Van den Bergh, F2011-11-182011-11-182011-07Van den Bergh, F. 2011. Effects of viewing- and illumination geometry on settlement type classification of quickbird images. 2011 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Vancouver, Canada, 24-29 July 2011http://hdl.handle.net/10204/53202011 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Vancouver, Canada, 24-29 July 2011Image texture features extracted from high-resolution remotely sensed images over urban areas have shown promise in their ability to distinguish different settlement classes. Without any explicit mechanism to counter the effects of variable illumination- and viewing geometries, these features may not generalize well in multi-date applications such as change detection. This paper presents the results of a small study of the effects of unwanted variability on low-income settlement classification performance in the Soweto residential area of the city of Johannesburg, South Africa. Somewhat surprisingly, the Gray-Level Co-occurrence Matrix (GLCM) features were found to perform better than Local Binary Pattern (LBP) features on combined spatial and temporal generalization tasks, although the LBP features offered better performance on spatial-only generalization problems.enImage classificationUrban areasImage texture analysisQuickbird imagesGeometryGeoscienceRemote sensingIGARSS 2011Conference PresentationVan den Bergh, F. (2011). Effects of viewing- and illumination geometry on settlement type classification of quickbird images. IEEE. http://hdl.handle.net/10204/5320Van den Bergh, F. "Effects of viewing- and illumination geometry on settlement type classification of quickbird images." (2011): http://hdl.handle.net/10204/5320Van den Bergh F, Effects of viewing- and illumination geometry on settlement type classification of quickbird images; IEEE; 2011. http://hdl.handle.net/10204/5320 .TY - Conference Presentation AU - Van den Bergh, F AB - Image texture features extracted from high-resolution remotely sensed images over urban areas have shown promise in their ability to distinguish different settlement classes. Without any explicit mechanism to counter the effects of variable illumination- and viewing geometries, these features may not generalize well in multi-date applications such as change detection. This paper presents the results of a small study of the effects of unwanted variability on low-income settlement classification performance in the Soweto residential area of the city of Johannesburg, South Africa. Somewhat surprisingly, the Gray-Level Co-occurrence Matrix (GLCM) features were found to perform better than Local Binary Pattern (LBP) features on combined spatial and temporal generalization tasks, although the LBP features offered better performance on spatial-only generalization problems. DA - 2011-07 DB - ResearchSpace DP - CSIR KW - Image classification KW - Urban areas KW - Image texture analysis KW - Quickbird images KW - Geometry KW - Geoscience KW - Remote sensing KW - IGARSS 2011 LK - https://researchspace.csir.co.za PY - 2011 T1 - Effects of viewing- and illumination geometry on settlement type classification of quickbird images TI - Effects of viewing- and illumination geometry on settlement type classification of quickbird images UR - http://hdl.handle.net/10204/5320 ER -