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
Deep Fusion of Imaging Modalities for Semantic Segmentation of Satellite Imagery
Linköping University, Department of Electrical Engineering, Computer Vision.
2018 (Swedish)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

In this report I summarize my master’s thesis work, in which I have investigated different approaches for fusing imaging modalities for semantic segmentation with deep convolutional networks. State-of-the-art methods for semantic segmentation of RGB-images use pre-trained models, which are fine-tuned to learn task-specific deep features. However, the use of pre-trained model weights constrains the model input to images with three channels (e.g. RGB-images). In some applications, e.g. classification of satellite imagery, there are other imaging modalities that can complement the information from the RGB modality and, thus, improve the performance of the classification. In this thesis, semantic segmentation methods designed for RGB images are extended to handle multiple imaging modalities, without compromising on the benefits, that pre-training on RGB datasets offers.

In the experiments of this thesis, RGB images from satellites have been fused with normalised difference vegetation index (NDVI) and a digital surface model (DSM). The evaluation shows that the modality fusion can significantly improve the performance of semantic segmentation networks in comparison with a corresponding network with only RGB input. However, the different investigated approaches to fuse the modalities proved to achieve similar performance. The conclusion of the experiments is, that the fusion of imaging modalities is necessary, but the method of fusion has shown to be of less importance.

Place, publisher, year, edition, pages
2018. , p. 88
Keywords [en]
Semantic segmentation, convolutional neural networks, remote sensing, satellite imagery, multimodal images
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:liu:diva-145193ISRN: LiTH-ISY-EX--18/5110--SEOAI: oai:DiVA.org:liu-145193DiVA, id: diva2:1182913
External cooperation
Vricon Systems AB
Subject / course
Electrical Engineering
Supervisors
Examiners
Available from: 2018-02-15 Created: 2018-02-15 Last updated: 2018-02-15Bibliographically approved

Open Access in DiVA

fulltext(38566 kB)142 downloads
File information
File name FULLTEXT01.pdfFile size 38566 kBChecksum SHA-512
5738f900c1c4180206f959979b63ef646d136dc008dd6d5eeacaf5a58638ead7fee9bab8ff26b79b148d60fadbd333fa9c2505089effc853c5579bc3ecffdd7f
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Sundelius, Carl
By organisation
Computer Vision
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 142 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: 445 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