Van Den Bergh, FUdahemuka, GVan Wyk, BJ2010-04-182010-04-182009-07Van Den Bergh, F, Udahemuka, G and Van Wyk, BJ 2009. Potential fire detection based on Kalman-driven change detection. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Cape Town, South Africa, 12-17 July 2009, pp 1-4978-1-4244-3395-7http://hdl.handle.net/10204/4034Copyright: 2009 IEEE, International Geoscience and Remote Sensing Symposium (IGARSS), Cape Town, South Africa, 12-17 July 2009A new active fire event detection algorithm for data collected with the Spinning Enhanced Visible and Infrared Imager (SEVIRI) sensor, based on the extended Kalman filter, is introduced. Instead of using the observed temperatures of the spatial neighbours of a pixel to detect anomalous temperatures, the new algorithm only considers previous observations at the current pixel. The algorithm harnesses the Kalman filter to obtain a prediction of the expected brightness temperature at a given location, which is then compared to the actual SEVIRI observation. An adaptive threshold is used to determine whether the observed difference is indicative of a potential fire event. Initial tests show that the performance of this method is comparable to that of the EUMETSAT FIR product.enFiresFire detection algorithmsSpinning enhanced visible and infrared imagerSEVIRIKalman FilterEUMETSAT FIRDiurnal temperature cycleDTCMeteosat second generationRemote sensingGeoscienceConference PresentationVan Den Bergh, F., Udahemuka, G., & Van Wyk, B. (2009). Potential fire detection based on Kalman-driven change detection. IEEE. http://hdl.handle.net/10204/4034Van Den Bergh, F, G Udahemuka, and BJ Van Wyk. "Potential fire detection based on Kalman-driven change detection." (2009): http://hdl.handle.net/10204/4034Van Den Bergh F, Udahemuka G, Van Wyk B, Potential fire detection based on Kalman-driven change detection; IEEE; 2009. http://hdl.handle.net/10204/4034 .TY - Conference Presentation AU - Van Den Bergh, F AU - Udahemuka, G AU - Van Wyk, BJ AB - A new active fire event detection algorithm for data collected with the Spinning Enhanced Visible and Infrared Imager (SEVIRI) sensor, based on the extended Kalman filter, is introduced. Instead of using the observed temperatures of the spatial neighbours of a pixel to detect anomalous temperatures, the new algorithm only considers previous observations at the current pixel. The algorithm harnesses the Kalman filter to obtain a prediction of the expected brightness temperature at a given location, which is then compared to the actual SEVIRI observation. An adaptive threshold is used to determine whether the observed difference is indicative of a potential fire event. Initial tests show that the performance of this method is comparable to that of the EUMETSAT FIR product. DA - 2009-07 DB - ResearchSpace DP - CSIR KW - Fires KW - Fire detection algorithms KW - Spinning enhanced visible and infrared imager KW - SEVIRI KW - Kalman Filter KW - EUMETSAT FIR KW - Diurnal temperature cycle KW - DTC KW - Meteosat second generation KW - Remote sensing KW - Geoscience LK - https://researchspace.csir.co.za PY - 2009 SM - 978-1-4244-3395-7 T1 - Potential fire detection based on Kalman-driven change detection TI - Potential fire detection based on Kalman-driven change detection UR - http://hdl.handle.net/10204/4034 ER -