A Fast and Light-weight Non-Iterative Visual Odometry with RGB-D Cameras

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Zheng, Xu, Kuan, Yuan, Shenghai, Xie, Lihua
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915408909434880
author Yang, Zheng
Xu, Kuan
Yuan, Shenghai
Xie, Lihua
author_facet Yang, Zheng
Xu, Kuan
Yuan, Shenghai
Xie, Lihua
contents In this paper, we introduce a novel approach for efficiently estimating the 6-Degree-of-Freedom (DoF) robot pose with a decoupled, non-iterative method that capitalizes on overlapping planar elements. Conventional RGB-D visual odometry(RGBD-VO) often relies on iterative optimization solvers to estimate pose and involves a process of feature extraction and matching. This results in significant computational burden and time delays. To address this, our innovative method for RGBD-VO separates the estimation of rotation and translation. Initially, we exploit the overlaid planar characteristics within the scene to calculate the rotation matrix. Following this, we utilize a kernel cross-correlator (KCC) to ascertain the translation. By sidestepping the resource-intensive iterative optimization and feature extraction and alignment procedures, our methodology offers improved computational efficacy, achieving a performance of 71Hz on a lower-end i5 CPU. When the RGBD-VO does not rely on feature points, our technique exhibits enhanced performance in low-texture degenerative environments compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18886
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Fast and Light-weight Non-Iterative Visual Odometry with RGB-D Cameras
Yang, Zheng
Xu, Kuan
Yuan, Shenghai
Xie, Lihua
Robotics
In this paper, we introduce a novel approach for efficiently estimating the 6-Degree-of-Freedom (DoF) robot pose with a decoupled, non-iterative method that capitalizes on overlapping planar elements. Conventional RGB-D visual odometry(RGBD-VO) often relies on iterative optimization solvers to estimate pose and involves a process of feature extraction and matching. This results in significant computational burden and time delays. To address this, our innovative method for RGBD-VO separates the estimation of rotation and translation. Initially, we exploit the overlaid planar characteristics within the scene to calculate the rotation matrix. Following this, we utilize a kernel cross-correlator (KCC) to ascertain the translation. By sidestepping the resource-intensive iterative optimization and feature extraction and alignment procedures, our methodology offers improved computational efficacy, achieving a performance of 71Hz on a lower-end i5 CPU. When the RGBD-VO does not rely on feature points, our technique exhibits enhanced performance in low-texture degenerative environments compared to state-of-the-art methods.
title A Fast and Light-weight Non-Iterative Visual Odometry with RGB-D Cameras
topic Robotics
url https://arxiv.org/abs/2507.18886