Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Local Feature Correspondence on Side-Scan Sonar Seafloor Images
KTH, School of Electrical Engineering and Computer Science (EECS).
2021 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Lokal kännerteckensmatching av side-scan sonarbilder på havsbotten (Swedish)
Abstract [en]

In underwater environments, the perception and navigation systems are heavily dependent on the acoustic wave based sonar technology. Side-scan sonar (SSS) provides high-resolution, photo-realistic images of the seafloor at a relatively cheap price. These images could be considered potential candidates for place recognition and navigation of autonomous underwater vehicles (AUVs). Local feature correspondence matching, or the detection, description and matching of keypoints in overlapping images is a necessary building block for AUV navigation. Recent deep learning based research has resulted in state-of-the-art local correspondence models for camera images. For SSS images, however, deep learning based studies are limited and handcrafted methods such as SIFT and RootSIFT still dominate the field. In this study, SSS images taken from a seafloor area with bottom trawling marks were used for correspondence matching. D2-Net, a detect-and-describe VGG16 based network architecture designed for and tested on camera image correspondence was fine-tuned for SSS image correspondence. Using triplet margin ranking loss, the network was trained to simultaneously detect salient keypoints and produce similar descriptors for corresponding pixels and dissimilar descriptors for non-corresponding pixels. When evaluated on the nontrivial SSS images pairs in the test dataset, the best performing D2-Net based network was found to outperform the RootSIFT baseline in terms of number of detected keypoints, keypoint repeatability and mean matching accuracy at above 10 pixel threshold. 

Abstract [sv]

I undervattensmiljöer så är perception och navigationssystem ofta beroende av ekolodsteknik. Side scan sonar (SSS) ger högupplösta, fotorealistiska bilder av havsbottnen till en relativt låg kostnad. Dessa bilder kan användas för områdesigenkänning och navigation av autonoma undervattensfordon (AUV). Lokal kännerteckensmatchning består av detektion, beskrivning och matchning av nyckelpunkter på överlappande bilder. Detta är en viktig byggsten för AUV navigation. Nya metoder baserade på djupinlärning har varit i framkant för kännerteckensmatching av kamerabilder. Däremot är kännerteckensmatchning av SSS bilder fortfarande dominerat av traditionella metoder så som SIFT och RootSIFT. Denna rapport använder SSS bilder av havsbottnen där bottentrålning har förekommit för kännerteckensmatching. D2-Net är en detect-and-describe VGG16 baserad nätverksarkitektur designad och testad på kännerteckensmatching av kamerabilder. I denna rapport anpassas denna metod till SSS bilder. Kostnadsfunktionen använder sig av trippelmarginalsrankning så att nätverket ska kunna detektera distinkta nyckelpunkter samt producera liknande deskriptorer för matchande pixlar. Metoden utvärderades på icke-triviala SSS bildpar och uppnådde bättre resultat än RootSIFT.

Place, publisher, year, edition, pages
2021. , p. 88
Series
TRITA-EECS-EX ; 2021:62
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-291803OAI: oai:DiVA.org:kth-291803DiVA, id: diva2:1538568
Supervisors
Examiners
Available from: 2021-03-22 Created: 2021-03-19 Last updated: 2022-06-25Bibliographically approved

Open Access in DiVA

fulltext(21530 kB)416 downloads
File information
File name FULLTEXT01.pdfFile size 21530 kBChecksum SHA-512
8ed2456faf68ac99eec40d7e094a5b004c07573a3487ebbcc73a7862e58e82b6caeba3e45644dad74bc217c459ac375b7e14e728ee961d0060e8d7bb785595f5
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 416 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 824 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf