Early Skip Mode Decision for HEVC Encoder With Emphasis on Coding Quality

Lee, Hoyoung; Shim, Huik Jae; Park, Younghyeon

doi:10.1109/tbc.2015.2419172

Cited by 34 publications

(10 citation statements)

References 19 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Same authors adapt this principle to speedup the coding of motion sequences in [17] by using a motion compensated area as reference in previously encoded frame (instead of co-located area) and by using depths of spatial neighboring CTUs. In [18], a thresholding process applied on RD cost of M × M merge mode determines if the skip mode shall be used for the PU. These techniques [15] [17] [18] reduce the encoding complexity between 30% and 50% with a BD-BR increase in the range 0.4% to 1.4%.…”

Section: B Complexity Reduction Of Frame Partitioningmentioning

confidence: 99%

“…In [18], a thresholding process applied on RD cost of M × M merge mode determines if the skip mode shall be used for the PU. These techniques [15] [17] [18] reduce the encoding complexity between 30% and 50% with a BD-BR increase in the range 0.4% to 1.4%.…”

Section: B Complexity Reduction Of Frame Partitioningmentioning

confidence: 99%

“…Other techniques reduce the complexity of the encoding process by focusing on the partitioning scheme and testing a reduced number of partition configurations. In HEVC, to predict the most probable Quad Tree (QT) partitions, these techniques leverage intermediate encoding information [14]- [18], texture characteristics [19]- [21], motion divergence [22]- [24] or ML solutions [24]- [28]. More recently, some techniques have already investigated the complexity reduction of QTBT partitioning scheme [29]- [34].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tunable VVC Frame Partitioning Based on Lightweight Machine Learning

Amestoy

Mercat

Hamidouche

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Block partition structure is a critical module in video coding scheme to achieve significant gap of compression performance. Under the exploration of the future video coding standard, named Versatile Video Coding (VVC), a new Quad Tree Binary Tree (QTBT) block partition structure has been introduced. In addition to the QT block partitioning defined in High Efficiency Video Coding (HEVC) standard, new horizontal and vertical BT partitions are enabled, which drastically increases the encoding time compared to HEVC. In this paper, we propose a lightweight and tunable QTBT partitioning scheme based on a Machine Learning (ML) approach. The proposed solution uses Random Forest classifiers to determine for each coding block the most probable partition modes. To minimize the encoding loss induced by misclassification, risk intervals for classifier decisions are introduced in the proposed solution. By varying the size of risk intervals, tunable trade-off between encoding complexity reduction and coding loss is achieved. The proposed solution implemented in the JEM-7.0 software offers encoding complexity reductions ranging from 30% to 70% in average for only 0.7% to 3.0% Bjøntegaard Delta Rate (BD-BR) increase in Random Access (RA) coding configuration, with very slight overhead induced by Random Forest. The proposed solution based on Random Forest classifiers is also efficient to reduce the complexity of the Multi-Type Tree (MTT) partitioning scheme under the VTM-5.0 software, with complexity reductions ranging from 25% to 61% in average for only 0.4% to 2.2% BD-BR increase.

show abstract

Section: B Complexity Reduction Of Frame Partitioningmentioning

confidence: 99%

Section: B Complexity Reduction Of Frame Partitioningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tunable VVC Frame Partitioning Based on Lightweight Machine Learning

Amestoy

Mercat

Hamidouche

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…The concept of the RD-cost-based fast mode decision is extended to the multiview video coding system [12][13]. [14][15][16] focus on the Merge modes to accelerate the coding process. Gweon et al [17] check the coded block flag (CBF) when a PU mode is performed.…”

Section: Related Workmentioning

confidence: 99%

Efficient CU and PU Decision Based on Motion Information for Interprediction of HEVC

Chen

Yeh

et al. 2018

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

High-efficiency video coding encoders provide great improvements in coding efficiency and can also support higher resolution and multiple coding tools. The new coding structures such as coding unit (CU) and prediction unit (PU) have helped a lot, but the computational complexity is much higher than those of previous standards. This paper proposes a fast algorithm combining with CU and PU early termination decisions to reduce computational demand. Based on the analytic results, we can set up an adaptive threshold that can be obtained for early termination. Meanwhile, we also develop an adaptive search range determination according to the motion vector (MV). Compared with HM 12.0, our proposed method achieves an approximate 57% time saving, whereas the average Bjøntegaard-Delta Bit-rate (BDBR) increase is only 0.43%. In addition, our fast algorithm outperforms the previous works in both coding speed and coding performance. Index Terms-Coding unit (CU), high-efficiency video coding (HEVC) encoder, motion vector, prediction unit (PU), rate-distortion cost. I. INTRODUCTIONH IGH-EFFICIENCY video coding (HEVC), also known as H.265, is the newest video compression standard finalized in 2013, and a potential successor of H.264/AVC, which is currently widely used. When compared to H.264, HEVC offers around double compression ratio at the same level of video quality, or substantially improved video quality at the same bitrate, and HEVC supports resolutions up to 8192 × 4320, which are

show abstract

“…According to the differential motion vector and coded block flag, an early determination of the prediction unit mode decision for HEVC was proposed in [ 20 ]. In [ 21 ], Lee et al proposed an early Skip mode decision for the HEVC encoder by utilizing the rate distortion characteristics of the Merge mode. By considering the motion activity and hierarchical depth correlation, Pan et al proposed an early Merge/Skip decision method for the low complexity HEVC encoder [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

Low Complexity HEVC Encoder for Visual Sensor Networks

Pan

Chen

Sun

2015

Sensors

View full text Add to dashboard Cite

Visual sensor networks (VSNs) can be widely applied in security surveillance, environmental monitoring, smart rooms, etc. However, with the increased number of camera nodes in VSNs, the volume of the visual information data increases significantly, which becomes a challenge for storage, processing and transmitting the visual data. The state-of-the-art video compression standard, high efficiency video coding (HEVC), can effectively compress the raw visual data, while the higher compression rate comes at the cost of heavy computational complexity. Hence, reducing the encoding complexity becomes vital for the HEVC encoder to be used in VSNs. In this paper, we propose a fast coding unit (CU) depth decision method to reduce the encoding complexity of the HEVC encoder for VSNs. Firstly, the content property of the CU is analyzed. Then, an early CU depth decision method and a low complexity distortion calculation method are proposed for the CUs with homogenous content. Experimental results show that the proposed method achieves 71.91% on average encoding time savings for the HEVC encoder for VSNs.

show abstract

Early Skip Mode Decision for HEVC Encoder With Emphasis on Coding Quality

Cited by 34 publications

References 19 publications

Tunable VVC Frame Partitioning Based on Lightweight Machine Learning

Tunable VVC Frame Partitioning Based on Lightweight Machine Learning

Efficient CU and PU Decision Based on Motion Information for Interprediction of HEVC

Low Complexity HEVC Encoder for Visual Sensor Networks

Contact Info

Product

Resources

About