计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (10): 211-217.DOI: 10.3778/j.issn.1002-8331.2002-0191

• 工程与应用 • 上一篇    下一篇

基于深度学习的眼动跟踪数据融合算法

赵怡,高淑萍,何迪   

  1. 1.西安电子科技大学 数学与统计学院,西安 710126
    2.西安电子科技大学 通信工程学院,西安 710071
  • 出版日期:2021-05-15 发布日期:2021-05-10

Eye Movement and Tracking Data Fusion Algorithm Based on Deep Learning

ZHAO Yi, GAO Shuping, HE Di   

  1. 1.School of Mathematics and Statistics, Xidian University, Xi’an 710126, China
    2.School of Telecommunications Engineering, Xidian University, Xi’an 710071, China
  • Online:2021-05-15 Published:2021-05-10

摘要:

针对传统数据融合算法在多场景下的眼动跟踪数据融合效果较差的问题,提出一种新的基于深度学习的眼动跟踪数据融合算法,即Eye-CNN-BLSTM算法。该算法在原始眼动跟踪数据空间位置信息基础上添加新的人工特征;将卷积神经网络(Convolutional Neural Network,CNN)与双向长短时记忆网络(Bi-directional Long Short-Term Memory,BLSTM)结合,设计了新的融合结构。实验结果表明,与六种经典数据融合算法相比,该算法在OTB-100数据集上融合性能更优。

关键词: 眼动跟踪数据, 数据融合, 卷积神经网络(CNN), 双向长短时记忆网络(BLSTM)

Abstract:

For traditional data fusion algorithms, the fusion effect of eye movement and tracking data in multiple scenarios is poor. This paper proposes a new eye movement and tracking data fusion algorithm based on deep learning, namely Eye-CNN BLSTM algorithm. Firstly, the algorithm adds new artificial features based on the spatial position information of the original eye movement and tracking data. Secondly, CNN(Convolutional Neural Network) and BLSTM(Bi-directional Long Short-Term Memory) are combined to design a new fusion structure. Finally, the experimental results show that compared with six classic data fusion algorithms, the fusion performance of the proposed algorithm is better on OTB-100 dataset.

Key words: eye movement and tracking data, data fusion, Convolutional Neural Network(CNN), Bi-directional Long Short-Term Memory(BLSTM)