Low power scheme for image based object identification in wireless multimedia sensor networks

Applications based on video and image in Wireless Sensor Network are highly attractive due to their wealth of information´s. However, the implementation of such application with WMSN requires a specific image processing scheme and an efficient communication protocol. In fact, the efficiency and the validity of these multimedia applications over wireless sensor networks are dependent on the capabilities of the designer to provide low-power data processing and energy-aware communication protocols. This paper presents a contribution to the design of low complexity scheme for object identification using Multimedia Wireless Sensor Networks. The proposed scheme intended to achieve low-power was tested and it proves good performances to identify objects. The power consumption and the time processing were estimated for MICA2 and MICAZ motes and showed that the scheme outperforms the methods based on image compression.