Intensity normalization of sidescan sonar imagery

M. S. Al-Rawi, Adrián Galdrán, Xin Yuan, Martina Eckert, José Fernán Martínez, Fredrik Elmgren, Baran Cürüklü, Jonathan Rodriguez, Joaquim Bastos, Marc Pinto

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Citations (Scopus)

Abstract

Sonar imaging is currently the exemplary choice used in underwater imaging. However, since sound signals are absorbed by water, an image acquired by a sonar will have gradient illumination; thus, underwater maps will be difficult to process. In this work, we investigated this phenomenon with the objective to propose methods to normalize the images with regard to illumination. We propose to use MIxed exponential Regression Analysis (MIRA) estimated from each image that requires normalization. Two sidescan sonars have been used to capture the seabed in Lake Vattern in Sweden in two opposite directions west-east and east-west; hence, the task is extremely difficult due to differences in the acoustic shadows. Using the structural similarity index, we performed similarity analyses between corresponding regions extracted from the sonar images. Results showed that MIRA has superior normalization performance. This work has been carried out as part of the SWARMs project (http://www.swarms.eu/).

Original languageEnglish
Title of host publication2016 6th International Conference on Image Processing Theory, Tools and Applications, IPTA 2016
EditorsMatti Pietikainen, Abdenour Hadid, Miguel Bordallo Lopez
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467389105
DOIs
Publication statusPublished - 17 Jan 2017
Event6th International Conference on Image Processing Theory, Tools and Applications, IPTA 2016 - Oulu, Finland
Duration: 12 Dec 201615 Dec 2016

Publication series

Name2016 6th International Conference on Image Processing Theory, Tools and Applications, IPTA 2016

Conference

Conference6th International Conference on Image Processing Theory, Tools and Applications, IPTA 2016
Country/TerritoryFinland
CityOulu
Period12/12/1615/12/16

Keywords

  • acoustic shadow
  • dark channel prior
  • echo decay
  • exponential regression
  • illumination normalization
  • inverse square law
  • Sidscan sonar

Fingerprint

Dive into the research topics of 'Intensity normalization of sidescan sonar imagery'. Together they form a unique fingerprint.

Cite this