A Fast Intra Cu Size Decision Algorithm Based on Canny Operator and SVM Classifier

Sun, Chentian; Fan, Xiaopeng; Zhao, Debin

doi:10.1109/icip.2018.8451178

Cited by 16 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [12,13], the authors utilized CU texture characteristics and adjacent CU depth information to train a decision tree model to predict CU partition. Support Vector Machine (SVM) was used to classify CU partition or non-partition in HEVC in [14][15][16][17][18]. Specifically, Sun et al [14] improved the Canny edge algorithm to extract the edge points in CU and used the EPR as a feature to train the SVM classifier.…”

Section: Methods For Hevcmentioning

confidence: 99%

“…Support Vector Machine (SVM) was used to classify CU partition or non-partition in HEVC in [14][15][16][17][18]. Specifically, Sun et al [14] improved the Canny edge algorithm to extract the edge points in CU and used the EPR as a feature to train the SVM classifier. In [16], the authors introduced two fast partition models of offline training SVM and online training Bayesian probability, and the feature used to train the model is the gray-level co-occurrence matrix (GLCM).…”

Section: Methods For Hevcmentioning

confidence: 99%

See 1 more Smart Citation

SVM-Based Fast CU Partition Decision Algorithm for VVC Intra Coding

Zhao

Zhang

2022

Electronics

View full text Add to dashboard Cite

As a new coding standard, Versatile Video Coding (VVC) introduces the quad-tree plus multi-type tree (QTMT) partition structure, which significantly improves coding efficiency compared to High-Efficiency Video Coding (HEVC). The QTMT partition structure further enhances the flexibility of coding unit (CU) partitioning and improves the efficiency of VVC encoding high-resolution video, but introduces an unacceptable coding complexity at the same time. This paper proposes an SVM-based fast CU partition decision algorithm to reduce the coding complexity for VVC. First, the proportion of split modes with different CU sizes is analyzed to explore a method to effectively reduce coding complexity. Then, more reliable correlation features are selected based on the maximum ratio of the standard deviation (SD) and the edge point ratio (EPR) in sub-CUs. Finally, two SVM models are designed and trained using the selected features to provide guidance for deciding whether to divide and the direction of partition. The simulation results indicate that the proposed algorithm can save 54.05% coding time on average with 1.54% BDBR increase compared with VTM7.0.

show abstract

Section: Methods For Hevcmentioning

confidence: 99%

Section: Methods For Hevcmentioning

confidence: 99%

SVM-Based Fast CU Partition Decision Algorithm for VVC Intra Coding

Zhao

Zhang

2022

Electronics

View full text Add to dashboard Cite

show abstract

“…The Acquisition of Spatial and Temporal Feature Complexity 1) The Acquisition of Spatial Feature Complexity : According to [28], the edge information can effectively reflect the spatial characteristics of video content. Herein, the Canny operator, a popular edge detection operator [39]- [42], is employed to extract the edge information. Nevertheless, the conventional double-threshold algorithm in the Canny operator has limitations.…”

Section: The Model Of Spatial and Temporal Complexitymentioning

confidence: 99%

A High-Performance Rate Control Algorithm in Versatile Video Coding Based on Spatial and Temporal Feature Complexity

Zhao

Xiong

et al. 2023

IEEE Trans. on Broadcast.

View full text Add to dashboard Cite

This paper presents a high-performance rate control (HPRC) algorithm for the Versatile Video Coding (VVC) standard that aims to achieve higher coding efficiency by considering spatial and temporal feature complexity. The HPRC algorithm differs from conventional rate control (RC) algorithms in that it uses an adaptive Canny operator (ACO) with a novel doublethreshold algorithm to obtain the feature complexity of video content accurately. Moreover, an advanced bit allocation strategy at the frame-level and coding tree unit (CTU)-level is constructed to realize rational RC by thoroughly exploring the relationship between coding bits and complexity. To improve the precision of RC, an appropriate parameter updating based on the quasi-Newton algorithm is also proposed. Experimental results demonstrate that the proposed HPRC algorithm outperforms the default RC algorithm in VVC Test Model (VTM) 18.0, with Bjøntegaard Delta Rate (BD-Rate) savings of 8.77 % and 10.34 % under Low Delay P and Random Access configurations, respectively. Furthermore, the proposed algorithm also shows performance enhancements compared to other advanced algorithms.

show abstract

“…In this method, the coding flags, coding metrics and motion cues were utilized as the inputs of SVM. The SVM-based models were also explored in [24], [25], which utilized the average number of contour points in current CU and the image texture complexity, respectively. [26] employed the CNN to analyze the luminance components of video frame, which was furthermore employed to determine the depth range of CTU.…”

Section: B Low-complexity Hevc Prediction With Learningmentioning

confidence: 99%