Identifying Informal Settlements Using Contourlet Assisted Deep Learning
As the global urban population grows due to the influx of migrants from rural areas, many cities in developing countries face the emergence and proliferation of unplanned and informal settlements. However, even though the rise of unplanned development influences planning and management of residentia...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/9/2733 |
_version_ | 1797568317760733184 |
---|---|
author | Rizwan Ahmed Ansari Rakesh Malhotra Krishna Mohan Buddhiraju |
author_facet | Rizwan Ahmed Ansari Rakesh Malhotra Krishna Mohan Buddhiraju |
author_sort | Rizwan Ahmed Ansari |
collection | DOAJ |
description | As the global urban population grows due to the influx of migrants from rural areas, many cities in developing countries face the emergence and proliferation of unplanned and informal settlements. However, even though the rise of unplanned development influences planning and management of residential land-use, reliable and detailed information about these areas is often scarce. While formal settlements in urban areas are easily mapped due to their distinct features, this does not hold true for informal settlements because of their microstructure, instability, and variability of shape and texture. Therefore, detecting and mapping these areas remains a challenging task. This research will contribute to the development of tools to identify such informal built-up areas by using an integrated approach of multiscale deep learning. The authors propose a composite architecture for semantic segmentation using the U-net architecture aided by information obtained from a multiscale contourlet transform. This work also analyzes the effects of wavelet and contourlet decompositions in the U-net architecture. The performance was evaluated in terms of precision, recall, F-score, mean intersection over union, and overall accuracy. It was found that the proposed method has better class-discriminating power as compared to existing methods and has an overall classification accuracy of 94.9–95.7%. |
first_indexed | 2024-03-10T19:54:43Z |
format | Article |
id | doaj.art-a26c8ce842ca433aa1d8697ee494b684 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T19:54:43Z |
publishDate | 2020-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-a26c8ce842ca433aa1d8697ee494b6842023-11-20T00:03:26ZengMDPI AGSensors1424-82202020-05-01209273310.3390/s20092733Identifying Informal Settlements Using Contourlet Assisted Deep LearningRizwan Ahmed Ansari0Rakesh Malhotra1Krishna Mohan Buddhiraju2Department of Environmental, Earth and Geospatial Sciences, North Carolina Central University, Durham, NC 27707, USADepartment of Environmental, Earth and Geospatial Sciences, North Carolina Central University, Durham, NC 27707, USACentre of Studies in Resources Engineering, Indian Institute of Technology Bombay, Mumbai 400076, IndiaAs the global urban population grows due to the influx of migrants from rural areas, many cities in developing countries face the emergence and proliferation of unplanned and informal settlements. However, even though the rise of unplanned development influences planning and management of residential land-use, reliable and detailed information about these areas is often scarce. While formal settlements in urban areas are easily mapped due to their distinct features, this does not hold true for informal settlements because of their microstructure, instability, and variability of shape and texture. Therefore, detecting and mapping these areas remains a challenging task. This research will contribute to the development of tools to identify such informal built-up areas by using an integrated approach of multiscale deep learning. The authors propose a composite architecture for semantic segmentation using the U-net architecture aided by information obtained from a multiscale contourlet transform. This work also analyzes the effects of wavelet and contourlet decompositions in the U-net architecture. The performance was evaluated in terms of precision, recall, F-score, mean intersection over union, and overall accuracy. It was found that the proposed method has better class-discriminating power as compared to existing methods and has an overall classification accuracy of 94.9–95.7%.https://www.mdpi.com/1424-8220/20/9/2733remote sensinginformal settlementsmultiresolutiondeep learningcontourlet transformsemantic segmentation |
spellingShingle | Rizwan Ahmed Ansari Rakesh Malhotra Krishna Mohan Buddhiraju Identifying Informal Settlements Using Contourlet Assisted Deep Learning Sensors remote sensing informal settlements multiresolution deep learning contourlet transform semantic segmentation |
title | Identifying Informal Settlements Using Contourlet Assisted Deep Learning |
title_full | Identifying Informal Settlements Using Contourlet Assisted Deep Learning |
title_fullStr | Identifying Informal Settlements Using Contourlet Assisted Deep Learning |
title_full_unstemmed | Identifying Informal Settlements Using Contourlet Assisted Deep Learning |
title_short | Identifying Informal Settlements Using Contourlet Assisted Deep Learning |
title_sort | identifying informal settlements using contourlet assisted deep learning |
topic | remote sensing informal settlements multiresolution deep learning contourlet transform semantic segmentation |
url | https://www.mdpi.com/1424-8220/20/9/2733 |
work_keys_str_mv | AT rizwanahmedansari identifyinginformalsettlementsusingcontourletassisteddeeplearning AT rakeshmalhotra identifyinginformalsettlementsusingcontourletassisteddeeplearning AT krishnamohanbuddhiraju identifyinginformalsettlementsusingcontourletassisteddeeplearning |