CitationShao, Yang; Taff, Gregory N.; & Walsh, Stephen J. (2011). Shadow Detection and Building-Height Estimation Using IKONOS Data. International Journal of Remote Sensing, 32(22), 6929-6944.
AbstractThe spectral confusion between shadow and water (or other dark surfaces) often results in suboptimal urban classification performances, especially from high-resolution satellite imagery (e.g. IKONOS). A classification method was developed to incorporate spatial indices of image objects to improve the shadow/water detection. A number of spatial indices, such as size, shape and spatial neighbour of image objects, were characterized to differentiate water and shadow objects. This generated superior shadow/water detection performance compared to a traditional per-field Extraction and Classification of Homogeneous Objects (ECHO) classification method. The user's accuracies for shadow and water classes were increased to 88% and 92%, compared to 80% and 76% obtained from the traditional ECHO classification approach. Furthermore, an automated approach was developed for shadow-length and corresponding building-height estimation. The accuracy assessment suggested good results for very high buildings, especially for isolated high-rise buildings.
Reference TypeJournal Article
Journal TitleInternational Journal of Remote Sensing
Taff, Gregory N.
Walsh, Stephen J.