Browse/search for people

Publication - Professor David Bull

    Understanding video texture — A basis for video compression

    Citation

    Katsenou, A, Ntasios, T, Afonso, M, Agrafiotis, D & Bull, D, 2018, ‘Understanding video texture — A basis for video compression’. in: 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP 2017): Proceedings of a meeting held 16-18 October 2017, Luton, United Kingdom. Institute of Electrical and Electronics Engineers (IEEE), pp. 232-238

    Abstract

    Encoding spatio-temporally varying textures is challenging for standardised video encoders, with significantly more bits required for textured blocks compared to non-textured blocks. It is therefore beneficial to understand video textures in terms of both their spatio-temporal characteristics and their encoding statistics in order to optimize coding modes and performance. To this end, we examine the classification of video texture based on encoder performance. For this purpose, we employ spatio-temporal features and follow a two-step feature selection process by employing unsupervised machine learning approaches across the selected feature space. Finally, supervised machine learning approaches are applied on the set of the selected features that support classification prior to encoding with up to 95.1% accuracy. The results of this study offer the potential to underpin a new informed approach to a new informed approach to codec configuration and mode selection.

    Full details in the University publications repository