A method for detecting land cover change using NDVI timeseries data derived fromMODerate-resolution Imaging Spectroradiometer (MODIS) satellite data is proposed. The algorithm acts as a per pixel change alarm and takes as input the NDVI time-series of a 3x3 grid of MODIS pixels. An Extended Kalman Filter was used to estimate a series of parameters related to each NDVI signal. A spatial comparison between the center pixel of the the 3x3 grid and each of its neighboring pixels’ parameters was done to calculate a change metric which compared to a threshold yielded a change or no-change decision. The method was tested on real change examples in the study area and results indicate 90% detection of new settlements occurring in naturally vegetated areas.
Reference:
Kleynhans, W, Olivier, JC, Salmon, BP et al. Spatio-temporal approach to detecting land cover change using an extended kalman filter on modis time series data. IEEE International Geoscience and Remote Sensing Symposium, Honululu, Hawaii, USA. 25-30 July 2010, pp 4
Kleynhans, W., Olivier, J., Salmon, B., Wessels, K. J., & Van den Bergh, F. (2010). Spatio-temporal approach to detecting land cover change using an extended kalman filter on modis time series data. http://hdl.handle.net/10204/4872
Kleynhans, W, JC Olivier, BP Salmon, Konrad J Wessels, and F Van den Bergh. "Spatio-temporal approach to detecting land cover change using an extended kalman filter on modis time series data." (2010): http://hdl.handle.net/10204/4872
Kleynhans W, Olivier J, Salmon B, Wessels KJ, Van den Bergh F, Spatio-temporal approach to detecting land cover change using an extended kalman filter on modis time series data; 2010. http://hdl.handle.net/10204/4872 .