Efficient Image Registration for Underwater Optical Mapping Using Geometric Invariants

Image registration is one of the most fundamental and widely used tools in optical mapping applications. It is mostly achieved by extracting and matching salient points (features) described by vectors (feature descriptors) from images. While matching the descriptors, mismatches (outliers) do appear....

Full description

Saved in:
Bibliographic Details
Published in:Journal of marine science and engineering 2019-06, Vol.7 (6), p.178
Main Authors: Elibol, Armagan, Chong, Nak Young
Format: Article
Language:English
Subjects:
Algorithms
Computer applications
Computing time
Coordinate transformations
Decomposition
Feature extraction
Geometric accuracy
geometric invariants
image mosaicking
Image registration
Invariants
Iterative methods
Mapping
Matching
optical mapping
Outliers (statistics)
Probabilistic methods
Registration
Underwater
Vectors
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Image registration is one of the most fundamental and widely used tools in optical mapping applications. It is mostly achieved by extracting and matching salient points (features) described by vectors (feature descriptors) from images. While matching the descriptors, mismatches (outliers) do appear. Probabilistic methods are then applied to remove outliers and to find the transformation (motion) between images. These methods work in an iterative manner. In this paper, an efficient way of integrating geometric invariants into feature-based image registration is presented aiming at improving the performance of image registration in terms of both computational time and accuracy. To do so, geometrical properties that are invariant to coordinate transforms are studied. This would be beneficial to all methods that use image registration as an intermediate step. Experimental results are presented using both semi-synthetically generated data and real image pairs from underwater environments.
ISSN:2077-1312
2077-1312
DOI:10.3390/jmse7060178