A Robust Online Saccadic Eye Movement Recognition Method Combining Electrooculography and Video

Eye movement is proven to be the most frequent activities of human beings; as a result research on recognition of unit eye movement has become a hotspot in human activity recognition. In this paper, we propose a robust online saccade recognition algorithm, which integrates electrooculography (EOG) and video together. Initially, EOG signals and video data are collected simultaneously from eight saccadic directions. Then online active eye movement segment detection algorithm is developed to detect the effective saccadic signal from ongoing eyeball activities. Furthermore, we extract features from different modalities and explore two fusion strategies [i.e., feature level fusion (FLF) and decision level fusion (DLF)]. In laboratory environment, the average recognition accuracy of FLF and DLF achieves 89.37% and 89.96%, respectively, which reveals that the proposed method can improve the performance of consecutive saccade recognition in comparison with sole modality.

[1]  Aurobinda Routray,et al.  Video & EOG based investigation of pure saccades in human subjects , 2012, 2012 4th International Conference on Intelligent Human Computer Interaction (IHCI).

[2]  Cordelia Schmid,et al.  A Robust and Efficient Video Representation for Action Recognition , 2015, International Journal of Computer Vision.

[3]  Kent Larson,et al.  Activity Recognition in the Home Using Simple and Ubiquitous Sensors , 2004, Pervasive.

[4]  Yong Peng,et al.  Discriminative extreme learning machine with supervised sparsity preserving for image classification , 2017, Neurocomputing.

[5]  Marcus Nyström,et al.  Detection of Saccades and Postsaccadic Oscillations in the Presence of Smooth Pursuit , 2013, IEEE Transactions on Biomedical Engineering.

[6]  Umer Fareed,et al.  Smartphone Sensor Fusion based Activity Recognition System for Elderly Healthcare , 2015, MobileHealth@MobiHoc.

[7]  J.K. Aggarwal,et al.  Human activity analysis , 2011, ACM Comput. Surv..

[8]  Doru Talaba,et al.  EOG-based visual navigation interface development , 2012, Expert Syst. Appl..

[9]  Zhao Lv,et al.  An algorithm for reading activity recognition based on electrooculogram , 2015, 2015 10th International Conference on Information, Communications and Signal Processing (ICICS).

[10]  Wu,et al.  A recursive calculating algorithm for higher-order cumulants over sliding window and its application in speech endpoint detection , 2015 .

[11]  Gerhard Tröster,et al.  Eye Movement Analysis for Activity Recognition Using Electrooculography , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Manoochehr Nahvi,et al.  An intelligent video surveillance system for fall and anesthesia detection for elderly and patients , 2015, 2015 2nd International Conference on Pattern Recognition and Image Analysis (IPRIA).

[13]  Wenjie Chen,et al.  Robust eye tracking and location method based on Particle filtering algorithm , 2014, 2014 IEEE 3rd International Conference on Cloud Computing and Intelligence Systems.

[14]  Jaideep Srivastava,et al.  Robust Automated Human Activity Recognition and Its Application to Sleep Research , 2016, 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW).

[15]  Leo Pauly,et al.  A novel method for eye tracking and blink detection in video frames , 2015, 2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS).

[16]  Mohiuddin Ahmad,et al.  Implementation of an EOG based security system by analyzing eye movement patterns , 2015, 2015 International Conference on Advances in Electrical Engineering (ICAEE).

[17]  Zhao Lv,et al.  A novel eye movement detection algorithm for EOG driven human computer interface , 2010, Pattern Recognit. Lett..