251 0

OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems

Title
OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems
Author
임종우
Keywords
Cameras; Three-dimensional displays; Estimation; Feature extraction; Visual odometry; Sensors; Trajectory
Issue Date
2020-06
Publisher
IEEE
Citation
2020 IEEE International Conference on Robotics and Automation (ICRA), page. 559-566
Abstract
In this paper, we present an omnidirectional localization and dense mapping system for a wide-baseline multiview stereo setup with ultra-wide field-of-view (FOV) fisheye cameras, which has a 360◦ coverage of stereo observations of the environment. For more practical and accurate reconstruction, we first introduce improved and light-weighted deep neural networks for the omnidirectional depth estimation, which are faster and more accurate than the existing networks. Second, we integrate our omnidirectional depth estimates into the visual odometry (VO) and add a loop closing module for global consistency. Using the estimated depth map, we reproject keypoints onto each other view, which leads to a better and more efficient feature matching process. Finally, we fuse the omnidirectional depth maps and the estimated rig poses into the truncated signed distance function (TSDF) volume to acquire a 3D map. We evaluate our method on synthetic datasets with ground-truth and real-world sequences of challenging environments, and the extensive experiments show that the proposed system generates excellent reconstruction results in both synthetic and real-world environments.
URI
hhttps://ieeexplore.ieee.org/document/9196695https://repository.hanyang.ac.kr/handle/20.500.11754/168953
ISBN
978-1-7281-7395-5
ISSN
2577-087X
DOI
10.1109/ICRA40945.2020.9196695
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE(컴퓨터소프트웨어학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE