Robust Scalable Video Streaming over Internet with Network-Adaptive Congestion Control and Unequal Loss Protection

Video communication with Quality of Service (QoS) is an important and challenging task. To have QoS provision or guarantee at application level in the current best-effort Internet, congestion control and error control are two effective approaches. In this paper, we propose a new network-adaptive congestion control scheme for scalable video streaming in conjunction with Unequal Loss Protection (ULP). The proposed scheme not only dynamically adapts the bit rate to the varying network condition, but also has the error-concealment capability. In other words, our proposed approach is capable of simultaneously controlling congestion and packet loss occurred across the Internet. More specifically, first, we dynamically estimate the available network bandwidth on the fly. Secondly, congestion control is performed to smoothly adjust the sending rate for continuous media. Thirdly, error protection at packet level is added using ULP while performing congestion control. Fourthly, unequal interleaving and fixed length packetization are introduced to improve the efficiency of network bandwidth utilization. Lastly, Rate-Distortion (R-D)-based bit allocation is proposed to minimize the end-to-end distortion. Simulation results demonstrate effectiveness of our approach.