Kleynhans, WSalmon, BPWessels, Konrad JOlivier, JC2014-02-132014-02-132013-07Kleynhans, W, Salmon, B.P, Wessels, K.J and Olivier, J.C. 2013. A spatio-temporal autocorrelation change detection approach using hyper-temporal satellite data. In: IEEE International Geoscience and Remote Sensing Symposium, Melbourne, Australia 21-26 July 2013http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=06723573http://hdl.handle.net/10204/7210IEEE International Geoscience and Remote Sensing Symposium, Melbourne, Australia 21-26 July 2013. Abstract only attached.There has been recent developments in the use of hypertemporal satellite time series data for land cover change detection and classification in South Africa and in particular, the monitoring of human settlement expansion is of relevance as it is the most pervasive form of land-cover change in the country. In this paper, a spatio-temporal change detection method is proposed that is applicable over large regions. This is achieved by adjusting the change threshold based on the change properties of a neighbourhood of pixels. Results indicate that the addition of spatial information increase change detection accuracy when compared to a pixel based approach.enHyper-temporal satellite dataSpatial informationConference PresentationKleynhans, W., Salmon, B., Wessels, K. J., & Olivier, J. (2013). A spatio-temporal autocorrelation change detection approach using hyper-temporal satellite data. IEEE Xplore. http://hdl.handle.net/10204/7210Kleynhans, W, BP Salmon, Konrad J Wessels, and JC Olivier. "A spatio-temporal autocorrelation change detection approach using hyper-temporal satellite data." (2013): http://hdl.handle.net/10204/7210Kleynhans W, Salmon B, Wessels KJ, Olivier J, A spatio-temporal autocorrelation change detection approach using hyper-temporal satellite data; IEEE Xplore; 2013. http://hdl.handle.net/10204/7210 .TY - Conference Presentation AU - Kleynhans, W AU - Salmon, BP AU - Wessels, Konrad J AU - Olivier, JC AB - There has been recent developments in the use of hypertemporal satellite time series data for land cover change detection and classification in South Africa and in particular, the monitoring of human settlement expansion is of relevance as it is the most pervasive form of land-cover change in the country. In this paper, a spatio-temporal change detection method is proposed that is applicable over large regions. This is achieved by adjusting the change threshold based on the change properties of a neighbourhood of pixels. Results indicate that the addition of spatial information increase change detection accuracy when compared to a pixel based approach. DA - 2013-07 DB - ResearchSpace DP - CSIR KW - Hyper-temporal satellite data KW - Spatial information LK - https://researchspace.csir.co.za PY - 2013 T1 - A spatio-temporal autocorrelation change detection approach using hyper-temporal satellite data TI - A spatio-temporal autocorrelation change detection approach using hyper-temporal satellite data UR - http://hdl.handle.net/10204/7210 ER -