A Shape-Based Object Identification Scheme in Wireless Multimedia Sensor Networks

Abstract

Multimedia communication is highly attractive in Wireless Multimedia Sensor Networks (WMSN) due to their wealth of information’s. However, the transmission of multimedia information such as image and video requires a specific scheme and an efficient communication protocol. In fact, the performances of multimedia based applications on WMSN are highly dependent on the capabilities of the designer to provide low-power data processing and energy-aware communication protocols. This chapter presents a contribution to the design of low complexity scheme for object identification using Wireless Multimedia Sensor Networks. The main idea behind the design of this scheme is to avoid useless multimedia data streaming on the network. In depth, it ensures the detection of the specific event (target) before sending image to notify the end user. The chapter discusses the capabilities of the proposed scheme to identify a target and to achieve low-power processing at the source mote while unloading the network. The power consumption and the time processing of this scheme were estimated for MICA2 and MICAZ motes and showed that it outperforms other methods for communication in WMSN such as the methods based on image compression.KeywordsWireless Sensor NetworkObject DetectionWireless Sensor NodeObject ExtractionCentroid DistanceThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.