Population Estimation Mining Using Satellite Imagery

Dittakan, Kwankamon, Coenen, Frans ORCID: 0000-0003-1026-6649, Christley, Rob ORCID: 0000-0001-9250-3032 and Wardeh, Maya ORCID: 0000-0002-2316-5460
(2013) Population Estimation Mining Using Satellite Imagery. In: DaWaK'13, University of Prague.

[img] Text
DittakanKwa_Sep2015_2050379.pdf - Unspecified
Available under License Creative Commons Attribution.

Download (9MB)


Many countries around the world regularly collect census data. This census data provides statistical information regarding populations to in turn support decision making processes. However, traditional approaches to the collation of censes data are both expensive and time consuming. The analysis of high resolution satellite imagery provides a useful alternative to collecting census data which is significantly cheaper than traditional methods, although less accurate. This paper describes a technique for mining satellite imagery, to extract census information, founded on the use of classification techniques coupled with a graph based representation of the relevant imagery. The fundamental idea is to build a classifier that can label households according to "family size" which can then be used to collect census data. To act as a focus for the work training data obtained from villages lying some 300km to the northwest of Addis Ababa in Ethiopia was used. The nature of each household in the segmented training data was captured using a tree-based representation. Each tree represented household had a "family size" class label associated with it. This data was then used to build a classifier that can be used to predict household sizes according to the nature of the tree-based structure. © 2013 Springer-Verlag GmbH.

Item Type: Conference or Workshop Item (Unspecified)
Additional Information: ## TULIP Type: Conference Proceedings (contribution) ##
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 25 Aug 2016 15:55
Last Modified: 17 Dec 2022 01:32
DOI: 10.1007/978-3-642-40131-2_25
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/2050379