Next Article in Journal
Unstable Limit Cycles and Singular Attractors in a Two-Dimensional Memristor-Based Dynamic System
Next Article in Special Issue
Learning Using Concave and Convex Kernels: Applications in Predicting Quality of Sleep and Level of Fatigue in Fibromyalgia
Previous Article in Journal
Acknowledging Uncertainty in Economic Forecasting. Some Insight from Confidence and Industrial Trend Surveys
Previous Article in Special Issue
Supervisors’ Visual Attention Allocation Modeling Using Hybrid Entropy
Open AccessArticle

Action Recognition Using Single-Pixel Time-of-Flight Detection

1
iCv Lab, Institute of Technology, University of Tartu, 50411 Tartu, Estonia
2
University of Barcelona, 08007 Barcelona, Spain
3
Institute of Physics, University of Tartu, 50411 Tartu, Estonia
4
The Computer Vision Centre, 08193 Barcelona, Spain
5
Trinity College Dublin, Dublin 2, Ireland
6
Department of Electrical and Electronic Engineering, Hasan Kalyoncu University, Gaziantep 27000, Turkey
7
Institute of Digital Technologies, Loughborough University London, London E15 2GZ, UK
*
Author to whom correspondence should be addressed.
All authors contributed equally to this work.
Entropy 2019, 21(4), 414; https://doi.org/10.3390/e21040414
Received: 14 January 2019 / Revised: 15 April 2019 / Accepted: 15 April 2019 / Published: 18 April 2019
(This article belongs to the Special Issue Statistical Machine Learning for Human Behaviour Analysis)
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’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 recurrent neural network. View Full-Text
Keywords: single pixel single photon image acquisition; time-of-flight; action recognition single pixel single photon image acquisition; time-of-flight; action recognition
Show Figures

Figure 1

MDPI and ACS Style

Ofodile, I.; Helmi, A.; Clapés, A.; Avots, E.; Peensoo, K.M.; Valdma, S.-M.; Valdmann, A.; Valtna-Lukner, H.; Omelkov, S.; Escalera, S.; Ozcinar, C.; Anbarjafari, G. Action Recognition Using Single-Pixel Time-of-Flight Detection. Entropy 2019, 21, 414.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop