Network-optimized adaptive SVC-based live video streaming

In this work, a network-optimized live scalable video streaming scheme with adaptive preprocessing is presented, while showing significant improvements in visual quality. According to the proposed scheme, an adaptive pre-filter is applied prior to encoding each Scalable Video Coding (SVC) layer, while each pre-filter parameters are dynamically adjusted according to varying network conditions, such as the network Round Trip Time (RTT) and packet loss ratio, thereby enabling to continuously obtain an optimal visual quality at the decoder side. The performance of the presented scheme is evaluated and tested in detail, thereby demonstrating a significant gain of up to 5dB.