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
Classification of post-wildfire aerial imagery using convolutional neural networks: A study of machine learning and resampling techniques to assist post-wildfire efforts
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Klassificering av flygfotografering efter skogsbränder med hjälp av "convolutional neural networks" (Swedish)
Abstract [en]

Assessment of post-wildfire damages to human structures is a manual task which currently uses ground-level observations of the structures by a human inspector to classify the burn severity of the affected structure. This study investigated the potential of using machine learning and specifically computer vision techniques in order to produce a classification of burn severity using post-wildfire aerial imagery. Specifically, a convolutional neural network model was trained on post-wildfire aerial imagery of affected human structures, and learned to classify their burn severity. The dataset used also suffered from a class-imbalance problem, meaning that the ratio of the different burn severity classes was skewed. Resampling techniques were studied as a method of improving performance given the class imbalance problem.

The study showed that convolutional neural networks were able to provide valuable classifications of the affected structures given post-wildfire aerial imagery. However, the results of the study showed that resampling using random oversampling did not provide an increase in model performance, and in fact lead to a worse performance when compared to a model trained on the same dataset without resampling.

Abstract [sv]

Bedömning av brandskador av mänskliga strukturer efter skogsbränder är en manuell uppgift som för närvarande använder observationer på marknivå av strukturerna med hjälp av en mänsklig inspektör för att klassificera bränskadorna av de drabbade strukturerna. Denna studie undersökte potentialen att använda maskininlärning och specifikt datasyntekniker för att producera en klassificering av bränskadorna med hjälp av flygfoton efter skogsbranden. Specifikt en "convolutional neural networktränad på flygfotografering av de drabbade mänskliga strukturerna och lärde sig klassificera deras brännskador. Datasetet som användes lider också av ett problem med obalans av klasser, vilket betyder distributionen mellan de olika bränningsgradsklasserna var skevt. Resamplingstekniker studerades som ett sätt att bekämpa obalansproblemet i datasetet.

Studien visade att "convolutional neural networks" kunde ge värdefulla klassificeringar av de drabbade strukturerna. Men resultaten av studien visade dock att resampling med slumpmässig översampling gav ingen ökning av modellprestanda, och ledde faktiskt till en sämre prestation jämfört med samma modell tränad på samma dataset utan resampling.

Place, publisher, year, edition, pages
2019. , p. 27
Series
TRITA-EECS-EX ; 2019:351
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-259695OAI: oai:DiVA.org:kth-259695DiVA, id: diva2:1353041
Supervisors
Examiners
Available from: 2019-09-24 Created: 2019-09-20 Last updated: 2019-09-24Bibliographically approved

Open Access in DiVA

fulltext(2075 kB)4 downloads
File information
File name FULLTEXT01.pdfFile size 2075 kBChecksum SHA-512
6c43e8dc36da43509d288746c1f2928d740e137a56fe7b3fb0b4830bbf4d1eda62272ed6fb818a3bb7a708bf4d1d1bdaeff494a3b9ebbbafa0c6844e400e8551
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: 4 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: 74 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