English

Recognition of Activities from Eye Gaze and Egocentric Video

Computer Vision and Pattern Recognition 2018-05-21 v1

Abstract

This paper presents a framework for recognition of human activity from egocentric video and eye tracking data obtained from a head-mounted eye tracker. Three channels of information such as eye movement, ego-motion, and visual features are combined for the classification of activities. Image features were extracted using a pre-trained convolutional neural network. Eye and ego-motion are quantized, and the windowed histograms are used as the features. The combination of features obtains better accuracy for activity classification as compared to individual features.

Keywords

Cite

@article{arxiv.1805.07253,
  title  = {Recognition of Activities from Eye Gaze and Egocentric Video},
  author = {Anjith George and Aurobinda Routray},
  journal= {arXiv preprint arXiv:1805.07253},
  year   = {2018}
}

Comments

7 pages, 9 figures