Advertisement

Attention Detection by Learning Hierarchy Feature Fusion on Eye Movement

  • Bing Liu
  • Peilin Jiang
  • Fei Wang
  • Xuetao Zhang
  • Haifan Hao
  • Shanglin Bai
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)

Abstract

Human concentration state detection using the eye movement information is now a popular research topic in computer vision, especially the detection of driver fatigue and advertising analysis. In this paper we analyze eye movement styles on a person’s concentration state through watching different video clips. We propose a novel method including the fusion features of eye event data and raw eye movement to detect attention. Firstly, we use the logistic regression algorithm to conduct the new feature by eye movement event data, and use wavelet and approximate entropy algorithm to conduct the new feature by raw eye movement data. Secondly, we train attention detection model using these new merged features. In order to avoid the problem caused by insufficient samples, crossing method is used to train the model to ensure its accuracy. Our model achieves a satisfying 95.25% accuracy.

Keywords

Attention Eye movement data Logistic regression Wavelet Entropy Learning 

References

  1. 1.
    Yan, G., Bai, X.: Research and Development Trend of Eye Movement in Advertising Psychology. Tianjin Normal University (2004). (in Chinese)Google Scholar
  2. 2.
    Yan, G., et al.: A review of the main eye movement indicators in reading. Adv. Psychol. Sci. 21(004), 589–605 (2013). (in Chinese)Google Scholar
  3. 3.
    Duchowski, A.T.: Eye Tracking Methodology: Theory and Practice. Springer, London (2003).  https://doi.org/10.1007/978-1-4471-3750-4CrossRefMATHGoogle Scholar
  4. 4.
    Xu, W.: The tracking effect assessment by eye tracker in movie and television play implanted by advertising. Shanghai Jiaotong University (2016). (in Chinese)Google Scholar
  5. 5.
    Kliegl, R., Grabner, E., Rolfs, M.: Length frequency predictability effects of words on eye movement in reading. Eur. J. Cognit. Psychol. 16(1), 262–284 (2001)Google Scholar
  6. 6.
    Du, Z., Pan, X., Guo, X.: Study on the application of traffic safety evaluation indicator in import and export of highway tunnel. J. Tongji Univ. (Natural Science Edition) 36(3), 325–329 (2008). (in Chinese)Google Scholar
  7. 7.
    Stato, S.: Does fatigue exist in a quantitative measurement of eye movement. Ergonomics 35(5), 607–615 (1992)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Bing Liu
    • 1
  • Peilin Jiang
    • 2
  • Fei Wang
    • 3
  • Xuetao Zhang
    • 3
  • Haifan Hao
    • 1
  • Shanglin Bai
    • 1
  1. 1.The Software Engineering SchoolXi’an Jiaotong UniversityXi’anChina
  2. 2.The Software Engineering School, National Engineering Laboratory for Visual Information Processing and ApplicationXi’an Jiaotong UniversityXi’anChina
  3. 3.The Electric and Information Engineering SchoolXi’an Jiaotong UniversityXi’anChina

Personalised recommendations