- MOBVIS is a Specifically Targeted Research Project (STReP) funded by the European Commission
- IST-2002-22.214.171.124 FET open
- Project Number: FP6-511051
The MOBVIS project identifies the key issue for the realisation of smart mobile vision services to be the application of context to solve otherwise intractable vision tasks. In order to achieve this challenging goal, MOBVIS claims that three components, (1) multi-modal context awareness, (2) vision based object recognition, and (3) intelligent map technology, should be combined for the first time into a completely innovative system - the attentive interface.
In multi-modal interface design, “Attentive User Interfaces” are an emerging paradigm with the emphasis to generate interface control directing attention in human and machine. MOBVIS conceptually and functionally extends this framework to “Attentive Interfaces” that involve machine attention mechanisms, i.e., to selectively index into information spaces dependent on a given user relevant context.
The attentive interface would be the only possible way to cut down the numerous system’s hypotheses on the real world, by first aggregating context information, then applying context to make mobile vision based object awareness feasible, and incremental updating of map based geo-information to provide a knowledge base for future context exploitation.
The project goal is research to identify and investigate on key challenges for the development of mobile vision interfaces, and providing a demonstrator interface that is attentive to objects of interest in urban scenarios, such as, buildings, infrastructure, faces, cars, and informative icons and text. The detected objects will together define contextual situations, they cue to expected places, objects, information and events, and they feed into an augmented digital map representation, as a basis for enriched smart services in personal assistance for the mobile and automotive industry.
Mobile vision will become a fundamental technology for enhanced perceptive presence, context aware and attentive interfaces, and urban environments provide the scenarios for emerging applications. The MOBVIS project overtakes the impetus of upcoming mobile imaging, and encounters the challenges to integrate computer vision and intelligent map technology, in order to enable mobile vision services become reality in the near future.