This chapter describes the field of Behaviour Monitoring and Interpretation, BMI for short, which defines a framework for the analysis and design of systems for the monitoring and interpretation of human behaviour. As an example scenario which is analysed by means of that framework, a pedestrian navigation and service tool is presented. This scenario is about a mobile user who is wearing a hearing-aid similar device that instructs him while walking through the city. The navigation assistant can be equipped with specific application constraints in order to enrich the navigation system with an application context. The navigation system guides the user through the environment while taking care of the application constraints. One application context is a child at pre-school age: within this context the idea is to guide the child along a safe path to kindergarten. There are many challenges involved in the development of such a pedestrian navigation system. This chapter focuses on the analysis of the behaviour of the user that determines how the navigation assistant can provide help in an appropriate way. By this means, principles underlying the field of behaviour monitoring and interpretation are explained. More specifically, how the BMI framework aids in analysing is shown along with how top-down and bottom-up processes are to be involved in behaviour recognition; additionally, how the framework supports the identification of information fusion at different abstraction layers is shown.
Top1. Introduction
“Navigation is the art of getting from one place to another, efficiently and safely,” accordingly to a widely used saying. Today a number of different navigation tools are available for several mobile devices. Although most have been designed for car navigation (Lee 2008), some are also available for pedestrian navigation (Aslan 2006). The omnipresence of tasks requiring humans to navigate from one place to another makes this an attractive issue to investigate the monitoring and interpretation of humans’ behaviours (Stark 2007). This is the reason for this paper to discuss the field of behaviour monitoring and interpretation by looking at how pedestrians could be supported by a navigation system.
Usually, the idea of pedestrian navigation tools consists in presenting the user a map of the environment (Delikostidis 2009). Additionally, information insets are displayed onto the map, in order to indicate the whereabouts of the user as well as where she has to go next; others augment audio information with visual cues about directions (Chittaro 2005). While such approaches simulate the employment of conventional city maps, there are other modes conceivable how an assistant could provide help for wayfinding tasks. For example, as opposed to conventional maps which show the environment from the bird’s eye view, a three dimensional view can be shown to the user on a graphical display (Maehara 2002); such a view simulates the perspective of the pedestrian, and hence, seems more plausible than a conventional map. Moreover, there are tactile maps which are particularly designed for visually impaired people (Caddeo 2006). Yet another example is a system giving audio instructions which completely replace the employment of maps (Fickas 2008). This has the advantage that devices are not necessary in order to display maps. Such devices require usually interactions with the user who does not always have his hands free. Another problem is that sun light is frequently too bright, making it impossible recognising information on the display. Eventually, many people have difficulties in reading maps, since maps contain normally too much information and because users have to know how they have to orient themselves with regard to the map. What all those navigation tools have in common are the underlying mechanisms to provide efficient routes.
While technology takes care of efficiency, safety is hardly taken into account by pedestrian navigation tools available today. Users might have difficulties in wayfinding tasks for quite different reasons, influencing what safety means in a particular context. Elderly, for instance, have sometimes difficulties in finding a place in unfamiliar environments (Chang 2010). Orientation abilities, it seems, degrade. Frequently elderly would feel uncomfortable when being at foreign places; little support is already of help. Even much more difficult is the situation for elderly who suffer from dementia, because orientation abilities of such patients significantly decrease.
Quite another group are children who are not trained to find their way alone (Read 2003). They usually have been together with their parents who take care of wayfinding. As soon as they would be allowed to go to school and elsewhere alone, they are in an age where most of them are particularly curious about everything happening around them. Additionally, they are active and behave vividly. Sometimes they do even unexpected things, posing a problem for themselves as well as other traffic participants. A kid following the ball that jumps onto the street is textbook.
Yet another target group are visually impaired pedestrians (Caddeo 2006). While they are used to find their way in familiar environments, foreign areas are difficult to exploit for them. In addition to the genuine wayfinding problem, appropriate instructions need to be given to visually impaired users. Depending on the specific environment that surrounds the user it will be more or less a challenge to take everything into account that should be known by the visually impaired user in order to guide him safely through the environment.