File(s) under permanent embargo
An autocorrection analysis approach to detecting land cover change using hyper-temporal time-series data
conference contribution
posted on 2023-05-23, 06:49 authored by Kleynhans, W, Brian SalmonBrian Salmon, Jan OlivierJan Olivier, Wessels, KJ, van den Bergh, JCHuman settlement expansion is one of the most pervasive forms of land cover change in the Gauteng province of South Africa. A method for detecting new settlement developments in areas that are typically covered by natural vegetation using 500m MODIS time-series satellite data is proposed. The method is a per pixel change alarm that uses the temporal autocorrelation to infer a change metric which yields a change or no-change decision after thresholding. Simulated change data was generated and used to determine a threshold during a preliminary off-line optimization phase. After optimization the method was evaluated on examples of known land cover change in the study area and experimental results indicate a 92% change detection accuracy with a 15% false alarm rate.
History
Publication title
Proceedings of the IEEE International Geoscience and Remote Sensing Symposium 2011Pagination
94-97ISBN
978-1-4577-1003-2Department/School
School of EngineeringPublisher
IEEE ExplorePlace of publication
USAEvent title
IEEE International Geoscience and Remote Sensing SymposiumEvent Venue
Vancouver, CanadaDate of Event (Start Date)
2011-07-24Date of Event (End Date)
2011-07-29Repository Status
- Restricted