Pervasive smart camera networks exploiting heterogeneous wireless channels

Smart cameras are embedded systems that perform on-board video content analysis and only report detected events instead of permanently streaming videos. Visual sensor networks aim at integrating smart cameras with wireless sensor networks. Camera sensors have higher requirements regarding computing power and communication bandwidth than those typically used in wireless sensor network applications. Consequently, power management is an even more critical issue. This work in progress presents an attempt to address this by combining high and low power radios as well as high and low performance computing systems in one single platform. This allows to control power consumption by selectively enabling only required components.

I. Introduction

Smart cameras are real-time embedded systems that perform image analysis on-board and typically deliver high-level event descriptions [1]. For important events, videos can be streamed allowing operators to visually evaluate the situation. Networks of smart cameras combine distributed sensing with distributed computing and have emerged thanks to a confluence of advances in the fields of computer vision, sensor networks, embedded systems and distributed computing [2]. Besides ongoing progress in areas like lenses, image sensors and processors, these networks are one key aspect of the revolution in the field of cameras taking place at the dawn of the twenty first century. This revolution will change our conception of cameras as boxes that capture images into a more general notion of cameras as spatially distributed sensors that generate data and events.