Carregant...
Miniatura

Tipus de document

Article

Versió

Versió publicada

Data de publicació

Llicència de publicació

cc-by (c) Ofodile, Ikechukwu et al., 2019
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/176061

Action recognition using single-pixel time-of-flight detection

Títol de la revista

Director/Tutor

ISSN de la revista

Títol del volum

Resum

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.

Descripció

Citació

Citació

OFODILE, Ikechukwu, HELMI, Ahmed, CLAPÉS I SINTES, Albert, AVOTS, Egils, PEENSOO, Kerttu maria, VALDMA, Sandhra mirella, VALDMANN, Andreas, VALTNA LUKNER, Heli, OMELKOV, Sergey, ESCALERA GUERRERO, Sergio, OZCINAR, Cagri, ANBARJAFARI, Gholamreza. Action recognition using single-pixel time-of-flight detection. _Entropy_. 2019. Vol. 21, núm. 4, pàgs. 414. [consulta: 6 de desembre de 2025]. ISSN: 1099-4300. [Disponible a: https://hdl.handle.net/2445/176061]

Exportar metadades

JSON - METS

Compartir registre