Efficient support for application-specific video adaptation

As video applications become more diverse, video must be adapted in different ways to meet the requirements of different applications when there are insufficient resources. In this dissertation, we address two sorts of requirements that cannot be addressed by existing video adaptation technologies: (i) accommodating large variations in resolution and (ii) collecting video effectively in a multi-hop sensor network. In addition, we also address requirements for implementing video adaptation in a sensor network. Accommodating large variation in resolution is required by the existence of display devices with widely disparate screen sizes. Existing resolution adaptation technologies usually aim at adapting video between two resolutions. We examine the limitations of these technologies that prevent them from supporting a large number of resolutions efficiently. We propose several hybrid schemes and study their performance. Among these hybrid schemes, Bonneville, a framework that combines Multiple encodings with limited scalability, can make good trade-offs when organizing compressed video to support a wide range of resolutions. Video collection in a sensor network requires adapting video in a multi-hop store-and-forward network and with multiple video sources. This task cannot be supported effectively by existing adaptation technologies, which are designed for real-time streaming applications from a single source over IP-style end-to-end connections. We propose to adapt video in the network instead of at the network edge. We also propose a framework, Steens, to compose adaptation mechanisms on multiple nodes. We design two signaling protocols in Steens to coordinate multiple nodes. Our simulations show that in-network adaptation can use buffer space on intermediate nodes for adaptation and achieve better video quality than conventional network-edge adaptation. Our simulations also show that explicit collaboration among multiple nodes through signaling can improve video quality, waste less bandwidth, and maintain bandwidth-sharing fairness. The implementation of video adaptation in a sensor network requires system support for programmability, retaskability, and high performance. We propose Cascades, a component-based framework, to provide the required support. A prototype implementation of Steens in this framework shows that the performance overhead is less than 5% compared to a hard-coded C implementation.