**5.1 Data fusion**

Data fusion plays an important role in co-operative systems. A stand alone sensor or several sensors installed in a vehicle cannot overcome certain physical limitations as, for example, the limited range and field of view. Therefore combing information coming from both onboard sensors and wireless messages, encompassing information from other vehicles, broadens the awareness of the driver and increases the reliability of the whole system in case of sensor failure. However, fusing information from highly mobile vehicles, forming a wireless network, is a challenging task (Ahlers & Stimming, 2008; Lytrivis et al., 2008).

The Joint Directors of Laboratories (JDL) functional model, which is the most prevalent in data fusion community, is depicted in Figure 10. According to this model the data processing is divided to the following levels: signal, object, situation and application. All these levels communicate and exchange data through a storage and system manager (Liggins et al., 2008).

Fig. 10. Joint Directors of Laboratories (JDL) model.

In the data fusion process the main focus is on object and situation refinement levels, which refer to the state estimation of objects and the relations among them, correspondingly. The discrimination between these levels is also made by using the terms low and high level fusion instead of object and situation refinement. The different levels of the JDL model are summarized below:


In the past decade the advances in autonomous sensor technologies and the major objective of the European Union to reduce to a half road accidents and fatalities by 2010, led to the development of advanced driver assistance systems (ADAS). The fusion of data coming from different advanced in-vehicle sensors was initially in the centre of this attempt. However, this approach suffers from serious limitations. Specifically:


Recently the focus of research activities on co-operative systems is driven by the attempts to overcome all the above limitations. The limited bandwidth, security issues, privacy, reliability and propagation are some of the emerging disadvantages of the wireless connectivity in vehicles. All these issues poses additional challenges to the data fusion process. The association and synchronization of data from on-board sensors together with the wireless network data is the main challenge. Moreover, the manipulation of delayed information and the reliability of the information transferred via the network are other important issues.
