next up previous
Next: A Set of Basic Up: Computer Vision for Support Previous: Remarks Concerning the History

Discussion of CV for Driver Support

CV will constitute a major, but clearly not the only type of sensoric channel required to offer a driver comprehensive support for his activities. In order to indicate more precisely the role which CV might play in this context, we subdivide the overall capabilities of a DSS into four sectors:

  1. The DSS must communicate with the driver in order to learn about his current goal(s) and to inform him about whatever messages it deems important for the driver.
  2. The DSS must continuously monitor the vehicle and its reaction to the `commands' which the driver transmits by operating actuators like, e. g., steering wheel, gas and brake pedals. In order to properly assess such driver activities, a basic DSS capability to operate these and other actuators under suitable boundary conditions for a satisfactory performance of automatic driving manouvers will be an advantage.
  3. The DSS must continuously monitor the traffic situation (i) in the immediate environment of the vehicle as well as (ii) that on future road segments along the intended route. Whereas state information about the latter may be received via a Radio Data System Traffic Message Channel (RDS/TMC), via microwave or via infrared beacons, in general CV is expected to provide the most powerful sensing capability for case (i).
  4. The DSS must continuously monitor the driver's state in order to assess his ability to react appropriately: for example, a DSS activity like a warning about some potentially minor thread should not be transmitted to the driver while he attempts to avoid an imminent collision.
CV is expected to contribute predominantly to monitoring the traffic situation and possibly to some extent to monitoring the driver's state. In view of recent research regarding Multimedia approaches as communication tools, it is conceivable that video input of gestures in combination with speech input may offer further perspectives for driver support by CV. The DSS is considered to be an agent, i. e. an encapsulated digital process endowed not only with its own internal state space and control, but in addition with an explicitly statable goal, externally visible actions which enable the agent to sense the state of its environment as well as to communicate with and to influence its environment, and a planning capability which concatenates actions into a plan in order to achieve the goal of the agent. Such an `agent concept' provides a computational model which facilitates to talk about the DSS in a precise manner: it is assumed that a DSS is permanently alive once the vehicle electronics has been switched on, the DSS may at any time initiate activities - for example communicate with the driver - and it may spawn subagents to whom it may delegate to pursue clearly circumscribed subtasks as their (sub)goals.




next up previous
Next: A Set of Basic Up: Computer Vision for Support Previous: Remarks Concerning the History

ECVNet-Tutorial