Fast CU Partition Decision Strategy Based on Human Visual System Perceptual Quality

Abstract

A fast Coding Unit (CU) partition decision strategy based on Human Visual System (HVS) perception quality is proposed in this paper. Considering that it is difficult for existing fast algorithms to further improve compression efficiency, perceptual coding technology has been tried to remove visual redundancy for achieving the purpose of reducing the bit rate on the basis of maintaining subjective visual quality. However, the existing perceptual coding model is still insufficient to reflect the characteristics of the HVS, which has limited improvement in coding efficiency, especially in fast algorithms. In this method, the characteristics of the limited human capacity for spatial-temporal resolution and the visual sensory memory are used to improve coding performance. First, the color complexity is used as a control factor to optimize the Just Noticeable Difference (JND) model to remove visual redundancy in a way that is more in line with the characteristics of visual perception. Second, a classification model of motion patterns based on human visual saliency is designed to provide a basis for CU classification, which effectively improves the coding accuracy. Finally, an offline Decision Tree (DT) classifier is designed based on the above model, and texture features are incorporated into the classifier as another key attribute to further reduce the computational complexity. The results of performance evaluation confirm that the proposed method achieves significantly improved coding performance compared with original Versatile Test Model (VTM). Compared with existing algorithms, our method not only improves coding efficiency, but also improves subjective visual quality.

Efficient Partition Decision Based on Visual Perception and Machine Learning for H.266/Versatile Video Coding

“…Since the solution of [16] is originally designed for the complexity reduction of QT/BT partitioning scheme, to adapt to the MTT partitioning, horizontal partition modes (BTH and TTH) and vertical partition modes (BTV and TTV) are both grouped as the output of the BH/BV classifier. Zhao et al [17] design a decision tree classifier by using just noticeable difference model threshold, motion pattern and image texture features for fast CU partition decision strategy. Park and Kang [18] use a lightweight neural network model to decide whether to terminate the nested TT block structures subsequent to a quadtree based on the two kinds of features.…”

Learning adaptive motion search for fast versatile video coding in visual surveillance systems

“…As reported in [9], the proposed method achieved around 30.63% time saving but asking for 3.18% BDBR (Bjontegaard Bitrate) loss [10]. Afterwards, Zhao et al introduced in [11] a Decision Tree classifier based on human visual saliency to classify CU and decide how the CU is partitioned. Experimental results show that the complexity of this method is reduced by about 48.01%, while the increase of BDBR is only 0.79%.…”