Skip to Main content Skip to Navigation
Conference papers

Multi-scale Direct Sparse Visual Odometry for Large-Scale Natural Environment

Xiaolong Wu 1 Cédric Pradalier 2, 1
2 SHARP - Automatic Programming and Decisional Systems in Robotics
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes
Abstract : In this paper, we describe a multi-scale monocular direct sparse visual odometry (DSO) system to recover large-scale trajectories in unstructured natural environments in real time, while building a consistent metric map of the visited scenes. In contrast to the current state-of-the-art DSO system, the proposed method allows for more robust motion estimation and more accurate reconstruction in distant scenes by exploiting the characteristics of short- and long-range pixels, respectively. The long-range pixels, which are less sensitive to small camera translations, are used to initialize the camera rotation, so as to boost the tracking robustness in challenging natural environments. A multi-scale reconstruction framework is developed to recover short-range structure over successive frames, as well as the long-range structure over distant frames, hence allowing for a more consistent mapping precision. The reconstruction precision, the tracking accuracy, and the robustness of the proposed system are extensively evaluated with a publicly available vKITTI dataset, as well as the challenging Devon Island dataset, and Symphony Lake dataset. A detailed performance comparison between the proposed method and the state-of-the-art DSO system is presented.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-02278006
Contributor : Nadege Dastillung <>
Submitted on : Wednesday, September 4, 2019 - 9:43:38 AM
Last modification on : Friday, April 2, 2021 - 3:38:51 AM

Identifiers

  • HAL Id : hal-02278006, version 1

Citation

Xiaolong Wu, Cédric Pradalier. Multi-scale Direct Sparse Visual Odometry for Large-Scale Natural Environment. 2018 International Conference on 3D Vision (3DV), Sep 2018, Verona, France. pp.89-97. ⟨hal-02278006⟩

Share

Metrics

Record views

94