Machine learning approaches for slum detection using very high resolution satellite images

Published

Conference Paper

© 2018 IEEE. Detecting informal settlements has become an important area of research in the past decade, owing to the availability of high resolution satellite imagery. Traditional per-pixel based classification methods provide high degree of accuracy in distinguishing primitive instances such as buildings, roads, forests and water. However, these methods fail to capture the complex relationships between neighboring pixels that is necessary for distinguishing complex objects such as informal and formal settlements. In this paper, we perform several experiments to compare and contrast how various per-pixel based classification methods, when combined with various features perform in detecting slums. In addition, we also explored a deep neural network, which showed better accuracy than the pixel based methods.

Full Text

Duke Authors

Cited Authors

  • Gadiraju, KK; Vatsavai, RR; Kaza, N; Wibbels, E; Krishna, A

Published Date

  • February 7, 2019

Published In

Volume / Issue

  • 2018-November /

Start / End Page

  • 1397 - 1404

Electronic International Standard Serial Number (EISSN)

  • 2375-9259

International Standard Serial Number (ISSN)

  • 2375-9232

International Standard Book Number 13 (ISBN-13)

  • 9781538692882

Digital Object Identifier (DOI)

  • 10.1109/ICDMW.2018.00198

Citation Source

  • Scopus