LiDAR-camera fusion for depth enhanced unsupervised odometry

Fetic, Naida and Aydemir, Eren and Ünel, Mustafa (2022) LiDAR-camera fusion for depth enhanced unsupervised odometry. In: IEEE 95th Vehicular Technology Conference: (VTC2022-Spring), Helsinki, Finland

[thumbnail of LiDAR-Camera_Fusion_for_Depth_Enhanced_Unsupervised_Odometry.pdf] PDF
Restricted to Registered users only

Download (2MB) | Request a copy


This paper proposes a robust and safe perception system for an odometry framework based on the fusion of LiDAR data with an RGB image. These multi-modal sensor measurements are fused using their depth proposals and confidence measures in a Bayesian inference module. The resulting fused depth map enhances unsupervised odometry estimates. Experimental results show that the LiDAR-camera fused depth map is an accurate 3D structure representation of the environment. This method can be used in an online adaption of the learningbased odometry algorithms to increase their generalizability to different scenes. We perform experiments on the benchmark odometry datasets and obtain promising results compared to the previous approaches. Compared to the state-of-the-art methods, the average translation error shows a 44% reduction, and the average rotation error is better or comparable.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: depth prediction; LiDAR-camera fusion; Odometry; reprojection error
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: 08 Oct 2022 14:24
Last Modified: 08 Oct 2022 14:24

Actions (login required)

View Item
View Item