Human 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.
Reference:
Kleynhans, W, Salmon, BP, Olivier, JC et al. 2011. An autocorrelation analysis approach to detecting land cover change using hyper-temporal time-series data. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Vancouver, Canada, 24-29 July 2011
Kleynhans, W., Salmon, B., Olivier, J., Wessels, K. J., & Van den Bergh, F. (2011). An autocorrelation analysis approach to detecting land cover change using hyper-temporal time-series data. http://hdl.handle.net/10204/5363
Kleynhans, W, BP Salmon, JC Olivier, Konrad J Wessels, and F Van den Bergh. "An autocorrelation analysis approach to detecting land cover change using hyper-temporal time-series data." (2011): http://hdl.handle.net/10204/5363
Kleynhans W, Salmon B, Olivier J, Wessels KJ, Van den Bergh F, An autocorrelation analysis approach to detecting land cover change using hyper-temporal time-series data; 2011. http://hdl.handle.net/10204/5363 .
ResearchSpace
