Publication statistics

Pub. period:2010-2012
Pub. count:5
Number of co-authors:3


Number of publications with 3 favourite co-authors:

Oliver Schlatter:
Andreas M. Kunz:
Tim Schmidt:



Productive colleagues

Bastian Migge's 3 most productive colleagues in number of publications:

Andreas M. Kunz:73
Tim Schmidt:3
Oliver Schlatter:1

Upcoming Courses

go to course
Affordances: Designing Intuitive User Interfaces
go to course
Mobile User Experience Design
91% booked. Starts in 4 days

Featured chapter

Marc Hassenzahl explains the fascinating concept of User Experience and Experience Design. Commentaries by Don Norman, Eric Reiss, Mark Blythe, and Whitney Hess

User Experience and Experience Design !


Our Latest Books

The Social Design of Technical Systems: Building technologies for communities. 2nd Edition
by Brian Whitworth and Adnan Ahmad
start reading
Gamification at Work: Designing Engaging Business Software
by Janaki Mythily Kumar and Mario Herger
start reading
The Social Design of Technical Systems: Building technologies for communities
by Brian Whitworth and Adnan Ahmad
start reading
The Encyclopedia of Human-Computer Interaction, 2nd Ed.
by Mads Soegaard and Rikke Friis Dam
start reading

Bastian Migge

Personal Homepage:

Current place of employment:
ETH Zurich

Bastians research interests are in the area of artificial intelligence and control (reasoning, planning) and its applications for machine tools and manufacturing as well as virtual reality., This includes the design and development of non myopic controller to improve human machine interaction, which are based on decision-theoretic planning under uncertanty using Markov decision processes., Further fields of application are the autonomous environment adaptation of mobile devices, context recognition, and semi-autonomous assistant systems as well as combined simulation and planning methods.


Publications by Bastian Migge (bibliography)

 what's this?
Edit | Del

Schlatter, Oliver, Migge, Bastian and Kunz, Andreas M. (2012): User-aware Content Orientation on Interactive Tabletop Surfaces. In: Cyberworlds 2012 September 25-27, 2012, Darmstadt, Germany. pp. 246-250. Available online

An increasing number of human computer interaction systems are employing interactive table surfaces. For these horizontally aligned screens, the orientation of text passages and any other 'oriented' graphical content is a common problem. A user will not be able to easily read the same text from different sides of such a table unless it adapts to his position. To overcome this problem, we present an interactive system that extends the interaction space from measuring the direct manipulation on the interaction plane to observing the user in the space above the table. Hence, the content of the graphical user interface can automatically be aligned to the position of the active user, which enables the ergonomic reading of a text. We present a viewpoint tracking system, which utilizes the Microsoft Kinect depth sensor accessed with the OpenNI framework. This system does not need initial pose calibration and smoothens the vision based tracking data. In a next step, we show the benefit of extending the interaction space for a drawing application that allows multiple users to work on automatically oriented, digital notepads while still being able to freely move around the table.

© All rights reserved Schlatter et al. and/or their publisher

Edit | Del

Migge, Bastian and Kunz, Andreas M. (2012): Interaction Prediction for Content Synchronization of Net-based SharedWorkspaces. In: Proceedings of the 2012 International Conference on Cyberworlds CW 2012 September 25-27, 2012, Darmstadt, Germany. pp. 241-245.

Digital collaborative environments enable spatially separated users to access and modify shared data over network. However, transmission delays of the network lead to inconsistent data and reduce the efficiency of collaboration due to interaction conflicts. In this paper, we present a predictive screen-locking algorithm to avoid interaction collisions on net-based shared interactive screens. A model-based predictor calculates the user's next interaction given his past one. The algorithms locks critical objects to the remote station which is less likely to interact with the object. Although the predictor continuously adapts to the user's interaction behavior, an initial interaction model is needed when the collaboration session is started. Hence, we deduce a reasonable, probabilistic interaction model from a large screen collaboration user study.

© All rights reserved Migge and Kunz and/or their publisher

Edit | Del

Migge, Bastian, Kunz, Andreas M. and Schmidt, Tim (2011): Interaction Error Based Viewpoint Estimation for Continuous Parallax Correction on Interactive Screens. In: IADIS International Conference ICT, Society and Human Beings 2011 July 24, 2011, Rome. pp. 93-104. Available online

Many interactive screens suffer from the incoherence between image plane and interaction plane. The resulting gap causes parallax errors that hinder a precise interaction with the system. For many reasons, this gap cannot be physically reduced any further, while a software correction is still missing. Thus, this paper introduces an observation model for a continuous automatic recalibration controller of the touch sensitive surface. First, we show that the overall interaction error stems partly from the parallax error, which depends on the changing viewpoint of the user. Hence, a static calibration cannot overcome this error. Being not directly measurable, a continuously adapting correction controller sets the appropriate correction parameter based on updating the estimate of the user's viewpoint from the history of his interaction errors. To estimate the user's viewpoint in front of the screen based on the interaction error on the screen, we secondly investigate the correlation of the two domains from data of a user study, working on a large interactive screen with a significant gap between image plane and interaction plane. The correlation analysis shows significant differences in the interaction error stemming for different viewpoints, which allows the controller to infer the viewpoint. Finally, we model the results as a discrete observation model for the Partially Observable Markov Decision Processes (POMDP) correction controller.

© All rights reserved Migge et al. and/or their publisher

Edit | Del

Migge, Bastian, Schmidt, Tim and Kunz, Andreas M. (2010): POMDP Models for Continuous Calibration of Interactive Surfaces. In: Proceedings of the 2010 AAAI Spring Symposium, Embedded Reasoning Intelligence in Embedded Systems March 22-24, 2010, Palo Alto, USA. pp. 86-92. Available online

On interactive surfaces, an accurate calibration is crucial for a precise user interaction. Today, geometric distortions are eliminated by a static calibration. However, this calibration is specific to a user's posture and parallax distortions occur if this changes (i.e. when the user moves in front of the screen or multiple users take turns). In this paper, we describe an approach to apply Partially Observable Markov Decision Processes (POMDPs) for automatic online re-calibration to cope with changing viewpoints, which are indicated by uncertain observations of the user's interaction quality on the surface.

© All rights reserved Migge et al. and/or their publisher

Edit | Del

Migge, Bastian and Kunz, Andreas M. (2010): User Model for Predictive Calibration Control on Interactive Screens. In: Proceedings 2010 International Conference on Cyberworlds - Cyberworlds 2010 October 20-22, 2010, Singapur, Singapore. . Available online

On interactive surfaces, a precise calibration of the tracking system is necessary for an exact user interaction. So far, common calibration techniques focus on eliminating geometric distortions. This static calibration is only correct for a specific viewpoint of one single user and parallax error distortions still occur if this changes (i.e. if the user moves in front of the digital screen). In order to overcome this problem, we present an empirical model of the user_s position and movement in front of a digital screen. With this, a model predictive controller is able to correct the parallax error for future positions of the user. We deduce the model_s parameters from a user study on a large interactive whiteboard, in which we measured the 3D position of the user_s viewpoint during common interaction tasks.

© All rights reserved Migge and Kunz and/or IEEE Computer Society

Add publication
Show list on your website

Join our community and advance:




Join our community!

Page Information

Page maintainer: The Editorial Team