Background simplification for ROI-oriented low bitrate video coding

Abstract : Low-bitrate video compression is a challenging task, particularly with the increasing complexity of video sequences. Re-shaping video data before its compression with modern hybrid encoders has provided interesting results in the low and ultra-low bitrate domains. In this work, we propose a novel saliency guided preprocessing approach, which combines adaptive re-sampling and background texture removal, to achieve efficient ROI-oriented compression. Evaluated with HEVC, we show that our solution improves the ROI encoding over a wide range of resolutions and bitrates whilst maintaining a high background intelligibility level.