| Author: | Williams, Trecia Kay-Ann |
| Title: | Mapping urban slum settlements using high resolution satellite imagery to support slum upgrading and management : a first attempt in Jamaica |
| Advisors: | Zhu, Xiaolin (LSGI) |
| Degree: | M.Sc. |
| Year: | 2018 |
| Subject: | Human settlements -- Data processing Human settlements -- Jamaica Remote sensing High resolution imaging Spatial analysis (Statistics) Hong Kong Polytechnic University -- Dissertations |
| Department: | Faculty of Construction and Environment Department of Land Surveying and Geo-Informatics |
| Pages: | 92 pages : color illustrations |
| Language: | English |
| Abstract: | Developing Caribbean countries are regarded as some of most urbanized countries in the world (UN-Habitat, 2012). As a consequence of urbanization and with limited resources and places to live, urban slum settlements have become a global problem. Most slum studies focus on methodology development and there is need for more implementation of slum mapping to improve the global slum inventory. For Jamaica, urban slum settlement is a major concern. In addressing physical problems such as slum settlements spatial data is a priority. There is still a need for comprehensive mapping and analysis of urban slum settlements using spatial technologies in Jamaica. HRSI offers high temporal spatial data as well as can cover extensive areas quickly and therefore becomes economical when used in slum mapping. These datasets are available in the country. This research maps urban slum settlements in two sites in the KMA, Jamaica based on multiple local slum indicators. Using multiple features within a CART classifier, HNs created using a parcel map, are trained and classified to output a multi – characteristic slum classification. A 93% overall accuracy was achieved. Post classifier, a contextual rule set is used to improve the overall accuracy to 99%. The most important features and their thresholds from Site 1 are transferred to Site 2 and an overall accuracy of 87% was achieved confirming that building layout, building density, building roof colour and texture and edge distance from building to gullies are useful slum mapping indicators in the KMA. From the mapped settlements, statistical slum information, a slum geodatabase, existing land cover within each settlement, slum patterns, land boundaries affected by slum settlements and registration status of parcels within slum settlements are determined. This information is foundation for developing effective and sustainable plans and decisions towards slum upgrading and management. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 991022385847203411.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 7.94 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/10520