Wireless Multimedia Sensor Networks (WMSN)


Wireless Sensor Networks  (WSN) have recently been the focus of a significant amount of attention and effort of the research community. The main motivation has been to address the challenges posed by the WSN paradigm, i.e., limited node power, processing, and communication capabilities, dense network deployment, multi-hop communications, and heterogeneous application-specific requirements. The vast majority of these studies applies to conventional WSN applications which need reliable and efficient communication of scalar event features and sensor data such as temperature, pressure, humidity.

 

With the availability of low-cost small-scale imaging sensors, CMOS cameras, microphones, which may ubiquitously capture multimedia content from the field, Wireless Multimedia Sensor Networks (WMSN) have been proposed and drawn the immediate attention of the research community. WMSN applications, e.g., multimedia surveillance networks, target tracking, environmental monitoring, and traffic management systems, require effective harvesting and communication of event features in the form of multimedia such as audio, image, and video. To this end, additional challenges for energy-efficient multimedia processing and communication in WMSN, i.e., heterogeneous multimedia reliability definitions, tight QoS expectations, and high bandwidth demands, must be addressed as well.

Current research activities:  We are building a WMSN Lab to experiment with multimedia applications in sensor architectures. Frame manipulation is required to minimize the amount of data to be sent. Visual Computing techniques such as background subtraction, object recognition, etc, may play an interesting role in this applications. We are also defining and evaluating network protocols for WMSN taking into account traffic characteristics.

Publications


People

Ruken Zilan, Sergio Navarro, José Mª Barceló-Ordinas

Collaboration with Dr. Bulent Tavli (TOBB Univ. of Economics and Technology, Ankara, Turkey)



 

Home