Luus, FPSVan den Bergh, FMaharaj, BTJ2014-04-102014-04-102012-07Luus, F.P.S, Van den Bergh, F and Maharaj, B.T.J. 2012. The effects of shadow removal on across-date settlement type classification of quickbird images. In: International Geoscience and Remote Sensing Symposium (IGARSS) 2012, Munich, Germany, 22-27 July 2012http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6352672http://hdl.handle.net/10204/7352International Geoscience and Remote Sensing Symposium (IGARSS) 2012, Munich, Germany, 22-27 July 2012. Abstract attached.QuickBird imagery acquired on separate dates may have significant differences in viewing- and illumination geometries, which can negatively impact across-date settlement type classification accuracy. The effect of cast shadows on classification accuracy is specifically investigated in this study by performing shadow removal, before the calculation of texture features which are then used as classifier inputs. It is shown that popular texture features are sensitive to differences in shadow profiles, and that across-date classification accuracy can be improved with shadow removal. The strong relationship between the best shadow detection threshold and the best settlement classification accuracy is indicated for the study data set. A refined shadow correction algorithm is proposed, and demonstrated to be more effective than basic shadow correction methods.enQuickBird imageryGeosciencesRemote sensingShadow removalShadow maskingImage classificationUrban areasImage texture analysisConference PresentationLuus, F., Van den Bergh, F., & Maharaj, B. (2012). The effects of shadow removal on across-date settlement type classification of quickbird images. IEEE Xplore. http://hdl.handle.net/10204/7352Luus, FPS, F Van den Bergh, and BTJ Maharaj. "The effects of shadow removal on across-date settlement type classification of quickbird images." (2012): http://hdl.handle.net/10204/7352Luus F, Van den Bergh F, Maharaj B, The effects of shadow removal on across-date settlement type classification of quickbird images; IEEE Xplore; 2012. http://hdl.handle.net/10204/7352 .TY - Conference Presentation AU - Luus, FPS AU - Van den Bergh, F AU - Maharaj, BTJ AB - QuickBird imagery acquired on separate dates may have significant differences in viewing- and illumination geometries, which can negatively impact across-date settlement type classification accuracy. The effect of cast shadows on classification accuracy is specifically investigated in this study by performing shadow removal, before the calculation of texture features which are then used as classifier inputs. It is shown that popular texture features are sensitive to differences in shadow profiles, and that across-date classification accuracy can be improved with shadow removal. The strong relationship between the best shadow detection threshold and the best settlement classification accuracy is indicated for the study data set. A refined shadow correction algorithm is proposed, and demonstrated to be more effective than basic shadow correction methods. DA - 2012-07 DB - ResearchSpace DP - CSIR KW - QuickBird imagery KW - Geosciences KW - Remote sensing KW - Shadow removal KW - Shadow masking KW - Image classification KW - Urban areas KW - Image texture analysis LK - https://researchspace.csir.co.za PY - 2012 T1 - The effects of shadow removal on across-date settlement type classification of quickbird images TI - The effects of shadow removal on across-date settlement type classification of quickbird images UR - http://hdl.handle.net/10204/7352 ER -