Szczegóły publikacji
Opis bibliograficzny
Continuous hand gesture recognition for human-robot collaborative assembly / Bogdan KWOLEK // W: ICCVW 2023 [Dokument elektroniczny] : IEEE/CVF International Conference on Computer Vision Workshop : October 2–6, 2023, Paris, France. — Wersja do Windows. — Dane tekstowe. — Piscataway : IEEE, cop. 2023. — (IEEE International Conference on Computer Vision Workshops ; ISSN 2473-9936). — Dod. ISBN: 979-8-3503-0745-0. — e-ISBN: 979-8-3503-0744-3. — S. 1992–1999. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 1998–1999, Abstr. — Publikacja dostępna online od: 2023-12-25
Autor
Dane bibliometryczne
| ID BaDAP | 149167 |
|---|---|
| Data dodania do BaDAP | 2023-10-17 |
| Tekst źródłowy | URL |
| DOI | 10.1109/ICCVW60793.2023.00214 |
| Rok publikacji | 2023 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Konferencja | IEEE International Conference on Computer Vision 2023 |
| Czasopismo/seria | IEEE International Conference on Computer Vision Workshops |
Abstract
In this work, we present a framework for dynamic hand gesture recognition on RGB images acquired by an overhead camera. The recognition is realized for Methods Time Measurement-based planning of human-robot collaborative workspace. The 3D hand posture is estimated by MediaPipe. The recognition is done by a neural network in which a layer-wise feature combination takes place. We combine features extracted by basic blocks of Spatio-Temporal Adaptive Graph Convolutional Neural Network and by basic spatio-temporal self-attention blocks. We recorded and manually annotated 12 videos consisting of 54,659 RGB images with five basic motion sequences: grasp, move, position, release, and reach. We demonstrate experimentally that results of our networks are superior to results achieved by RNNs, ST-GCN, ST-AGCN, and CTR-GCN networks.
