@Article{IkechukwuOfodile2019,
author="Ikechukwu Ofodile
and Ahmed Helmi
and Albert Clapes
and Egils Avots
and Kerttu Maria Peensoo
and Sandhra Mirella Valdma
and Andreas Valdmann
and Heli Valtna Lukner
and Sergey Omelkov
and Sergio Escalera
and Cagri Ozcinar
and Gholamreza Anbarjafari",
title="Action recognition using single-pixel time-of-flight detection",
journal="Entropy",
year="2019",
volume="21",
number="4",
pages="414",
optkeywords="single pixel single photon image acquisition",
optkeywords="time-of-flight",
optkeywords="action recognition",
abstract="Action recognition is a challenging task that plays an important role in many robotic systems, which highly depend on visual input feeds. However, due to privacy concerns, it is important to find a method which can recognise actions without using visual feed. In this paper, we propose a concept for detecting actions while preserving the test subject{\textquoteright}s privacy. Our proposed method relies only on recording the temporal evolution of light pulses scattered back from the scene.Such data trace to record one action contains a sequence of one-dimensional arrays of voltage values acquired by a single-pixel detector at 1 GHz repetition rate. Information about both the distance to the object and its shape are embedded in the traces. We apply machine learning in the form of recurrent neural networks for data analysis and demonstrate successful action recognition. The experimental results show that our proposed method could achieve on average 96.47\% accuracy on the actions walking forward, walking backwards, sitting down, standing up and waving hand, using recurrentneural network.",
optnote="HuPBA; no proj",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3319), last updated on Fri, 20 Mar 2020 09:19:15 +0100",
doi="10.3390/e21040414",
opturl="https://www.mdpi.com/1099-4300/21/4/414"
}