Online Vigilance Analysis Combining Video and Electrooculography Features

It is widely acknowledged that one can never emphasize vigilance too much, especially for drivers, policemen and soldiers. Unfortunately, almost every existing vigilance analysis system has its limitations and suffers from poor illumination, horizon of the cameras, together with various appearance and behaviors of the subjects. In this paper, we propose a novel system to analysis vigilance level combining both video and Electrooculography (EOG) features. Our system exploits 16 kinds of features extracted from an infrared camera and 48 kinds of features from horizontal and vertical channels of EOG signals. For one thing, the video features include percentage of closure (PERCLOS), eye blinks, slow eye movement (SEM), rapid eye movement (REM), which are also extracted from EOG signals. For another, other features like yawn frequency, body posture and face orientation are extracted from the video based on Active Shape Model (ASM). The results of our experiments indicate that our approach outperforms that based on either video or EOG merely. In addition, the prediction offered by our model is in close proximity to the actual error rate of the subject. We firmly believe that this method can be widely applied to prevent accidents like fatigued driving in the future.

Publications

teaser image of Online Vigilance Analysis Combining Video and Electrooculography Features

Online Vigilance Analysis Combining Video and Electrooculography Features

Neural Information Processing - 19th International Conference (ICONIP), 2012.
Keywords: Vigilance Analysis Fatigue Detection Active Shape Model Electrooculography Support Vector Machine

Videos

Online Vigilance Analysis Combining Video and Electrooculography Features


Talks

Online Vigilance Analysis Combining Video and Electrooculography Features Teaser Image.

Online Vigilance Analysis Combining Video and Electrooculography Features

Ruofei Du

ICONIP2012, Doha, Qatar.


Cited By

  • Detection of Driving Fatigue Based on Grip Force on Steering Wheel With Wavelet Transformation and Support Vector Machine. 9. Fan Li, Xiao-Wei Wang, and Bao-Liang Lu. source | cite
  • Testing of Features for Fatigue Detection in EOG. Bio-Medical Materials and Engineering. Andrea Němcová, Oto Janoušek, Martin Vítek, and Ivo Provazník. source | cite
  • Eye Tracking and Eye-Based Human\textendashComputer Interaction. Advances in Physiological Computing. Päivi Majaranta and Andreas Bulling. source | cite
  • Classification of Electrooculograph Signals: Comparing Conventional Classifiers Using CBFS Feature Selection Algorithm. 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT). S. Mala and K. Latha. source | cite
  • Feature Selection in Categorizing Activities by Eye Movements Using Electrooculograph Signals. 2014 International Conference on Science Engineering and Management Research (ICSEMR). S. Mala and K. Latha. source | cite
  • Demystification of Electrooculogram Signals: An Introductory Approach to Activity Recognition. The 3rd International Conference on Computer Engineering and Mathematical Sciences (ICCEMS 2014). S. Mala and K. Latha. source | cite
  • The Role of Feature Selection With Applications to Eye Movements Using Electrooculography. Biosciences Biotechnology Research Asia. S. Mala and K. Latha. source | cite
  • Stay In Touch