Learning Adaptive Quantization Parameter for Consistent Quality Oriented Video Coding
Preprint
- 31 October 2023
- preprint
- Published by MDPI AG in Preprints.org
Abstract
In industry 4.0 era, video applications such as surveillance visual systems, video conferencing, or video broadcasting have been playing a vital role. In these applications, for manipulating and tracking objects in decoded video, the quality of decoded video should be consistent because it largely affects to the performance of the machine analysis. To cope with this problem, we propose a novel perceptual video coding (PVC) solution in which a full reference quality metric named Video Multimethod Assessment Fusion (VMAF) is employed together with a deep convolutional neural network (CNN) to obtain the consistent quality while still achieving the high compression performance. First of all, to achieve the consistent quality requirement, we propose a CNN model with an expected VMAF as input to adaptively adjust the quantization parameters (QP) for each coding block. Afterwards, to increase the compression performance, a Lagrange coefficient of Rate-Distortion optimization (RDO) mechanism is adaptively computed under Rate-QP and Quality-QP models. Experimental results show that the proposed PVC has achieved two targets simultaneously: the quality of video sequence is kept consistently with an expected quality level and the bit rate saving of the proposed method is higher than traditional video coding standards and relevant benchmark, notably with around 10% bitrate saving in average.Keywords
All Related Versions
- Version 1, 2023-10-31, Preprints
- Published version: Electronics, 12 (24), 4905.
This publication has 25 references indexed in Scilit:
- VMAF based quantization parameter prediction model for low resolution video coding2022
- A VMAF Directed Perceptual Rate Distortion Optimization for Video Coding2020
- Perceptual Adaptive Quantization Parameter Selection Using Deep Convolutional Features for HEVC EncoderIEEE Access, 2020
- Comparison of objective quality models for adaptive bit-streaming services2017
- VMAF reproducibility: Validating a perceptual practical video quality metric2017
- A saliency-based rate control for people detection in video2013
- Visual perception based Lagrangian rate distortion optimization for video coding2011
- An SSIM-optimal H.264/AVC inter frame encoder2009
- PSNR control for GOP-level constant quality in H.264 video coding2006
- Rate-distortion optimization for video compressionIEEE Signal Processing Magazine, 1998