004 Datenverarbeitung; Informatik
Refine
Institute
Keywords
- Angewandte Informatik (1)
- Anpassung (1)
- Association for Computing Machinery / Special Interest Group on Graphics (1)
- Awareness (1)
- CGI <Computergraphik> (1)
- Group Awareness (1)
- Gruppengewahrsein (1)
- Handy (1)
- Kalibrierung (1)
- Maschinelles Sehen (1)
- Museum (1)
- Neuronales Netz (1)
- Objekterkennung (1)
- Objektverfolgung (1)
- Privacy (1)
- Privatsphäre (1)
- Projektor-Kamera Systeme (1)
- Radiometrische Kompensation (1)
- Reciprocity (1)
- Reziprozität (1)
- Ubiquitous Computing (1)
- calibration (1)
- imperceptible pattern projection (1)
- mobile phones (1)
- museum guidance (1)
- neural networks (1)
- object recognition (1)
- pervasive tracking (1)
- projector-camera systems (1)
- radiometric compensation (1)
- temporal adaptation (1)
- unsichtbare Muster Projektion (1)
Year of publication
- 2007 (3) (remove)
We present a novel multi-step technique for imperceptible geometry and radiometry calibration of projector-camera systems. Our approach can be used to display geometry and color corrected images on non-optimized surfaces at interactive rates while simultaneously performing a series of invisible structured light projections during runtime. It supports disjoint projector-camera configurations, fast and progressive improvements, as well as real-time correction rates of arbitrary graphical content. The calibration is automatically triggered when mis-registrations between camera, projector and surface are detected.
In ubiquitous environments an increasing number of sensors capture information on users and at the same time an increasing number of actuators are available to present information to users. This vast capturing of information potentially enables the system to adapt to the users. At the same time the system might violate the users' privacy by capturing information that the users do not want to share, and the system might disrupt the users by being too obtrusive in its adaptation or information supply. In this paper we present CoDaMine - a novel approach for providing users with system - generated feedback and control in ubiquitous environments giving them the freedom they need while reducing their effort. Basically, CoDaMine captures and analyses the users' online communication to learn about their social relationships in order to provide them with recommendations for inter-personal privacy and trust management.
We present an enhancement towards adaptive video training for PhoneGuide, a digital museum guidance system for ordinary camera–equipped mobile phones. It enables museum visitors to identify exhibits by capturing photos of them. In this article, a combined solution of object recognition and pervasive tracking is extended to a client–server–system for improving data acquisition and for supporting scale–invariant object recognition.