DeepKalPose: An enhanced deep‐learning Kalman filter for temporally consistent monocular vehicle pose estimation
Electronics Letters · 2024-04 · 60 (8)
DOI: 10.1049/ell2.13191 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics Letters, online erschienen am 25.04.2024. Verfasst von Leandro Di Bella und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Innoviris.
Abstract (Originalsprache)
This paper presents DeepKalPose, a novel approach for enhancing temporal consistency in monocular vehicle pose estimation applied on video through a deep‐learning‐based Kalman filter. By integrating a bi‐directional Kalman filter strategy utilizing forward and backward time‐series processing, combined with a learnable motion model to represent complex motion patterns, the method significantly improves pose accuracy and robustness across various conditions, particularly for occluded or distant vehicles. Experimental validation on the KITTI dataset confirms that DeepKalPose outperforms existing methods in both pose accuracy and temporal consistency.
Förderung
- Innoviris
Zitieren
APA
Bella, L. D., Lyu, Y., & Munteanu, A. (2024). DeepKalPose: An enhanced deep‐learning Kalman filter for temporally consistent monocular vehicle pose estimation. Electronics Letters, 60(8). https://doi.org/10.1049/ell2.13191
Vancouver
Bella LD, Lyu Y, Munteanu A. DeepKalPose: An enhanced deep‐learning Kalman filter for temporally consistent monocular vehicle pose estimation. Electronics Letters. 2024;60(8). doi:10.1049/ell2.13191
BibTeX
@article{Bella2024,
author = {Bella, Leandro Di and Lyu, Yangxintong and Munteanu, Adrian},
title = {DeepKalPose: An enhanced deep‐learning Kalman filter for temporally consistent monocular vehicle pose estimation},
journal = {Electronics Letters},
year = {2024},
volume = {60},
number = {8},
doi = {10.1049/ell2.13191}
}
EUVIMED