Semi-Supervised First-Person Activity Recognition in Body-Worn Video
Abstract
Body-worn cameras are now commonly used for logging daily life, sports, and law enforcement activities, creating a large volume of archived footage. This paper studies the problem of classifying frames of footage according to the activity of the camera-wearer with an emphasis on application to real-world police body-worn video. Real-world datasets pose a different set of challenges from existing egocentric vision datasets: the amount of footage of different activities is unbalanced, the data contains personally identifiable information, and in practice it is difficult to provide substantial training footage for a supervised approach. We address these challenges by extracting features based exclusively on motion information then segmenting the video footage using a semi-supervised classification algorithm. On publicly available datasets, our method achieves results comparable to, if not better than, supervised and/or deep learning methods using a fraction of the training data. It also shows promising results on real-world police body-worn video.
Cite
@article{arxiv.1904.09062,
title = {Semi-Supervised First-Person Activity Recognition in Body-Worn Video},
author = {Honglin Chen and Hao Li and Alexander Song and Matt Haberland and Osman Akar and Adam Dhillon and Tiankuang Zhou and Andrea L. Bertozzi and P. Jeffrey Brantingham},
journal= {arXiv preprint arXiv:1904.09062},
year = {2019}
}