Full-Reference Video Quality Assessment by Decoupling Detail Losses and Additive Impairments

Abstract

Video quality assessment plays a fundamental role in video processing and communication applications. In this paper, we study the use of motion information and temporal human visual system (HVS) characteristics for objective video quality assessment. In our previous work, two types of spatial distortions, i.e., detail losses and additive impairments, are decoupled and evaluated separately for spatial quality assessment. The detail losses refer to the loss of useful visual information that will affect the content visibility, and the additive impairments represent the redundant visual information in the test image, such as the blocking or ringing artifacts caused by data compression and so on. In this paper, a novel full-reference video quality metric is developed, which conceptually comprises the following processing steps: 1) decoupling detail losses and additive impairments within each frame for spatial distortion measure; 2) analyzing the video motion and using the HVS characteristics to simulate the human perception of the spatial distortions; and 3) taking into account cognitive human behaviors to integrate frame-level quality scores into sequence-level quality score. Distinguished from most studies in the literature, the proposed method comprehensively investigates the use of motion information in the simulation of HVS processing, e.g., to model the eye movement, to predict the spatio-temporal HVS contrast sensitivity, to implement the temporal masking effect, and so on. Furthermore, we also prove the effectiveness of decoupling detail losses and additive impairments for video quality assessment. The proposed method is tested on two subjective quality video databases, LIVE and IVP, and demonstrates the state-of-the-art performance in matching subjective ratings.Index Terms-Human visual system (HVS), spatial distortions decoupling, video quality assessment.

Video quality assessment and machine learning: Performance and interpretability

“…To test the performance of our methods we have used several publicly available datasets denoted in this work as follows: LIVE [22], Lisbon [23], and IVP [24]. Videos with artifacts caused by anything other than H.264/AVC encoding were excluded from the datasets.…”

Bursty interference-oriented video quality assessment method

“…And in [12], Inazumi et al proposed an evaluation algorithm considering the video quality varying with time based on effect of human brain short-term memory storage, in which the overall video quality is weight evaluated by the quality of each frame and the video varying factors are taken into account as the weighting function. Besides, research shows that the human observers are more sensitive to degradation than improvement in video frames quality [16].…”

Performance Analysis of a No-Reference Temporal Quality Assessment Metric for Videos Impaired by Frame Freezing Artefacts

“…Full reference (FR), reduced reference (RR) and no reference (NR)are the 3 kinds methods used to monitor the received videos on the reception side. These methods have been used and described in details in [2]- [5]. FR method requires the full reference of the transmitted video on the receiving side in order to assess the video quality and reduced referenceuses partial reference or a few statistics of the transmitted video.…”