Xinggong Zhang

Profiling Skype video calls: Rate control and video quality

Video telephony has recently gained its momentum and is widely adopted by end-consumers. But there have been very few studies on the network impacts of video calls and the user Quality-of-Experience (QoE) under different network conditions. In this paper, we study the rate control and video quality of Skype video calls. We first measure the behaviors of Skype video calls on a controlled network testbed. By varying packet loss rate, propagation delay and bandwidth, we observe how Skype adjusts its rates, FEC redundancy and video quality. We find that Skype is robust against mild packet losses and propagation delays, and can efficiently utilize the available network bandwidth. We also find that Skype employs an overly aggressive FEC protection strategy. Based on the measurement results, we develop rate control model, FEC model, and video quality model for Skype. Extrapolating from the models, we conduct numerical analysis to study the network impacts of Skype. We demonstrate that user back-offs upon quality degradation serve as an effective user-level rate control scheme. We also show that Skype video calls are indeed TCP-friendly and respond to congestion quickly when the network is overloaded.

A control-theoretic approach to rate adaptation for dynamic HTTP streaming

Recently, dynamic adaptive HTTP streaming has been widely used for video content delivery over Internet. However, it is still a challenge how to switch video bitrate under time-varying bandwidth. In this paper, we propose a novel control-theoretic approach to adapt video segments in dynamic HTTP streaming. The rate control is based on a sink-buffer, which has an overflow-threshold and an underflow-threshold. The objective is to maximize the playback quality while keeping the receiver buffer from either overflow or underflow. Using control theory, we formulate this rate control scheme as a proportional (P) control system, which exists oscillations and steady-errors. Furthermore, we design a proportional derivative (PD) controller to improve its adaptation performance. The conditions for stability and settling time of the PD controller are also derived. Numerous experiment results demonstrate the effectiveness of our proposed PD control scheme for dynamic HTTP streaming.

Parallelizing video transcoding using Map-Reduce-based cloud computing

Due to the complexity of video coding, fast transcoding is still a challenge. Various parallel coding methods have been proposed. In this paper, we present a parallel transcoding system over Map/Reduce cloud computing architecture. Input video sequences are divided into segments, and mapped to multiple computers. The sub-tasks are launched in parallel with processing results concatenated to the final output sequences. For heterogeneous clips, computing capacity, and task-launching overhead, the task scheduling over cloud is an NP-hard problem. We propose a low-complexity heuristic algorithm, Max-MCT, to find out the optimal solutions for task scheduling. By estimating the low-bound of finish time, we transform the problem into a virtual knapsack problem. But it is not an optimal solution for the original problem therefore we use a minimal complete time (MCT) algorithm to minimize the entire finish time. We carry out extensive experiments on numerical simulations. The results verified that our algorithm outperforms the existing algorithms.

Buffer-based smooth rate adaptation for dynamic HTTP streaming

Recently, Dynamic Streaming over HTTP (DASH) has been widely deployed in the Internet. However, it is still a challenge to play back video smoothly with high quality in the time-varying Internet. In this paper, we propose a buffer based rate adaptation scheme, which is able to smooth bandwidth variations and provide a continuous video playback. Through analysis, we show that simply preventing buffer underflow/overflow in the greedy rate adaptation method may incur serious rate oscillations, which is poor quality-of-experience for users. To improve it, we present a novel control-theoretic approach to control buffering size and rate adaptation. We modify the buffered video time model by adding two thresholds: an overflow threshold and an underflow threshold, to filter the effect of short-term network bandwidth variations while keeping playback smooth. However, the modified rate adaptation system is nonlinear. By choosing operating point properly, we linearize the rate control system. By a Proportional-Derivative (PD) controller, we are able to adapt video rate with high responsiveness and stability. We carefully design the parameters for the PD controller. Moreover, we show that reserving a small positive/negative bandwidth margin can greatly decrease the opportunities of buffer underflow/overflow incurred by the bandwidth prediction error. At last, we demonstrate that our proposed control-theoretic approach are highly efficient through real network trace.

A novel JSCC scheme for scalable video transmission over MIMO systems

MIMO recently emerges as one of promising techniques for wireless video streaming. It is still a challenge to provide un-equal error protections by joint source-channel coding (JSCC) over multiple diverse MIMO sub-channels. In this paper, a joint source-channel coding and antenna mapping scheme for scalable video transmission over MIMO systems is proposed. Bandwidth are elaborately allocated between video source and channel protections by layer extracting and FEC coding. For the extracted layers, we determine i) which antenna will they be transmitted over and ii) how much redundancy bits will be added for error protections. We formulate this scheme into a non-linear integer optimization problem, whose complexity is very high. Instead, a low-complexity branch-and-bound algorithm is presented. Source layers are partitioned into subsets of layers, and the selected layer are mapped to antennas using Min-max scheduling algorithm. By branching and pruning, the computation complexity are reduced significantly. We carry out extensive numerical experiments under various network conditions. The results demonstrate our algorithms efficiency and the overall transmission quality is improved significantly.

Sparsity estimation in image compressive sensing

Compressive sensing is an emerging technology which can recover a K-sparse signal vector from M = O(Klog(K=N)) measurements. However, it is a challenge to know exactly how many measurements an image requires to achieve an acceptable recovered visual quality. In this paper, we study the relationship between the images complexity and its sparsity. We propose a mathematical model to estimate the number of needed measurements by using the images texture, the edge density and the target reconstruction quality. There exists a linear function between them. The experimental results with a large number of photo pictures show that, quite most reconstructed images using our pre-calculated number of measurements have good enough quality, which confirms our proposed image-complexity-based model well.

Collision-detection based rate-adaptation for video multicasting over IEEE 802.11 wireless networks

Wireless video multicasting/broadcasting is an efficient method for simultaneous transmission of data to a group of users. But the multicasting rates are fixed in current IEEE 802.11 PHYs standard. In this paper, we propose a novel collision-detection based rate-adaptation scheme (CDRA), which fully exploits the potential of rate adaptation capability of wireless physical layer, to improve service qualities of video multicasting. The received signal strength indication (RSSI) and packet error ratio (PER) are comprehensively used to detect collision. The PER-guided rate adjustment algorithm is performed when no collision happens. Otherwise the collision-avoid mechanism works. By detecting the collision, our scheme could adaptively select the maximum data rates for video multicasting. We construct a practical multicasting test-bed in IEEE 802.11b network and carry out extensive experiments. The results show that CDRA achieves throughput gain up to 166% and PSNR gain to 139% compared with existing methods.

Probabilistic chunk scheduling approach in parallel multiple-server DASH

Recently parallel Dynamic Adaptive Streaming over HTTP (DASH) has emerged as a promising way to supply higher bandwidth, connection diversity and reliability. However, it is still a big challenge to download chunks sequentially in parallel DASH due to heterogeneous and time-varying bandwidth of multiple servers. In this paper, we propose a novel probabilistic chunk scheduling approach considering time-varying bandwidth. Video chunks are scheduled to the servers which consume the least time while with the highest probability to complete downloading before the deadline. The proposed approach is formulated as a constrained optimization problem with the objective to minimize the total downloading time. Using the probabilistic model of time-varying bandwidth, we first estimate the probability of successful downloading chunks before the playback deadline. Then we estimate the download time of chunks. A near-optimal solution algorithm is designed which schedules chunks to the servers with minimal downloading time while the completion probability is under the constraint. Compared with the existing schemes, the experimental results demonstrate that our proposed scheme greatly increases the number of chunks that are received orderly.

A control theory based rate adaption scheme for dash over multiple servers

Recently, Dynamic Adaptive Streaming over HTTP (DASH) has been widely deployed in the Internet. However, the research about DASH over Multiple Content Distribution Servers (MCDS) is few. Compared with traditional single-server-DASH, MCDS are able to offer expanded bandwidth, link diversity, and reliability. It is, however, a challenging problem to smooth video bitrate switchings over multiple servers due to their diverse bandwidths. In this paper, we propose a block-based rate adaptation method considering both the diverse bandwidths and feedback buffered video time. Multiple fragments are grouped into a block, and the fragments are downloaded in parallel from multiple servers. We propose to adapt video bitrate at the block level rather than at the fragment level. By dynamically adjusting the block length and scheduling fragment requests to multiple servers, the requested video bitrates from the multiple servers are synchronized, making the fragments downloaded orderly. Then, we propose a control-theoretic approach to select an appropriate bitrate for each block. By modeling and linearizing the rate adaption system, we propose a novel Proportional-Derivative (PD) controller to adapt video bitrate with high responsiveness and stability. Theoretical analysis and extensive experiments on the Internet demonstrate the good efficiency of our DASH designs.

Buffer-based control theoretic approach for dynamically HTTP Streaming

Dynamic adaptive streaming over HTTP (DASH) has recently been widely deployed in the Internet. It, however, does not impose any adaptation logic for selecting the quality of video fragments requested by clients. In this challenge, we have designed a novel rate adaptation scheme for Dynamic HTTP Streaming, by which, low start-up time, continuous and smooth video playback, and high bandwidth utilization are obtained. The algorithm is mainly based on our previous work [1] [2] that a PD controller are adopted to guide the rate adaptation. Moreover, we further improve the performance of start-up delay by fast-start approach and dynamic buffer size adjustment. The numerous experiment results have demonstrated the good performance of our designed rate adaptation compared with the Bitdash [3].