Intensity Normalization of Sidescan Sonar Imagery Al Rawi,MS en Adrian Galdran en Yuan,X en Eckert,M en Martinez,JF en Elmgren,F en Curuklu,B en Rodriguez,J en Bastos,J en Pinto,M en 2018-01-15T10:26:25Z 2018-01-15T10:26:25Z 2016 en
dc.description.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 ( en
dc.language eng en
dc.relation 6825 en
dc.rights info:eu-repo/semantics/embargoedAccess en
dc.title Intensity Normalization of Sidescan Sonar Imagery en
dc.type conferenceObject en
dc.type Publication en
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
1.25 MB
Adobe Portable Document Format