conferences

The publications below have been peer reviewed by an international committee of domain experts.

All datasets - if not stated otherwise - are licensed under a
Creative Commons Attribution-Noncommercial 3.0 Unported License.

:: 2010

• On the issue of variability in labels and sensor configurations in activity recognition systems
  Daniel Roggen, Kilian Förster, Alberto Calatroni, Andreas Bulling and Gerhard Tröster
  Proc. of the Workshop "How to do good activity recognition research? Experimental methodologies, evaluation metrics, and reproducibility issues" (Pervasive 2010)
  Helsinki, Finland, pages ?-?, May 2010.
  [Abstract BibTeX RIS PDF]
  
  

  Two aspects of the design and characterization of activity recognition systems are rarely elaborated in the literature. First, the influence of system performance with variability in sensor placement and orientation is often overlooked. This is important for the deployment of robust activity recognition systems. Second, the influence of labeling variability is also overlooked, especially w.r.t. label boundary jitter and labeling errors. This is important during the development of an activity recognition system as acquiring labels is costly. We argue that there is a need to explicitly address the consequences of such variability in publications, together with the mitigation strategies that are used. Elaborating on this is required to move the state of the art towards real-world applications, such as in industrial wearable assistance applications or pervasive healthcare.

:: 2009

• Eye Movement Analysis for Activity Recognition
  Andreas Bulling, Jamie A. Ward, Hans Gellersen and Gerhard Tröster
  Proc. of the 11th International Conference on Ubiquitous Computing (UbiComp 2009)
  Orlando, United States, pages 41-50, ACM Press, September 2009.
  [Abstract BibTeX RIS DOI PDF] acceptance rate: 12.4%, best paper nominee
  
  

  In this work we investigate eye movement analysis as a new modality for recognising human activity. We devise 90 different features based on the main eye movement characteristics: saccades, fixations and blinks. The features are derived from eye movement data recorded using a wearable electrooculographic (EOG) system. We describe a recognition methodology that combines minimum redundancy maximum relevance feature selection (mRMR) with a support vector machine (SVM) classifier. We validate the method in an eight participant study in an office environment using five activity classes: copying a text, reading a printed paper, taking hand-written notes, watching a video and browsing the web. In addition, we include periods with no specific activity. Using a person-independent (leave-one-out) training scheme, we obtain an average precision of 76.1% and recall of 70.5% over all classes and participants. We discuss the most relevant features and show that eye movement analysis is a rich and thus promising modality for activity recognition.
• Speech as a Feedback Modality for Smart Objects
  Clemens Lombriser, Andreas Bulling, Andreas Breitenmoser and Gerhard Tröster
  Proc. of the 2nd International Workshop on Intelligent Pervasive Devices (PerDev 2009)
  Galveston, United States, pages 1-5, IEEE Press, March 2009.
  [Abstract BibTeX RIS DOI PDF]
  
  

  One part of the vision of ubiquitous computing is the integration of sensing and actuation nodes into everyday objects, clothes worn on the body, and in large numbers in the environment. These augmented environments require novel types of interfaces that provide for naturalistic and adaptive interaction depending on the user context. In this paper, we evaluate the use of speech synthesis on small, low-power sensor nodes that may be integrated into smart objects. We evaluate the so-called Wireless Voice Node, a wireless sensor node with the ability to produce speech as a novel feedback modality for ambient intelligence applications. As an example, we present a doll that aims at using speech synthesis to improve the playing experience of children.
• Wearable EOG Goggles: Eye-Based Interaction in Everyday Environments
  Andreas Bulling, Daniel Roggen and Gerhard Tröster
  Ext. Abstracts of the 27th ACM Conference on Human Factors in Computing Systems (CHI 2009)
  Boston, United States, pages 3259-3264, ACM Press, April 2009.
  [Abstract BibTeX RIS DOI PDF]
  
  

  In this paper, we present an embedded eye tracker for context-awareness and eye-based human-computer interaction – the wearable EOG goggles. In contrast to common systems using video, this unobtrusive device relies on Electrooculography (EOG). It consists of goggles with dry electrodes integrated into the frame and a small pocket-worn component with a powerful microcontroller for EOG signal processing. Using this lightweight system, sequences of eye movements, so-called eye gestures, can be efficiently recognised from EOG signals in real-time for HCI purposes. The device is self-contained solution and allows for seamless eye motion sensing, context-recognition and eye-based interaction in everyday environments.

:: 2008

• EyeMote - Towards Context-Aware Gaming Using Eye Movements Recorded From Wearable Electrooculography
  Andreas Bulling, Daniel Roggen and Gerhard Tröster
  Proc. of the 2nd International Conference on Fun and Games (FnG 2008)
  Eindhoven, The Netherlands, pages 33-45, Springer, October 2008.
  [Abstract BibTeX RIS DOI PDF]
  
  

  Physical activity has emerged as a novel input modality for so-called active video games. Input devices such as music instruments, dance mats or the Wii accessories allow for novel ways of interaction and a more immersive gaming experience. In this work we describe how eye movements recognised from electrooculographic (EOG) signals can be used for gaming purposes in three different scenarios. In contrast to common video-based systems, EOG can be implemented as a wearable and light-weight system which allows for long-term use with unconstrained simultaneous physical activity. In a stationary computer game we show that eye gestures of varying complexity can be recognised online with equal performance to a state-of-the-art video-based system. For pervasive gaming scenarios, we show how eye movements can be recognised in the presence of signal artefacts caused by physical activity such as walking. Finally, we describe possible future context-aware games which exploit unconscious eye movements and show which possibilities this new input modality may open up.
• It's in Your Eyes - Towards Context-Awareness and Mobile HCI Using Wearable EOG Goggles
  Andreas Bulling, Daniel Roggen and Gerhard Tröster
  Proc. of the 10th International Conference on Ubiquitous Computing (UbiComp 2008)
  Seoul, South Korea, pages 84-93, ACM Press, September 2008.
  [Abstract BibTeX RIS DOI PDF] acceptance rate: 18.6%
  
  

  In this work we describe the design, implementation and evaluation of a novel eye tracker for context-awareness and mobile HCI applications. In contrast to common systems using video cameras, this compact device relies on Electrooculography (EOG). It consists of goggles with dry electrodes integrated into the frame and a small pocket-worn component with a DSP for real-time EOG signal processing. The device is intended for wearable and standalone use: It can store data locally for long-term recordings or stream processed EOG signals to a remote device over Bluetooth. We describe how eye gestures can be efficiently recognised from EOG signals for HCI purposes. In an experiment conducted with 11 subjects playing a computer game we show that 8 eye gestures of varying complexity can be continuously recognised with equal performance to a state-of-the-art video-based system. Physical activity leads to artefacts in the EOG signal. We describe how these artefacts can be removed using an adaptive filtering scheme and characterise this approach on a 5-subject dataset. In addition to explicit eye movements for HCI, we discuss how the analysis of unconscious eye movements may eventually allow to deduce information on user activity and context not available with current sensing modalities.
• Robust Recognition of Reading Activity in Transit Using Wearable Electrooculography
  Andreas Bulling, Jamie A. Ward, Hans Gellersen and Gerhard Tröster
  Proc. of the 6th International Conference on Pervasive Computing (Pervasive 2008)
  Sydney, Australia, pages 19-37, Springer, May 2008.
  [Abstract BibTeX RIS DOI PDF Dataset] acceptance rate: 15.8%
  
  

  In this work we analyse the eye movements of people in transit in an everyday environment using a wearable electrooculographic (EOG) system. We compare three approaches for continuous recognition of reading activities: a string matching algorithm which exploits typical characteristics of reading signals, such as saccades and fixations; and two variants of Hidden Markov Models (HMMs) - mixed Gaussian and discrete. The recognition algorithms are evaluated in an experiment performed with eight subjects reading freely chosen text without pictures while sitting at a desk, standing, walking indoors and outdoors, and riding a tram. A total dataset of roughly 6 hours was collected with reading activity accounting for about half of the time. We were able to detect reading activities over all subjects with a top recognition rate of 80.2% (71.0% recall, 11.6% false positives) using string matching. We show that EOG is a potentially robust technique for reading recognition across a number of typical daily situations.

www.andreas-bulling.de | © 2006-2010 Andreas Bulling
last update: 07 March 2010