H-VLO: hybrid LiDAR-camera fusion for self-supervised odometry

Aydemir, Eren and Fetic, Naida and Ünel, Mustafa (2022) H-VLO: hybrid LiDAR-camera fusion for self-supervised odometry. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan

This is the latest version of this item.

[thumbnail of iros2022_aydemir_fetic_unel_final.pdf] PDF
iros2022_aydemir_fetic_unel_final.pdf
Restricted to Registered users only

Download (2MB) | Request a copy

Abstract

In this paper, we propose a hybrid visual-LiDAR odometry (H-VLO) framework that fuses predicted visual depth map and completed LiDAR map. Compared to the previous visual-LiDAR odometry methods, our approach leverages 2D feature matching and 3D association by utilizing deep depth map, deep flow map and deep LiDAR depth completion networks. Rather than extraction of the depth values from LiDAR measurements for each visual feature, our method first densifies a LiDAR scan with a deep depth completion network and then fuses it with visual deep depth map estimation in a Bayesian framework. This method reduces pose estimation drift by improving feature-to-feature and point-to-feature matching, as well as scale recovery. The evaluations on the public KITTI odometry benchmark show that our technique achieves better or at least comparable estimates than the state-of-the-art visual-LiDAR and monocular visual odometry approaches.
Item Type: Papers in Conference Proceedings
Subjects: T Technology > TJ Mechanical engineering and machinery > TJ163.12 Mechatronics
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Mechatronics
Faculty of Engineering and Natural Sciences
Depositing User: Mustafa Ünel
Date Deposited: 03 Oct 2023 15:59
Last Modified: 03 Oct 2023 15:59
URI: https://research.sabanciuniv.edu/id/eprint/48289

Available Versions of this Item

Actions (login required)

View Item
View Item