Adaptive data partitioning for ambient multimedia

Xiaoping Hu, Radu Marculescu

Abstract: In the near future, Ambient Intelligence (AmI) will become part of everyday life. Combining feature-rich multimedia with AmI (dubbed Ambient Multimedia for short) has the potential of changing the way we perceive and interact with our environment. One major difficulty, however, in designing Ambient Multimedia Systems (AMS) comes from the strong constraints imposed on system resources by the AmI application requirements. In this paper, we propose a method for mapping multimedia applications on systems with very limited resources (i.e. memory, computing capability and battery lifetime) by combining adaptive data partitioning with dynamic power management. The potential of the approach is illustrated through a case study of an object tracking application running on a resource-constrained platform.