Registration of Infrared and Visible Images Based on Edge Extraction and Phase Correlation Approaches

Jan Klimaszewski , Marcin Kondej , Mariusz Kawecki , Barbara Putz

Abstract

The paper presents test results of several edge detectors intended to be used for multimodal image registration. It was found that application of edge detectors before running phase correlation algorithms allows achievement of good quality of registration and assure simultaneously high performance of registration necessary particularly in real time applications. Canny edge detector implemented in OpenCV and its simplification, Harris edge detector and two types of morphological edge detectors: basic and extended have been tested. It has been shown that OpenCV implementation of Canny algorithm gives best translation coefficients for IR and TV images registration. The results show that edge extraction with subsequent phase correlation is a very promising for multisensor image registration.
Author Jan Klimaszewski (FM / IACR)
Jan Klimaszewski,,
- The Institute of Automatic Control and Robotics
, Marcin Kondej (FM / IACR)
Marcin Kondej,,
- The Institute of Automatic Control and Robotics
, Mariusz Kawecki (FM / IACR)
Mariusz Kawecki,,
- The Institute of Automatic Control and Robotics
, Barbara Putz (FM / IACR)
Barbara Putz,,
- The Institute of Automatic Control and Robotics
Pages153-162
Publication size in sheets0.5
Book Choraś Ryszard S. (eds.): Image Processing and Communications Challenges 4, Advances in Intelligent Systems and Computing, vol. 184, part 1, 2013, Heidelberg New York Dordrecht London, Springer-Verlag, ISBN 978-3-642-32383-6, 311 p., DOI:10.1007/978-3-642-32384-3
Keywords in EnglishArtificial Intelligence (incl. Robotics), Communications Engineering, Networks, Computational Intelligence, Image Processing and Computer Vision, Signal, Image and Speech Processing
DOIDOI:10.1007/978-3-642-32384-3_19
URL http://link.springer.com/chapter/10.1007/978-3-642-32384-3_19
Languageen angielski
Score (nominal)5
ScoreMinisterial score = 5.0, 07-01-2020, MonographChapterAuthor
Publication indicators WoS Citations = 8; GS Citations = 15.0
Citation count*15 (2020-09-15)
Cite
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.
Back
Confirmation
Are you sure?