IRIS Institutional Research Information System - OPENBS Open Archive UniBS
il nuovo catalogo dedicato alla raccolta e alla disseminazione della produzione scientifica dell'Università degli Studi di
Brescia, denominato OPENBS. E' possibile cercare pubblicazioni in OPENBS:
- per parola chiave, utilizzando la barra di ricerca situata in alto
- per filtro di ricerca (Autore, Titolo, Riviste), utilizzando il pulsante Sfoglia
- specificando criteri di ricerca con possibilità di aggiungere gradualmente più filtri (Autore, Data, Tipologia,..) che
perfezionino i risultati, utilizzando la finestra Ricerca - per elemento di filtro di ricerca (e.g. per un elemento di Tipologia: contributo su rivista) nella sezione Scopri
EnglishIn this paper, we present a smart hand gesture recognition experimental set up for collaborative robots using a Faster R-CNN object detector to find the accurate position of the hands in the RGB images taken from a Kinect v2 camera. We used MATLAB to code the detector and a purposely designed function for the prediction phase, necessary for detecting static gestures in the way we have defined them. We performed a number of experiments with different datasets to evaluate the performances of the model in different situations: A basic hand gestures dataset with four gestures performed by the combination of both hands, a dataset where the actors wear skin-like color clothes while performing the gestures, a dataset where the actors wear light-blue gloves and a dataset similar to the first one but with the camera placed close to the operator. The same tests have been conducted in a situation where also the face of the operator was detected by the algorithm, in order to improve the prediction accuracy. Our experiments show that the best model accuracy and Fl-Score are achieved by the complete model without the face detection. We tested the model in real-Time, achieving good performances that can lead to real-Time human-robot interaction, being the inference time around 0.2 seconds.
| Titolo: | Deep Learning Based Machine Vision: First Steps Towards a Hand Gesture Recognition Set Up for Collaborative Robots |
| Autori: | |
| Data di pubblicazione: | 2018 |
| Abstract: | In this paper, we present a smart hand gesture recognition experimental set up for collaborative robots using a Faster R-CNN object detector to find the accurate position of the hands in the RGB images taken from a Kinect v2 camera. We used MATLAB to code the detector and a purposely designed function for the prediction phase, necessary for detecting static gestures in the way we have defined them. We performed a number of experiments with different datasets to evaluate the performances of the model in different situations: A basic hand gestures dataset with four gestures performed by the combination of both hands, a dataset where the actors wear skin-like color clothes while performing the gestures, a dataset where the actors wear light-blue gloves and a dataset similar to the first one but with the camera placed close to the operator. The same tests have been conducted in a situation where also the face of the operator was detected by the algorithm, in order to improve the prediction accuracy. Our experiments show that the best model accuracy and Fl-Score are achieved by the complete model without the face detection. We tested the model in real-Time, achieving good performances that can lead to real-Time human-robot interaction, being the inference time around 0.2 seconds. |
| Handle: | http://hdl.handle.net/11379/510656 |
| ISBN: | 9781538624975 |
| Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| 08439044.pdf | Full Text | DRM non definito | Utenti riconosciuti Richiedi una copia |
http://hdl.handle.net/11379/510656
Copyright © 2021