Title
OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems
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.
Year
DOI
Venue
2020
10.1109/ICRA40945.2020.9196695
2020 IEEE International Conference on Robotics and Automation (ICRA)
Keywords
DocType
Volume
omnidirectional localization,wide-baseline multicamera systems,dense mapping system,wide-baseline multiview stereo setup,ultrawide field-of-view fisheye cameras,stereo observations,light-weighted deep neural networks,loop closing module,efficient feature matching process,omnidirectional depth maps,truncated signed distance function volume,rig estimation,omnidirectional depth map estimation,VO,FOV,TSDF,OmniSLAM
Conference
2020
Issue
ISSN
ISBN
1
1050-4729
978-1-7281-7396-2
Citations 
PageRank 
References 
0
0.34
27
Authors
5
Name
Order
Citations
PageRank
changhee won111.92
Hochang Seok201.01
Zhaopeng Cui39316.66
Marc Pollefeys47671475.90
Jongwoo Lim54105144.58