Assunção

Agostini

et al. 2015

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

168

View full text Add to dashboard Cite

 Abstract-The High Efficiency Video Coding (HEVC) standard provides improved compression ratio in comparison to its predecessors at the cost of large increases in the encoding computational complexity. An important share of this increase is due to the new flexible partitioning structures, namely the Coding Trees, the Prediction Units and the Residual Quadtrees, with the best configurations decided through an exhaustive RateDistortion Optimization (RDO) process. In this article we propose a set of procedures for deciding whether the partition structure optimization algorithm should be terminated early or run to the end of an exhaustive search for the best configuration. The proposed schemes are based on decision trees obtained through data mining techniques. By extracting intermediate data, such as encoding variables from a training set of video sequences, three sets of decision trees are built and implemented to avoid running the RDO algorithm to its full extent. When separately implemented, these schemes achieve average computational complexity reductions of up to 50% at a negligible cost of 0.56% in terms of Bjontegaard Delta (BD)-rate increase. When the schemes are jointly implemented, an average computational complexity reduction of up to 65% is achieved, with a small BDrate increase of 1.36%. Extensive experiments and comparisons with similar works demonstrate that the proposed early termination schemes achieve the best Rate-Distortion-Complexity trade-offs among all the compared works.Index Terms-Early termination, decision trees, data mining, computational complexity, high efficiency video coding (HEVC).

show abstract

Section: B Early Termination For Determining Coding Treesmentioning

confidence: 99%

Fast HEVC Encoding Decisions Using Data Mining

Corrêa

Assunção

Agostini

et al. 2015

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

168

View full text Add to dashboard Cite

show abstract

“…The rationale of considering such variable is that there exists a strong correlation among maximum depths of spatially and Fig. 3 Occurrence of a 64 9 64 CUs, b 32 9 32 CUs, and c 16 9 16 CUs split and not split into smaller CUs according to the PU mode chosen (i.e., Partition) Analog Integr Circ Sig Process temporally neighboring CTUs, as shown in [10]. The attribute DNeighDepth is calculated as follows.…”

Section: Selecting Attributes and Training Classification Treesmentioning

confidence: 99%

“…Some authors have recently proposed heuristics for simplifying the Coding Tree decision process, aiming at decreasing the computational complexity of HEVC [9][10][11][12][13]. However, even though these works succeed in their goal of decreasing the encoding complexity up to a certain extent, the majority of them come with associated non-negligible losses in terms of rate-distortion (R-D) efficiency.…”

Section: Introductionmentioning

confidence: 99%

Fast coding tree structure decision for HEVC based on classification trees

Corrêa

Assunção

Agostini

et al. 2016

Analog Integr Circ Sig Process

Self Cite

View full text Add to dashboard Cite

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 set of video sequences and implemented in the encoder to avoid 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.

show abstract

“…CODES/ISSS '17 Companion, Seoul, Republic of Korea on multiprocessor systems-on-chip (MPSoCs). Current research in the area is mostly focused on the optimization of one or several blocks of the encoding algorithm [4] shown in Figure 1. Each block contains several parameters to congure the encoder (i.e., conguration knobs), which aect encoding eciency, power consumption, temperature, and processing time.…”

Section: Introductionmentioning

confidence: 99%

A machine learning-based approach for power and thermal management of next-generation video coding on MPSoCs

Iranfar

Zapater

Atienza

2017

Proceedings of the Twelfth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis Companion

View full text Add to dashboard Cite

High Eciency Video Coding (HEVC) provides high eciency at the cost of increased computational complexity followed by increased power consumption and temperature of current MultiProcessor Systems-on-Chip (MPSoCs). In this paper, we propose a machine learning-based power and thermal management approach that dynamically learns the best encoder conguration and core frequency for each of the several video streams running in an MPSoC, using information from frame compression, quality, performance, total power and temperature. We implement our approach in an enterprise multicore server and compare it against state-of-the-art techniques. Our approach improves video quality and performance by 17% and 11%, respectively, while reducing average temperature by 12%, without degrading compression or increasing power.

show abstract

Complexity scalability for real-time HEVC encoders

Cited by 29 publications

References 19 publications

Fast HEVC Encoding Decisions Using Data Mining

Fast HEVC Encoding Decisions Using Data Mining

Fast coding tree structure decision for HEVC based on classification trees

A machine learning-based approach for power and thermal management of next-generation video coding on MPSoCs

Contact Info

Product

Resources

About