Robust multi-dimensional motion features for first-person vision activity recognition
作者：
Highlights：
• We design a set of multi-dimensional motion features from first-person video.
• We extract virtual inertial data from video only.
• We combine motion magnitude, direction and dynamics with virtual inertial data.
• The features are independent of the classifier and validated on multiple datasets.
• Two new datasets are made available to the research community.
摘要
•We design a set of multi-dimensional motion features from first-person video.•We extract virtual inertial data from video only.•We combine motion magnitude, direction and dynamics with virtual inertial data.•The features are independent of the classifier and validated on multiple datasets.•Two new datasets are made available to the research community.
论文关键词：Human activity recognition,First-person vision,Grid optical flow,Inertial data,Wearable camera
论文评审过程：Received 17 April 2015, Revised 21 October 2015, Accepted 23 October 2015, Available online 7 June 2016, Version of Record 7 June 2016.
论文官网地址：https://doi.org/10.1016/j.cviu.2015.10.015
