Szczegóły publikacji
Opis bibliograficzny
View-independent 3D gait recognition using sequence-based Siamese networks / Mikołaj KLIMEK, Bogdan KWOLEK // W: Computational Science – ICCS 2026 workshops : 26th International Conference : Hamburg, Germany, June 29–July 1, 2026 : proceedings , Pt. 2 / eds. Maciej Paszynski, Amanda S. Barnard, Yongjie Jessica Zhang. — Cham : Springer, cop. 2026. — ( Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 16787 ). — ISBN: 978-3-032-29908-6; e-ISBN: 978-3-032-29909-3. — S. 488–503. — Bibliogr., Abstr. — Publikacja dostępna online od: 2026-06-28
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 168931 |
|---|---|
| Data dodania do BaDAP | 2026-08-31 |
| DOI | 10.1007/978-3-032-29909-3_35 |
| Rok publikacji | 2026 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | International Conference on Computational Science 2026 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
Gait recognition is a rapidly evolving area of computer vision research. In recent years, emphasis has been placed on the approaches based on multi-camera datasets and the three-dimensional data derived from them. However, a notable research gap persists between gait recognition results obtained from precise motion capture data and those achieved using marker-less approaches. The synchronized GPJATK dataset used in this study enables this issue to be addressed by validating methods that rely on approximated joint positions obtained via linear triangulation against ground-truth motion capture data. We propose a sequence-based Siamese framework for view-independent 3D gait recognition. Using low-dimensional representations derived from similarity learning, the proposed approach achieves a Rank-1 person identification of 91.79% on triangulated data and 98.74% when evaluated using ground-truth motion capture data.
