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.
%0 Conference Paper
%1 bulling09_ubicomp
%A Bulling, Andreas
%A Ward, Jamie A.
%A Gellersen, Hans
%A Tröster, Gerhard
%B Proc. ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp)
%D 2009
%K (EOG), Activities Activity Analysis, Electrooculography Eye Movement Office Recognition Recognition, hcics of vis
%P 41-50
%R 10.1145/1620545.1620552
%T Eye Movement Analysis for Activity Recognition
%X 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.
@inproceedings{bulling09_ubicomp,
abstract = {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.},
added-at = {2024-07-11T10:05:52.000+0200},
author = {Bulling, Andreas and Ward, Jamie A. and Gellersen, Hans and Tr{\"{o}}ster, Gerhard},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/27cf536b4f15069c4da406d3963dbce75/hcics},
booktitle = {Proc. ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp)},
doi = {10.1145/1620545.1620552},
interhash = {295a5ae8af30d6bb12db8d51c63d8e19},
intrahash = {7cf536b4f15069c4da406d3963dbce75},
keywords = {(EOG), Activities Activity Analysis, Electrooculography Eye Movement Office Recognition Recognition, hcics of vis},
pages = {41-50},
timestamp = {2024-07-11T10:11:36.000+0200},
title = {Eye Movement Analysis for Activity Recognition},
year = 2009
}
