Utilization of textured stereovision for registration of 3D models of objects

Tomasz Michał Kornuta , Maciej Stefańczyk


RGB-D sensors triggered a rapid progress in the field of robot visual perception. A typical visual perception subsystem relies on finding the correspondences between features extracted from RGB-D images retrieved from robot sensors and models of objects. In this paper we introduce a multi-camera setup supplemented with an additional pattern projector used for registration of high-resolution images of objects. The objects are placed on a fiducial board with two dot patterns enabling robust extraction of masks of the placed objects and estimation of their initial poses. The acquired dense point clouds constituting subsequent object views undergo pairwise registration and at the end are optimized with a graph-based technique derived from SLAM. The combination of all those elements resulted in a system for generation of consistent 3D models of objects. We present details of the developed system and conclude the paper with discussion of the achieved results
Author Tomasz Michał Kornuta (FEIT / AK)
Tomasz Michał Kornuta,,
- The Institute of Control and Computation Engineering
, Maciej Stefańczyk (FEIT / AK)
Maciej Stefańczyk,,
- The Institute of Control and Computation Engineering
Publication size in sheets0.5
Book Proceedings of 21st IEEE Conference on Method and Models in Automation and Robotics, 2016, IEEE Institute of electrical and Electronics Engineers, ISBN 978-1-5090-1715-7, 1285 p., DOI:10.1109/MMAR.2016.7575223
Keywords in EnglishFeature extraction, Three-dimensional displays, Cameras, Solid modeling, Cloud computing, Estimation, Sensors
URL http://ieeexplore.ieee.org/document/7575289/
ProjectDevelopment of methodology of control, decision support and production management. Project leader: Zieliński Cezary, , Phone: 5102, start date 19-05-2015, end date 31-12-2016, 504/02233/1031, Completed
WEiTI Działalność statutowa
Languageen angielski
kornuta stefancz_utilization mmar16.pdf 1.09 MB
Score (nominal)15
Score sourceconferenceIndex
ScoreMinisterial score = 15.0, 04-02-2020, BookChapterMatConfByConferenceseries
Ministerial score (2013-2016) = 15.0, 04-02-2020, BookChapterMatConfByConferenceseries
Publication indicators Scopus Citations = 1; WoS Citations = 1; GS Citations = 2.0
Citation count*2 (2020-09-20)
Share Share

Get link to the record

* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Are you sure?