Fast CU Decision Algorithm Based on CNN and Decision Trees for VVC
Compared with the previous generation of High Efficiency Video Coding (HEVC), Versatile Video Coding (VVC) introduces a quadtree and multi-type tree (QTMT) partition structure with nested multi-class trees so that the coding unit (CU) partition can better match the video texture features. This parti...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/14/3053 |
| _version_ | 1797589539373449216 |
|---|---|
| author | Hongchan Li Peng Zhang Baohua Jin Qiuwen Zhang |
| author_facet | Hongchan Li Peng Zhang Baohua Jin Qiuwen Zhang |
| author_sort | Hongchan Li |
| collection | DOAJ |
| description | Compared with the previous generation of High Efficiency Video Coding (HEVC), Versatile Video Coding (VVC) introduces a quadtree and multi-type tree (QTMT) partition structure with nested multi-class trees so that the coding unit (CU) partition can better match the video texture features. This partition structure makes the compression efficiency of VVC significantly improved, but the computational complexity is also significantly increased, resulting in an increase in encoding time. Therefore, we propose a fast CU partition decision algorithm based on DenseNet network and decision tree (DT) classifier to reduce the coding complexity of VVC and save more coding time. We extract spatial feature vectors based on the DenseNet network model. Spatial feature vectors are constructed by predicting the boundary probabilities of 4 × 4 blocks in 64 × 64 coding units. Then, using the spatial features as the input of the DT classifier, through the classification function of the DT classifier model, the top N division modes with higher prediction probability are selected, and other division modes are skipped to reduce the computational complexity. Finally, the optimal partition mode is selected by comparing the RD cost. Our proposed algorithm achieves 47.6% encoding time savings on VTM10.0, while BDBR only increases by 0.91%. |
| first_indexed | 2024-03-11T01:07:54Z |
| format | Article |
| id | doaj.art-97e9ac6b50f04747af65149a89b88a92 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T01:07:54Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-97e9ac6b50f04747af65149a89b88a922023-11-18T19:05:09ZengMDPI AGElectronics2079-92922023-07-011214305310.3390/electronics12143053Fast CU Decision Algorithm Based on CNN and Decision Trees for VVCHongchan Li0Peng Zhang1Baohua Jin2Qiuwen Zhang3College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaCollege of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaCollege of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaCollege of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaCompared with the previous generation of High Efficiency Video Coding (HEVC), Versatile Video Coding (VVC) introduces a quadtree and multi-type tree (QTMT) partition structure with nested multi-class trees so that the coding unit (CU) partition can better match the video texture features. This partition structure makes the compression efficiency of VVC significantly improved, but the computational complexity is also significantly increased, resulting in an increase in encoding time. Therefore, we propose a fast CU partition decision algorithm based on DenseNet network and decision tree (DT) classifier to reduce the coding complexity of VVC and save more coding time. We extract spatial feature vectors based on the DenseNet network model. Spatial feature vectors are constructed by predicting the boundary probabilities of 4 × 4 blocks in 64 × 64 coding units. Then, using the spatial features as the input of the DT classifier, through the classification function of the DT classifier model, the top N division modes with higher prediction probability are selected, and other division modes are skipped to reduce the computational complexity. Finally, the optimal partition mode is selected by comparing the RD cost. Our proposed algorithm achieves 47.6% encoding time savings on VTM10.0, while BDBR only increases by 0.91%.https://www.mdpi.com/2079-9292/12/14/3053versatile video codingdecision treesQTMTDenseNet |
| spellingShingle | Hongchan Li Peng Zhang Baohua Jin Qiuwen Zhang Fast CU Decision Algorithm Based on CNN and Decision Trees for VVC Electronics versatile video coding decision trees QTMT DenseNet |
| title | Fast CU Decision Algorithm Based on CNN and Decision Trees for VVC |
| title_full | Fast CU Decision Algorithm Based on CNN and Decision Trees for VVC |
| title_fullStr | Fast CU Decision Algorithm Based on CNN and Decision Trees for VVC |
| title_full_unstemmed | Fast CU Decision Algorithm Based on CNN and Decision Trees for VVC |
| title_short | Fast CU Decision Algorithm Based on CNN and Decision Trees for VVC |
| title_sort | fast cu decision algorithm based on cnn and decision trees for vvc |
| topic | versatile video coding decision trees QTMT DenseNet |
| url | https://www.mdpi.com/2079-9292/12/14/3053 |
| work_keys_str_mv | AT hongchanli fastcudecisionalgorithmbasedoncnnanddecisiontreesforvvc AT pengzhang fastcudecisionalgorithmbasedoncnnanddecisiontreesforvvc AT baohuajin fastcudecisionalgorithmbasedoncnnanddecisiontreesforvvc AT qiuwenzhang fastcudecisionalgorithmbasedoncnnanddecisiontreesforvvc |