Capturing the diversity of deprived areas with image-based features: the case of Mumbai

Research output: Contribution to journalArticleAcademicpeer-review

22 Citations (Scopus)
40 Downloads (Pure)

Abstract

Many cities in the Global South are facing rapid population and slum growth, but lack detailed information to target these issues. Frequently, municipal datasets on such areas do not keep up with such dynamics, with data that are incomplete, inconsistent, and outdated. Aggregated census-based statistics refer to large and heterogeneous areas, hiding internal spatial differences. In recent years, several remote sensing studies developed methods for mapping slums; however, few studies focused on their diversity. To address this shortcoming, this study analyzes the capacity of very high resolution (VHR) imagery and image processing methods to map locally specific types of deprived areas, applied to the city of Mumbai, India. We analyze spatial, spectral, and textural characteristics of deprived areas, using a WorldView-2 imagery combined with auxiliary spatial data, a random forest classifier, and logistic regression modeling. In addition, image segmentation is used to aggregate results to homogenous urban patches (HUPs). The resulting typology of deprived areas obtains a classification accuracy of 79% for four deprived types and one formal built-up class. The research successfully demonstrates how image-based proxies from VHR imagery can help extract spatial information on the diversity and cross-boundary clusters of deprivation to inform strategic urban management.
Original languageEnglish
Article number384
JournalRemote sensing
Volume9
Issue number2
DOIs
Publication statusPublished - 2017

Fingerprint

imagery
typology
spatial data
image processing
segmentation
census
logistics
remote sensing
modeling
method
city
urban management
statistics
WorldView

Keywords

  • METIS-322154
  • ITC-GOLD

Cite this

@article{d77fdced121f48f58a417a79452ae6be,
title = "Capturing the diversity of deprived areas with image-based features: the case of Mumbai",
abstract = "Many cities in the Global South are facing rapid population and slum growth, but lack detailed information to target these issues. Frequently, municipal datasets on such areas do not keep up with such dynamics, with data that are incomplete, inconsistent, and outdated. Aggregated census-based statistics refer to large and heterogeneous areas, hiding internal spatial differences. In recent years, several remote sensing studies developed methods for mapping slums; however, few studies focused on their diversity. To address this shortcoming, this study analyzes the capacity of very high resolution (VHR) imagery and image processing methods to map locally specific types of deprived areas, applied to the city of Mumbai, India. We analyze spatial, spectral, and textural characteristics of deprived areas, using a WorldView-2 imagery combined with auxiliary spatial data, a random forest classifier, and logistic regression modeling. In addition, image segmentation is used to aggregate results to homogenous urban patches (HUPs). The resulting typology of deprived areas obtains a classification accuracy of 79{\%} for four deprived types and one formal built-up class. The research successfully demonstrates how image-based proxies from VHR imagery can help extract spatial information on the diversity and cross-boundary clusters of deprivation to inform strategic urban management.",
keywords = "METIS-322154, ITC-GOLD",
author = "M. Kuffer and K. Pfeffer and R.V. Sliuzas and I. Baud and {van Maarseveen}, M.F.A.M.",
year = "2017",
doi = "10.3390/rs9040384",
language = "English",
volume = "9",
journal = "Remote sensing",
issn = "2072-4292",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "2",

}

Capturing the diversity of deprived areas with image-based features : the case of Mumbai. / Kuffer, M.; Pfeffer, K.; Sliuzas, R.V.; Baud, I.; van Maarseveen, M.F.A.M.

In: Remote sensing, Vol. 9, No. 2, 384, 2017.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Capturing the diversity of deprived areas with image-based features

T2 - the case of Mumbai

AU - Kuffer, M.

AU - Pfeffer, K.

AU - Sliuzas, R.V.

AU - Baud, I.

AU - van Maarseveen, M.F.A.M.

PY - 2017

Y1 - 2017

N2 - Many cities in the Global South are facing rapid population and slum growth, but lack detailed information to target these issues. Frequently, municipal datasets on such areas do not keep up with such dynamics, with data that are incomplete, inconsistent, and outdated. Aggregated census-based statistics refer to large and heterogeneous areas, hiding internal spatial differences. In recent years, several remote sensing studies developed methods for mapping slums; however, few studies focused on their diversity. To address this shortcoming, this study analyzes the capacity of very high resolution (VHR) imagery and image processing methods to map locally specific types of deprived areas, applied to the city of Mumbai, India. We analyze spatial, spectral, and textural characteristics of deprived areas, using a WorldView-2 imagery combined with auxiliary spatial data, a random forest classifier, and logistic regression modeling. In addition, image segmentation is used to aggregate results to homogenous urban patches (HUPs). The resulting typology of deprived areas obtains a classification accuracy of 79% for four deprived types and one formal built-up class. The research successfully demonstrates how image-based proxies from VHR imagery can help extract spatial information on the diversity and cross-boundary clusters of deprivation to inform strategic urban management.

AB - Many cities in the Global South are facing rapid population and slum growth, but lack detailed information to target these issues. Frequently, municipal datasets on such areas do not keep up with such dynamics, with data that are incomplete, inconsistent, and outdated. Aggregated census-based statistics refer to large and heterogeneous areas, hiding internal spatial differences. In recent years, several remote sensing studies developed methods for mapping slums; however, few studies focused on their diversity. To address this shortcoming, this study analyzes the capacity of very high resolution (VHR) imagery and image processing methods to map locally specific types of deprived areas, applied to the city of Mumbai, India. We analyze spatial, spectral, and textural characteristics of deprived areas, using a WorldView-2 imagery combined with auxiliary spatial data, a random forest classifier, and logistic regression modeling. In addition, image segmentation is used to aggregate results to homogenous urban patches (HUPs). The resulting typology of deprived areas obtains a classification accuracy of 79% for four deprived types and one formal built-up class. The research successfully demonstrates how image-based proxies from VHR imagery can help extract spatial information on the diversity and cross-boundary clusters of deprivation to inform strategic urban management.

KW - METIS-322154

KW - ITC-GOLD

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2017/isi/kuffer_cap.pdf

U2 - 10.3390/rs9040384

DO - 10.3390/rs9040384

M3 - Article

VL - 9

JO - Remote sensing

JF - Remote sensing

SN - 2072-4292

IS - 2

M1 - 384

ER -