Detection of informal settlements from VHR satellite images using convolutional neural networks

Nicholus Mboga, C. Persello, J. R. Bergado, A. Stein

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

4 Citations (Scopus)

Abstract

Convolutional neural networks (CNNs), widely studied in the domain of computer vision, are more recently finding application in the analysis of high-resolution aerial and satellite imagery. In this paper, we investigate a deep feature learning approach based on CNNs for the detection of informal settlements in Dar es Salaam, Tanzania. This information is vital for decision making and planning of upgrading processes. Distinguishing the different urban structure types is challenging because of the abstract semantic definition of the classes as opposed to the separation of standard land-cover classes. This task requires the extraction of complex spatial-contextual features. To this aim, we trained a CNN in an end-to-end fashion and used it to classify informal and formal settlements. Our experimental results show that CNNs outperform state of the art methods using hand-crafted features. We conclude that CNNs are able to effectively learn the spatial-contextual features for accurately discriminating formal and informal settlements.
Original languageEnglish
Title of host publication2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Subtitle of host publication23-28 July 2017, Fort Worth Texas, USA
PublisherIEEE
Pages5169-5172
Number of pages4
ISBN (Electronic)978-1-5090-4951-6
DOIs
Publication statusPublished - 1 Jul 2017

Keywords

  • computer vision
  • convolution
  • feature extraction
  • geophysical image processing
  • image classification
  • learning (artificial intelligence)
  • neural nets
  • CNNs outperform state
  • Dar es Salaam
  • VHR satellite images
  • convolutional neural networks
  • deep feature
  • different urban structure types
  • end-to-end fashion
  • high-resolution aerial
  • informal settlements
  • satellite imagery
  • spatial-contextual features
  • standard land-cover classes
  • Convolution
  • Feature extraction
  • Kernel
  • Machine learning
  • Support vector machines
  • Training
  • Image classification
  • deep learning
  • high resolution satellite imagery

Fingerprint Dive into the research topics of 'Detection of informal settlements from VHR satellite images using convolutional neural networks'. Together they form a unique fingerprint.

Cite this