Multimodal Video Analysis on Self-Powered Resource-Limited Wireless Smart Camera

Abstract

Surveillance is one of the most promising applications for wireless sensor networks, stimulated by a confluence of simultaneous advances in key disciplines: computer vision, image sensors, embedded computing, energy harvesting, and sensor networks. However, computer vision typically requires notable amounts of computing performance, a considerable memory footprint and high power consumption. Thus, wireless smart cameras pose a challenge to current hardware capabilities in terms of low-power consumption and high imaging performance. For this reason, wireless surveillance systems still require considerable amount of research in different areas such as mote architectures, video processing algorithms, power management, energy harvesting and distributed engine. In this paper, we introduce a multimodal wireless smart camera equipped with a pyroelectric infrared sensor and solar energy harvester. The aim of this work is to achieve the following goals: 1) combining local processing, low power hardware design, power management and energy harvesting to develop a low-power, low-cost, power-aware, and self-sustainable wireless video sensor node for video processing on board; 2) develop an energy efficient smart camera with high accuracy abandoned/removed object detection capability. The efficiency of our approach is demonstrated by experimental results in terms of power consumption and video processing accuracy as well as in terms of self-sustainability. Finally, simulation results show how perpetual work can be achieved in an outdoor scenario within a typical video surveillance application dealing with abandoned/removed object detection.