Efficient screen content coding based on convolutional neural network guided by a large-scale database

Lili Zhao; Zhiwen Wei; Weitong Cai; Wenyi Wang; Liaoyuan Zeng; Jianwen Chen

doi:10.1109/ICIP.2019.8803294

Efficient screen content coding based on convolutional neural network guided by a large-scale database

Lili Zhao, Zhiwen Wei, Weitong Cai, Wenyi Wang, Liaoyuan Zeng, Jianwen Chen

Western Sydney University

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

5 Citations (Scopus)

Abstract

![CDATA[Screen content videos (SCVs) are becoming popular in many applications. Compared with natural content videos (NCVs), the SCVs have different characteristics. Therefore, the screen content coding (SCC) based on HEVC adopts some new coding tools (intra block copy and palette mode etc.) to improve coding efficiency, but these tools increase the computational complexity as well. In this paper, we propose to predict the CU partition of the SCVs by a convolutional neural network (CNN) which is trained by the large-scale database that we firstly established for screen content coding. The proposed approach is implemented in SCC reference software SCM-6.1. Experimental results show that our proposed approach can save 53.2% encoding time with 2.67% BD-rate increase on average in All Intra (AI) configurations.]]

Original language	English
Title of host publication	Proceedings of the 2019 IEEE International Conference on Image Processing, September 22-25, 2019, Taipei International Convention Center (TICC), Taipei, Taiwan
Publisher	IEEE
Pages	2656-2660
Number of pages	5
ISBN (Print)	9781538662496
DOIs	https://doi.org/10.1109/ICIP.2019.8803294
Publication status	Published - 2019
Event	International Conference on Image Processing - Duration: 22 Sept 2019 → …

Publication series

Name
ISSN (Print)	1522-4880

Conference

Conference	International Conference on Image Processing
Period	22/09/19 → …

Access to Document

10.1109/ICIP.2019.8803294

Cite this

Zhao, L., Wei, Z., Cai, W., Wang, W., Zeng, L., & Chen, J. (2019). Efficient screen content coding based on convolutional neural network guided by a large-scale database. In Proceedings of the 2019 IEEE International Conference on Image Processing, September 22-25, 2019, Taipei International Convention Center (TICC), Taipei, Taiwan (pp. 2656-2660). IEEE. https://doi.org/10.1109/ICIP.2019.8803294

@inproceedings{86e81885c34a44ee8dea6460304e029a,

title = "Efficient screen content coding based on convolutional neural network guided by a large-scale database",

abstract = "![CDATA[Screen content videos (SCVs) are becoming popular in many applications. Compared with natural content videos (NCVs), the SCVs have different characteristics. Therefore, the screen content coding (SCC) based on HEVC adopts some new coding tools (intra block copy and palette mode etc.) to improve coding efficiency, but these tools increase the computational complexity as well. In this paper, we propose to predict the CU partition of the SCVs by a convolutional neural network (CNN) which is trained by the large-scale database that we firstly established for screen content coding. The proposed approach is implemented in SCC reference software SCM-6.1. Experimental results show that our proposed approach can save 53.2% encoding time with 2.67% BD-rate increase on average in All Intra (AI) configurations.]]",

author = "Lili Zhao and Zhiwen Wei and Weitong Cai and Wenyi Wang and Liaoyuan Zeng and Jianwen Chen",

year = "2019",

doi = "10.1109/ICIP.2019.8803294",

language = "English",

isbn = "9781538662496",

publisher = "IEEE",

pages = "2656--2660",

booktitle = "Proceedings of the 2019 IEEE International Conference on Image Processing, September 22-25, 2019, Taipei International Convention Center (TICC), Taipei, Taiwan",

note = "International Conference on Image Processing ; Conference date: 22-09-2019",

}

Zhao, L, Wei, Z, Cai, W, Wang, W, Zeng, L & Chen, J 2019, Efficient screen content coding based on convolutional neural network guided by a large-scale database. in Proceedings of the 2019 IEEE International Conference on Image Processing, September 22-25, 2019, Taipei International Convention Center (TICC), Taipei, Taiwan. IEEE, pp. 2656-2660, International Conference on Image Processing, 22/09/19. https://doi.org/10.1109/ICIP.2019.8803294

Efficient screen content coding based on convolutional neural network guided by a large-scale database. / Zhao, Lili; Wei, Zhiwen; Cai, Weitong et al.
Proceedings of the 2019 IEEE International Conference on Image Processing, September 22-25, 2019, Taipei International Convention Center (TICC), Taipei, Taiwan. IEEE, 2019. p. 2656-2660.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Efficient screen content coding based on convolutional neural network guided by a large-scale database

AU - Zhao, Lili

AU - Wei, Zhiwen

AU - Cai, Weitong

AU - Wang, Wenyi

AU - Zeng, Liaoyuan

AU - Chen, Jianwen

PY - 2019

Y1 - 2019

N2 - ![CDATA[Screen content videos (SCVs) are becoming popular in many applications. Compared with natural content videos (NCVs), the SCVs have different characteristics. Therefore, the screen content coding (SCC) based on HEVC adopts some new coding tools (intra block copy and palette mode etc.) to improve coding efficiency, but these tools increase the computational complexity as well. In this paper, we propose to predict the CU partition of the SCVs by a convolutional neural network (CNN) which is trained by the large-scale database that we firstly established for screen content coding. The proposed approach is implemented in SCC reference software SCM-6.1. Experimental results show that our proposed approach can save 53.2% encoding time with 2.67% BD-rate increase on average in All Intra (AI) configurations.]]

AB - ![CDATA[Screen content videos (SCVs) are becoming popular in many applications. Compared with natural content videos (NCVs), the SCVs have different characteristics. Therefore, the screen content coding (SCC) based on HEVC adopts some new coding tools (intra block copy and palette mode etc.) to improve coding efficiency, but these tools increase the computational complexity as well. In this paper, we propose to predict the CU partition of the SCVs by a convolutional neural network (CNN) which is trained by the large-scale database that we firstly established for screen content coding. The proposed approach is implemented in SCC reference software SCM-6.1. Experimental results show that our proposed approach can save 53.2% encoding time with 2.67% BD-rate increase on average in All Intra (AI) configurations.]]

UR - https://hdl.handle.net/1959.7/uws:72658

U2 - 10.1109/ICIP.2019.8803294

DO - 10.1109/ICIP.2019.8803294

M3 - Conference Paper

SN - 9781538662496

SP - 2656

EP - 2660

BT - Proceedings of the 2019 IEEE International Conference on Image Processing, September 22-25, 2019, Taipei International Convention Center (TICC), Taipei, Taiwan

PB - IEEE

T2 - International Conference on Image Processing

Y2 - 22 September 2019

ER -

Efficient screen content coding based on convolutional neural network guided by a large-scale database

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this