1. Repositório Aberto da Universidade do Porto
2. FEUP - Faculdade de Engenharia
3. FEUP - Dissertação

Author(s):	António José Ventura de Oliveira
Title:	Feature-based underwater localization using an imaging sonar
Issue Date:	2020-07-20
Description:	The ability of an AUV to locate itself in an environment as well as to detect relevant environmental features is of key importance for navigation success. Sonars are one the most common sensing devices for underwater localization and mapping, being used to detect and identify underwater structural features. This study explores the processing and analysis of acoustic images, through the data acquired by a mechanical scanning imaging sonar, in order to extract relevant environmental features that enable location estimation. For this purpose, the performances of different state-of-the art feature extraction algorithms were evaluated. Furthermore, an improvement to the feature matching step is proposed, in order to adapt this procedure to the characteristics of acoustic images. The extracted features are then used to feed a location estimator composed of a Simultaneous Localization and Mapping algorithm implementing an Extended Kalman Filter. Several tests were performed in a structured environment and the results of the feature extraction process and localization are presented.
Subject:	Engenharia electrotécnica, electrónica e informática Electrical engineering, Electronic engineering, Information engineering
Scientific areas:	Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática Engineering and technology::Electrical engineering, Electronic engineering, Information engineering
DOI:	10.34626/rm37-cx96
TID identifier:	202588513
URI:	https://hdl.handle.net/10216/132785
Document Type:	Dissertação
Rights:	openAccess
Appears in Collections:	FEUP - Dissertação

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.