Szczegóły publikacji
Opis bibliograficzny
Embedded features for 1D CNN-based action recognition on depth maps / Jacek TRELIŃSKI, Bogdan KWOLEK // W: VISIGRAPP 2021 [Dokument elektroniczny] : proceedings of the 16th international joint conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Vol. 4, VISAPP / eds. Giovanni Maria Farinella, [et al.]. — [Lisbon] : SCITEPRESS - Science and Technology Publications, [2021]. — (VISIGRAPP ; ISSN 2184-5921). — e-ISBN: 978-989-758-488-6. — S. 536–543. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 543, Abstr.
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 136456 |
|---|---|
| Data dodania do BaDAP | 2021-09-27 |
| Tekst źródłowy | URL |
| DOI | 10.5220/0010340105360543 |
| Rok publikacji | 2021 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Creative Commons | |
| Konferencja | 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications |
| Czasopismo/seria | VISIGRAPP |
Abstract
In this paper we present an algorithm for human action recognition using only depth maps. A convolutional autoencoder and Siamese neural network are trained to learn embedded features, encapsulating the content of single depth maps. Afterwards, statistical features and multichannel 1D CNN features are extracted on multivariate time-series of such embedded features to represent actions on depth map sequences. The action recognition is achieved by voting in an ensemble of one-vs-all weak classifiers. We demonstrate experimentally that the proposed algorithm achieves competitive results on UTD-MHAD dataset and outperforms by a large margin the best algorithms on 3D Human-Object Interaction Set (SYSU 3DHOI).