Objective Assessment of Region of Interest-Aware Adaptive Multimedia Streaming Quality

Abstract

Adaptive multimedia streaming relies on controlled adjustment of content bitrate and consequent video quality variation in order to meet the bandwidth constraints of the communication link used for content delivery to the end-user. The values of the easy to measure network-related Quality of Service metrics have no direct relationship with the way moving images are perceived by the human viewer. Consequently variations in the video stream bitrate are not clearly linked to similar variation in the user perceived quality. This is especially true if some human visual system-based adaptation techniques are employed. As research has shown, there are certain image regions in each frame of a video sequence on which the users are more interested than in the others. This paper presents the Region of Interestbased Adaptive Scheme (ROIAS) which adjusts differently the regions within each frame of the streamed multimedia content based on the user interest in them. ROIAS is presented and discussed in terms of the adjustment algorithms employed and their impact on the human perceived video quality. Comparisons with existing approaches, including a constant quality adaptation scheme across the whole frame area, are performed employing two objective metrics which estimate user perceived video quality.

Objective Video Quality Assessment Methods: A Classification, Review, and Performance Comparison

“…In contrast, for real-time quality assessments at the receiver without availability of the original video data, low-complexity reducedreference or no-reference methods are needed. The objective methods can also be classified in terms of their usability in the context of adaptive streaming solutions [20], [21] as out-ofservice methods and in-service methods. In the out-of-service methods, no time constraints are imposed and the original sequence can be available.…”

An Adaptive Live Streaming Mechanism for Heterogeneous Vehicular Networks

“…ROI is a subset of an image that a user is mostly interested in, and the rest parts are the unnoticeable areas. In addition, an approach, region of interest-based adaptive scheme (ROIAS), was proposed by Ciubotaru, Muntean, and Ghinea (2009) to differently adjust the regions within each frame of the streamed multimedia content according to each user's interest. Liu, Li, and Soh (2008) presented an ROI-based H.264/AVC system for real-time conversational video communication; this method can allocate more resources, such as bits and computational power, and can adaptively adjust several coding parameters, including QP, macroblock candidate modes, the number of reference frames, motion estimation (ME) accuracy, and ME search range.…”

Subjective Assessment of BitDetect—A Mechanism for Energy-Aware Multimedia Content Adaptation

“…This involves detecting the areas of maximum user interest (AMUI), and when necessary, affecting the quality of the regions users are less interested in. Two versions were proposed, linear-ROIAS and logarithmic-ROIAS, which were shown to improve the quality on the AMUI when compared to QOAS [17].…”