Szczegóły publikacji
Opis bibliograficzny
Convolutional neural network-based action recognition on depth maps / Jacek TRELIŃSKI, Bogdan KWOLEK // W: Computer vision and graphics : international conference : ICCVG 2018 : Warsaw, Poland, September 17–19, 2018 : proceedings / eds. Leszek J. Chmielewski [et al.]. — [Cham] : Springer International Publishing, cop. 2018. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 11114. Image Processing, Computer Vision, Pattern Recognition, and Graphics). — ISBN: 978-3-030-00691-4; e-ISBN: 978-3-030-00692-1. — S. 209–221. — Bibliogr. s. 219–221, Abstr. — Publikacja dostępna online od: 2018-09-14
Autorzy (2)
Dane bibliometryczne
| ID BaDAP | 117106 |
|---|---|
| Data dodania do BaDAP | 2018-10-15 |
| Tekst źródłowy | URL |
| DOI | 10.1007/978-3-030-00692-1_19 |
| Rok publikacji | 2018 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | International Conference on Computer Vision and Graphics 2018 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
In this paper, we present an algorithm for action recognition that uses only depth maps. We propose a set of handcrafted features to describe person’s shape in noisy depth maps. We extract features by a convolutional neural network (CNN), which has been trained on multi-channel input sequences consisting of two consecutive depth maps and depth map projected onto an orthogonal Cartesian plane. We show experimentally that combining features extracted by the CNN and proposed features leads to better classification performance. We demonstrate that an LSTM trained on such aggregated features achieves state-of-the-art classification performance on UTKinect dataset. We propose a global statistical descriptor of temporal features. We show experimentally that such a descriptor has high discriminative power on time-series of concatenated CNN features with handcrafted features.
