Human action recognition with MPEG-7 descriptors and architectures

Modern video surveillance requires addressing high-level concepts such as humans' actions and activities. In addition, surveillance applications need to be portable over a variety of platforms, from servers to mobile devices. In this paper, we explore the potential of the MPEG-7 standard to provide interfaces, descriptors, and architectures for human action recognition from surveillance cameras. Two novel MPEG-7 descriptors, symbolic and feature-based, are presented alongside two different architectures, server-intensive and client-intensive. The descriptors and architectures are evaluated in the paper by way of a scenario analysis.