Dynamic video playout smoothing method for multimedia applications

Abstract

Multimedia applications including video data require the smoothing of video playout to prevent potential discontinuity. In this paper, we propose a dynamic video playout smoothing method, called the Video Smoother, which dynamically adopts various playout rates in an attempt to compensate for high delay variance of networks. Specifically, if the number of frames in the buffer exceeds a given threshold (TH), the Smoother employs a maximum playout rate. Otherwise, the Smoother uses proportionally reduced rates in an effort to eliminate playout pauses resulting from the emptiness of the playout buffer. To determine THs under various loads, we present an analytic model assuming the Interrupted Poisson Process (IPP) arrival. Based on the analytic results, we establish a paradigm of determining THs and playout rates for achieving different playout qualities under various loads of networks. Finally, to demonstrate the viability of the Video Smoother, we have implemented a prototyping system including a multimedia teleconferencing application and the Video Smoother performing as part of the transport layer. The prototyping results show that the Video Smoother achieves smooth playout incurring only unnoticeable delays.

Playout buffer and rate optimization for streaming over IEEE 802.11 wireless networks

“…There are a variety of strategies proposed to improve the effectiveness of client-side buffering that include optimizing the buffer size based on jitter removal [Mundur et al 1999;Ramjee et al 1994; Moon et al 1998;Fujimoto et al 2002], slowing down the media playout rate at the client to reduce the consumption rate and help prevent buffer underflow [Yuang et al 1996;Steinbach et al 2001;Laoutaris and Stavrakakis 2001;Kalman et al 2004], and mitigating the buffer size required by VBR media codecs [Yuang et al 1997;Feng and Sechrest 1995]. Since VBR streaming smoothers usually have a static size based on the media codec, and the adaptive playout rate can be used as an additive for reducing the buffer underflow events in most streaming systems, most buffer optimization algorithms are primarily for jitter removal.…”

“…To study the buffer size required for removing the jitter in networks, Yuang et al [1996Yuang et al [ , 1997, Steinbach et al [2001], Kalman et al [2004], and Laoutaris and Stavrakakis [2001] present Markov chain models based on Poisson arrivals. However, in wireless networks, the arrival of streaming traffic cannot be simply modeled as a Poisson distribution because the capacity changes due to wireless rate adaptation algorithms produces variance in the streaming traffic arrival rate.…”

“…Most of the previously developed playout buffer models use a Poisson arrival process [Yuang et al 1997[Yuang et al , 1996Steinbach et al 2001]. Poisson arrivals can be used as a lower bound on system performance when analyzing the buffer behavior [Laoutaris and Stavrakakis 2001].…”

Adaptive playout strategies for packet video receivers with finite buffer capacity

“…The main idea in threshold based rate adaptation is the linear reduction of playout rate as the number of buffered frames approaches zero. Yuang et al [3] . It should be noticed that when the system operates above TH it employs a maximum playout rate ¢ which is greater than , the actual video frame rate.…”

“…In source rate adaptation [1], [2], it is the sending system that adapts to the time-varying bandwidth availability by regulating the rate of its output video stream. On the other hand, Packet Video Receiving systems (PVRs), adapt their playout rate in an effort to avoid underflows (lack of a frame to display) caused by excessively delayed frames [3], [4], [5]. PVRs use a playout buffer to accumulate incoming frames as a measure against network jitter.…”