Unsupervised land cover change detection: meaningful sequential time series analysis

Salmon, BPOlivier, JCWessels, Konrad JKleynhans, WVan den Bergh, FSteenkamp, Karen C2011-12-132011-12-132011-06Salmon, B.P., Olivier, J.C., Wessels, K.J. et al. 2011. Unsupervised land cover change detection: meaningful sequential time series analysis. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 4(2), pp 327-3351939-1404http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?reload=true&arnumber=5535230http://hdl.handle.net/10204/5400Copyright: 2011 IEEE. This is an ABSTRACT ONLYAn automated land cover change detection method is proposed that uses coarse spatial resolution hyper-temporal earth observation satellite time series data. The study compared three different unsupervised clustering approaches that operate on short term Fourier transform coefficients computed over subsequences of 8-day composite MODerate-resolution Imaging Spectroradiometer (MODIS) surface reflectance data that were extracted with a temporal sliding window. The method uses a feature extraction process that creates meaningful sequential time series that can be analyzed and processed for change detection. The method was evaluated on real and simulated land cover change examples and obtained a change detection accuracy exceeding 76% on real land cover conversion and more than 70% on simulated land cover conversion.enChange detectionClusteringSatelliteTime seriesLand coverEarth observationsRemote sensingUnsupervised land cover change detection: meaningful sequential time series analysisArticleSalmon, B., Olivier, J., Wessels, K. J., Kleynhans, W., Van den Bergh, F., & Steenkamp, K. C. (2011). Unsupervised land cover change detection: meaningful sequential time series analysis. http://hdl.handle.net/10204/5400Salmon, BP, JC Olivier, Konrad J Wessels, W Kleynhans, F Van den Bergh, and Karen C Steenkamp "Unsupervised land cover change detection: meaningful sequential time series analysis." (2011) http://hdl.handle.net/10204/5400Salmon B, Olivier J, Wessels KJ, Kleynhans W, Van den Bergh F, Steenkamp KC. Unsupervised land cover change detection: meaningful sequential time series analysis. 2011; http://hdl.handle.net/10204/5400.TY - Article AU - Salmon, BP AU - Olivier, JC AU - Wessels, Konrad J AU - Kleynhans, W AU - Van den Bergh, F AU - Steenkamp, Karen C AB - An automated land cover change detection method is proposed that uses coarse spatial resolution hyper-temporal earth observation satellite time series data. The study compared three different unsupervised clustering approaches that operate on short term Fourier transform coefficients computed over subsequences of 8-day composite MODerate-resolution Imaging Spectroradiometer (MODIS) surface reflectance data that were extracted with a temporal sliding window. The method uses a feature extraction process that creates meaningful sequential time series that can be analyzed and processed for change detection. The method was evaluated on real and simulated land cover change examples and obtained a change detection accuracy exceeding 76% on real land cover conversion and more than 70% on simulated land cover conversion. DA - 2011-06 DB - ResearchSpace DP - CSIR KW - Change detection KW - Clustering KW - Satellite KW - Time series KW - Land cover KW - Earth observations KW - Remote sensing LK - https://researchspace.csir.co.za PY - 2011 SM - 1939-1404 T1 - Unsupervised land cover change detection: meaningful sequential time series analysis TI - Unsupervised land cover change detection: meaningful sequential time series analysis UR - http://hdl.handle.net/10204/5400 ER -