Publication detail

On registration of vector maps with known correspondences

JELÍNEK, A.

Original Title

On registration of vector maps with known correspondences

Type

conference paper

Language

English

Original Abstract

Data association and registration is an important and actively researched topic in robotics. This paper deals with registration of two sets of line segments, which is especially useful in mapping applications. Our method is non-iterative, finding an optimal transformation in a single step, in a time proportional only to a number of the corresponding line segments. The procedure also provides diagnostic measures of reliability of the computation and of similarity of the data sets being registered. At this point, the method presumes known correspondences, which is limiting, but the discussion in the end reveals some possibilities to overcome this issue, which we are examining. Practical properties are demonstrated on a typical task of localization of a robot with a known map.

Keywords

point cloud; registration; vectorization; least squares; correspondence search

Authors

JELÍNEK, A.

Released

21. 5. 2018

Publisher

IEEE

Location

Žilina

ISBN

978-1-5386-4758-5

Book

Proceedings of 12th International Conference Elektro 2018

Pages from

1

Pages to

6

Pages count

6

URL

https://ieeexplore.ieee.org/document/8398367/

Full text in the Digital Library

http://hdl.handle.net/11012/85283

BibTex

@inproceedings{BUT148111,
  author="Aleš {Jelínek}",
  title="On registration of vector maps with known correspondences",
  booktitle="Proceedings of 12th International Conference Elektro 2018",
  year="2018",
  pages="1--6",
  publisher="IEEE",
  address="Žilina",
  doi="10.1109/ELEKTRO.2018.8398367",
  isbn="978-1-5386-4758-5",
  url="https://ieeexplore.ieee.org/document/8398367/"
}