Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 5 of 37
Back to Result List

Targetless Lidar-camera registration using patch-wise mutual information

  • Targetless Lidar-camera registration is a repeating task in many computer vision and robotics applications and requires computing the extrinsic pose of a point cloud with respect to a camera or vice-versa. Existing methods based on learning or optimization lack either generalization capabilities or accuracy. Here, we propose a combination of pre-training and optimization using a neural network-based mutual information estimation technique (MINE [1]). This construction allows back-propagating the gradient to the calibration parameters and enables stochastic gradient descent. To ensure orthogonality constraints with respect to the rotation matrix we incorporate Lie-group techniques. Furthermore, instead of optimizing on entire images, we operate on local patches that are extracted from the temporally synchronized projected Lidar points and camera frames. Our experiments show that this technique not only improves over existing techniques in terms of accuracy, but also shows considerable generalization capabilities towards new Lidar-camera configurations.

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Matthias Hermann, Dennis Grießer, Bernhard Gundel, Daniel Dold, Georg UmlaufORCiDGND, Matthias O. FranzORCiDGND
DOI:https://doi.org/10.23919/FUSION49751.2022.9841290
ISBN:978-1-7377497-2-1
ISBN:978-1-6654-8941-6
Parent Title (English):25th International Conference on Information Fusion (FUSION 2022), 4-7 July 2022, Linköping, Schweden
Publisher:IEEE
Document Type:Conference Proceeding
Language:English
Year of Publication:2022
Release Date:2022/12/07
Tag:Lidar-camera registration; Mutual information
Page Number:8 Seiten
Note:
Volltext im Campusnetz der Hochschule Konstanz via Datenbank IEEE Xplore abrufbar.
Institutes:Institut für Optische Systeme - IOS
Relevance:Peer reviewed nach anderen Listungen (mit Nachweis zum Peer Review Verfahren)
Open Access?:Nein
Licence (German):License LogoUrheberrechtlich geschützt