Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Eye Movement Analysis for Activity Recognition
AU - Bulling, Andreas
AU - Ward, Jamie A
AU - Gellersen, Hans
AU - Tröster, Gerhard
PY - 2009/9/30
Y1 - 2009/9/30
N2 - 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.
AB - 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.
KW - Ubiquitous computing
U2 - 10.1145/1620545.1620552
DO - 10.1145/1620545.1620552
M3 - Conference contribution/Paper
SN - 978-1-60558-431-7
SP - 41
EP - 50
BT - Ubicomp '09 Proceedings of the 11th international conference on Ubiquitous computing
PB - ACM
CY - New York
T2 - International Conference on Ubiquitous Computing (UbiComp 2009)
Y2 - 30 September 2009 through 3 October 2009
ER -