A fast algorithm of intra prediction modes pruning for HEVC based on decision trees and a new three-step search

Zhu, Shiping; Zhang, Chunyan

doi:10.1007/s11042-016-4056-0

Cited by 19 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To testify the coding effectiveness of the proposed fast CU size decision algorithms, we select five state-of-the-art algorithms including one algorithm DDET [32] based on traditional analysis, and three machine learning algorithms, FADT [33], FARF [34] and DA-SVM [17], for the comparison of performance. Specifically for machine learning methods employed in these three algorithms, FADT uses decision tree, FARF is based on random forest, and DA-SVM uses SVM.…”

Section: Comparison With State-of-the-artmentioning

confidence: 99%

Bagged Tree Based Frame-Wise Beforehand Prediction Approach for HEVC Intra-Coding Unit Partitioning

Peng

et al. 2020

Electronics

View full text Add to dashboard Cite

High Efficiency Video Coding (HEVC) has achieved about 50% bit-rates saving compared with its predecessor H.264 standard, while the encoding complexity increases dramatically. Due to the introduction of more flexible partition structures and more optional prediction directions, HEVC takes a brute force approach to find the optimal partitioning result which is much more time consuming. Therefore, this paper proposes a bagged trees based fast approach (BTFA) and focuses on the coding unit (CU) size decision for HEVC intra-coding. First, several key features of a target CU are extracted for three-output classifiers. Then, to avoid feature extraction and prediction time over head, our approach is designed frame-wisely, and the procedure is applied parallel with the encoding process. Using the adaptive threshold determination algorithm, our approach achieves 42.04% time saving with negligible 0.92% Bit-Distortion (BD)-rate loss. Furthermore, in order to calculate the optimal thresholds to balance BD-rate loss and complexity reduction, the neural network based mathematical fitting is added to BTFA, which is called the advanced bagged trees based fast approach (ABTFA). Finally, experimental results show that ABTFA achieves 47.87% time saving with only 0.96% BD-rate loss, which outperforms other state-of-the-art approaches.

show abstract

Section: Comparison With State-of-the-artmentioning

confidence: 99%

Bagged Tree Based Frame-Wise Beforehand Prediction Approach for HEVC Intra-Coding Unit Partitioning

Peng

et al. 2020

Electronics

View full text Add to dashboard Cite

show abstract

“…In addition to the widely adopted SVM and NN based approaches, several other machine learning techniques have been utilized to develop fast encoding algorithms for HEVC. For example, logistic regression [15], decision trees [16], [17], random forest [18], and Bayesian classification [19] are some of the state-of-the-art learning based approaches that have been considered in the literature for reducing HEVC's encoding complexity.…”

Section: Other Machine Learning Based Approachesmentioning

confidence: 99%

Machine Learning Approaches for Intra-Prediction in HEVC

Erabadda

Mallikarachchi

Kulupana

et al. 2018

2018 IEEE 7th Global Conference on Consumer Electronics (GCCE)

View full text Add to dashboard Cite

The use of machine learning techniques for encoding complexity reduction in recent video coding standards such as High Efficiency Video Coding (HEVC) has received prominent attention in the recent past. Yet, the dynamically changing nature of the video contents makes it evermore challenging to use rigid traditional inference models for predicting the encoding decisions for a given content. In this context, this paper investigates the resulting implications on the coding efficiency and the encoding complexity, when using offline trained and online trained machine-learning models for coding unit size selection in the HEVC intra-prediction. The experimental results demonstrate that the ground truth encoding statistics of the content being encoded, is crucial to the efficient encoding decision prediction when using machine learning based prediction models.

show abstract

“…the motion vector and parameters , s o of fractal iterative function system, as shown in Fig.1. The searching of matched block is the most key and time-consuming step [16][17][18]. Between the neighboring coding blocks exists a certain correlation, and their motion vectors also mutually have certain dependence.…”

Section: Fractal-based Interframe Prediction Algorithmmentioning

confidence: 99%

Fractal Coding based Optimization Algorithm for Interframe Prediction of High-definition Video

Liu¹

2018

Proceedings of the 2018 8th International Conference on Management, Education and Information (MEICI 2018)

View full text Add to dashboard Cite

A fractal coding based interframe prediction algorithm is proposed, to hugely reduce the calculation amount of interframe prediction and raise the coding velocity. The complexity of interframe prediction algorithm is the motion search. The interframe prediction in HEVC needs to find out the best matched block for each image block of each division mode of the current frame in the reference frame. The defining of the reference frame is also very complex, especially for the frame of bidirectional prediction, its reference frame needs to be defined on two directions, and then the best matched image block for the current image block in the reference frame is to be further defined. To cope this high complexity of interframe prediction, we make some improvements on the part of motion search for the interframe prediction by introducing the fractal idea to match the image block to realize more rapid matching of image block. The experimental result shows that the coding efficiency of fractal coding-based interframe prediction algorithm averagely improves by 7.86%, the peak SNR averagely reduces 0.164 dB and the coding time averagely reduces by 22.37%. The proposed algorithm can significantly raise the coding velocity and cut the coding time hardly with any influence on the coding quality.2) Equidistant transformation: Some equidistance transformations can be made for D blocks to make D blocks more approximate R blocks [1].3) Error measurement: Measure the error MSE for matching D blocks and R blocks, then the PSNR   Peak signal to noise ratio measuring the quality of coded image can be calculated according to MSE [11,12].

show abstract

A fast algorithm of intra prediction modes pruning for HEVC based on decision trees and a new three-step search

Cited by 19 publications

References 24 publications

Bagged Tree Based Frame-Wise Beforehand Prediction Approach for HEVC Intra-Coding Unit Partitioning

Bagged Tree Based Frame-Wise Beforehand Prediction Approach for HEVC Intra-Coding Unit Partitioning

Machine Learning Approaches for Intra-Prediction in HEVC

Fractal Coding based Optimization Algorithm for Interframe Prediction of High-definition Video

Contact Info

Product

Resources

About