Person detection and face analysis for human machine interaction
|Duration:||1.11.2010 - 30.10.2013|
|Funding:||Sächsische Aufbaubank (SAB), Cognitec Systems GmbH Dresden|
|Project colaborator:||Dipl.-Inf. (FH) Peter Poschmann|
In the past years, multi-modal human-machine-interaction has gained a lot of interest. The main reason is the fact that modern systems, though usually being very powerful and efficient, have substantial deficits concerning the intuitive operability by the actual user. For example, information terminals and ticket machines often demand a high level of frustration tolerance from their users. That is because of the insufficient and little intuitive user guidance, caused by the flawed or inflexible dialog modeling and usually insufficient cognitive abilities of such systems, restricting the possibilities of situation-dependent reactions.
Recently, a trend arises towards interactive technical assistance systems that possess the necessary sensor channels to perceive the human counterpart and can then adjust their own behavior based on the observations. Based on that foundation, entirely novel interactive assistance systems are developed, which have communication skills that are as natural and intuitively comprehensible as possible, and therefore ease the usage with these systems immense.
A special focus is set on the detailed analysis of the human interaction partner's face, because there cognition of a person and interpretation of its mimics play a crucial role in human-human communication, as well. There are existing methods that already yield good results under ideal conditions, but there is a strong need for research of the applicability under the broad spectrum of real world conditions.
The above statements are in particular true for the research area of interactive mobile service and assistance systems and robots. Especially in this area the success of an application depends on theability of the robot to perform its tasks using preferably natural and intuitive comprehensible interaction with its human user(s).