Operations Research Approach Towards Layered Multi-Source Video Delivery

We address the problem of rate scaling of multiple layered video streams in applications such as a multi-camera video surveillance system. This differs from the single video streaming scenario in that relevant information from all sources has to be aggregated and a collective decision made. We propose a scenario to achieve better granularity in quality adaptation by considering inter-source and inter-layer streaming jointly, using Operation Research techniques to arrive at an optimal or nearoptimal solution. We formulate our Multi-Source MultiLayer Selection (SLS) problem in the form of a MultipleChoice Knapsack Problem (MCKP). We analyze optimal and approximate algorithms to determine their suitability for solving the problem. We present a simple modification based on an existing greedy aglorithm by exploiting some properties of layered video. The modified SLS algorithm is extended to incorporate weights (Weighted SLS - WSLS - algorithm). Via experimental results using MPEG-4 FGS, we show that WSLS improves the performance for specialized applications. We also discuss the various network configurations of a multi-source video distribution system.