Image based classification of slums, built-up and non-built-up areas in Kalyan and Bangalore, India
Slums, characterized by sub-standard housing conditions, are a common in fast growing Asian cities. However, reliable and up-to-date information on their locations and development dynamics is scarce. Despite numerous studies, the task of delineating slum areas remains a challenge and no general agre...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2019-03-01
|
Series: | European Journal of Remote Sensing |
Subjects: | |
Online Access: | http://dx.doi.org/10.1080/22797254.2018.1535838 |
id |
doaj-9a64d4e89dc941a191d78a2871c4fb8a |
---|---|
record_format |
Article |
spelling |
doaj-9a64d4e89dc941a191d78a2871c4fb8a2020-11-25T01:46:42ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542019-03-01520406110.1080/22797254.2018.15358381535838Image based classification of slums, built-up and non-built-up areas in Kalyan and Bangalore, IndiaElena Ranguelova0Berend Weel1Debraj Roy2Monika Kuffer3Karin Pfeffer4Michael Lees5Netherlands eScience CenterNetherlands eScience CenterUniversity of AmsterdamUniversity of TwenteUniversity of TwenteUniversity of AmsterdamSlums, characterized by sub-standard housing conditions, are a common in fast growing Asian cities. However, reliable and up-to-date information on their locations and development dynamics is scarce. Despite numerous studies, the task of delineating slum areas remains a challenge and no general agreement exists about the most suitable method for detecting or assessing detection performance. In this paper, standard computer vision methods – Bag of Visual Words framework and Speeded-Up Robust Features have been applied for image-based classification of slum and non-slum areas in Kalyan and Bangalore, India, using very high resolution RGB images. To delineate slum areas, image segmentation is performed as pixel-level classification for three classes: Slums, Built-up and Non-Built-up. For each of the three classes, image tiles were randomly selected using ground truth observations. A multi-class support vector machine classifier has been trained on 80% of the tiles and the remaining 20% were used for testing. The final image segmentation has been obtained by classification of every 10th pixel followed by a majority filtering assigning classes to all remaining pixels. The results demonstrate the ability of the method to map slums with very different visual characteristics in two very different Indian cities.http://dx.doi.org/10.1080/22797254.2018.1535838Image segmentationinformal settlementssupport vector machinesbag of visual wordsspeeded-up robust features |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Elena Ranguelova Berend Weel Debraj Roy Monika Kuffer Karin Pfeffer Michael Lees |
spellingShingle |
Elena Ranguelova Berend Weel Debraj Roy Monika Kuffer Karin Pfeffer Michael Lees Image based classification of slums, built-up and non-built-up areas in Kalyan and Bangalore, India European Journal of Remote Sensing Image segmentation informal settlements support vector machines bag of visual words speeded-up robust features |
author_facet |
Elena Ranguelova Berend Weel Debraj Roy Monika Kuffer Karin Pfeffer Michael Lees |
author_sort |
Elena Ranguelova |
title |
Image based classification of slums, built-up and non-built-up areas in Kalyan and Bangalore, India |
title_short |
Image based classification of slums, built-up and non-built-up areas in Kalyan and Bangalore, India |
title_full |
Image based classification of slums, built-up and non-built-up areas in Kalyan and Bangalore, India |
title_fullStr |
Image based classification of slums, built-up and non-built-up areas in Kalyan and Bangalore, India |
title_full_unstemmed |
Image based classification of slums, built-up and non-built-up areas in Kalyan and Bangalore, India |
title_sort |
image based classification of slums, built-up and non-built-up areas in kalyan and bangalore, india |
publisher |
Taylor & Francis Group |
series |
European Journal of Remote Sensing |
issn |
2279-7254 |
publishDate |
2019-03-01 |
description |
Slums, characterized by sub-standard housing conditions, are a common in fast growing Asian cities. However, reliable and up-to-date information on their locations and development dynamics is scarce. Despite numerous studies, the task of delineating slum areas remains a challenge and no general agreement exists about the most suitable method for detecting or assessing detection performance. In this paper, standard computer vision methods – Bag of Visual Words framework and Speeded-Up Robust Features have been applied for image-based classification of slum and non-slum areas in Kalyan and Bangalore, India, using very high resolution RGB images. To delineate slum areas, image segmentation is performed as pixel-level classification for three classes: Slums, Built-up and Non-Built-up. For each of the three classes, image tiles were randomly selected using ground truth observations. A multi-class support vector machine classifier has been trained on 80% of the tiles and the remaining 20% were used for testing. The final image segmentation has been obtained by classification of every 10th pixel followed by a majority filtering assigning classes to all remaining pixels. The results demonstrate the ability of the method to map slums with very different visual characteristics in two very different Indian cities. |
topic |
Image segmentation informal settlements support vector machines bag of visual words speeded-up robust features |
url |
http://dx.doi.org/10.1080/22797254.2018.1535838 |
work_keys_str_mv |
AT elenaranguelova imagebasedclassificationofslumsbuiltupandnonbuiltupareasinkalyanandbangaloreindia AT berendweel imagebasedclassificationofslumsbuiltupandnonbuiltupareasinkalyanandbangaloreindia AT debrajroy imagebasedclassificationofslumsbuiltupandnonbuiltupareasinkalyanandbangaloreindia AT monikakuffer imagebasedclassificationofslumsbuiltupandnonbuiltupareasinkalyanandbangaloreindia AT karinpfeffer imagebasedclassificationofslumsbuiltupandnonbuiltupareasinkalyanandbangaloreindia AT michaellees imagebasedclassificationofslumsbuiltupandnonbuiltupareasinkalyanandbangaloreindia |
_version_ |
1725017689216253952 |