ResearchSpace

Improving features used for hyper-temporal land cover change detection by reducing the uncertainty in the feature extraction method

Show simple item record

dc.contributor.author Salmon, BP
dc.contributor.author Kleynhans, Waldo
dc.contributor.author Olivier, JC
dc.contributor.author Schwegmann, Colin P
dc.date.accessioned 2018-01-15T09:58:10Z
dc.date.available 2018-01-15T09:58:10Z
dc.date.issued 2017-07
dc.identifier.citation Salmon, B.P. et al. 2017. Improving features used for hyper-temporal land cover change detection by reducing the uncertainty in the feature extraction method. 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Fort Worth, TX, USA, 23-28 July 2017 en_US
dc.identifier.issn 2153-7003
dc.identifier.uri DOI: 10.1109/IGARSS.2017.8127310
dc.identifier.uri http://ieeexplore.ieee.org/document/8127310/
dc.identifier.uri http://hdl.handle.net/10204/9953
dc.description Copyright: 2017 IEEE. Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, please consult the publisher's website. en_US
dc.description.abstract The well-being of the environment is one of the major factors that contributes to sustainability. Sustainable human settlements require local governance to plan, implement, develop, and manage human settlements expansions. This is important as the number anthropogenic activities is directly correlated to the increase in human population within a geographical region. Regional mapping of land cover conversion of natural vegetation to new human settlements is essential. In this paper we explore the effect which the length of a temporal sliding window has on the success of detecting land cover change. It is shown using a short Fourier transform as a feature extraction method provides meaningful robust input to a machine learning method. In theory, the performance is increased by improving the estimates on the features by increasing the length of the sliding window. Experiments were conducted in the Limpopo province of South Africa and were found that increasing the length of the sliding window beyond 12 months yield minor improves due to other seasonal and external factors. en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.relation.ispartofseries Worklist;20043
dc.subject Change detection en_US
dc.subject Satellite en_US
dc.subject Time series en_US
dc.subject Fourier transform en_US
dc.title Improving features used for hyper-temporal land cover change detection by reducing the uncertainty in the feature extraction method en_US
dc.type Conference Presentation en_US
dc.identifier.apacitation Salmon, B., Kleynhans, W., Olivier, J., & Schwegmann, C. P. (2017). Improving features used for hyper-temporal land cover change detection by reducing the uncertainty in the feature extraction method. IEEE. http://hdl.handle.net/10204/9953 en_ZA
dc.identifier.chicagocitation Salmon, BP, Waldo Kleynhans, JC Olivier, and Colin P Schwegmann. "Improving features used for hyper-temporal land cover change detection by reducing the uncertainty in the feature extraction method." (2017): http://hdl.handle.net/10204/9953 en_ZA
dc.identifier.vancouvercitation Salmon B, Kleynhans W, Olivier J, Schwegmann CP, Improving features used for hyper-temporal land cover change detection by reducing the uncertainty in the feature extraction method; IEEE; 2017. http://hdl.handle.net/10204/9953 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Salmon, BP AU - Kleynhans, Waldo AU - Olivier, JC AU - Schwegmann, Colin P AB - The well-being of the environment is one of the major factors that contributes to sustainability. Sustainable human settlements require local governance to plan, implement, develop, and manage human settlements expansions. This is important as the number anthropogenic activities is directly correlated to the increase in human population within a geographical region. Regional mapping of land cover conversion of natural vegetation to new human settlements is essential. In this paper we explore the effect which the length of a temporal sliding window has on the success of detecting land cover change. It is shown using a short Fourier transform as a feature extraction method provides meaningful robust input to a machine learning method. In theory, the performance is increased by improving the estimates on the features by increasing the length of the sliding window. Experiments were conducted in the Limpopo province of South Africa and were found that increasing the length of the sliding window beyond 12 months yield minor improves due to other seasonal and external factors. DA - 2017-07 DB - ResearchSpace DP - CSIR KW - Change detection KW - Satellite KW - Time series KW - Fourier transform LK - https://researchspace.csir.co.za PY - 2017 SM - 2153-7003 T1 - Improving features used for hyper-temporal land cover change detection by reducing the uncertainty in the feature extraction method TI - Improving features used for hyper-temporal land cover change detection by reducing the uncertainty in the feature extraction method UR - http://hdl.handle.net/10204/9953 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record