Region of Interest-Based Adaptive Multimedia Streaming Scheme

Muntean, Gabriel‐Miro; Ghinea, Gheorghiţă; Sheehan, Tanya

doi:10.1109/tbc.2008.919012

Cited by 41 publications

(27 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the face of challenging network conditions during real-time video streaming, UEP strategies [4,5,6] protect visually important (salient) regions more heavily. An often overlooked question in these works is how to conceal missing blocks in the less important regions when packet losses do occur?…”

Section: Related Workmentioning

confidence: 99%

“…Under these practical constraints, it is very difficult to guarantee error-free delivery of the entire video from sender to receiver in a timely manner. Many previous works [4,5,6] employed the pro-active methodology of unequal error protection (UEP) of video data, where important packets are protected more heavily (e.g., using stronger Forward Error Correction (FEC) codes). Typically, more important packets contain viewer's probable Regions-of-Interest (ROI) [7] in a video frame, or regions with higher visual saliency [8]-where viewers most likely will focus their visual attention.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Saliency-Cognizant Error Concealment in Loss-Corrupted Streaming Video

Hadizadeh

Bajić

Cheung

2012

2012 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

Error concealment in packet-loss-corrupted streaming video is inherently an under-determined problem, as there are insufficient number of well-defined criteria to recover the missing blocks perfectly. When a Region-of-Interest (ROI) based unequal error protection (UEP) scheme is deployed during video streaming-i.e., more visually salient regions are strongly protected-a lost block is likely to be of low saliency in the original frame. In this paper, we propose to add a low-saliency prior to the error concealment problem as a regularization term. It serves two purposes. First, in ROI-based UEP video streaming, low-saliency prior provides the right side information for the client to identify the correct replacement blocks for concealment. Second, in the event that a perfectly matched block cannot be unambiguously identified, the low-saliency prior reduces viewer's visual attention on the loss-stricken region, resulting in higher overall subjective quality.We study the effectiveness of a low-saliency prior in the context of a previously proposed RECAP [1] error concealment system. RECAP transmits a low-resolution (LR) version of an image alongside the original high-resolution (HR) version, so that if blocks in the HR version are lost, the correctly-received LR version can serve as a template for matching of suitable replacement blocks from a previously correctly-decoded HR frame. We add a low-saliency prior to the block identification process, so that only replacement candidate blocks with good match and low saliency can be selected. Further, we design and apply four saliency reduction operators iteratively in a loop, in order to reduce the saliency of candidate blocks. Experimental results show that: i) PSNR of the error-concealed frames can be increased dramatically (up to 3.2dB over the original RE-CAP), showing the effectiveness of a low-saliency prior in the underdetermined error concealment problem; and ii) subjective quality of the repaired video using our proposal, as confirmed by an extensive user study, is better than the original RECAP.Index Terms-Video streaming, error concealment, visual saliency INTRODUCTIONDespite ongoing efforts to further advance communication technologies, high quality real-time video streaming over best-effort, packetswitched networks remains challenging for a number of reasons. First, consumer demand for interactive streaming video (e.g., conference video such as Skype, Google Talk, etc.) continues to outpace the rate of increase in network bandwidth [2], resulting in congestion and packet queue overflows in packet-switched networks. Second, when packet losses do occur, persistent server-client retransmission is not practical due to the timing constraint of streaming video (i.e., a video packet arriving at decoder past its playback deadline is useless). Third, new media types such as ultra-high-resolution videoThis work was supported in part by the NSERC grant RGPIN 327249.and multiple-view video [3] that promise enhancement of viewing experience are also further straini...

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Saliency-Cognizant Error Concealment in Loss-Corrupted Streaming Video

Hadizadeh

Bajić

Cheung

2012

2012 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

show abstract

“…Objective VQA metrics are wildly employed for assessing the video quality in both prototype-based [12] and simulationbased solutions [13]. Relative to the presence of the original reference video stream unaffected by the factors under test, the existing objective VQA metrics can be classified in: noreference (NR), reduced-reference (RR) and full-reference (FR) metrics [7].…”

Section: B Objective Vqa Metricsmentioning

confidence: 99%

A novel methodology for mapping objective video quality metrics to the subjective MOS scale

Moldovan

Ghergulescu

Muntean

2014

2014 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting

View full text Add to dashboard Cite

Abstract-With the rapid growth in video-based services, and as users are becoming increasingly quality-aware, the reliable estimation of video quality has become extremely important. While a multitude of objective Video Quality Assessment (VQA) metrics with various performance and complexity have been proposed, the nonlinearity of video quality and the lack of clear interpretations of the metrics make difficult to understand how the objective metric values reflect the video quality as perceived subjectively in terms of Mean Opinion Scores (MOS). This paper proposes and evaluates a methodology for mapping objective VQA metric values to subjective MOS scores based on publicly available VQA databases. Three different databases were used for comparing the performance of various objective metrics and evaluating the proposed methodology.Index Terms-Video quality assessment (VQA), mean opinion score (MOS), subjective methods, objective metrics, video quality mapping, performance evaluation, public video quality databases.

show abstract

“…In Engelke and Zepernick's study (2009), the result from image quality assessment showed that subjects were more sensitive to the image quality distortion in the ROI area than that in the background. According to Muntean et al (2008), by blurring the background and decreasing its saturation but increasing that of the foreground, better visibility could be achieved on mobile devices; and marginal background changes could reduce the video bitrate. Other studies (Knoche, Papaleo, Sasse & Vanelli-Coralli, 2007;Song, Tjondronegoro, Wang, et al, 2010) revealed that properly zooming the ROI or enhancing the quality of ROI based on the shot type of video content could efficiently improve the overall UX on a mobile device in a low bitrate condition.…”

Section: Optimizing User Experience Of Mobile Videomentioning

confidence: 99%