A Synthetic Video Dataset for Video Compression Evaluation

Di Ma, Angeliki Katsenou, David Bull

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

4 Citations (Scopus)
469 Downloads (Pure)

Abstract

In this paper, a new Synthetic video Texture dataset (SynTex) is introduced. It was generated using a Computer Graphics Imagery (CGI) environment and offers the capability of being able to generate many versions of the same scenes with different video parameters. This will support research in video compression enabling researchers to understand and model the relationship between video content and its coding parameters. To validate that SynTex is suitable for this purpose, firstly, typical spatio-temporal descriptors were calculated and compared against existing real video datasets with similar parameters. Then, the encoding statistics of SynTex were extracted using the HEVC reference software and compared to natural video datasets. The comparisons show that SynTex exhibits a comparable coverage over the spatial and temporal domain and it has similar encoding statistics to real video datasets.
Original languageEnglish
Title of host publication2019 26th IEEE International Conference on Image Processing (ICIP 2019)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages5
ISBN (Electronic)9781538662496
ISBN (Print)9781538662502
DOIs
Publication statusPublished - 26 Aug 2019

Publication series

Name
ISSN (Print)1522-4880

Keywords

  • Synthetic Video Dataset
  • Video Texture
  • Video Compression
  • HEVC Coding Statistics

Fingerprint

Dive into the research topics of 'A Synthetic Video Dataset for Video Compression Evaluation'. Together they form a unique fingerprint.

Cite this