Szczegóły publikacji
Opis bibliograficzny
3D model-based 6D object pose tracking on RGB images / Mateusz MAJCHER, Bogdan KWOLEK // W: Intelligent Information and Database Systems : 12th Asian Conference, ACIIDS 2020 : Phuket, Thailand, March 23–26, 2020 : proceedings, Pt. 1 / eds. Ngoc Thanh Nguyen, [et al.]. — Cham : Springer, cop. 2020. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 12033. Lecture Notes in Artificial Intelligence). — ISBN: 978-3-030-41963-9; e-ISBN: 978-3-030-41964-6. — S. 271–282. — Bibliogr. s. 281–282, Abstr. — Publikacja dostępna online od: 2020-03-04
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 131674 |
|---|---|
| Data dodania do BaDAP | 2020-12-29 |
| DOI | 10.1007/978-3-030-41964-6_24 |
| Rok publikacji | 2020 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | Asian Conference on Intelligent Information and Database Systems 2020 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
In this paper, we present a 3D-model based algorithm for 6D object pose estimation and tracking on segmented RGB images. The object of interest is segmented by U-Net neural network trained on a set of manually delineated images. A Particle Swarm Optimization is used to estimate the 6D object pose by projecting the 3D object model and then matching the projected image with the image acquired by the camera. The tracking of 6D object pose is formulated as a dynamic optimization problem. In order to keep necessary human intervention minimal, we use an automated turntable setup to prepare a 3D object model and to determine the ground-truth poses. We compare the experimental results obtained by our algorithm with results achieved by PWP3D algorithm. © 2020, Springer Nature Switzerland AG.
