Head and eye egocentric gesture recognition for human-robot interaction using eyewear cameras
comunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/43662
comunitat-uji-handle3:10234/43643
comunitat-uji-handle4:
INVESTIGACIONMetadades
Títol
Head and eye egocentric gesture recognition for human-robot interaction using eyewear camerasData de publicació
2022-06-08Editor
IEEECita bibliogràfica
Marina-Miranda, J., & Traver, V. J. (2022). Head and Eye Egocentric Gesture Recognition for Human-Robot Interaction. IEEE Robotics and Automation Letters.Tipus de document
info:eu-repo/semantics/articleVersió de l'editorial
https://ieeexplore.ieee.org/document/9790312Versió
info:eu-repo/semantics/acceptedVersionParaules clau / Matèries
Resum
Non-verbal communication plays a particularly important role in a wide range of scenarios in Human-Robot Interaction (HRI). Accordingly, this work addresses the problem of human gesture recognition. In particular, we ... [+]
Non-verbal communication plays a particularly important role in a wide range of scenarios in Human-Robot Interaction (HRI). Accordingly, this work addresses the problem of human gesture recognition. In particular, we focus on head and eye gestures, and adopt an egocentric (first-person) perspective using eyewear cameras. We argue that this egocentric view may offer a number of conceptual and technical benefits over scene- or robot-centric perspectives. A motion-based recognition approach is proposed, which operates at two temporal granularities. Locally, frame-to-frame homographies are estimated with a convolutional neural network (CNN). The output of this CNN is input to a long short-term memory (LSTM) to capture longer-term temporal visual relationships, which are relevant to characterize gestures. Regarding the configuration of the network architecture, one particularly interesting finding is that using the output of aninternal layer of the homography CNN increases the recognition rate with respect to using the homography matrix itself. While this work focuses on action recognition, and no robot or user study has been conducted yet, the system has been designed to meet real-time constraints. The encouraging results suggest that the proposed egocentric perspective is viable, and this proofof-concept work provides novel and useful contributions to the exciting area of HRI. [-]
Publicat a
IEEE Robotics and Automation Letters ( Volume: 7, Issue: 3, July 2022)Entitat finançadora
Universitat Jaume I | Ministerio de Ciencia, Innovación y Universidades (Spain)
Codi del projecte o subvenció
UJI-B2018-44 | RED2018-102511-T
Drets d'accés
Apareix a les col.leccions
- INIT_Articles [752]