Salmon, BPKleynhans, WVan den Bergh, FOlivier, JCMarais, WJGrobler, TLWessels, Konrad J2013-02-252013-02-252012-07Salmon, BP, Kleynhans, W, Van den Bergh, F, Olivier, JC, Marais, WJ, Grobler, TL and Wessels, KJ. 2012. A search algorithm to meta-optimize the parameters for an extended Kalman filter to improve classification on hyper-temporal image. In: IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany, 22-27 July 2012http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6352495http://hdl.handle.net/10204/6570https://ieeexplore.ieee.org/document/6352495/Copyright: 2012 IEEE. This is the accepted version of the published item. The published version can be obtained via the publisher's website: https://ieeexplore.ieee.org/document/6352495/In this paper the Bias Variance Search Algorithm is proposed as an algorithm to optimize a candidate set of initial parameters for an Extended Kalman filter (EKF). The search algorithm operates on a Bias Variance Equilibrium Point criterion to determine how to set the initial parameters. The candidate set is then used by the EKF to estimate state parameters to fit a triply modulated cosine function to time series of the first two spectral bands of the MODerate-resolution Imaging Spectroradiometer (MODIS) land product. The state parameters are then used for land cover classification. The results of the search algorithm was tested on classifying land cover in the Limpopo province, South Africa. An improvement in land cover classification was observed when the method was compared to a robust regression method.enHellinger distanceKalman filterTime series analysisSpatial informationConference PresentationSalmon, B., Kleynhans, W., Van den Bergh, F., Olivier, J., Marais, W., Grobler, T., & Wessels, K. J. (2012). A search algorithm to meta-optimize the parameters for an extended Kalman filter to improve classification on hyper-temporal images. IEEE Xplore. http://hdl.handle.net/10204/6570Salmon, BP, W Kleynhans, F Van den Bergh, JC Olivier, WJ Marais, TL Grobler, and Konrad J Wessels. "A search algorithm to meta-optimize the parameters for an extended Kalman filter to improve classification on hyper-temporal images." (2012): http://hdl.handle.net/10204/6570Salmon B, Kleynhans W, Van den Bergh F, Olivier J, Marais W, Grobler T, et al, A search algorithm to meta-optimize the parameters for an extended Kalman filter to improve classification on hyper-temporal images; IEEE Xplore; 2012. http://hdl.handle.net/10204/6570 .TY - Conference Presentation AU - Salmon, BP AU - Kleynhans, W AU - Van den Bergh, F AU - Olivier, JC AU - Marais, WJ AU - Grobler, TL AU - Wessels, Konrad J AB - In this paper the Bias Variance Search Algorithm is proposed as an algorithm to optimize a candidate set of initial parameters for an Extended Kalman filter (EKF). The search algorithm operates on a Bias Variance Equilibrium Point criterion to determine how to set the initial parameters. The candidate set is then used by the EKF to estimate state parameters to fit a triply modulated cosine function to time series of the first two spectral bands of the MODerate-resolution Imaging Spectroradiometer (MODIS) land product. The state parameters are then used for land cover classification. The results of the search algorithm was tested on classifying land cover in the Limpopo province, South Africa. An improvement in land cover classification was observed when the method was compared to a robust regression method. DA - 2012-07 DB - ResearchSpace DP - CSIR KW - Hellinger distance KW - Kalman filter KW - Time series analysis KW - Spatial information LK - https://researchspace.csir.co.za PY - 2012 T1 - A search algorithm to meta-optimize the parameters for an extended Kalman filter to improve classification on hyper-temporal images TI - A search algorithm to meta-optimize the parameters for an extended Kalman filter to improve classification on hyper-temporal images UR - http://hdl.handle.net/10204/6570 ER -