Sökning: id:"swepub:oai:research.chalmers.se:809e0f19-c116-452d-956e-fa985a0b21d0" >
Real-Time Dense Map...
Real-Time Dense Mapping for Self-Driving Vehicles using Fisheye Cameras
-
- Cui, Zhaopeng (författare)
- Eidgenössische Technische Hochschule Zürich (ETH),Swiss Federal Institute of Technology in Zürich (ETH)
-
- Heng, Lionel (författare)
- DSO National Laboratories
-
- Yeo, Ye Chuan (författare)
- DSO National Laboratories
-
visa fler...
-
- Geiger, Andreas (författare)
- Eberhard Karls Universität Tübingen,Eberhard Karls University of Tübingen,Max Planck Gesellschaft zur Förderung der Wissenschaften e.V. (MPG),Max Planck Society for the Advancement of Science (MPG)
-
- Pollefeys, Marc (författare)
- Eidgenössische Technische Hochschule Zürich (ETH),Swiss Federal Institute of Technology in Zürich (ETH),Microsoft
-
- Sattler, Torsten, 1983 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
visa färre...
-
(creator_code:org_t)
- ISBN 9781538660263
- 2019
- 2019
- Engelska.
-
Ingår i: Proceedings - IEEE International Conference on Robotics and Automation. - 1050-4729. - 9781538660263 ; , s. 6087-6093
- Relaterad länk:
-
https://research.cha...
-
visa fler...
-
https://research.cha...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- We present a real-time dense geometric mapping algorithm for large-scale environments. Unlike existing methods which use pinhole cameras, our implementation is based on fisheye cameras whose large field of view benefits various computer vision applications for self-driving vehicles such as visual-inertial odometry, visual localization, and object detection. Our algorithm runs on in-vehicle PCs at approximately 15 Hz, enabling vision-only 3D scene perception for self-driving vehicles. For each synchronized set of images captured by multiple cameras, we first compute a depth map for a reference camera using plane-sweeping stereo. To maintain both accuracy and efficiency, while accounting for the fact that fisheye images have a lower angular resolution, we recover the depths using multiple image resolutions. We adopt the fast object detection framework, YOLOv3, to remove potentially dynamic objects. At the end of the pipeline, we fuse the fisheye depth images into the truncated signed distance function (TSDF) volume to obtain a 3D map. We evaluate our method on large-scale urban datasets, and results show that our method works well in complex dynamic environments.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Annan teknik -- Mediateknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Other Engineering and Technologies -- Media Engineering (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Medicinteknik -- Medicinsk bildbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Medical Engineering -- Medical Image Processing (hsv//eng)
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas