Tracking in Urban Environments Using Sensor Networks Based on Audio-Video Fusion

Heterogeneous sensor networks (HSNs) are gaining popularity in diverse fields, such as military surveillance, equipment monitoring, and target tracking [41]. They are natural steps in the evolution of wireless sensor networks (WSNs) driven by several factors. Increasingly, WSNs will need to support multiple, although not necessarily concurrent, applications. Different applications may require different resources. Some applications can make use of nodes with different capabilities. As the technology matures, new types of nodes will become available and existing deployments will be refreshed. Diverse nodes will need to coexist and support old and new applications. Furthermore, as WSNs are deployed for applications that observe more complex phenomena, multiple sensing modalities become necessary. Different sensors usually have different resource requirements in terms of processing power, memory capacity, or communication bandwidth. Instead of using a network of homogeneous devices supporting resource intensive sensors, an HSN can have different nodes for different sensing tasks [22, 34, 10]. For example, at one end of the spectrum low data-rate sensors measuring slowly changing physical parameters such as temperature, humidity or light, require minimal resources; while on the other end even low resolution video sensors require orders of magnitude more resources.